Fusion of Multimodality Features for Improved Classification of Alzheimer Disease

Fusion of Multimodality Features for Improved Classification of Alzheimer Disease | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Fusion of Multimodality Features for Improved Classification of Alzheimer Disease S Shobha, B R Karthikeyan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1676817/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This paper focus on improved classification accuracy in classification of Alzheimer Disease (AD) vs Mild cognitive impairment (MCI) vs Normal Controls (NC) by feature reduction technique and fusion of multimodality features. The gray matter of specified ROI regions of brain is extracted from MRI and FDG-PET images. The LASSO feature selection technique is used to identify the relevant features significant for the classification of AD from MCI and NC. The reduction of features leads to 92.27% of accuracy which is improved by 11% compared without feature selection in classification of AD vs MCI. The classification of AD vs MCI and MCI vs NC is challenging due to the high correlations of the features. Through the analysis it is found that for AD vs MCI a maximum of 92.27% of classification accuracy accomplished for multimodal combination of features using linear Support vector Machine (SVM) algorithm and for MCI vs NC 99% accomplished using linear SVM algorithm. It is identified that fusion of features of all the modalities provides 94.9% accuracy for AD vs MCI vs NC. The analysis solidifies that fusion of multi-modality features always improves the classification accuracy compared to using any one of the single modality features. All the analysis were carried out using ADNI-1 data base and subject IDs are listed in Table 10. Alzheimer Disease (AD) Mild Cognitive Impairment (MCI) Normal Controls (NC) Feature Selection Figures Figure 1 Figure 2 1 Introduction Alzheimer Disease (AD) is a common neurogenerative disorder, found in elderly people which develops with time by destroying brain cells leading to dementia. The progression of AD will be evaluated through imaging modalities and data are categorized into three stages Normal Controls (NC), Mild Cognitive Impairment (MCI) and Alzheimer Disease. All subjects of MCI will not develop AD, only few subjects will be converted into AD over time period [ 1 ]. Early diagnosis of AD may help the clinicians to improve the quality of life of AD subjects. Diverse modalities are available such as Magnetic Resonance Imaging (MRI) and (Fluorodeoxyglucose Positron Emission Tomography) FDG-PET Imaging, Genetic and Cerebrospinal Fluid (CSF) to diagnose the progression of AD. The structural MRI is one of the most widely used modality due to its ability to distinguish between gray matter and white matter [ 6 ] [ 35 ] in dementia subjects. The change in the volume of gray matter in the hippocampus region of the brain is used as a biomarker in diagnosis of AD. The Gray matter present in the predefined 116 ROIs in the Hippocampus region is measured and used as a feature vector for classification. The Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a significant imaging modality in the early diagnosis of AD and several research studies have revealed significant reductions in metabolic rate of glucose in several regions of human brain [ 23 ] [ 27 ] which can be exploited to identify AD. In genotype, dementia is the cause of permanent variations in Apolipoprotein-E APOE gene. The APOE gene has three versions such as e2, e3 and e4 alleles, among them subjects with APOE e4 have greater chance of developing AD [ 18 ] [ 32 ] at an early age compared to e2 [ 32 ]. In CSF, the Aβ38, Aβ40, Aβ42, tau-total, tau-phosphor are the hallmarked biomarkers used for the diagnosis of AD. The presence of low level of Aβ42 has been validated by many authors [ 34 ] in subjects suffering from AD. The Aβ40, and Aβ42 can be together used to detect AD which increases diagnosis accuracy [ 25 ]. Several authors have shown that the ratio of Aβ42/Aβ40 can be used to identify AD with higher accuracy instead of using alone Aβ42 [ 13 ] [ 37 ]. The significant correlation between low levels of Aβ38 with higher level of P-tau [ 15 ] and higher level of t-tau in CSF [ 4 ] in subjects suffering from AD has been investigated by many researchers. The Plaques and tangles in subjects suffering from dementia, composed of amyloid beta fragments found in human brain block communication between neurons [ 5 ]. The correlation between p-tau and tangle count in dementia subjects is reported by [ 11 ]. The above-mentioned modality provides limited information regarding dementia if used individually, thus multi-modality features when fused to extract different aspects of AD and provide complementary information. The combination of features from different modality will improve early detection of dementia [ 39 ]. Many researchers have worked on developing computerized techniques for diagnosing AD. Among them MRI [ 8 ] [ 9 ] [ 14 ] [ 17 ] [ 26 ] and PET [ 10 ] are frequently used modalities. MRI provides fine structural anatomy and PET provides metabolic function of tissues of human brain [ 24 ]. Therefore, fusion of multimodal features of MRI, PET, CSF, APOE and clinical features could improve the classification accuracy of AD [ 12 ][ 16 ] [ 21 ]. This paper addresses the analysis of classification of AD vs MCI vs NC subjects by fusion of multiple modality features using machine learning algorithms. The features of Region of Interest (ROI) of MRI and PET were extracted and used for the classification of AD vs MCI vs NC. The relevant features were identified using LASSO cross validation technique to reduce the number of features. The analysis was carried to identify the possible combination of modalities for improved diagnosis of AD. The reduced features of MRI and PET are fused with APOE gene, CSF and clinical data in all possible combination to evaluate the classification accuracy. The analysis solidifies that fusion of multi-modality features always improves the classification accuracy compared to using any one of the single modality features. The results also revealed that APOE genotype identified as biomarker for AD doesn’t provide a notable classification accuracy as a single modality, whereas, by fusing it with other modalities exhibit a notable classification accuracy. 2 Dataset And Feature Extraction The ADNI LONI Image Data archives of ADNI was used for the analysis presented in this paper. The demographic details of the subjects selected for analysis is listed in Table 1. The SPM12 and CAT12 software tool box [3] were used for pre-processing and features extraction from MRI and PET images. Table 1 . Summary of Demographic characteristics of subjects Group/ Gender No. of Subjects Age (Mean ± Std) MMSE score (Mean ± Std) GDS (Mean ± Std) CDR (Mean ± Std) AD Male/ Female 78 75.87 ± 7.6 23.50± 2.07 1.53 ± 1.32 1.00 ± 1.06 MCI Male/ Female 100 75.85 ± 6.81 28.92 ± 1.08 1.00 ± 1.27 0 ± 0 NC Male/ Female 96 75.81 ± 4.8 27.31 ± 2.27 1.77 ± 1.59 0.51 ± 0.09 The values are denoted as mean ± standard deviation. MMSE=Mini Mental State Examination, CDR=Clinical Dementia Rating, GDS=Global Deterioration Scale To extract features of MRI and FDG-PET images, a ROI Analysis [2] with an atlas specified by [22] was used. The FDG-PET images were pre-processed using the standard protocols (185 MBq (5 mCi) Dynamic 3D scan of six 5-min frames 30-60 min post injection) (http://adni.loni.usc.edu/methods/pet-analysis-method/pet-analysis/). The pre-processed FDG-PET scans were coregistered with the corresponding pre-processed MRI (http://adni.loni.usc.edu/methods/mri-tool/mri-analysis/) by using a three-dimensional method. The APOE gene in human body responsible for AD has three alleles e2, e3 and e4. The genetic feature for each subject consists of any one of the 6 genetic combinations such as (e2, e2), (e2, e3), (e2, e4), (e3, e3), (e3, e4) and (e4, e4). The APOE measures used in the current study is tabulated in Table 2. Table 2 . Each diagnostic group possessing each of the Six APOE allele pairs. Genetic biomarkers AD MCI NC (e3, e3) 22 48 54 (e3, e4) 37 36 21 (e4, e4) 12 11 2 (e2, e3) 3 2 16 (e2, e4) 4 3 1 (e2, e2) 2 Total Subjects 78 100 96 The CSF biomarkers such as Aβ42, Aβ40, Aβ38, Aβ, t-tau and p-tau were acquired using the notable fully automated Roche Elecsys and cobas e 601 immunoassay analyzer system from ADNI. The CSF biomarkers were not available for all the subjects, the missing data were compensated using mean value imputation technique. The measure of CSF biomarkers used in the classification of AD is depicted in Table 3. Table 3 . CSF measures and biomarkers used in classification of AD CSF Biomarkers AD MCI NC Ab 38 , 1718.20± 499.99 1747.11± 584.04 1754.81± 566.55 Ab 40 7398± 2098.97 7319.08± 2306.10 7573.32± 2260.77 Ab 42 651.17 ± 258.75 868.63± 456.40 1096.05± 404.72 Ab 624.58±267.26 943.39±616.30 1174.17±507.89 t-tau 363.06±141.00 264.27±90.67 227.23±77.59 p-tau 37.47897±17.30 25.74±9.87 21.165±7.96 pg ⁄ ml=Picograms/milliliter 3 Feature Selection Using Lasso Technique The Least Absolute Shrinkage and Selection Operator (LASSO) feature selection selects the relevant features among the available features. The LASSO performs L1 regularization and was developed by Tibshirani [ 30 ], it identifies the most relevant features by performing cross validation of features against its class labels. This intern reduces the number of features, result in improving accuracy of the classifier. The authors have explored the LASSO based features selection on volumetric features and cortical thickness features to accomplish the improvement of classification Accuracy [ 28 ]. In the proposed analysis the relevant features of MRI and FDG-PET identified using LASSO technique are provided in Table 4 . Table 4 List of ROI biomarkers selected from MRI and PET images using LASSO Model Sl. no ROI biomarkers MRI PET Sl. no Volumetric Features MRI PET 1 Precentral_L 59 Parietal_Sup_L √ 2 Precentral_R √ 60 Parietal_Sup_R √ 3 Frontal_Sup_L 61 Parietal_Inf_L 4 Frontal_Sup_R √ 62 Parietal_Inf_R 5 Frontal_Sup_Orb_L √ 63 SupraMarginal_L 6 Frontal_Sup_Orb_R 64 SupraMarginal_R 7 Frontal_Mid_L 65 Angular_L 8 Frontal_Mid_R 66 Angular_R 9 Frontal_Mid_Orb_L 67 Precuneus_L 10 Frontal_Mid_Orb_R 68 Precuneus_R 11 Frontal_Inf_Oper_L 69 Paracentral_Lobule_L √ √ 12 Frontal_Inf_Oper_R 70 Paracentral_Lobule_R 13 Frontal_Inf_Tri_L √ 71 Caudate_L √ 14 Frontal_Inf_Tri_R √ 72 Caudate_R √ 15 Frontal_Inf_Orb_L 73 Putamen_L √ 16 Frontal_Inf_Orb_R √ 74 Putamen_R √ √ 17 Rolandic_Oper_L 75 Pallidum_L √ √ 18 Rolandic_Oper_R √ 76 Pallidum_R √ 19 Supp_Motor_Area_L 77 Thalamus_L √ 20 Supp_Motor_Area_R √ 78 Thalamus_R √ 21 Olfactory_L 79 Heschl_L 22 Olfactory_R √ 80 Heschl_R 23 Frontal_Sup_Medial_L 81 Temporal_Sup_L 24 Frontal_Sup_Medial_R 82 Temporal_Sup_R √ 25 Frontal_Mid_Orb_L 83 Temporal_Pole_Sup_L √ 26 Frontal_Mid_Orb_R 84 Temporal_Pole_Sup_R √ 27 Rectus_L 85 Temporal_Mid_L 28 Rectus_R 86 Temporal_Mid_R 29 Insula_L 87 Temporal_Pole_Mid_L √ √ 30 Insula_R 88 Temporal_Pole_Mid_R √ √ 31 Cingulum_Ant_L 89 Temporal_Inf_L 32 Cingulum_Ant_R 90 Temporal_Inf_R 33 Cingulum_Mid_L 91 Cerebelum_Crus1_L 34 Cingulum_Mid_R 92 Cerebelum_Crus1_R √ 35 Cingulum_Post_L 93 Cerebelum_Crus2_L 36 Cingulum_Post_R √ 94 Cerebelum_Crus2_R √ √ 37 Hippocampus_L √ 95 Cerebelum_3_L 38 Hippocampus_R √ 96 Cerebelum_3_R √ 39 ParaHippocampal_L √ 97 Cerebelum_4_5_L 40 ParaHippocampal_R √ 98 Cerebelum_4_5_R √ 41 Amygdala_L 99 Cerebelum_6_L √ 42 Amygdala_R √ 100 Cerebelum_6_R √ √ 43 Calcarine 101 Cerebelum_7b_L 44 Calcarine √ 102 Cerebelum_7b_R 45 Cuneus 103 Cerebelum_8_L √ √ 46 Cuneus √ 104 Cerebelum_8_R 47 Lingual 105 Cerebelum_9_L √ 48 Lingual_R 106 Cerebelum_9_R √ 49 Occipital_Sup_L 107 Cerebelum_10_L √ 50 Occipital_Sup_R √ 108 Cerebelum_10_R √ 51 Occipital_Mid_L 109 Vermis_1_2 52 Occipital_Mid_R √ 110 Vermis_3 53 Occipital_Inf_L 111 Vermis_4_5 54 Occipital_Inf_R √ 112 Vermis_6 55 Fusiform_L 113 Vermis_7 √ 56 Fusiform_R 114 Vermis_8 √ 57 Postcentral_L √ 115 Vermis_9 √ 58 Postcentral_R √ 116 Vermis_10 √ √ 4 Classification Performance Analysis The overall workflow incorporated in the analysis is described through the Fig. 1 . The method comprised of four major steps: Image pre-processing and Feature Extraction, Feature Selection using LASSO algorithm, Fusion and Classification. In the current analysis the complete MRI, PET and APOE genotype data were available for all the subjects. The unavailable CSF data for some of the subjects were filled with mean value in each subgroup (AD, MCI and NC group) [ 7 ]. The features were normalized using min-max normalization technique and relevant features selected using LASSO feature selection technique were applied to SVM classifier. The classification accuracy was computed by averaging 100 iterations using 5-fold cross validation. In order to evaluate the performance of classification model, in each iterations the Accuracy (ACC) and F1score were computed. The classification results obtained using the proposed method is tabulated in Table 6 . Table 5 Classification results obtained using Linear SVM (using All features) Sl. no Modality AD vs NC AD vs MCI MCI vs NC AD vs MCI vs NC ACC F1 ACC F1 ACC F1 ACC 1 MRI 97.8± 2.8 96.2± 2.46 74.5 ± 1.86 67.96 ± 2.45 90.99 ± 3.94 91.88 ± 3.27 81.65 ± 1.13 2 PET 87.0 ± 4.19 87.28 ± 3.57 76.6 ± 2.49 78.33 ± 1.78 89.5 ± 0.98 89.53 ± 0.99 86.54 ± 0.9 3 MRI + PET 96.3 ± 1.49 96.04 ± 1.56 75.0 ± 1.91 77.04 ± 1.42 93.05 ± 3.9 93.6 ± 3.4 83.65 ± 1.91 4 MRI + CSF 98.5 ± 0.53 98.38 ± 0.59 83.3 ± 1.4 81.11 ± 1.67 91.67 ± 3.04 92.37 ± 2.63 87.17 ± 1.13 5 MRI + Genetic 97.6 ± 1.81 97.38 ± 1.89 74.2 ± 2.34 68.03 ± 2.8 90.39 ± 3.36 91.33 ± 2.81 80.88 ± 1.42 6 MRI + Clinical 100 ± 0 100 ± 0 85.8 ± 1.6 82.87 ± 2.04 99.51 ± 0.31 99.52 ± 0.3 90.42 ± 1.04 7 PET + CSF 91.2 ± 3.22 91.06 ± 3.03 78.1 ± 2.12 79.55 ± 1.62 86.49 ± 0.93 86.45 ± 0.96 83.88 ± 0.97 8 PET + Genetic 88.0 ± 4.48 88.09 ± 3.96 76.4 ± 2.29 78.19 ± 1.62 82.4 ± 1.55 81.98 ± 1.66 79.61 ± 1.19 9 PET + Clinical 91.6 ± 4.31 91.66 ± 4.02 79.7 ± 3.1 81 ± 2.37 99.49 ± 0 99.5 ± 0 96.47 ± 0.6 10 MRI + PET + CSF 98.3 ± 0.62 98.18 ± 0.68 98.3 ± 0.62 98.18 ± 0.68 95.55 ± 2.39 95.75 ± 2.18 88.86 ± 1.54 11 MRI + PET + Genetic 96.1 ± 1.34 95.77 ± 1.42 96.1 ± 1.34 95.77 ± 1.42 92.91 ± 3.3 93.46 ± 2.9 83.94 ± 1.58 12 MRI + PET + Clinical 99 ± 0.63 98.89 ± 0.7 99 ± 0.63 98.89 ± 0.7 99.67 ± 0.25 99.67 ± 0.25 92.21 ± 1.15 13 MRI + CSF + Clinical 99.7 ± 0.35 99.7 ± 0.39 99.7 ± 0.35 99.7 ± 0.39 99.46 ± 0.28 99.47 ± 0.27 91.87 ± 0.8 14 MRI + Genetic + Clinical 100 ± 0 100± 0 100 ± 0 100± 0 99.49 ± 0.07 99.5± 0.07 90.03 ± 1.11 15 PET + CSF + Genetic 91.2 ± 3.17 91.02 ± 2.95 91.2 ± 3.17 91.02 ± 2.95 86.04 ± 0.97 86.02 ± 0.98 83.76 ± 0.94 16 PET + CSF + Clinical 95.4 ± 2.35 95.24 ± 2.37 95.4 ± 2.35 95.24 ± 2.37 99.49 ± 0 99.5± 0 96.25 ± 0.38 17 MRI + PET + CSF + Genetic 98.1 ± 0.55 97.93 ± 0.61 78.6 ± 2.29 80.02 ± 1.79 95.7± 1.67 95.85 ± 1.54 88.58 ± 1.19 18 MRI + PET + CSF + Clinical 99.7 ± 0.32 99.76 ± 0.36 81.5 ± 2.38 82.39 ± 1.96 99.72 ± 0.35 99.72 ± 0.34 93.63 ± 0.91 19 MRI + PET + Genetic + Clinical 98.9 ± 0.44 98.8 ± 0.48 78.4 ± 2.16 79.62 ± 1.63 99.58 ± 0.19 99.58 ± 0.19 92.06 ± 1.2 20 MRI + CSF + Genetic + Clinical 99.3 ± 0.35 99.27 ± 0.39 87.2 ± 1.38 85.52 ± 1.6 99.4± 0.23 99.41 ± 0.23 91.58 ± 0.88 21 PET + CSF + Genetic + Clinical 96.2 ± 1.65 95.96 ± 1.7 81.9 ± 2.11 82.78 ± 1.66 99.49 ± 0 99.5± 0 96.33 ± 0.43 22 MRI + PET + CSF + Genetic + Clinical 99.57 ± 0.44 99.52 ± 0.49 81.93 ± 2.68 82.68 ± 2.2 99.47 ± 0.32 99.47 ± 0.31 93.35 ± 0.95 Table 6 Classification results obtained using Linear SVM with Feature selection Sl. no Modality AD Vs NC AD Vs MCI MCI vs NC AD Vs MCI Vs NC ACC F1 ACC F1 ACC F1 ACC 1 MRI 99.49 ± 0.37 99.43 ± 0.41 80.13 ± 1.75 75.8 ± 2.18 96.35 ± 1.99 96.54 ± 1.83 85.09± 