IDH mutation prediction in non-enhancing gliomas with relaxed T2-FLAIR mismatch and fractal dimension: a two-center study

IDH mutation prediction in non-enhancing gliomas with relaxed T2-FLAIR mismatch and fractal dimension: a two-center study | 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 IDH mutation prediction in non-enhancing gliomas with relaxed T2-FLAIR mismatch and fractal dimension: a two-center study Yu Han, Jin Zhang, Yi-bin Xi, Si-jie Xiu, Yang Yang, Yu-yao Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7334338/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Jan, 2026 Read the published version in BMC Medical Imaging → Version 1 posted 13 You are reading this latest preprint version Abstract Background To explore the relationship between relaxed T2-FLAIR mismatch (RT2FM) sign, fractal dimension (FD) of tumor contour and IDH mutation status, and construct models for IDH mutation prediction in non-enhancing gliomas. Methods This retrospective study enrolled 364 patients with non-enhancing gliomas from two independent cohorts: cohort A (n = 267) for training & internal validation set and cohort B (n = 97) for external testing set. RT2FM, FD, and other MRI semantic features were extracted. Boruta and least absolute shrinkage and selection operator algorithms were employed to select intersecting features. Four machine learning models were constructed using the intersecting features and their diagnostic performance was evaluated. Results The RT2FM sign predicted IDH mutation with an accuracy, sensitivity, and specificity of 0.969, 0.650, and 0.921 in cohort A, and 0.924, 0.419, and 0.762 in cohort B, respectively. In cohort A, FD were significantly higher in IDH wild-type than in IDH mutant groups (1.264 vs. 1.190; P < 0.001). Using an FD cutoff value of 1.225, the area under the curve (AUC) and accuracy for predicting IDH mutation were 0.884 and 0.839, respectively. Among models constructed using four intersecting features (FD, RT2FM, multifocal/multicentric, and tumor location), XGBoost demonstrated the optimal predictive performance, with AUCs of 0.974, 0.968 and 0.895 in the training, internal validation and external testing set, respectively. Conclusions RT2FM and FD can provide informative imaging biomarkers for predicting IDH mutation. The XGBoost model constructed by these features demonstrated favorable diagnostic performance for IDH mutation prediction in non-enhancing gliomas. Clinical trial number Not applicable Isocitrate dehydrogenase T2-FLAIR mismatch Magnetic resonance imaging Gliomas Fractal analysis Figures Figure 1 Figure 2 Figure 3 Figure 4 1. Introduction Diffuse glioma is the most common primary malignant brain tumor in adults. The 2021 World Health Organization (WHO) classification of tumors of central nervous system integrates molecular profiling with histopathology for the precise classification of diffuse glioma[ 1 ]. Isocitrate dehydrogenase (IDH) mutation status is established as a pivotal molecular biomarker for therapeutic decision-making and prognostic stratification[ 2 ]. Magnetic resonance imaging (MRI) is an important tool for gliomas diagnosis, with contrast enhancement on contrast-enhanced T1-weighted imaging (T1CE) serving as a radiographic biomarker indicative of aggressive biological behavior[ 3 , 4 ]. However, subsequent evidence has confirmed that non-enhancing gliomas are a large and heterogeneous group. Of these, approximately 18% are IDH wild-type (IDHwt)[ 5 ], and exhibiting aggressive biological behavior. Therefore, preoperative prediction of IDH mutation is important in non-enhancing adult-type gliomas. Glioma IDH mutation status drives tumor cell proliferative heterogeneity and spatial architecture[ 6 ], radiologically manifesting as MRI signal heterogeneity and irregular contours. Consequently, accurate quantification of these MRI-derived