1.22 2 PET 89.45 ± 4.38 89.63 ± 3.95 76.82 ± 1.98 78.6 ± 1.46 87.89 ± 0.74 87.86 ± 0.73 84.81 ± 0.81 3 MRI + PET 98.49 ± 0.6 98.3 ± 0.68 78.47 ± 1.99 79.0 ± 1.77 98.57 ± 0.87 98.61 ± 0.83 88.08 ± 1.16 4 MRI + CSF 98.35 ± 0.45 98.17 ± 0.49 84.87 ± 1.36 83.2 ± 1.64 96.58 ± 1.09 96.66 ± 1.05 87.82 ± 0.98 5 MRI + Genetic 99.28 ± 0.44 99.19 ± 0.5 79.26 ± 1.72 74.7 ± 2.28 96.68 ± 1.07 96.81 ± 1.01 84.34 ± 1.14 6 MRI + Clinical 100± 0 100± 0 89.11 ± 1.41 87.1 ± 1.71 99.49 ± 0 99.5± 0 92.57 ± 0.85 7 PET + CSF 95.94 ± 0.6 95.55 ± 0.65 81.71 ± 2.07 82.0 ± 1.71 84.95 ± 0.8 84.93 ± 0.77 83.81 ± 0.79 8 PET + Genetic 90.65 ± 4.3 90.62 ± 3.94 76.17 ± 1.9 78.0 ± 1.45 80.59 ± 1.53 80.57 ± 1.55 78.59 ± 1.47 9 PET + Clinical 99.99 ± 0.08 99.99 ± 0.09 86.11 ± 2.98 86.2 ± 2.56 99.49 ± 0 99.5± 0 97.26 ± 0.5 10 MRI + PET + CSF 99.32 ± 0.23 99.24 ± 0.26 86.94 ± 1.42 86.5 ± 1.41 97.51 ± 0.76 97.55 ± 0.74 90.9 ± 0.9 11 MRI + PET + Genetic 98.22 ± 0.63 97.99 ± 0.72 79.41 ± 2.05 79.9 ± 1.79 98.06 ± 0.63 98.11 ± 0.6 87.75 ± 1.17 12 MRI + PET + Clinical 99.95 ± 0.15 99.95 ± 0.17 88.93 ± 1.9 87.9 ± 1.99 99.49 ± 0 99.5± 0 94.84 ± 0.85 13 MRI + CSF + Clinical 99.79 ± 0.28 99.76 ± 0.31 88.78 ± 1.23 87.3 ± 1.44 99.49 ± 0 99.5± 0 92.22 ± 0.93 14 MRI + Genetic + Clinical 100± 0 100± 0 88.18 ± 1.33 85.9 ± 1.65 99.49 ± 0 99.5± 0 92.14 ± 0.84 15 PET + CSF + Genetic 95.48 ± 0.57 95.06 ± 0.62 82.49 ± 2.15 82.6 ± 1.79 85.15 ± 0.82 85.15 ± 0.8 83.78 ± 0.71 16 PET + CSF + Clinical 98.81 ± 0.41 98.68 ± 0.45 92.87 ± 0.8 92.2 ± 0.82 99.49 ± 0 99.5± 0 95.99 ± 0.43 17 MRI + PET + CSF + Genetic 99.11 ± 0.3 99.01 ± 0.34 87.98 ± 1.31 87.5 ± 1.32 96.79 ± 0.82 96.86 ± 0.79 90.68 ± 0.89 18 MRI + PET + CSF + Clinical 100± 0 100± 0 92.15 ± 1.2 91.3 ± 1.32 99.53 ± 0.14 99.54 ± 0.14 95 ± 0.56 19 MRI + PET + Genetic + Clinical 99.98 ± 0.11 99.97 ± 0.13 89.37 ± 1.74 88.4 ± 1.83 99.4 ± 0 99.5± 0 94.71 ± 1.01 20 MRI + CSF + Genetic + Clinical 99.74 ± 0.3 99.71 ± 0.33 88.6 ± 1.31 87.1 ± 1.56 99.49 ± 0 99.5± 0 92.55 ± 0.89 21 PET + CSF + Genetic + Clinical 98.65 ± 0.44 98.5 ± 0.49 92.74 ± 0.86 92.1 ± 0.88 99.49 ± 0 99.5± 0 96.0± 0.39 22 MRI + PET + CSF + Genetic + Clinical 99.99 ± 0.08 99.99 ± 0.09 92.27 ± 1.29 91.6 ± 1.38 99.49 ± 0 99.5± ss0 94.99 ± 0.8 5 Results And Discussion In the data of AD and NC and also from the literature [ 19 ] [ 20 ] [ 29 ] [ 31 ] [ 33 ] [ 36 ] [ 38 ], it is noted that higher classification accuracy above 90% is accomplished due to lesser correlation of features between AD and NC. However, in case of MCI vs NC the distinguished features were lesser and hence the accuracy will be mostly less than 90% reported [ 19 ] [ 20 ] [ 29 ] [ 31 ] [ 33 ] [ 36 ] [ 38 ]. Also, AD vs MCI classification were not reported in literature. The LASSO feature reduction techniques used over MRI and PET features reduces 116 features of MRI to 41 features, which is a 65% reduction from the list of ROI features. Similarly for PET, 116 features were reduced to 21 features, which is an 82% reduction from the ROI features. Comparison of SVM classifier performance of original set of ROI features against reduced set of MRI and PET features were carried out and the results are provided in a Fig. 2 . The classification performance of the original set of features and reduced set of features of MRI and PET were compared against the fusion of MRI, PET features with the modalities of CSF, Genetic and Clinical data. The results depict that a significant improvement of 4 to 5% of classification accuracy with the feature of reduction of MRI. However, in case PET, only 2% improvement in case of AD vs NC, which is a very meagre improvement for the classification and also the feature reduction becomes inferior for the case of MCI vs NC and AD vs MCI vs NC. This paper addresses the significance of feature selection with LASSO to improve the classification accuracy and report the accuracy using linear SVM technique with 5-fold cross validation. With the proposed technique MRI as single modality, accuracy of AD vs NC as 99.49% and MCI vs NC as 96.35% is accomplished. From literature using Hierarchical classifier learning proposed by [ 29 ] accuracy of 92.38% for AD vs NC and 84.24% for MCI vs NC is achieved which is significantly lesser compared to proposed technique. Similarly, using the PET and other modalities also compared against the classification accuracy reported in literature. The detailed comparison of accuracy of single and multi-modality fusion of features are provided in Tables 7 , 8 and 9 , for the case of AD vs NC, MCI vs NC and AD vs MCI vs NC. From the results of the Table 6 , it is evident that for single and multi-modality, fusion of features, the proposed LASSO feature selection shows improved classification accuracy compared to other methods reported in literature. The proposed LASSO based feature selection technique is also compared for multiclass classification of AD vs MCI vs NC against the methods reported in literature. The comparison of results of multiclass AD vs MCI vs NC is shown in Table 9 , also depicts that proposed features selection improves the classification accuracy significantly. Table 7 Comparison of accuracy in classification of Alzheimer’s disease (AD) and cognitively normal (NC) subjects Sl. no Author Data AD/NC (count) Algorithm Validation method ACC (%) 1. Westman, E., et. al. 2012[ 36 ] CSF 96/111 Orthogonal partial least squares to latent structures (OPLS) 7-Fold 81.6 MRI 87.0 MRI + CSF 91.8 2. Zhang, D et.al.2012 [ 38 ] MRI 45/50 SVM 10-Fold 84.80 ± 2.6 PET 84.5 ± 3.5 CSF 80.5 ± 2.2 MRI + PET + CSF 92.0 ± 3.3 MRI + PET + CSF Multi-modal multi-task learning 93.3 ± 2.2 3. Suk, H. I.,2014 [ 29 ] MRI 93/101 Hierarchical learning Scheme 10-Fold 92.38 ± 5.32 PET 92.20 ± 6.70 MRI + PET 95.35 ± 5.23 4. Lei, B et.al.,2016 [ 19 ] MRI 93/101 Simple modality fusion and SVM 10-Fold 91.76 ± 6.14 PET 90.89 ± 5.81 MRI + PET 94.4 ± 5.65 MRI + PET Hybrid level fusion 96.93 ± 2.65 5. Lei, B. et. al. 2017 [ 20 ] MRI + PET + CSF 226/186 Support Vector Classification (SVC) by sigmoid kernel 10-fold 94.68 6. Tong, T. et.al.,2017 [ 31 ] MRI 37/35 Nonlinear Graph Fusion, Random Forest classifier - 82.6 PET - 88.6 MRI + PET - 89.5 MRI + PET + CSF + Genetic - 91.8 MRI + PET + CSF + Genetic SVM - 91.4 7. Wang, Z, et. al., 2017 [ 33 ] MRI 93/101 Progressive Graph-based transductive learning (pGTL) 10-fold 88.6 ± 1.69 PET 87.3 ± 1.47 MRI + PET 92.6 ± 0.65 8. Proposed method MRI 78/96 LASSO feature selection, feature normalization and SVM classifier 5-fold 99.49 ± 0.37 PET 89.45 ± 4.38 MRI + PET 98.49 ± 0.6 MRI + CSF 98.35 ± 0.45 MRI + PET + CSF 99.32 ± 0.23 MRI + PET + CSF + Genetic 99.11 ± 0.3 MRI + PET + CSF + Genetic + Cognitive 99.99 ± 0.08 Table 8 Comparison of accuracy in classification of Mild cognitive impairment (MCI) and cognitively normal (NC) subjects Sl. no Author Data MCI/NC (count) Algorithm Validation method ACC (%) 1. Westman, E et. al.,2012 [ 36 ] CSF 162/111 orthogonal partial least squares to latent structures (OPLS) 7-Fold 70.3 MRI 71.8 MRI + CSF 77.6 2. Zhang, D et.al.2012 [ 38 ] MRI 91/50 SVM 10-Fold 73.9 ± 2.8 PET 79.7 ± 2.3 CSF 53.6 ± 4.4 MRI + PET + CSF 80.0 ± 2.4 MRI + PET + CSF Multi-modal multi-task learning 83.2 ± 1.5 3. Suk, H. I.,2014 [ 29 ] MRI 204/101 Hierarchical learning scheme 10-Fold 84.24 ± 6.26 PET 84.29 ± 7.22 MRI + PET 85.67 ± 5.22 4. Lei, B et.al.,2016 [ 19 ] MRI 204/101 Simple modality fusion and SVM 10-Fold 83.52 ± 5.38 PET 82.95 ± 6.37 MRI + PET 83.67 ± 5.49 MRI + PET Hybrid level fusion and SVM 86.57 ± 4.72 5. Lei, B. et. al. 2017 [ 20 ] MRI + PET + CSF 393/186 support vector classification (SVC) by sigmoid kernel 10-fold 80.32 6. Tong, T. et.al.,2017 [ 31 ] MRI 75/35 Nonlinear Graph Fusion, Random Forest classifier - 73.3 PET 75.4 MRI + PET 76.7 MRI + PET + CSF + Genetic 79.5 MRI + PET + CSF + Genetic SVM 77.4 7. Wang, Z, et. al., 2017 [ 33 ] MRI 102/101 Progressive Graph-based transductive learning (pGTL) 10-fold 70.7 ± 0.81 PET 72.5 ± 0.76 MRI + PET 78.9 ± 1.80 8. Proposed method MRI 100/96 LASSO feature selection, feature normalization and SVM classifier 5-fold 96.35 ± 1.99 PET 87.89 ± 0.74 MRI + PET 98.57 ± 0.87 MRI + CSF 96.58 ± 1.09 MRI + PET + CSF 97.51 ± 0.76 MRI + PET + CSF + Genetic 96.79 ± 0.82 MRI + PET + CSF + Genetic + Cognitive 99.49 ± 0 Table 9 Comparison of accuracy in classification of Alzheimer Disease (AD), Mild cognitive impairment (MCI) and cognitively normal (NC) subjects. Sl no Author Data AD/MCI/NC (count) Algorithm Validation method ACC (%) 1. Tong, T. et.al.,2017 [ 31 ] MRI 37/75/35 Random forest classifier - 56.3 PET - 56.5 MRI + PET - 58.2 MRI + PET + CSF + Genetic - 60.2 MRI + PET + CSF + Genetic SVM - 59.6 2. Proposed method MRI 78/100/96 LASSO feature selection, feature normalization and SVM classifier 5-fold 85.09 ± 1.22 PET 84.81 ± 0.81 MRI + PET 88.08 ± 1.16 MRI + CSF 87.82 ± 0.98 MRI + PET + CSF 90.09 ± 0.9 MRI + PET + CSF + Genetic 90.68 ± 0.89 MRI + PET + CSF + Genetic + Cognitive 94.99 ± 0.8 The analysis also carried to compare the effect of the proposed LASSO based feature selection technique for the single and multi-modality fusion of features. The features selection applied to MRI and PET modality were compared with fusion of CSF, Genetic and Clinical features for the classification accuracy of AD vs MCI vs NC. The results provided in the Table 5 depicts the accuracy and F1 score of all the 116 ROI features of MRI and PET, whereas Table 6 describe the accuracy and F1 score of selected 41 ROI features of MRI and 21 ROI features of PET selected using LASSO. The comparison of fusion of MRI and PET with other modalities were also carried and the results are depicted in Table 6 to validate the proposed feature selection technique. An improvement of 2–6% is accomplished in the proposed LASSO feature selection, in both single and multi-modality fusion of features. The results also illustrate that genetic and clinical features as a single modality are not suitable for the classification of either of AD vs MCI vs NC classes. From the analysis it is noted that, fusion of features of MRI + PET + CSF combination yields better accuracy for all the three categories of classification, however higher accuracy can be accomplished by fusing clinical or genetic features. The analysis was carried out on ADNI-1 dataset, for which the chosen patient IDs are provided in Table 10 . The results generated in the Tables 5 and 6 are computed as an average accuracy of 100 iterations. 6 Conclusion In this paper, the LASSO feature selection method is explored and evaluated for the improvement of the classification of MRI and PET ROI features, for AD vs MCI vs NC. The analysis was carried out for feature selection of ROI features of MRI and PET along with fusion of CSF, Genetic and Clinical features. In this fusion of features, the clinical data and genetic data fused with typical modalities like MRI, PET and CSF combination, improves the classification accuracy. The proposed LASSO based features selection and multimodality fusion improve the classification accuracy of AD vs MCI by 11% and AD vs MCI vs NC by 2%, compared to without employing any feature selection technique to the data. Declarations Acknowledgements Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf Author’s Contributions Shobha S (SS) has contributed in collecting MRI images, pre-processing and feature extraction, while Dr. Karthikeyan B R (KBR) has proposed the algorithm. SS was a major contributor to image analysis and writing the manuscript. KBR has reviewed the work, results and the manuscript, post which the final approved document has been submitted. Funding Not Applicable Conflict of interest Statement No conflict of interest was declared References 2021 Alzheimer’s disease facts and figures. (2021). Alzheimer’s and Dementia, 17(3), 327–406. https://doi.org/10.1002/alz.12328 Alzheimer, E., Mcevoy, L. K., Fennema-notestine, C., Jennings, R. G., Brewer, J. B., Hoh, C. K., & Dale, A. M. (2010). Relative Capability of MR Imaging and FDG PET to Depict Changes Associated with Purpose : Methods : Results. Radiology, 256(3), 932–942. https://doi.org/10.1148/radiol.10091402/-/DC1 Ashburner, J. (2009). Computational anatomy with the SPM software. Magnetic Resonance Imaging, 27(8), 1163–1174. https://doi.org/10.1016/j.mri.2009.01.006 Blennow, K., & Hampel, H. (2003). Review CSF markers for incipient Alzheimer ’ s disease CSF markers for incipient AD. 2(October), 605–613. Buerger, K., Ewers, M., Pirttilä, T., Zinkowski, R., Alafuzoff, I., Teipel, S. J., DeBernardis, J., Kerkman, D., McCulloch, C., Soininen, H., & Hampel, H. (2006). CSF phosphorylated tau protein correlates with neocortical neurofibrillary pathology in Alzheimer’s disease. Brain, 129(11), 3035–3041. https://doi.org/10.1093/brain/awl269 Cho, Y., Seong, J. K., Jeong, Y., & Shin, S. Y. (2012). Individual subject classification for Alzheimer’s disease based on incremental learning using a spatial frequency representation of cortical thickness data. NeuroImage, 59(3), 2217–2230. https://doi.org/10.1016/j.neuroimage.2011.09.085 Coley, N., Gardette, V., Cantet, C., Gillette-Guyonnet, S., Nourhashemi, F., Vellas, B., & Andrieu, S. (2011). How Should We Deal with Missing Data in Clinical Trials Involving Alzheimer’s Disease Patients? Current Alzheimer Research, 999(999), 1–12. https://doi.org/10.2174/1567211212443482050 Cuingnet, R., Gerardin, E., Tessieras, J., Auzias, G., Lehéricy, S., Habert, M. O., Chupin, M., Benali, H., & Colliot, O. (2011). Automatic classification of patients with Alzheimer’s disease from structural MRI: A comparison of ten methods using the ADNI database. NeuroImage, 56(2), 766–781. https://doi.org/10.1016/j.neuroimage.2010.06.013 De Magalhães Oliveira, P. P., Nitrini, R., Busatto, G., Buchpiguel, C., Sato, J. R., & Amaro, E. (2010). Use of SVM methods with surface-based cortical and volumetric subcortical measurements to detect Alzheimer’s disease. Journal of Alzheimer’s Disease, 19(4), 1263–1272. https://doi.org/10.3233/JAD-2010-1322 Gray, K. R., Wolz, R., Heckemann, R. A., Aljabar, P., Hammers, A., & Rueckert, D. (2012). Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer’s disease. NeuroImage, 60(1), 221–229. https://doi.org/10.1016/j.neuroimage.2011.12.071 Grundke-Iqbal, I., Iqbal, K., & Tung, Y. C. (1986). Abnormal phosphorylation of the microtubule-associated protein τ (tau) in Alzheimer cytoskeletal pathology. Proceedings of the National Academy of Sciences of the United States of America, 83(13), 44913–44917. https://doi.org/10.1097/00002093-198701030-00020 Gupta, Y., Lama, R. K., & Kwon, G. R. (2019). Prediction and Classification of Alzheimer’s Disease Based on Combined Features From Apolipoprotein-E Genotype, Cerebrospinal Fluid, MR, and FDG-PET Imaging Biomarkers. Frontiers in Computational Neuroscience, 13(October), 1–18. https://doi.org/10.3389/fncom.2019.00072 Hansson, O., Zetterberg, H., Buchhave, P., Andreasson, U., Londos, E., Minthon, L., & Blennow, K. (2007). Prediction of Alzheimer’s disease using the CSF Aβ42/Aβ40 ratio in patients with mild cognitive impairment. Dementia and Geriatric Cognitive Disorders, 23(5), 316–320. https://doi.org/10.1159/000100926 Hao, X., Bao, Y., Guo, Y., Yu, M., Zhang, D., Risacher, S. L., Saykin, A. J., Yao, X., & Shen, L. (2020). Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer’s disease. Medical Image Analysis, 60, 101625. https://doi.org/10.1016/j.media.2019.101625 Heywood, W. E., Hallqvist, J., Heslegrave, A. J., Zetterberg, H., Fenoglio, C., Scarpini, E., Rohrer, J. D., Galimberti, D., & Mills, K. (2018). CSF pro-orexin and amyloid-β38 expression in Alzheimer’s disease and frontotemporal dementia. Neurobiology of Aging, 72, 171–176. https://doi.org/10.1016/j.neurobiolaging.2018.08.019 Hinrichs, C., Singh, V., Xu, G., & Johnson, S. C. (2011). Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population. NeuroImage, 55(2), 574–589. https://doi.org/10.1016/j.neuroimage.2010.10.081 Hu, K., Wang, Y., Chen, K., Hou, L., & Zhang, X. (2015). Multi-scale features extraction from baseline structure MRI for MCI patient classification and AD early diagnosis. Neurocomputing, 175(PartA), 132–145. https://doi.org/10.1016/j.neucom.2015.10.043 Jacquier, M., Arango, D., Villareal, E., Torres, O., Serrano, M. L., Cruts, M., Montañes, P., Cano, C., Rodriguez, M. N., Serneels, S., & Van Broeckhoven, C. (2001). APOE ε4 and Alzheimer’s disease: Positive association in a Colombian clinical series and review of the Latin-American studies. Arquivos de Neuro-Psiquiatria, 59(1), 11–17. https://doi.org/10.1590/s0004-282x2001000100004 Lei, B., Chen, S., Ni, D., & Wang, T. (2016). Discriminative learning for Alzheimer’s disease diagnosis via canonical correlation analysis and multimodal fusion. Frontiers in Aging Neuroscience, 8(MAY), 1–17. https://doi.org/10.3389/fnagi.2016.00077 Lei, B., Yang, P., Wang, T., Chen, S., & Ni, D. (2017). Relational-Regularized Discriminative Sparse Learning for Alzheimer’s Disease Diagnosis. IEEE Transactions on Cybernetics, 47(4), 1102–1113. https://doi.org/10.1109/TCYB.2016.2644718 Li, Y., Meng, F., & Shi, J. (2019). Learning using privileged information improves neuroimaging-based CAD of Alzheimer’s disease: a comparative study. Medical and Biological Engineering and Computing, 57(7), 1605–1616. https://doi.org/10.1007/s11517-019-01974-3 Maldjian, J. A., Laurienti, P. J., Kraft, R. A., & Burdette, J. H. (2003). An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets. NeuroImage, 19(3), 1233–1239. https://doi.org/10.1016/S1053-8119(03)00169-1 McKhann, G. M., Knopman, D. S., Chertkow, H., Hyman, B. T., Jack, C. R., Kawas, C. H., Klunk, W. E., Koroshetz, W. J., Manly, J. J., Mayeux, R., Mohs, R. C., Morris, J. C., Rossor, M. N., Scheltens, P., Carrillo, M. C., Thies, B., Weintraub, S., & Phelps, C. H. (2011). The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s and Dementia, 7(3), 263–269. https://doi.org/10.1016/j.jalz.2011.03.005 Riederer, I., Bohn, K. P., Preibisch, C., Wiedemann, E., Zimmer, C., Alexopoulos, P., & Förster, S. (2018). Alzheimer disease and mild cognitive impairment: Integrated pulsed arterial spin-labeling MRI and18F-FDG PET. Radiology, 288(1), 198–206. https://doi.org/10.1148/radiol.2018170575 Shoji, M., Matsubara, E., Kanai, M., Watanabe, M., Nakamura, T., Tomidokoro, Y., Shizuka, M., Katsumi, W., Igeta, Y., Ikeda, Y., Mizushima, K., Amari, M., Ishiguro, K., Kawarabayashi, T., Harigaya, Y., Okamoto, K., & Hirai, S. (1998). Combination assay of CSF Tau , A beta 1-40 and A beta 1-42 (43) as a biochemical marker of Alzheimer ’ s disease. J Neurol Sci., 158, 134–140. Sørensen, L., Igel, C., Pai, A., Balas, I., Anker, C., Lillholm, M., & Nielsen, M. (2017). Differential diagnosis of mild cognitive impairment and Alzheimer’s disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry. NeuroImage: Clinical, 13, 470–482. https://doi.org/10.1016/j.nicl.2016.11.025 Sperling, R. A., Aisen, P. S., Beckett, L. A., Bennett, D. A., Craft, S., Fagan, A. M., Iwatsubo, T., Jack, C. R., Kaye, J., Montine, T. J., Park, D. C., Reiman, E. M., Rowe, C. C., Siemers, E., Stern, Y., Yaffe, K., Carrillo, M. C., Thies, B., Morrison-Bogorad, M., … Phelps, C. H. (2011). Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s and Dementia, 7(3), 280–292. https://doi.org/10.1016/j.jalz.2011.03.003 S. S and B. R. Karthikeyan, "Feature Selection on MRI Data for Improved Classification of Alzheimer Disease," 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2021, pp. 1-6, doi: 10.1109/CONECCT52877.2021.9622551. Suk, H. Il, Lee, S. W., & Shen, D. (2014). Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage, 101, 569–582. https://doi.org/10.1016/j.neuroimage.2014.06.077 Tibshirani, R. (1996). Regression Shrinkage and Selection Via the Lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x Tong, T., Gray, K., Gao, Q., Chen, L., & Rueckert, D. (2017). Multi-modal classification of Alzheimer’s disease using nonlinear graph fusion. Pattern Recognition, 63(May 2016), 171–181. https://doi.org/10.1016/j.patcog.2016.10.009 Verghese, P. B., Castellano, J. M., & Holtzman, D. M. (2011). Apolipoprotein E in Alzheimer’s disease and other neurological disorders. The Lancet Neurology, 10(3), 241–252. https://doi.org/10.1016/S1474-4422(10)70325-2 Wang, Z., Zhu, X., Adeli, E., Zhu, Y., Nie, F., Munsell, B., & Wu, G. (2017). Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning. Medical Image Analysis, 39, 218–230. https://doi.org/10.1016/j.media.2017.05.003 Welge, V., Fiege, O., Lewczuk, P., Mollenhauer, B., Esselmann, H., Klafki, H. W., Wolf, S., Trenkwalder, C., Otto, M., Kornhuber, J., Wiltfang, J., & Bibl, M. (2009). Combined CSF tau, p-tau181 and amyloid-β 38/40/42 for diagnosing Alzheimer’s disease. Journal of Neural Transmission, 116(2), 203–212. https://doi.org/10.1007/s00702-008-0177-6 Westman, E., Aguilar, C., Muehlboeck, J. S., & Simmons, A. (2013). Regional magnetic resonance imaging measures for multivariate analysis in Alzheimer’s disease and mild cognitive impairment. Brain Topography, 26(1), 9–23. https://doi.org/10.1007/s10548-012-0246-x Westman, E., Muehlboeck, J. S., & Simmons, A. (2012). Combining MRI and CSF measures for classification of Alzheimer’s disease and prediction of mild cognitive impairment conversion. NeuroImage, 62(1), 229–238. https://doi.org/10.1016/j.neuroimage.2012.04.056 Wiltfang, J., Esselmann, H., Bibl, M., Hüll, M., Hampel, H., Kessler, H., Frölich, L., Schröder, J., Peters, O., Jessen, F., Luckhaus, C., Perneczky, R., Jahn, H., Fiszer, M., Maler, J. M., Zimmermann, R., Bruckmoser, R., Kornhuber, J., & Lewczuk, P. (2007). Amyloid β peptide ratio 42/40 but not Aβ42 correlates with phospho-Tau in patients with low- and high-CSF Aβ40 load. Journal of Neurochemistry, 101(4), 1053–1059. https://doi.org/10.1111/j.1471-4159.2006.04404.x Zhang, D., & Shen, D. (2012). Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease. NeuroImage, 59(2), 895–907. https://doi.org/10.1016/j.neuroimage.2011.09.069 Zhang, D., Wang, Y., Zhou, L., Yuan, H., & Shen, D. (2011). Multimodal classification of Alzheimer’s disease and mild cognitive impairment. NeuroImage, 55(3), 856–867. https://doi.org/10.1016/j.neuroimage.2011.01.008 Additional Declarations No competing interests reported. Supplementary Files Appendix.docx Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-1676817","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":108950725,"identity":"a32a706e-0f00-4aea-b037-bdebca55204b","order_by":0,"name":"S Shobha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCElEQVRIiWNgGAWjYDACCQY2ZiAlB2KDGDxQEoTwazEGYsZmkrQkNkC1QABu9QwM8rObjz0uqKlLn99+9jiQUStj3s7A+OBtG4OMOQ4tBneOpRvPOHY4d8OZvMTmGceO88gcZmA2nNvGwGPZgEOLRI6ZNA/bgdwNDDmGzTxsx3gkmBnYpHmBWgwO4HDYDJCWf3Xp8v1vgFr+gbWw/8anheEGUAtvG3MCkGHYzNtWA7aFGZ8Wgxtp6ca8fYcNN9x4lzibt+8AUAtjs+SccxJ4HJZ87DHPtzp5+f7cA5+BDHsJ/sMHP7wps7HH6TAEAMfFYSBmbGAAxRcRAKyljhiVo2AUjIJRMMIAAP9zUWmIAOc+AAAAAElFTkSuQmCC","orcid":"","institution":"Sapthagiri College of Engineering","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"S","middleName":"","lastName":"Shobha","suffix":""},{"id":108950726,"identity":"a4111fff-773b-4def-befd-af4ea8cd4935","order_by":1,"name":"B R Karthikeyan","email":"","orcid":"","institution":"M S Ramaiah University of Applied Sciences","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"B","middleName":"R","lastName":"Karthikeyan","suffix":""}],"badges":[],"createdAt":"2022-05-20 12:44:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1676817/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1676817/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":21971956,"identity":"77d98065-7808-4d18-b34a-91f8dfaad35f","added_by":"auto","created_at":"2022-05-27 16:53:07","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":58559,"visible":true,"origin":"","legend":"\u003cp\u003eThe workflow of AD vs MCI vs NC identification using LASSO feature selection\u003c/p\u003e\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-1676817/v1/ebdf6c05e982ce71d9e9e63c.png"},{"id":21971954,"identity":"00212e9b-25c7-4cf4-8062-ba00bb6b2e03","added_by":"auto","created_at":"2022-05-27 16:53:07","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":87321,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of classification accuracy with all 116 ROI features and Selected (41 features of MRI and 21 features of PET) ROI features\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-1676817/v1/7b90abb87de3c5d8d285e26d.png"},{"id":25206498,"identity":"d11e5775-ebae-4c99-9035-14d83297fd54","added_by":"auto","created_at":"2022-08-15 08:44:28","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":560891,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1676817/v1/73d81aea-3bb4-411b-bf0c-58d36182a8e8.pdf"},{"id":21971955,"identity":"31271ea8-9ad8-4064-bee3-af6d22221e9e","added_by":"auto","created_at":"2022-05-27 16:53:07","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":14227,"visible":true,"origin":"","legend":"","description":"","filename":"Appendix.docx","url":"https://assets-eu.researchsquare.com/files/rs-1676817/v1/6445c791c01b48f54644ca0b.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fusion of Multimodality Features for Improved Classification of Alzheimer Disease","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003eAlzheimer Disease (AD) is a common neurogenerative disorder, found in elderly people which develops with time by destroying brain cells leading to dementia. The progression of AD will be evaluated through imaging modalities and data are categorized into three stages Normal Controls (NC), Mild Cognitive Impairment (MCI) and Alzheimer Disease. All subjects of MCI will not develop AD, only few subjects will be converted into AD over time period [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Early diagnosis of AD may help the clinicians to improve the quality of life of AD subjects.\u003c/p\u003e \u003cp\u003eDiverse modalities are available such as Magnetic Resonance Imaging (MRI) and (Fluorodeoxyglucose Positron Emission Tomography) FDG-PET Imaging, Genetic and Cerebrospinal Fluid (CSF) to diagnose the progression of AD. The structural MRI is one of the most widely used modality due to its ability to distinguish between gray matter and white matter [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e] in dementia subjects. The change in the volume of gray matter in the hippocampus region of the brain is used as a biomarker in diagnosis of AD. The Gray matter present in the predefined 116 ROIs in the Hippocampus region is measured and used as a feature vector for classification. The Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a significant imaging modality in the early diagnosis of AD and several research studies have revealed significant reductions in metabolic rate of glucose in several regions of human brain [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e] [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] which can be exploited to identify AD. In genotype, dementia is the cause of permanent variations in Apolipoprotein-E APOE gene. The APOE gene has three versions such as e2, e3 and e4 alleles, among them subjects with APOE e4 have greater chance of developing AD [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e] at an early age compared to e2 [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. In CSF, the Aβ38, Aβ40, Aβ42, tau-total, tau-phosphor are the hallmarked biomarkers used for the diagnosis of AD. The presence of low level of Aβ42 has been validated by many authors [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e] in subjects suffering from AD. The Aβ40, and Aβ42 can be together used to detect AD which increases diagnosis accuracy [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Several authors have shown that the ratio of Aβ42/Aβ40 can be used to identify AD with higher accuracy instead of using alone Aβ42 [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. The significant correlation between low levels of Aβ38 with higher level of P-tau [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] and higher level of t-tau in CSF [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e] in subjects suffering from AD has been investigated by many researchers. The Plaques and tangles in subjects suffering from dementia, composed of amyloid beta fragments found in human brain block communication between neurons [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. The correlation between p-tau and tangle count in dementia subjects is reported by [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe above-mentioned modality provides limited information regarding dementia if used individually, thus multi-modality features when fused to extract different aspects of AD and provide complementary information. The combination of features from different modality will improve early detection of dementia [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. Many researchers have worked on developing computerized techniques for diagnosing AD. Among them MRI [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e] [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] and PET [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] are frequently used modalities. MRI provides fine structural anatomy and PET provides metabolic function of tissues of human brain [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. Therefore, fusion of multimodal features of MRI, PET, CSF, APOE and clinical features could improve the classification accuracy of AD [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e][\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis paper addresses the analysis of classification of AD vs MCI vs NC subjects by fusion of multiple modality features using machine learning algorithms. The features of Region of Interest (ROI) of MRI and PET were extracted and used for the classification of AD vs MCI vs NC. The relevant features were identified using LASSO cross validation technique to reduce the number of features. The analysis was carried to identify the possible combination of modalities for improved diagnosis of AD. The reduced features of MRI and PET are fused with APOE gene, CSF and clinical data in all possible combination to evaluate the classification accuracy. The analysis solidifies that fusion of multi-modality features always improves the classification accuracy compared to using any one of the single modality features. The results also revealed that APOE genotype identified as biomarker for AD doesn\u0026rsquo;t provide a notable classification accuracy as a single modality, whereas, by fusing it with other modalities exhibit a notable classification accuracy.\u003c/p\u003e"},{"header":"2 Dataset And Feature Extraction","content":"\u003cp\u003eThe ADNI LONI Image Data archives of ADNI was used for the analysis presented in this paper. The demographic details of the subjects selected for analysis is listed in Table 1. The SPM12 and CAT12 software tool box [3] were used for pre-processing and features extraction from MRI and PET images.