heterogeneity and morphological irregularity is essential for predicting IDH mutation status. Functional MRI enables IDH mutation prediction through quantification of intratumoral heterogeneity including cellular density, perfusion, and metabolite products[ 7 – 9 ]. Its clinical implementation is constrained by prolonged acquisition times, economic burdens, and inter-institutional heterogeneity in acquisition parameters and post-processing protocols. In contrast, the T2-fluid-attenuated inversion recovery mismatch (T2FM) sign is a promising radiogenomic biomarker detected on routine MRI with 100% specificity for predicting IDH mutant (IDHmut) astrocytomas[ 10 ]. However, its stringent diagnostic criteria result in limited predictive sensitivity and suboptimal interobserver agreement, significantly constraining clinical applicability[ 11 ]. Traditional morphological parameters (e.g., tumor volume, maximal diameter) based on Euclidean geometry provide only coarse approximations of contour irregularity. While radiomic features like sphericity, compactness, and sphericity enable quantitative assessment, their limited intuitive biological interpretability and requirement for complex computational pipelines hinder clinical adoption[ 12 ]. In contrast, the tumor-brain interface's inherent fractal properties offer an anatomically grounded framework[ 13 ], where fractal dimension (FD) emerging as a computationally metric that effectively quantifies contour irregularity without sophisticated mathematical operations[ 14 ]. In summary, previous studies on glioma intratumoral heterogeneity offered limited clinical utility and lacked effective methods for assessing tumor margin irregularity. Consequently, developing an IDH mutation prediction framework that integrates internal heterogeneity and contour irregularity indices, while ensuring clinical feasibility and interpretability, is imperative. In our study, we optimized T2FM to enhance its sensitivity, quantified contour irregularity using FD, and constructed an IDH prediction model combining FD with T2FM, accounting for both “internal heterogeneity” and “marginal invasiveness”. 2. Materials and Methods 2.1 Patients This study was approved by the institutional review board of *** Hospital (IRB No.********) and *** Hospital (IRB No.********). All procedures performed in this study involving human participants were in accordance with the ethical standards of the Declaration of Helsinki. Due to the retrospective nature of this study, the requirement for informed consent was waived. Potentially eligible patients with pathologically confirmed gliomas were consecutively enrolled according to the inclusion and exclusion criteria. The inclusion criteria were: (i) age ≥ 18 years; (ii) preoperative MRI scan was performed; (iii) clinicopathologic information was well documented, including age, gender, WHO grade and IDH mutation status. The exclusion criteria were: (i) patient underwent treatment before MRI; (ii) discernible enhancement in lesion was observed on T1CE; (iii) MRI image quality was unsatisfactory due to susceptibility or motion artifacts; (iv) missing in any of the four routine sequences, including T1 weighted imaging (T1WI), T2 weighted imaging (T2WI), FLAIR and T1CE. Finally, 267 patients from the *** Hospital between March 2017 and May 2023 were included in the training and internal validation set, and 97 patients from the *** Hospital between February 2018 and May 2022 were used as the external testing set. The patient selection process is depicted in Fig. 1 . 2.2 Histopathologic Analysis Histopathological and molecular analyses were in accordance with the 2021 WHO classification of tumors of the central nervous System. Sanger sequencing and next-generation sequencing were used to determine IDH mutation status. The lp/19q status was analyzed using fluorescent in situ hybridization or next-generation sequencing. 