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e1\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e Summary of Demographic characteristics of subjects\u003c/p\u003e\n\u003ctable border=\"1\" cellpadding=\"0\" cellspacing=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"15.492957746478874%\"\u003e\n \u003cp\u003e\u003cstrong\u003eGroup/ Gender\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"13.145539906103286%\"\u003e\n \u003cp\u003e\u003cstrong\u003eNo. of\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eSubjects\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.6056338028169%\"\u003e\n \u003cp\u003e\u003cstrong\u003eAge\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(Mean \u0026plusmn; Std)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.07511737089202%\"\u003e\n \u003cp\u003e\u003cstrong\u003eMMSE score\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(Mean \u0026plusmn; Std)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e\u003cstrong\u003eGDS\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(Mean \u0026plusmn; Std)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e\u003cstrong\u003eCDR\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(Mean \u0026plusmn; Std)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"15.492957746478874%\"\u003e\n \u003cp\u003eAD\u003c/p\u003e\n \u003cp\u003eMale/\u003c/p\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"13.145539906103286%\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.6056338028169%\"\u003e\n \u003cp\u003e75.87 \u0026plusmn; 7.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.07511737089202%\"\u003e\n \u003cp\u003e23.50\u0026plusmn; 2.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e1.53 \u0026plusmn; 1.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e1.00 \u0026plusmn; 1.06\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"15.492957746478874%\"\u003e\n \u003cp\u003eMCI\u003c/p\u003e\n \u003cp\u003eMale/\u003c/p\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"13.145539906103286%\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.6056338028169%\"\u003e\n \u003cp\u003e75.85 \u0026plusmn; 6.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.07511737089202%\"\u003e\n \u003cp\u003e28.92 \u0026plusmn; 1.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e1.00 \u0026plusmn; 1.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e0 \u0026plusmn; 0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"15.492957746478874%\"\u003e\n \u003cp\u003eNC\u003c/p\u003e\n \u003cp\u003eMale/\u003c/p\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"13.145539906103286%\"\u003e\n \u003cp\u003e96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.6056338028169%\"\u003e\n \u003cp\u003e75.81 \u0026plusmn; 4.8\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"18.07511737089202%\"\u003e\n \u003cp\u003e27.31 \u0026plusmn; 2.27\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e1.77 \u0026plusmn; 1.59\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"17.84037558685446%\"\u003e\n \u003cp\u003e0.51 \u0026plusmn; 0.09\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eThe values are denoted as mean \u0026plusmn; standard deviation.\u003c/p\u003e\n\u003cp\u003eMMSE=Mini Mental State Examination,\u003c/p\u003e\n\u003cp\u003eCDR=Clinical Dementia Rating, GDS=Global Deterioration Scale\u003c/p\u003e\n\u003cp\u003eTo extract features of MRI and FDG-PET images, a ROI Analysis [2] with an atlas specified by [22] was used. The FDG-PET images were pre-processed using the standard protocols (185 MBq (5 mCi) Dynamic 3D scan of six 5-min frames 30-60 min post injection) (http://adni.loni.usc.edu/methods/pet-analysis-method/pet-analysis/). The pre-processed FDG-PET scans were coregistered with the corresponding pre-processed MRI (http://adni.loni.usc.edu/methods/mri-tool/mri-analysis/) by using a three-dimensional method. The APOE gene in human body responsible for AD has three alleles e2, e3 and e4. The genetic feature for each subject consists of any one of the 6 genetic combinations such as (e2, e2), (e2, e3), (e2, e4), (e3, e3), (e3, e4) and (e4, e4). The APOE measures used in the current study is tabulated in Table 2.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e2\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e Each diagnostic group possessing each of the Six APOE allele pairs.\u003c/p\u003e\n\u003cdiv align=\"Left\"\u003e\n \u003ctable border=\"1\" cellpadding=\"0\" cellspacing=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e\u003cstrong\u003eGenetic\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003ebiomarkers\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u003cstrong\u003eAD\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u003cstrong\u003eMCI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e\u003cstrong\u003eNC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e3, e3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e54\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e3, e4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e4, e4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e2, e3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e2, e4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e(e2, e2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" width=\"36.36363636363637%\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal Subjects\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u003cstrong\u003e78\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"22.529644268774703%\"\u003e\n \u003cp\u003e\u003cstrong\u003e100\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" width=\"18.57707509881423%\"\u003e\n \u003cp\u003e\u003cstrong\u003e96\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eThe CSF biomarkers such as A\u0026beta;42, A\u0026beta;40, A\u0026beta;38, A\u0026beta;, t-tau and p-tau were acquired using the notable fully automated Roche Elecsys and cobas e 601 immunoassay analyzer system from ADNI. The CSF biomarkers were not available for all the subjects, the missing data were compensated using mean value imputation technique. The measure of CSF biomarkers used in the classification of AD is depicted in Table 3.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e3\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e CSF measures and biomarkers used in classification of AD\u003c/p\u003e\n\u003cdiv align=\"Left\"\u003e\n \u003ctable border=\"1\" cellpadding=\"0\" cellspacing=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003e\u003cstrong\u003eCSF Biomarkers\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e\u003cstrong\u003eAD\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e\u003cstrong\u003eMCI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e\u003cstrong\u003eNC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003eAb\u003csub\u003e38\u003c/sub\u003e,\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e1718.20\u0026plusmn; 499.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e1747.11\u0026plusmn; 584.04\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e1754.81\u0026plusmn; 566.55\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003eAb\u003csub\u003e40\u003c/sub\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e7398\u0026plusmn; 2098.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e7319.08\u0026plusmn; 2306.10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e7573.32\u0026plusmn; 2260.77\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003eAb\u0026nbsp;\u003csub\u003e42\u003c/sub\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e651.17 \u0026plusmn; 258.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e868.63\u0026plusmn; 456.40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e1096.05\u0026plusmn; 404.72\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003eAb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e624.58\u0026plusmn;267.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e943.39\u0026plusmn;616.30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e1174.17\u0026plusmn;507.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003et-tau\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e363.06\u0026plusmn;141.00\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e264.27\u0026plusmn;90.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e227.23\u0026plusmn;77.59\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" width=\"24.72885032537961%\"\u003e\n \u003cp\u003ep-tau\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e37.47897\u0026plusmn;17.30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"24.945770065075923%\"\u003e\n \u003cp\u003e25.74\u0026plusmn;9.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" width=\"25.162689804772235%\"\u003e\n \u003cp\u003e21.165\u0026plusmn;7.96\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003epg \u0026frasl; ml=Picograms/milliliter\u003c/p\u003e"},{"header":"3 Feature Selection Using Lasso Technique","content":"\u003cp\u003eThe Least Absolute Shrinkage and Selection Operator (LASSO) feature selection selects the relevant features among the available features. The LASSO performs L1 regularization and was developed by Tibshirani [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e], it identifies the most relevant features by performing cross validation of features against its class labels. This intern reduces the number of features, result in improving accuracy of the classifier. The authors have explored the LASSO based features selection on volumetric features and cortical thickness features to accomplish the improvement of classification Accuracy [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. In the proposed analysis the relevant features of MRI and FDG-PET identified using LASSO technique are provided in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eList of ROI biomarkers selected from MRI and PET images using LASSO Model\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSl. no\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eROI biomarkers\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMRI\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePET\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSl. no\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVolumetric Features\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eMRI\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003ePET\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecentral_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParietal_Sup_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecentral_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParietal_Sup_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParietal_Inf_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParietal_Inf_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_Orb_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSupraMarginal_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_Orb_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSupraMarginal_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAngular_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eAngular_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_Orb_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePrecuneus_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_Orb_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePrecuneus_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Oper_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParacentral_Lobule_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Oper_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParacentral_Lobule_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Tri_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCaudate_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Tri_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCaudate_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Orb_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePutamen_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Inf_Orb_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePutamen_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRolandic_Oper_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePallidum_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRolandic_Oper_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003ePallidum_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSupp_Motor_Area_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eThalamus_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSupp_Motor_Area_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eThalamus_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOlfactory_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHeschl_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOlfactory_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHeschl_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_Medial_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Sup_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Sup_Medial_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Sup_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_Orb_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Pole_Sup_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrontal_Mid_Orb_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Pole_Sup_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRectus_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Mid_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRectus_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Mid_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eInsula_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Pole_Mid_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eInsula_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Pole_Mid_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Ant_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Inf_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Ant_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTemporal_Inf_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Mid_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_Crus1_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Mid_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_Crus1_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Post_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_Crus2_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCingulum_Post_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_Crus2_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHippocampus_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_3_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHippocampus_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_3_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eParaHippocampal_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_4_5_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eParaHippocampal_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_4_5_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAmygdala_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_6_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAmygdala_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_6_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCalcarine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e101\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_7b_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCalcarine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e102\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_7b_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCuneus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e103\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_8_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCuneus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e104\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_8_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLingual\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e105\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_9_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLingual_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_9_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Sup_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e107\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_10_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Sup_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e108\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCerebelum_10_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Mid_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e109\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_1_2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Mid_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e110\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Inf_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e111\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_4_5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOccipital_Inf_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e112\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFusiform_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e113\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFusiform_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e114\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePostcentral_L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e115\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePostcentral_R\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e116\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eVermis_10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u0026radic;\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"4 