2.3 MRI Acquisitions MRI studies were performed at two institutions using either a 3.0 T or a 1.5 T unit from different scanners, with various parameters to reflect real inter-center heterogeneity. The brain tumor imaging protocol included T1WI, T2WI, FLAIR, and T1CE. The detailed acquisition parameters are provided in Supplementary Table S1 . 2.4. Image Analysis 2.4.1 Relaxed T2FM (RT2FM) Definition Diagnostic criteria for the relaxed T2FM sign: A lesion is classified as T2FM-positive if it displays focal region of T2WI hyperintensity with corresponding FLAIR hypointensity. Crucially, two points merit specification: First, the extent of mismatch region does not require involvement of the entire tumor region, and heterogeneous T2WI within this area is permissible. Second, cystic gliomas are classified as T2FM-positive. Representative cases are shown in Figure S1 . 2.4.2 MRI Semantic Feature Assessment Prior to feature assessment, all images were anonymized and radiologists were blinded to clinical history, pathological diagnosis, and molecular genotype of tumor. Two radiologists (*** and ***, with 5 and 8 years of brain tumor diagnostic experience, respectively) independently evaluated MRI semantic features including RT2FM, tumor location, multicentric/multifocal, T2WI homogeneity, deep white matter invasion, cyst, cortical involvement, tumor borders, and sinuous, wave-like intratumoral-wall (SWITW)[ 15 ]. In cases of inter-reader discrepancy, consensus was achieved through consultation with a third board-certified radiologist (***, with 20 years’ neuroimaging experience). Following a 3-month washout period, 30 randomly selected cases were reassessed for RT2FM sign by a senior radiologist. Intra- and inter-observer agreements of RT2FM were subsequently calculated. 2.5 Tumor Segmentation and Fractal Analysis Two radiologists (*** and ***, with 4 and 9 years of brain tumor diagnostic experience respectively) manually segmented tumor regions of interest (ROI) on axial FLAIR images, blinded to IDH mutation status. Previous studies demonstrated that tumor segmentation using fewer slices can effectively capture molecular subtype-associated heterogeneity in gliomas while reducing segmentation time and enhancing clinical feasibility[ 16 , 17 ]. In this study, ROIs were delineated on three adjacent consecutive slices centered on the slice demonstrating the maximal tumor diameter using open-source software ITK-SNAP (version 4.0.1; http://itk-snap.org ). The 2D FD values were calculated from the segmented masks using box-counting algorithms via Python[ 18 ]. As the optimal box size was unknown, a number of different 2D box sizes, ranging from 2 0 to 2 7 isotropic pixels, were adopted to compute the 2D FD[ 19 – 21 ]. The mean FD across the three slices was calculated per patient and utilized for subsequent analysis. Details of FD calculations are available in Supplementary S1 . 2.6 Model Development and Validation for IDH Mutation Prediction Patients from *** Hospital were randomly allocated to the training and internal validation sets at a 7:3 ratio for model construction and evaluation, while cases from *** Hospital served as an independent external testing set. In the training set, clinical and MRI semantic features underwent dual feature selection via least absolute shrinkage and selection operator (LASSO) regression and Boruta algorithm, with intersecting features retained as IDH mutation-associated predictors[ 22 ]. Subsequently, intersecting features were used for machine learning models construction, including light gradient boosting machine (LightGBM), logistic regression (LR), extreme gradient boosting (XGBoost) and support vector machine (SVM). Random search and manual fine-tuning with 5-fold cross-validation were used to determine the optimal hyperparameters for each model. Finally, SHapley Additive exPlanations (SHAP) was used to assess the significance of each feature in the model[ 23 ]. 2.7 Statistical Analysis Normality of the variables was assessed using the Shapiro-Wilk test. Quantitative variables were expressed as mean ± standard deviation for normal distribution or median with interquartile range (IQR) for non-normal distribution. Categorical variables were expressed as numbers and percentages. The Student’s t -test or one-way ANOVA test was used for continuous variables, and the Mann–Whitney U-test or Kruskal–Wallis H test was applied for nonparametric data. For comparative analyses of categorical variables in two groups, the chi-square test or Fisher’s exact test was used. Cohen’s Kappa analysis was used to assess the intra- and inter-observer agreement of RT2FM. Inter-class correlation coefficient (ICC) was calculated to evaluate the intra- and inter-observer agreement for FD. Receiver operating characteristic (ROC) curve was constructed to calculate area under the curve (AUC) and the optimal cut-off value was determined by the maximal Youden index. The performance of the IDH mutation prediction model was evaluated using multiple metrics, including AUC, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), F1 score, and Matthews correlation coefficient (MCC). The model’s fit was tested through calibration curve. The decision curve analysis (DCA) was utilized to assess the clinical utility of the model. Statistical analysis was performed using software (SPSS, version 26.0; MedCalc, version 15.0; R, version 4.3.2; Python, version 3.8.5). P < 0.05 was considered a statistically significant difference. 3. Results 3.1 Patient Characteristics Baseline characteristics is detailed in Table 1 . In cohort A, 267 patients (median age, 44 years; IQR, 36–52 years; 157 males) were included, comprising 129 astrocytomas, 98 oligodendrogliomas and 40 glioblastomas. Cohort B included 97 patients (median age, 42 years, IQR, 33–51 years; 56 males) with 66 IDHmut gliomas (25 astrocytomas, 41 oligodendrogliomas) and 31 glioblastomas. IDHmut gliomas exhibited a younger age compared to IDHwt group (cohort A, P = 0.002; cohort B, P < 0.001). Table 1 Patient characteristics. Characteristics Cohort A: Training set & Internal validation set Cohort B: External testing set IDHmut (n = 227) IDHwt (n = 40) P IDHmut (n = 66) IDHwt (n = 31) P Age(y) § 44 (36, 51) 52 (39, 61) 0.002 ‡ 39 (31,47) 51 (42, 62) < 0.001 ‡ Gender 0.380 Ψ 0.403 Ψ Male 136 (59.91) 21 (52.50) 40 (60.61) 16 (51.61) Female 91 (40.09) 19 (47.50) 26 (39.39) 15 (48.39) Histopathology NA NA Glioblastoma 0 (0.00) 40 (100.00) 0 (0.00) 31 (100.00) Astrocytoma 129 (56.83) 0 (0.00) 25 (37.88) 0 (0.00) Oligodendroglioma 98 (43.17) 0 (0.00) 41 (62.12) 0 (0.00) WHO Grade < 0.001 Ψ < 0.001 Ψ Grade 2 164 (72.25) 0 (0.00) 42 (63.64) 0 (0.00) Grade 3 54 (23.79) 0 (0.00) 22 (33.33) 0 (0.00) Grade 4 9 (3.96) 40 (100.00) 2 (3.03) 31 (100.00) Note. — Unless otherwise indicated, data are numbers of patients, and data in parentheses are percentages. IDH = isocitrate dehydrogenase, IDHmut = IDH mutant, IDHwt = IDH wild type, NA = not available. § Data are the median, and data in parentheses are the interquartile range. ‡ Mann-Whitney U test. Ψ Pearson's Chi-squared test. 3.2 MRI Semantic Features Table 2 presents MRI semantic feature differences between IDHmut and IDHwt groups across cohorts A and B. In cohort A, IDHmut gliomas exhibited frontal lobe predilection, well-defined tumor border, cortical involvement, heterogeneous T2WI, hyperintensity on T1WI and a positive SWITW sign. In contrast, IDHwt gliomas tended to show blurred borders, multifocal/multicentric and deep white matter invasion. Similar trends were observed in cohort B. No statistically differences were observed in cyst between IDHmut and IDHwt groups across both cohorts (all P > 0.05). Table 