Classification Performance Analysis","content":"\u003cp\u003eThe overall workflow incorporated in the analysis is described through the Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The method comprised of four major steps: Image pre-processing and Feature Extraction, Feature Selection using LASSO algorithm, Fusion and Classification. In the current analysis the complete MRI, PET and APOE genotype data were available for all the subjects. The unavailable CSF data for some of the subjects were filled with mean value in each subgroup (AD, MCI and NC group) [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. The features were normalized using min-max normalization technique and relevant features selected using LASSO feature selection technique were applied to SVM classifier. The classification accuracy was computed by averaging 100 iterations using 5-fold cross validation. In order to evaluate the performance of classification model, in each iterations the Accuracy (ACC) and F1score were computed. The classification results obtained using the proposed method is tabulated in Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results obtained using Linear SVM (using All features)\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSl. no\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModality\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eAD vs NC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003eAD vs MCI\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003eMCI vs NC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eAD vs MCI vs NC\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97.8\u0026plusmn;\u003c/p\u003e \u003cp\u003e2.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.2\u0026plusmn;\u003c/p\u003e \u003cp\u003e2.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e74.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e67.96\u0026thinsp;\u0026plusmn;\u0026thinsp;2.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e90.99\u0026thinsp;\u0026plusmn;\u0026thinsp;3.94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e91.88\u0026thinsp;\u0026plusmn;\u0026thinsp;3.27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e81.65\u0026thinsp;\u0026plusmn;\u0026thinsp;1.13\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.0\u0026thinsp;\u0026plusmn;\u0026thinsp;4.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e87.28\u0026thinsp;\u0026plusmn;\u0026thinsp;3.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e76.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e78.33\u0026thinsp;\u0026plusmn;\u0026thinsp;1.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e89.5\u0026thinsp;\u0026plusmn;\u0026thinsp;0.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e89.53\u0026thinsp;\u0026plusmn;\u0026thinsp;0.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e86.54\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e96.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.04\u0026thinsp;\u0026plusmn;\u0026thinsp;1.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e75.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e77.04\u0026thinsp;\u0026plusmn;\u0026thinsp;1.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e93.05\u0026thinsp;\u0026plusmn;\u0026thinsp;3.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e93.6\u0026thinsp;\u0026plusmn;\u0026thinsp;3.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.65\u0026thinsp;\u0026plusmn;\u0026thinsp;1.91\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.5\u0026thinsp;\u0026plusmn;\u0026thinsp;0.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.38\u0026thinsp;\u0026plusmn;\u0026thinsp;0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e83.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e81.11\u0026thinsp;\u0026plusmn;\u0026thinsp;1.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e91.67\u0026thinsp;\u0026plusmn;\u0026thinsp;3.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e92.37\u0026thinsp;\u0026plusmn;\u0026thinsp;2.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e87.17\u0026thinsp;\u0026plusmn;\u0026thinsp;1.13\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97.38\u0026thinsp;\u0026plusmn;\u0026thinsp;1.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e74.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e68.03\u0026thinsp;\u0026plusmn;\u0026thinsp;2.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e90.39\u0026thinsp;\u0026plusmn;\u0026thinsp;3.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e91.33\u0026thinsp;\u0026plusmn;\u0026thinsp;2.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e80.88\u0026thinsp;\u0026plusmn;\u0026thinsp;1.42\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e85.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.87\u0026thinsp;\u0026plusmn;\u0026thinsp;2.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.51\u0026thinsp;\u0026plusmn;\u0026thinsp;0.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.52\u0026thinsp;\u0026plusmn;\u0026thinsp;0.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e90.42\u0026thinsp;\u0026plusmn;\u0026thinsp;1.04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.2\u0026thinsp;\u0026plusmn;\u0026thinsp;3.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.06\u0026thinsp;\u0026plusmn;\u0026thinsp;3.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e78.1\u0026thinsp;\u0026plusmn;\u0026thinsp;2.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e79.55\u0026thinsp;\u0026plusmn;\u0026thinsp;1.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e86.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e86.45\u0026thinsp;\u0026plusmn;\u0026thinsp;0.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.88\u0026thinsp;\u0026plusmn;\u0026thinsp;0.97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.0\u0026thinsp;\u0026plusmn;\u0026thinsp;4.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e88.09\u0026thinsp;\u0026plusmn;\u0026thinsp;3.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e76.4\u0026thinsp;\u0026plusmn;\u0026thinsp;2.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e78.19\u0026thinsp;\u0026plusmn;\u0026thinsp;1.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e82.4\u0026thinsp;\u0026plusmn;\u0026thinsp;1.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e81.98\u0026thinsp;\u0026plusmn;\u0026thinsp;1.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e79.61\u0026thinsp;\u0026plusmn;\u0026thinsp;1.19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.6\u0026thinsp;\u0026plusmn;\u0026thinsp;4.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.66\u0026thinsp;\u0026plusmn;\u0026thinsp;4.02\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79.7\u0026thinsp;\u0026plusmn;\u0026thinsp;3.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e81\u0026thinsp;\u0026plusmn;\u0026thinsp;2.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e96.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.18\u0026thinsp;\u0026plusmn;\u0026thinsp;0.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e98.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e98.18\u0026thinsp;\u0026plusmn;\u0026thinsp;0.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e95.55\u0026thinsp;\u0026plusmn;\u0026thinsp;2.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e95.75\u0026thinsp;\u0026plusmn;\u0026thinsp;2.18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e88.86\u0026thinsp;\u0026plusmn;\u0026thinsp;1.54\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e96.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.77\u0026thinsp;\u0026plusmn;\u0026thinsp;1.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e96.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e95.77\u0026thinsp;\u0026plusmn;\u0026thinsp;1.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e92.91\u0026thinsp;\u0026plusmn;\u0026thinsp;3.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e93.46\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.94\u0026thinsp;\u0026plusmn;\u0026thinsp;1.58\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.89\u0026thinsp;\u0026plusmn;\u0026thinsp;0.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e98.89\u0026thinsp;\u0026plusmn;\u0026thinsp;0.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.67\u0026thinsp;\u0026plusmn;\u0026thinsp;0.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.67\u0026thinsp;\u0026plusmn;\u0026thinsp;0.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.21\u0026thinsp;\u0026plusmn;\u0026thinsp;1.15\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e99.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e99.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.46\u0026thinsp;\u0026plusmn;\u0026thinsp;0.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e91.87\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e100\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e90.03\u0026thinsp;\u0026plusmn;\u0026thinsp;1.11\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.2\u0026thinsp;\u0026plusmn;\u0026thinsp;3.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.02\u0026thinsp;\u0026plusmn;\u0026thinsp;2.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91.2\u0026thinsp;\u0026plusmn;\u0026thinsp;3.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e91.02\u0026thinsp;\u0026plusmn;\u0026thinsp;2.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e86.04\u0026thinsp;\u0026plusmn;\u0026thinsp;0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e86.02\u0026thinsp;\u0026plusmn;\u0026thinsp;0.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.76\u0026thinsp;\u0026plusmn;\u0026thinsp;0.94\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.4\u0026thinsp;\u0026plusmn;\u0026thinsp;2.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.24\u0026thinsp;\u0026plusmn;\u0026thinsp;2.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e95.4\u0026thinsp;\u0026plusmn;\u0026thinsp;2.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e95.24\u0026thinsp;\u0026plusmn;\u0026thinsp;2.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e96.25\u0026thinsp;\u0026plusmn;\u0026thinsp;0.38\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.1\u0026thinsp;\u0026plusmn;\u0026thinsp;0.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97.93\u0026thinsp;\u0026plusmn;\u0026thinsp;0.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e78.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e80.02\u0026thinsp;\u0026plusmn;\u0026thinsp;1.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e95.7\u0026plusmn;\u003c/p\u003e \u003cp\u003e1.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e95.85\u0026thinsp;\u0026plusmn;\u0026thinsp;1.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e88.58\u0026thinsp;\u0026plusmn;\u0026thinsp;1.19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.76\u0026thinsp;\u0026plusmn;\u0026thinsp;0.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e81.5\u0026thinsp;\u0026plusmn;\u0026thinsp;2.38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.39\u0026thinsp;\u0026plusmn;\u0026thinsp;1.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.72\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.72\u0026thinsp;\u0026plusmn;\u0026thinsp;0.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e93.63\u0026thinsp;\u0026plusmn;\u0026thinsp;0.91\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.9\u0026thinsp;\u0026plusmn;\u0026thinsp;0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.8\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e78.4\u0026thinsp;\u0026plusmn;\u0026thinsp;2.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e79.62\u0026thinsp;\u0026plusmn;\u0026thinsp;1.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.58\u0026thinsp;\u0026plusmn;\u0026thinsp;0.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.58\u0026thinsp;\u0026plusmn;\u0026thinsp;0.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.06\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.27\u0026thinsp;\u0026plusmn;\u0026thinsp;0.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e87.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e85.52\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.4\u0026plusmn;\u003c/p\u003e \u003cp\u003e0.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.41\u0026thinsp;\u0026plusmn;\u0026thinsp;0.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e91.58\u0026thinsp;\u0026plusmn;\u0026thinsp;0.88\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e96.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.96\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e81.9\u0026thinsp;\u0026plusmn;\u0026thinsp;2.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.78\u0026thinsp;\u0026plusmn;\u0026thinsp;1.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e96.33\u0026thinsp;\u0026plusmn;\u0026thinsp;0.43\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.57\u0026thinsp;\u0026plusmn;\u0026thinsp;0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.52\u0026thinsp;\u0026plusmn;\u0026thinsp;0.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e81.93\u0026thinsp;\u0026plusmn;\u0026thinsp;2.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.68\u0026thinsp;\u0026plusmn;\u0026thinsp;2.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e93.35\u0026thinsp;\u0026plusmn;\u0026thinsp;0.95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results obtained using Linear SVM with Feature selection\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSl. no\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModality\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eAD Vs NC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003eAD Vs MCI\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003eMCI vs NC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eAD Vs MCI Vs NC\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e\u003cb\u003eF1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e\u003cb\u003eACC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.43\u0026thinsp;\u0026plusmn;\u0026thinsp;0.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e80.13\u0026thinsp;\u0026plusmn;\u0026thinsp;1.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e75.8\u0026thinsp;\u0026plusmn;\u0026thinsp;2.18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e96.35\u0026thinsp;\u0026plusmn;\u0026thinsp;1.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96.54\u0026thinsp;\u0026plusmn;\u0026thinsp;1.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e85.09\u0026plusmn;\u003c/p\u003e \u003cp\u003e1.22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89.45\u0026thinsp;\u0026plusmn;\u0026thinsp;4.38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e89.63\u0026thinsp;\u0026plusmn;\u0026thinsp;3.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e76.82\u0026thinsp;\u0026plusmn;\u0026thinsp;1.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e78.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e87.89\u0026thinsp;\u0026plusmn;\u0026thinsp;0.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e87.86\u0026thinsp;\u0026plusmn;\u0026thinsp;0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e84.81\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e78.47\u0026thinsp;\u0026plusmn;\u0026thinsp;1.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e79.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e98.57\u0026thinsp;\u0026plusmn;\u0026thinsp;0.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e98.61\u0026thinsp;\u0026plusmn;\u0026thinsp;0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e88.08\u0026thinsp;\u0026plusmn;\u0026thinsp;1.16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.35\u0026thinsp;\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.17\u0026thinsp;\u0026plusmn;\u0026thinsp;0.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e84.87\u0026thinsp;\u0026plusmn;\u0026thinsp;1.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e83.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e96.58\u0026thinsp;\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96.66\u0026thinsp;\u0026plusmn;\u0026thinsp;1.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e87.82\u0026thinsp;\u0026plusmn;\u0026thinsp;0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.28\u0026thinsp;\u0026plusmn;\u0026thinsp;0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.19\u0026thinsp;\u0026plusmn;\u0026thinsp;0.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79.26\u0026thinsp;\u0026plusmn;\u0026thinsp;1.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e74.7\u0026thinsp;\u0026plusmn;\u0026thinsp;2.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e96.68\u0026thinsp;\u0026plusmn;\u0026thinsp;1.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96.81\u0026thinsp;\u0026plusmn;\u0026thinsp;1.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e84.34\u0026thinsp;\u0026plusmn;\u0026thinsp;1.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89.11\u0026thinsp;\u0026plusmn;\u0026thinsp;1.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e87.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.57\u0026thinsp;\u0026plusmn;\u0026thinsp;0.85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.94\u0026thinsp;\u0026plusmn;\u0026thinsp;0.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.55\u0026thinsp;\u0026plusmn;\u0026thinsp;0.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e81.71\u0026thinsp;\u0026plusmn;\u0026thinsp;2.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e84.95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e84.93\u0026thinsp;\u0026plusmn;\u0026thinsp;0.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.81\u0026thinsp;\u0026plusmn;\u0026thinsp;0.79\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e90.65\u0026thinsp;\u0026plusmn;\u0026thinsp;4.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e90.62\u0026thinsp;\u0026plusmn;\u0026thinsp;3.94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e76.17\u0026thinsp;\u0026plusmn;\u0026thinsp;1.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e78.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e80.59\u0026thinsp;\u0026plusmn;\u0026thinsp;1.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e80.57\u0026thinsp;\u0026plusmn;\u0026thinsp;1.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e78.59\u0026thinsp;\u0026plusmn;\u0026thinsp;1.47\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e86.11\u0026thinsp;\u0026plusmn;\u0026thinsp;2.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e86.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e97.26\u0026thinsp;\u0026plusmn;\u0026thinsp;0.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.32\u0026thinsp;\u0026plusmn;\u0026thinsp;0.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.24\u0026thinsp;\u0026plusmn;\u0026thinsp;0.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e86.94\u0026thinsp;\u0026plusmn;\u0026thinsp;1.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e86.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e97.51\u0026thinsp;\u0026plusmn;\u0026thinsp;0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e97.55\u0026thinsp;\u0026plusmn;\u0026thinsp;0.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e90.9\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.22\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e97.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79.41\u0026thinsp;\u0026plusmn;\u0026thinsp;2.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e79.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e98.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e98.11\u0026thinsp;\u0026plusmn;\u0026thinsp;0.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e87.75\u0026thinsp;\u0026plusmn;\u0026thinsp;1.17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88.93\u0026thinsp;\u0026plusmn;\u0026thinsp;1.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e87.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e94.84\u0026thinsp;\u0026plusmn;\u0026thinsp;0.85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.76\u0026thinsp;\u0026plusmn;\u0026thinsp;0.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88.78\u0026thinsp;\u0026plusmn;\u0026thinsp;1.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e87.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.22\u0026thinsp;\u0026plusmn;\u0026thinsp;0.93\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88.18\u0026thinsp;\u0026plusmn;\u0026thinsp;1.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e85.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.14\u0026thinsp;\u0026plusmn;\u0026thinsp;0.84\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.48\u0026thinsp;\u0026plusmn;\u0026thinsp;0.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e82.49\u0026thinsp;\u0026plusmn;\u0026thinsp;2.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e82.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e85.15\u0026thinsp;\u0026plusmn;\u0026thinsp;0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e85.15\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e83.78\u0026thinsp;\u0026plusmn;\u0026thinsp;0.71\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.81\u0026thinsp;\u0026plusmn;\u0026thinsp;0.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.68\u0026thinsp;\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92.87\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e92.2\u0026thinsp;\u0026plusmn;\u0026thinsp;0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e95.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.43\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.11\u0026thinsp;\u0026plusmn;\u0026thinsp;0.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.01\u0026thinsp;\u0026plusmn;\u0026thinsp;0.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e87.98\u0026thinsp;\u0026plusmn;\u0026thinsp;1.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e87.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e96.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e96.86\u0026thinsp;\u0026plusmn;\u0026thinsp;0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e90.68\u0026thinsp;\u0026plusmn;\u0026thinsp;0.89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e100\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92.15\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e91.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.53\u0026thinsp;\u0026plusmn;\u0026thinsp;0.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.54\u0026thinsp;\u0026plusmn;\u0026thinsp;0.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.98\u0026thinsp;\u0026plusmn;\u0026thinsp;0.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.97\u0026thinsp;\u0026plusmn;\u0026thinsp;0.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89.37\u0026thinsp;\u0026plusmn;\u0026thinsp;1.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e88.4\u0026thinsp;\u0026plusmn;\u0026thinsp;1.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.4\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e94.71\u0026thinsp;\u0026plusmn;\u0026thinsp;1.01\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.74\u0026thinsp;\u0026plusmn;\u0026thinsp;0.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.71\u0026thinsp;\u0026plusmn;\u0026thinsp;0.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e87.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e92.55\u0026thinsp;\u0026plusmn;\u0026thinsp;0.89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98.65\u0026thinsp;\u0026plusmn;\u0026thinsp;0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.5\u0026thinsp;\u0026plusmn;\u0026thinsp;0.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92.74\u0026thinsp;\u0026plusmn;\u0026thinsp;0.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e92.1\u0026thinsp;\u0026plusmn;\u0026thinsp;0.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e96.0\u0026plusmn;\u003c/p\u003e \u003cp\u003e0.39\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Clinical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92.27\u0026thinsp;\u0026plusmn;\u0026thinsp;1.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e91.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e99.5\u0026plusmn;\u003c/p\u003e \u003cp\u003ess0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e94.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"5 Results And Discussion","content":"\u003cp\u003eIn the data of AD and NC and also from the literature [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e], it is noted that higher classification accuracy above 90% is accomplished due to lesser correlation of features between AD and NC. However, in case of MCI vs NC the distinguished features were lesser and hence the accuracy will be mostly less than 90% reported [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e] [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e]. Also, AD vs MCI classification were not reported in literature.\u003c/p\u003e\n\u003cp\u003eThe LASSO feature reduction techniques used over MRI and PET features reduces 116 features of MRI to 41 features, which is a 65% reduction from the list of ROI features. Similarly for PET, 116 features were reduced to 21 features, which is an 82% reduction from the ROI features. Comparison of SVM classifier performance of original set of ROI features against reduced set of MRI and PET features were carried out and the results are provided in a Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003eThe classification performance of the original set of features and reduced set of features of MRI and PET were compared against the fusion of MRI, PET features with the modalities of CSF, Genetic and Clinical data. The results depict that a significant improvement of 4 to 5% of classification accuracy with the feature of reduction of MRI. However, in case PET, only 2% improvement in case of AD vs NC, which is a very meagre improvement for the classification and also the feature reduction becomes inferior for the case of MCI vs NC and AD vs MCI vs NC.\u003c/p\u003e\n\u003cp\u003eThis paper addresses the significance of feature selection with LASSO to improve the classification accuracy and report the accuracy using linear SVM technique with 5-fold cross validation. With the proposed technique MRI as single modality, accuracy of AD vs NC as 99.49% and MCI vs NC as 96.35% is accomplished. From literature using Hierarchical classifier learning proposed by [\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e] accuracy of 92.38% for AD vs NC and 84.24% for MCI vs NC is achieved which is significantly lesser compared to proposed technique. Similarly, using the PET and other modalities also compared against the classification accuracy reported in literature. The detailed comparison of accuracy of single and multi-modality fusion of features are provided in Tables \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e, \u003cspan class=\"InternalRef\"\u003e8\u003c/span\u003e and \u003cspan class=\"InternalRef\"\u003e9\u003c/span\u003e, for the case of AD vs NC, MCI vs NC and AD vs MCI vs NC. From the results of the Table \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e, it is evident that for single and multi-modality, fusion of features, the proposed LASSO feature selection shows improved classification accuracy compared to other methods reported in literature. The proposed LASSO based feature selection technique is also compared for multiclass classification of AD vs MCI vs NC against the methods reported in literature. The comparison of results of multiclass AD vs MCI vs NC is shown in Table \u003cspan class=\"InternalRef\"\u003e9\u003c/span\u003e, also depicts that proposed features selection improves the classification accuracy significantly.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"char\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\u0026nbsp;\u003ctable border=\"1\" id=\"Tab7\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of accuracy in classification of Alzheimer\u0026rsquo;s disease (AD) and cognitively normal (NC) subjects\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSl. no\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAuthor\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eData\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAD/NC (count)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAlgorithm\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eValidation method\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eACC\u003c/p\u003e\n \u003cp\u003e(%)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e1.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eWestman, E., et. al. 2012[\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e96/111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eOrthogonal partial\u003c/p\u003e\n \u003cp\u003eleast squares to latent structures (OPLS)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e7-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e81.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e87.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e91.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e2.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eZhang, D et.al.2012 [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e45/50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84.80\u0026thinsp;\u0026plusmn;\u0026thinsp;2.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84.5\u0026thinsp;\u0026plusmn;\u0026thinsp;3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e80.5\u0026thinsp;\u0026plusmn;\u0026thinsp;2.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e92.0\u0026thinsp;\u0026plusmn;\u0026thinsp;3.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMulti-modal multi-task learning\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e93.3\u0026thinsp;\u0026plusmn;\u0026thinsp;2.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e3.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eSuk, H. I.,2014 [\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e93/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eHierarchical learning\u003c/p\u003e\n \u003cp\u003eScheme\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e92.38\u0026thinsp;\u0026plusmn;\u0026thinsp;5.