2 MRI semantic feature comparisons between IDHmut and IDHwt groups. Characteristics Cohort A: Training set & Internal validation set Cohort B: External testing set IDHmut (n = 227) IDHwt (n = 40) P IDHmut (n = 66) IDHwt (n = 31) P Location < 0.001 ξ < 0.001 ξ Frontal 157 (69.16) 10 (25.00) 42 (63.64) 9 (29.03) Temporal-insular 56 (24.67) 6 (15.00) 19 (28.79) 6 (19.35) Parieto-occipital 12 (5.29) 5 (12.50) 4 (6.06) 7 (22.58) Other 2 (0.88) 19 (47.50) 1 (1.51) 9 (29.04) RT2FM < 0.001 ξ < 0.001 Ψ Present 220 (96.92) 14 (35.00) 61 (92.42) 18 (58.06) Absent 7 (3.08) 26 (65.00) 5 (7.58) 13 (41.94) Multifocal/Multicentric < 0.001 ξ < 0.001 Ψ Present 8 (3.52) 22 (55.00) 5 (7.58) 11 (35.48) Absent 219 (96.48) 18 (45.00) 61 (92.42) 20 (64.52) Deep WM invasion < 0.001 ξ 0.001 Ψ Present 10 (4.41) 14 (35.00) 7 (10.61) 12 (38.71) Absent 217 (95.59) 26 (65.00) 59 (89.39) 19 (61.29) Cyst (s) 0.642 Ψ 0.708 ξ Present 47 (20.70) 7 (17.50) 5 (7.58) 3 (9.68) Absent 180 (79.30) 33 (82.50) 61 (92.42) 28 (90.32) Cortical involvement < 0.001 ξ 0.032 ξ Present 224 (98.68) 31 (77.50) 64 (96.97) 26 (83.87) Absent 3 (1.32) 9 (22.50) 2 (3.03) 5 (16.13) T2WI homogeneity < 0.001 Ψ 0.046 Ψ Homogeneous 23 (10.13) 13 (32.50) 13 (19.70) 12 (38.71) Heterogeneous 204 (89.87) 27 (67.50) 53 (80.30) 19 (61.29) Tumor border < 0.001 Ψ 0.001 Ψ Well defined 96 (42.29) 4 (10.00) 36 (54.55) 6 (19.35) Poorly defined 131 (57.71) 36 (90.00) 30 (45.45) 25 (80.65) Hyperintensity on T1WI 0.032 Ψ Present 65 (28.63) 5 (12.50) 21 (31.82) 1 (3.23) 0.002 Ψ Absent 162 (71.37) 35 (87.50) 45 (68.18) 30 (96.77) SWITW 0.016 Ψ Present 56 (24.67) 3 (7.50) 22 (33.33) 4 (12.90) 0.034 Ψ Absent 171 (75.33) 37 (92.50) 44 (66.67) 27 (87.10) Note. — Unless otherwise indicated, data are numbers of patients, and data in parentheses are percentages. IDH = isocitrate dehydrogenase, IDHmut = IDH mutant, IDHwt = IDH wild type, T1WI = T1 weighted imaging, T2WI = T2 weighted imaging, FLAIR = fluid-attenuated inversion recovery, RT2FM = relaxed T2-FLAIR mismatch, Deep WM invasion = deep white matter invasion, SWITW = sinuous wave-like intratumoral-wall. ξ Fisher's exact test. Ψ Pearson's Chi-squared test. 3.3 RT2FM for IDH Mutation Prediction Figure 2 depicts RT2FM distribution across histopathology subtypes (Sankey plot, left) and its diagnostic performance for predicting IDH mutation status (Radar chart, right). In cohort A, 234 cases showed positive RT2FM (astrocytoma, 127/129; oligodendroglioma, 93/98; glioblastoma, 14/40), while 33 cases were negative (astrocytoma, 2/129; oligodendroglioma, 5/98; glioblastoma, 26/40). In cohort B, positive RT2FM was observed in 79 cases (astrocytoma, 24/25; oligodendroglioma, 37/41; glioblastoma, 18/31), and 18 cases were negative (astrocytoma, 1/25; oligodendroglioma, 4/41; glioblastoma, 13/31). The presence, sensitivity, specificity, and accuracy of RT2FM for predicting IDH mutation were 0.876, 0.969, 0.650, and 0.921 in cohort A, and 0.814, 0.924, 0.419, and 0.762 in cohort B, respectively. The intra-observer and inter-observer agreement for RT2FM was almost perfect, with κ values of 0.867 and 0.824, respectively. 3.4 FD for IDH Mutation Prediction Representative cases of fractal analysis are shown in Fig. 3 A. The FD measurements demonstrated excellent consistency, with intra-observer and inter-observer ICCs of 0.957 and 0.909, respectively ( Figure S2 ). In cohort A, IDHwt gliomas exhibited higher FD than the IDHmut group (IDHwt, 1.264 vs. IDHmut, 1.190; P < 0.001) (Fig. 3 B). Further subgroup analysis revealed no significant difference in FD was observed between oligodendrogliomas (IDHmut-Noncodel) and astrocytomas (IDHmut-Codel) (Fig. 3 C). When the cut-off value was set at 1.225, the AUC for predicting IDH mutation was 0.884, with a sensitivity of 0.837 and a specificity of 0.850 (Fig. 3 D). 