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e92.20\u0026thinsp;\u0026plusmn;\u0026thinsp;6.70\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e95.35\u0026thinsp;\u0026plusmn;\u0026thinsp;5.23\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e4.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eLei, B et.al.,2016 [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e93/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eSimple modality fusion and SVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e91.76\u0026thinsp;\u0026plusmn;\u0026thinsp;6.14\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e90.89\u0026thinsp;\u0026plusmn;\u0026thinsp;5.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e94.4\u0026thinsp;\u0026plusmn;\u0026thinsp;5.65\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHybrid level fusion\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e96.93\u0026thinsp;\u0026plusmn;\u0026thinsp;2.65\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLei, B. et. al. 2017 [\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e226/186\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSupport Vector Classification (SVC) by sigmoid kernel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e94.68\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e6.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eTong, T. et.al.,2017 [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e37/35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eNonlinear Graph Fusion, Random Forest classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e82.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e88.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e89.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e91.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e91.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e7.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eWang, Z, et. al., 2017 [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e93/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eProgressive Graph-based transductive learning (pGTL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e10-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e88.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.69\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e87.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e92.6\u0026thinsp;\u0026plusmn;\u0026thinsp;0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e8.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eProposed method\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e78/96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eLASSO feature selection, feature normalization and SVM classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e5-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e89.45\u0026thinsp;\u0026plusmn;\u0026thinsp;4.38\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e98.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e98.35\u0026thinsp;\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e99.32\u0026thinsp;\u0026plusmn;\u0026thinsp;0.23\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e99.11\u0026thinsp;\u0026plusmn;\u0026thinsp;0.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Cognitive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e99.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"char\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\u0026nbsp;\u003ctable border=\"1\" id=\"Tab8\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of accuracy in classification of Mild cognitive impairment (MCI) and cognitively normal (NC) subjects\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSl. no\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAuthor\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eData\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eMCI/NC (count)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAlgorithm\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eValidation method\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eACC\u003c/p\u003e\n \u003cp\u003e(%)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e1.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eWestman, E et. al.,2012 [\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e162/111\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eorthogonal partial least squares to latent structures (OPLS)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e7-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e70.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e71.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e77.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e2.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eZhang, D et.al.2012 [\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e91/50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e73.9\u0026thinsp;\u0026plusmn;\u0026thinsp;2.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e79.7\u0026thinsp;\u0026plusmn;\u0026thinsp;2.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eCSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e53.6\u0026thinsp;\u0026plusmn;\u0026thinsp;4.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e80.0\u0026thinsp;\u0026plusmn;\u0026thinsp;2.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMulti-modal multi-task learning\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e83.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e3.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eSuk, H. I.,2014 [\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e204/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eHierarchical learning\u003c/p\u003e\n \u003cp\u003escheme\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84.24\u0026thinsp;\u0026plusmn;\u0026thinsp;6.26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84.29\u0026thinsp;\u0026plusmn;\u0026thinsp;7.22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e85.67\u0026thinsp;\u0026plusmn;\u0026thinsp;5.22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e4.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eLei, B et.al.,2016 [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e204/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eSimple modality fusion and\u003c/p\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003e10-Fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e83.52\u0026thinsp;\u0026plusmn;\u0026thinsp;5.38\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e82.95\u0026thinsp;\u0026plusmn;\u0026thinsp;6.37\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e83.67\u0026thinsp;\u0026plusmn;\u0026thinsp;5.49\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHybrid level fusion and\u003c/p\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e86.57\u0026thinsp;\u0026plusmn;\u0026thinsp;4.72\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eLei, B. et. al. 2017 [\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e393/186\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003esupport vector classification (SVC) by sigmoid kernel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e80.32\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e6.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eTong, T. et.al.,2017 [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e75/35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eNonlinear Graph Fusion, Random Forest classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e73.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e75.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e76.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e79.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e77.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e7.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eWang, Z, et. al., 2017 [\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e102/101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003eProgressive Graph-based transductive learning (pGTL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"3\"\u003e\n \u003cp\u003e10-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e70.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e72.5\u0026thinsp;\u0026plusmn;\u0026thinsp;0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e78.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.80\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e8.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eProposed method\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e100/96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eLASSO feature selection, feature normalization and SVM classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e5-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e96.35\u0026thinsp;\u0026plusmn;\u0026thinsp;1.99\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e87.89\u0026thinsp;\u0026plusmn;\u0026thinsp;0.74\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e98.57\u0026thinsp;\u0026plusmn;\u0026thinsp;0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e96.58\u0026thinsp;\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e97.51\u0026thinsp;\u0026plusmn;\u0026thinsp;0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e96.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Cognitive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e99.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\n \u003cdiv align=\"char\" class=\"colspec\"\u003e\u003cbr\u003e\u003c/div\u003e\u0026nbsp;\u003ctable border=\"1\" id=\"Tab9\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of accuracy in classification of Alzheimer Disease (AD), Mild cognitive impairment (MCI) and cognitively normal (NC) subjects.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"7\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSl no\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAuthor\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eData\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAD/MCI/NC (count)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eAlgorithm\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eValidation method\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eACC\u003c/p\u003e\n \u003cp\u003e(%)\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e1.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003eTong, T. et.al.,2017 [\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"5\"\u003e\n \u003cp\u003e37/75/35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"4\"\u003e\n \u003cp\u003eRandom forest classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e56.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e56.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e58.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e60.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eSVM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e59.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e2.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eProposed method\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e78/100/96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003eLASSO feature selection, feature normalization and SVM classifier\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" rowspan=\"7\"\u003e\n \u003cp\u003e5-fold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e85.09\u0026thinsp;\u0026plusmn;\u0026thinsp;1.22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e84.81\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e88.08\u0026thinsp;\u0026plusmn;\u0026thinsp;1.16\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e87.82\u0026thinsp;\u0026plusmn;\u0026thinsp;0.98\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e90.09\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e90.68\u0026thinsp;\u0026plusmn;\u0026thinsp;0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eMRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF\u0026thinsp;+\u0026thinsp;Genetic\u0026thinsp;+\u0026thinsp;Cognitive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e94.99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eThe analysis also carried to compare the effect of the proposed LASSO based feature selection technique for the single and multi-modality fusion of features. The features selection applied to MRI and PET modality were compared with fusion of CSF, Genetic and Clinical features for the classification accuracy of AD vs MCI vs NC. The results provided in the Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e depicts the accuracy and F1 score of all the 116 ROI features of MRI and PET, whereas Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e describe the accuracy and F1 score of selected 41 ROI features of MRI and 21 ROI features of PET selected using LASSO. The comparison of fusion of MRI and PET with other modalities were also carried and the results are depicted in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e to validate the proposed feature selection technique. An improvement of 2\u0026ndash;6% is accomplished in the proposed LASSO feature selection, in both single and multi-modality fusion of features. The results also illustrate that genetic and clinical features as a single modality are not suitable for the classification of either of AD vs MCI vs NC classes. From the analysis it is noted that, fusion of features of MRI\u0026thinsp;+\u0026thinsp;PET\u0026thinsp;+\u0026thinsp;CSF combination yields better accuracy for all the three categories of classification, however higher accuracy can be accomplished by fusing clinical or genetic features. The analysis was carried out on ADNI-1 dataset, for which the chosen patient IDs are provided in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e10\u003c/span\u003e. The results generated in the Tables\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e and \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e are computed as an average accuracy of 100 iterations.\u003c/p\u003e\n\n"},{"header":"6 Conclusion","content":"\u003cp\u003eIn this paper, the LASSO feature selection method is explored and evaluated for the improvement of the classification of MRI and PET ROI features, for AD vs MCI vs NC. The analysis was carried out for feature selection of ROI features of MRI and PET along with fusion of CSF, Genetic and Clinical features. In this fusion of features, the clinical data and genetic data fused with typical modalities like MRI, PET and CSF combination, improves the classification accuracy. The proposed LASSO based features selection and multimodality fusion improve the classification accuracy of AD vs MCI by 11% and AD vs MCI vs NC by 2%, compared to without employing any feature selection technique to the data.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eAcknowledgements\u003c/p\u003e\n\u003cp\u003eData used in preparation of this article were obtained from the Alzheimer\u0026rsquo;s Disease\u0026nbsp;Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf\u003c/p\u003e\n\u003cp\u003eAuthor\u0026rsquo;s Contributions\u003c/p\u003e\n\u003cp\u003eShobha S (SS) has contributed in collecting MRI images, pre-processing and feature extraction, while Dr. Karthikeyan B R (KBR) has proposed the algorithm. \u0026nbsp;SS was a major contributor to image analysis and writing the manuscript. KBR has reviewed the work, results and the manuscript, post which the final approved document has been submitted.\u003c/p\u003e\n\u003cp\u003eFunding\u003c/p\u003e\n\u003cp\u003eNot Applicable\u003c/p\u003e\n\u003cp\u003eConflict of interest Statement\u003c/p\u003e\n\u003cp\u003eNo conflict of interest was declared\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003e2021 Alzheimer\u0026rsquo;s disease facts and figures. (2021). Alzheimer\u0026rsquo;s and Dementia, 17(3), 327\u0026ndash;406. https://doi.org/10.1002/alz.12328\u003c/li\u003e\n \u003cli\u003eAlzheimer, E., Mcevoy, L. K., Fennema-notestine, C., Jennings, R. G., Brewer, J. B., Hoh, C. K., \u0026amp; Dale, A. M. (2010). Relative Capability of MR Imaging and FDG PET to Depict Changes Associated with Purpose : Methods : Results. Radiology, 256(3), 932\u0026ndash;942. https://doi.org/10.1148/radiol.10091402/-/DC1\u003c/li\u003e\n \u003cli\u003eAshburner, J. (2009). Computational anatomy with the SPM software. Magnetic Resonance Imaging, 27(8), 1163\u0026ndash;1174. https://doi.org/10.1016/j.mri.2009.01.006\u003c/li\u003e\n \u003cli\u003eBlennow, K., \u0026amp; Hampel, H. (2003). Review CSF markers for incipient Alzheimer \u0026rsquo; s disease CSF markers for incipient AD. 2(October), 605\u0026ndash;613.\u003c/li\u003e\n \u003cli\u003eBuerger, K., Ewers, M., Pirttil\u0026auml;, T., Zinkowski, R., Alafuzoff, I., Teipel, S. J., DeBernardis, J., Kerkman, D., McCulloch, C., Soininen, H., \u0026amp; Hampel, H. (2006). CSF phosphorylated tau protein correlates with neocortical neurofibrillary pathology in Alzheimer\u0026rsquo;s disease. Brain, 129(11), 3035\u0026ndash;3041. https://doi.org/10.1093/brain/awl269\u003c/li\u003e\n \u003cli\u003eCho, Y., Seong, J. K., Jeong, Y., \u0026amp; Shin, S. Y. (2012). Individual subject classification for Alzheimer\u0026rsquo;s disease based on incremental learning using a spatial frequency representation of cortical thickness data. NeuroImage, 59(3), 2217\u0026ndash;2230. https://doi.org/10.1016/j.neuroimage.2011.09.085\u003c/li\u003e\n \u003cli\u003eColey, N., Gardette, V., Cantet, C., Gillette-Guyonnet, S., Nourhashemi, F., Vellas, B., \u0026amp; Andrieu, S. (2011). How Should We Deal with Missing Data in Clinical Trials Involving Alzheimer\u0026rsquo;s Disease Patients? Current Alzheimer Research, 999(999), 1\u0026ndash;12. https://doi.org/10.2174/1567211212443482050\u003c/li\u003e\n \u003cli\u003eCuingnet, R., Gerardin, E., Tessieras, J., Auzias, G., Leh\u0026eacute;ricy, S., Habert, M. O., Chupin, M., Benali, H., \u0026amp; Colliot, O. (2011). Automatic classification of patients with Alzheimer\u0026rsquo;s disease from structural MRI: A comparison of ten methods using the ADNI database. NeuroImage, 56(2), 766\u0026ndash;781. https://doi.org/10.1016/j.neuroimage.2010.06.013\u003c/li\u003e\n \u003cli\u003eDe Magalh\u0026atilde;es Oliveira, P. P., Nitrini, R., Busatto, G., Buchpiguel, C., Sato, J. R., \u0026amp; Amaro, E. (2010). Use of SVM methods with surface-based cortical and volumetric subcortical measurements to detect Alzheimer\u0026rsquo;s disease. Journal of Alzheimer\u0026rsquo;s Disease, 19(4), 1263\u0026ndash;1272. https://doi.org/10.3233/JAD-2010-1322\u003c/li\u003e\n \u003cli\u003eGray, K. R., Wolz, R., Heckemann, R. A., Aljabar, P., Hammers, A., \u0026amp; Rueckert, D. (2012). Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer\u0026rsquo;s disease. NeuroImage, 60(1), 221\u0026ndash;229. https://doi.org/10.1016/j.neuroimage.2011.12.071\u003c/li\u003e\n \u003cli\u003eGrundke-Iqbal, I., Iqbal, K., \u0026amp; Tung, Y. C. (1986). Abnormal phosphorylation of the microtubule-associated protein \u0026tau; (tau) in Alzheimer cytoskeletal pathology. Proceedings of the National Academy of Sciences of the United States of America, 83(13), 44913\u0026ndash;44917. https://doi.org/10.1097/00002093-198701030-00020\u003c/li\u003e\n \u003cli\u003eGupta, Y., Lama, R. K., \u0026amp; Kwon, G. R. (2019). Prediction and Classification of Alzheimer\u0026rsquo;s Disease Based on Combined Features From Apolipoprotein-E Genotype, Cerebrospinal Fluid, MR, and FDG-PET Imaging Biomarkers. Frontiers in Computational Neuroscience, 13(October), 1\u0026ndash;18. https://doi.org/10.3389/fncom.2019.00072\u003c/li\u003e\n \u003cli\u003eHansson, O., Zetterberg, H., Buchhave, P., Andreasson, U., Londos, E., Minthon, L., \u0026amp; Blennow, K. (2007). Prediction of Alzheimer\u0026rsquo;s disease using the CSF A\u0026beta;42/A\u0026beta;40 ratio in patients with mild cognitive impairment. Dementia and Geriatric Cognitive Disorders, 23(5), 316\u0026ndash;320. https://doi.org/10.1159/000100926\u003c/li\u003e\n \u003cli\u003eHao, X., Bao, Y., Guo, Y., Yu, M., Zhang, D., Risacher, S. L., Saykin, A. J., Yao, X., \u0026amp; Shen, L. (2020). Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer\u0026rsquo;s disease. Medical Image Analysis, 60, 101625. https://doi.org/10.1016/j.media.2019.101625\u003c/li\u003e\n \u003cli\u003eHeywood, W. E., Hallqvist, J., Heslegrave, A. J., Zetterberg, H., Fenoglio, C., Scarpini, E., Rohrer, J. D., Galimberti, D., \u0026amp; Mills, K. (2018). CSF pro-orexin and amyloid-\u0026beta;38 expression in Alzheimer\u0026rsquo;s disease and frontotemporal dementia. Neurobiology of Aging, 72, 171\u0026ndash;176. https://doi.org/10.1016/j.neurobiolaging.2018.08.019\u003c/li\u003e\n \u003cli\u003eHinrichs, C., Singh, V., Xu, G., \u0026amp; Johnson, S. C. (2011). Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population. NeuroImage, 55(2), 574\u0026ndash;589. https://doi.org/10.1016/j.neuroimage.2010.10.081\u003c/li\u003e\n \u003cli\u003eHu, K., Wang, Y., Chen, K., Hou, L., \u0026amp; Zhang, X. (2015). Multi-scale features extraction from baseline structure MRI for MCI patient classification and AD early diagnosis. Neurocomputing, 175(PartA), 132\u0026ndash;145. https://doi.org/10.1016/j.neucom.2015.10.043\u003c/li\u003e\n \u003cli\u003eJacquier, M., Arango, D., Villareal, E., Torres, O., Serrano, M. L., Cruts, M., Monta\u0026ntilde;es, P., Cano, C., Rodriguez, M. N., Serneels, S., \u0026amp; Van Broeckhoven, C. (2001). APOE \u0026epsilon;4 and Alzheimer\u0026rsquo;s disease: Positive association in a Colombian clinical series and review of the Latin-American studies. Arquivos de Neuro-Psiquiatria, 59(1), 11\u0026ndash;17. https://doi.org/10.1590/s0004-282x2001000100004\u003c/li\u003e\n \u003cli\u003eLei, B., Chen, S., Ni, D., \u0026amp; Wang, T. (2016). Discriminative learning for Alzheimer\u0026rsquo;s disease diagnosis via canonical correlation analysis and multimodal fusion. Frontiers in Aging Neuroscience, 8(MAY), 1\u0026ndash;17. https://doi.org/10.3389/fnagi.2016.00077\u003c/li\u003e\n \u003cli\u003eLei, B., Yang, P., Wang, T., Chen, S., \u0026amp; Ni, D. (2017). Relational-Regularized Discriminative Sparse Learning for Alzheimer\u0026rsquo;s Disease Diagnosis. IEEE Transactions on Cybernetics, 47(4), 1102\u0026ndash;1113. https://doi.org/10.1109/TCYB.2016.2644718\u003c/li\u003e\n \u003cli\u003eLi, Y., Meng, F., \u0026amp; Shi, J. (2019). Learning using privileged information improves neuroimaging-based CAD of Alzheimer\u0026rsquo;s disease: a comparative study. Medical and Biological Engineering and Computing, 57(7), 1605\u0026ndash;1616. https://doi.org/10.1007/s11517-019-01974-3\u003c/li\u003e\n \u003cli\u003eMaldjian, J. A., Laurienti, P. J., Kraft, R. A., \u0026amp; Burdette, J. H. (2003). An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI data sets. NeuroImage, 19(3), 1233\u0026ndash;1239. https://doi.org/10.1016/S1053-8119(03)00169-1\u003c/li\u003e\n \u003cli\u003eMcKhann, G. M., Knopman, D. S., Chertkow, H., Hyman, B. T., Jack, C. R., Kawas, C. H., Klunk, W. E., Koroshetz, W. J., Manly, J. J., Mayeux, R., Mohs, R. C., Morris, J. C., Rossor, M. N., Scheltens, P., Carrillo, M. C., Thies, B., Weintraub, S., \u0026amp; Phelps, C. H. (2011). The diagnosis of dementia due to Alzheimer\u0026rsquo;s disease: Recommendations from the National Institute on Aging-Alzheimer\u0026rsquo;s Association workgroups on diagnostic guidelines for Alzheimer\u0026rsquo;s disease. Alzheimer\u0026rsquo;s and Dementia, 7(3), 263\u0026ndash;269. https://doi.org/10.1016/j.jalz.2011.03.005\u003c/li\u003e\n \u003cli\u003eRiederer, I., Bohn, K. P., Preibisch, C., Wiedemann, E., Zimmer, C., Alexopoulos, P., \u0026amp; F\u0026ouml;rster, S. (2018). Alzheimer disease and mild cognitive impairment: Integrated pulsed arterial spin-labeling MRI and18F-FDG PET. Radiology, 288(1), 198\u0026ndash;206. https://doi.org/10.1148/radiol.2018170575\u003c/li\u003e\n \u003cli\u003eShoji, M., Matsubara, E., Kanai, M., Watanabe, M., Nakamura, T., Tomidokoro, Y., Shizuka, M., Katsumi, W., Igeta, Y., Ikeda, Y., Mizushima, K., Amari, M., Ishiguro, K., Kawarabayashi, T., Harigaya, Y., Okamoto, K., \u0026amp; Hirai, S. (1998). Combination assay of CSF Tau , A beta 1-40 and A beta 1-42 (43) as a biochemical marker of Alzheimer \u0026rsquo; s disease. J Neurol Sci., 158, 134\u0026ndash;140.\u003c/li\u003e\n \u003cli\u003eS\u0026oslash;rensen, L., Igel, C., Pai, A., Balas, I., Anker, C., Lillholm, M., \u0026amp; Nielsen, M. (2017). Differential diagnosis of mild cognitive impairment and Alzheimer\u0026rsquo;s disease using structural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry. NeuroImage: Clinical, 13, 470\u0026ndash;482. https://doi.org/10.1016/j.nicl.2016.11.025\u003c/li\u003e\n \u003cli\u003eSperling, R. A., Aisen, P. S., Beckett, L. A., Bennett, D. A., Craft, S., Fagan, A. M., Iwatsubo, T., Jack, C. R., Kaye, J., Montine, T. J., Park, D. C., Reiman, E. M., Rowe, C. C., Siemers, E., Stern, Y., Yaffe, K., Carrillo, M. C., Thies, B., Morrison-Bogorad, M., \u0026hellip; Phelps, C. H. (2011). Toward defining the preclinical stages of Alzheimer\u0026rsquo;s disease: Recommendations from the National Institute on Aging-Alzheimer\u0026rsquo;s Association workgroups on diagnostic guidelines for Alzheimer\u0026rsquo;s disease. Alzheimer\u0026rsquo;s and Dementia, 7(3), 280\u0026ndash;292. \u003ca href=\"https://doi.org/10.1016/j.jalz.2011.03.003\"\u003ehttps://doi.org/10.1016/j.jalz.2011.03.003\u003c/a\u003e\u003c/li\u003e\n \u003cli\u003eS. S and B. R. Karthikeyan, \u0026quot;Feature Selection on MRI Data for Improved Classification of Alzheimer Disease,\u0026quot; 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2021, pp. 1-6, doi: 10.1109/CONECCT52877.2021.9622551.\u003c/li\u003e\n \u003cli\u003eSuk, H. Il, Lee, S. W., \u0026amp; Shen, D. (2014). Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis. NeuroImage, 101, 569\u0026ndash;582. https://doi.org/10.1016/j.neuroimage.2014.06.077\u003c/li\u003e\n \u003cli\u003eTibshirani, R. (1996). Regression Shrinkage and Selection Via the Lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267\u0026ndash;288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x\u003c/li\u003e\n \u003cli\u003eTong, T., Gray, K., Gao, Q., Chen, L., \u0026amp; Rueckert, D. (2017). Multi-modal classification of Alzheimer\u0026rsquo;s disease using nonlinear graph fusion. Pattern Recognition, 63(May 2016), 171\u0026ndash;181. https://doi.org/10.1016/j.patcog.2016.10.009\u003c/li\u003e\n \u003cli\u003eVerghese, P. B., Castellano, J. M., \u0026amp; Holtzman, D. M. (2011). Apolipoprotein E in Alzheimer\u0026rsquo;s disease and other neurological disorders. The Lancet Neurology, 10(3), 241\u0026ndash;252. https://doi.org/10.1016/S1474-4422(10)70325-2\u003c/li\u003e\n \u003cli\u003eWang, Z., Zhu, X., Adeli, E., Zhu, Y., Nie, F., Munsell, B., \u0026amp; Wu, G. (2017). Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning. Medical Image Analysis, 39, 218\u0026ndash;230. https://doi.org/10.1016/j.media.2017.05.003\u003c/li\u003e\n \u003cli\u003eWelge, V., Fiege, O., Lewczuk, P., Mollenhauer, B., Esselmann, H., Klafki, H. W., Wolf, S., Trenkwalder, C., Otto, M., Kornhuber, J., Wiltfang, J., \u0026amp; Bibl, M. (2009). Combined CSF tau, p-tau181 and amyloid-\u0026beta; 38/40/42 for diagnosing Alzheimer\u0026rsquo;s disease. Journal of Neural Transmission, 116(2), 203\u0026ndash;212. https://doi.org/10.1007/s00702-008-0177-6\u003c/li\u003e\n \u003cli\u003eWestman, E., Aguilar, C., Muehlboeck, J. S., \u0026amp; Simmons, A. (2013). Regional magnetic resonance imaging measures for multivariate analysis in Alzheimer\u0026rsquo;s disease and mild cognitive impairment. Brain Topography, 26(1), 9\u0026ndash;23. https://doi.org/10.1007/s10548-012-0246-x\u003c/li\u003e\n \u003cli\u003eWestman, E., Muehlboeck, J. S., \u0026amp; Simmons, A. (2012). Combining MRI and CSF measures for classification of Alzheimer\u0026rsquo;s disease and prediction of mild cognitive impairment conversion. NeuroImage, 62(1), 229\u0026ndash;238. https://doi.org/10.1016/j.neuroimage.2012.04.056\u003c/li\u003e\n \u003cli\u003eWiltfang, J., Esselmann, H., Bibl, M., H\u0026uuml;ll, M., Hampel, H., Kessler, H., Fr\u0026ouml;lich, L., Schr\u0026ouml;der, J., Peters, O., Jessen, F., Luckhaus, C., Perneczky, R., Jahn, H., Fiszer, M., Maler, J. M., Zimmermann, R., Bruckmoser, R., Kornhuber, J., \u0026amp; Lewczuk, P. (2007). Amyloid \u0026beta; peptide ratio 42/40 but not A\u0026beta;42 correlates with phospho-Tau in patients with low- and high-CSF A\u0026beta;40 load. Journal of Neurochemistry, 101(4), 1053\u0026ndash;1059. https://doi.org/10.1111/j.1471-4159.2006.04404.x\u003c/li\u003e\n \u003cli\u003eZhang, D., \u0026amp; Shen, D. (2012). Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer\u0026rsquo;s disease. NeuroImage, 59(2), 895\u0026ndash;907. https://doi.org/10.1016/j.neuroimage.2011.09.069\u003c/li\u003e\n \u003cli\u003eZhang, D., Wang, Y., Zhou, L., Yuan, H., \u0026amp; Shen, D. (2011). Multimodal classification of Alzheimer\u0026rsquo;s disease and mild cognitive impairment. NeuroImage, 55(3), 856\u0026ndash;867. \u003ca href=\"https://doi.org/10.1016/j.neuroimage.2011.01.008\"\u003ehttps://doi.org/10.1016/j.neuroimage.2011.01.008\u003c/a\u003e\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Alzheimer Disease (AD), Mild Cognitive Impairment (MCI), Normal Controls (NC), Feature Selection","lastPublishedDoi":"10.21203/rs.3.rs-1676817/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1676817/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper focus on improved classification accuracy in classification of Alzheimer Disease (AD) vs Mild cognitive impairment (MCI) vs Normal Controls (NC) by feature reduction technique and fusion of multimodality features. The gray matter of specified ROI regions of brain is extracted from MRI and FDG-PET images. The LASSO feature selection technique is used to identify the relevant features significant for the classification of AD from MCI and NC. The reduction of features leads to 92.27% of accuracy which is improved by 11% compared without feature selection in classification of AD vs MCI. The classification of AD vs MCI and MCI vs NC is challenging due to the high correlations of the features. Through the analysis it is found that for AD vs MCI a maximum of 92.27% of classification accuracy accomplished for multimodal combination of features using linear Support vector Machine (SVM) algorithm and for MCI vs NC 99% accomplished using linear SVM algorithm. It is identified that fusion of features of all the modalities provides 94.9% accuracy for AD vs MCI vs NC. The analysis solidifies that fusion of multi-modality features always improves the classification accuracy compared to using any one of the single modality features. All the analysis were carried out using ADNI-1 data base and subject IDs are listed in Table 10.\u003c/p\u003e","manuscriptTitle":"Fusion of Multimodality Features for Improved Classification of Alzheimer Disease","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-05-27 16:53:05","doi":"10.21203/rs.3.rs-1676817/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f688b81b-2d65-4609-97bc-328638219101","owner":[],"postedDate":"May 27th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2022-08-15T08:44:19+00:00","versionOfRecord":[],"versionCreatedAt":"2022-05-27 16:53:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-1676817","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1676817","identity":"rs-1676817","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}