3.5 Model Performance for IDH Mutation Prediction Figure S3 illustrates the intersectional feature selection by LASSO and Boruta algorithm, identifying four critical features: FD, tumor location, multicentric/multifocal, and RT2FM. Utilizing these features, LightGBM, LR, XGBoost, and SVM were subsequently developed. As detailed in Table 3 , XGBoost model exhibited superior performance, with AUCs of 0.974/0.968/0.895 and ACCs of 0.952/0.950/0.876 across training/internal validation/external testing sets. The XGBoost model demonstrated good calibration and net benefit in the training set, internal validation set, and external testing set (Fig. 4 A). Figure 4 B-C displays SHAP-based feature rankings in the XGBoost model: FD > RT2FM > multifocal/multicentric > location. Specifically, lower FD, positive RT2FM, and negative multifocal/multicentric status were significantly associated with IDH mutation. Table 3 Comparisons of model performance for IDH mutation prediction across training, internal validation and external testing set. AUC (95%CI) SEN SPE PPV NPV ACC F1 score MCC XGBoost Training set 0.974 (0.936-1.000) 0.956 0.929 0.987 0.788 0.952 0.971 0.825 Internal validation set 0.968 (0.925-1.000) 0.941 0.833 0.970 0.714 0.950 0.955 0.728 External testing set 0.895 (0.820–0.970) 0.955 0.710 0.875 0.880 0.876 0.913 0.708 LightGBM Training set 0.969 (0.941–0.996) 0.893 0.893 0.979 0.595 0.893 0.934 0.672 Internal validation set 0.954 (0.901-1.000) 0.912 0.833 0.969 0.625 0.900 0.939 0.665 External testing set 0.893 (0.826–0.959) 0.803 0.774 0.883 0.649 0.794 0.841 0.599 SVM Training set 0.955 (0.909-1.000) 0.994 0.821 0.969 0.958 0.968 0.981 0.870 Internal validation set 0.850 (0.702–0.998) 0.985 0.583 0.931 0.875 0.925 0.957 0.677 External testing set 0.883 (0.810–0.957) 0.984 0.580 0.833 0.947 0.856 0.903 0.664 LR Training set 0.946 (0.892-1.000) 0.975 0.857 0.975 0.857 0.957 0.974 0.832 Internal validation set 0.968 (0.922-1.000) 0.985 0.667 0.944 0.889 0.938 0.964 0.737 External testing set 0.876 (0.801–0.951) 0.985 0.548 0.823 0.944 0.845 0.897 0.640 Note. — AUC = area under the receiver operating characteristic curve, CI = confidence interval, SEN = sensitivity, SPE = specificity, PPV = positive predictive value, NPV = negative predictive value, ACC = accuracy, MCC = matthews correlation coefficient, XGBoost = extreme gradient boosting, LightGBM = light gradient boosting machine, SVM = support vector machine, LR = logistic regression. 4. Discussion Exploration of a noninvasive tool to predict IDH mutation status is important to guide clinical decision-making in non-enhancing adult-type diffuse gliomas. Radiologically, gliomas with distinct IDH mutation status exhibit differences in intratumoral signal and contour irregularity. In our study, we employed RT2FM and other MRI semantic features to classify intratumoral heterogeneity while utilizing FD to quantify contour irregularity. Ultimately, four models were constructed to predict IDH mutation status by integrating RT2FM, FD and MRI semantic features. XGBoost model exhibited optimal diagnostic performance, with AUCs of 0.974/0.968/0.895 across training/internal validation/external testing sets. The classical T2FM requires a homogeneous T2WI signal and complete FLAIR signal attenuation (except for the high signal edge), resulting in reduced sensitivity for IDH mutation prediction in the real-world cohorts[ 24 , 25 ]. In this study, we applied a relaxed T2FM criterion that neither confines mismatch region to the entire tumor area nor requires homogeneous T2WI signal. Notably, for tumors exhibiting prominent cystic gliomas, we adopted the criteria established by Lee et al[ 26 ] to classify these cases as T2FM-positive, corresponding to IDHmut status. Following the aforementioned adjustments, our RT2FM demonstrated sensitivities of 0.969 and 0.924 in IDH mutation prediction across cohorts A and B, respectively. In alignment with our study design, Throckmorton et al.[ 11 ] demonstrated that incorporating T2WI heterogeneity (without restricting T2WI homogeneity) improved the sensitivity of T2FM for IDH prediction from 34–74%. Subsequent studies by Lasoki et al.[ 27 ] and Cho et al.[ 28 ] further quantified the spatial extent of mismatch involvement. By defining T2FM positive as a mismatch region involvement extent of ≥ 25% of tumor, these studies achieved sensitivities of 0.33–0.63 for IDH prediction while maintaining high specificity (0.92–1.00). However, the quantitative assessment of mismatch extent in these studies required complex postprocessing, and substantial interobserver variability, which may limit their clinical applicability. Although RT2FM improved the sensitivity for IDH mutation prediction, its specificity remained suboptimal, with values of 0.650 and 0.419 in cohorts A and B, respectively, likely attributable to local mismatch sign observed in glioblastoma[ 29 ]. Nevertheless, parameter complementarity in the multiparametric modeling framework mitigated this limitation. SHAP analysis further validated RT2FM as a critical predictive marker for IDH mutation prediction. It is well known that irregular morphology of gliomas arises from both heterogeneous distributions of tumor cells with differential proliferative capacities[ 30 ] and their selective, non-isotropic infiltration patterns along nerve bundles[ 31 ]. This makes tumors tend to exhibit more irregular geometries. Previous studies have reported that the contour of gliomas conforms to fractal geometry. Consequently, our study utilized FD to quantify irregularity of gliomas. Our results showed a higher median FD value of glioblastomas compared to the IDHmut gliomas, indicating a more irregular morphology. Similar to our findings, Saha et al.[ 32 ] found that IDHwt gliomas are more irregular compared to IDHmut gliomas based on morphological parameters. Indeed, pathological studies also suggest that the spatial heterogeneity and invasiveness of tumor cells are more pronounced in IDHwt gliomas than in IDHmut gliomas, thereby facilitating their anisotropic growth and potentially contributing to irregular morphology[ 33 ]. Considering clinical applicability, our study employed manual segmentation limited to three consecutive slices centered on tumor’s largest cross-sectional area. This approach not only reduced radiologists’time expenditure but also ensured reproducibility, thereby supporting potential clinical translation. Furthermore, SHAP-based feature rankings in the XGBoost model identified FD as the most critical variable for predicting IDH mutation in gliomas. During model construction, we incorporated two MRI semantic features, tumor location and multicentric/multifocal presentation, alongside RT2FM and FD. Our findings indicated that IDHmut gliomas were predominantly located in the frontal lobe, whereas multicentric/multifocal lesions were more common in IDHwt cases, aligning with previous studies[ 34 , 35 ]. Among the four constructed models for IDH mutation prediction, XGBoost achieved the highest performance, likely due to its gradient-boosted decision tree architecture, which efficiently handles nonlinear relationships, mitigates class imbalance, and ensures stable classification accuracy[ 36 , 37 ]. This algorithm has been widely implemented in artificial intelligence applications and is increasingly utilized for tumor molecular subtyping and prognostic prediction[ 38 , 39 ]. This study has several limitations. First, despite utilizing data from two independent medical institutions, the retrospective design inherently carries potential selection bias, and findings should be interpreted with caution. Second, the modest sample size necessitates future multicenter studies with larger cohorts to validate the findings. Third, although RT2FM demonstrated high sensitivity for IDH mutation prediction, sole reliance on RT2FM for diagnosis requires refined classification frameworks, which will be a focus of our future research. 5. Conclusions In our study, RT2FM significantly improved sensitivity for preoperative IDH mutation prediction in non-enhancing adult-type diffuse gliomas. Additionally, IDHwt gliomas exhibited higher FD compared to IDHmut counterparts. Furthermore, the XGBoost model integrating RT2FM, FD, and other MRI semantic features showed potential for IDH mutation prediction. However, validation for our findings in a prospective, multicenter cohort is warranted. Abbreviations AUC area under the curve FD fractal dimension FLAIR fluid-attenuated inversion recovery IDH isocitrate dehydrogenase IQR interquartile range LASSO least absolute shrinkage and selection operator MCC matthews correlation coefficient SHAP SHapley Additive exPlanations ROC receiver operating characteristic T1CE contrast-enhanced T1WI RT2FM relaxed T2-FLAIR mismatch WHO world health organization Declarations Acknowledgements The authors have no acknowledgements to declare. Author contributions Yu Han: Writing – review & editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. Jin Zhang: Writing – review & editing, Writing – original draft, Methodology, Conceptualization. Yi-bin Xi: Writing – review & editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. Si-jie Xiu: Writing – review & editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. Yang Yang: Writing – review & editing, Supervision, Project administration, Methodology, Conceptualization. Yu-yao Wang: Writing – review & editing, Writing – original draft, Visualization, Validation, Supervision, Software, Resources, Project administration, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. Funding This study received financial support from the National Natural Science Foundation of China (No. 82102127 to YY and No. 82371936 to YBX). Data Availability The datasets generated or analyzed during the study are not publicly available but are available from the corresponding author on reasonable request. Ethics approval and consent to participate This study was approved by the institutional review board of Tangdu Hospital (IRB No. K-HG-202507-05) and Xi'an People's Hospital (IRB No.20230904). All procedures performed in this study involving human participants were in accordance with the ethical standards of the Declaration of Helsinki. Due to the retrospective nature of this study, the requirement for informed consent was waived. Consent for publication Not applicable. Competing interests The authors declare no conflicts of interest. Author details Department of Radiology & Functional and Molecular Imaging Key Lab of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University, Xi'an, Shaanxi, P.R. China, 710038 Department of Radiology, Xi'an People's Hospital (Xi'an Fourth Hospital), Xi'an, Shaanxi, P.R. China, 710199 References Louis DN, Perry A, Wesseling P, Brat DJ, Cree IA, Figarella-Branger D et al . The 2021 WHO Classification of Tumors of the Central Nervous System: a summary. Neuro Oncol 2021, 23(8):1231-1251.http://doi.org/10.1093/neuonc/noab106. Berger TR, Wen PY, Lang-Orsini M, Chukwueke UN. World Health Organization 2021 Classification of Central Nervous System Tumors and Implications for Therapy for Adult-Type Gliomas: A Review. JAMA Oncol 2022, 8(10):1493-1501.http://doi.org/10.1001/jamaoncol.2022.2844. Brindle KM, Izquierdo-García JL, Lewis DY, Mair RJ, Wright AJ. Brain Tumor Imaging. J Clin Oncol 2017, 35(21):2432-2438.http://doi.org/10.1200/jco.2017.72.7636. Garzón B, Emblem KE, Mouridsen K, Nedregaard B, Due-Tønnessen P, Nome T et al . Multiparametric analysis of magnetic resonance images for glioma grading and patient survival time prediction. Acta Radiol 2011, 52(9):1052-1060.http://doi.org/10.1258/ar.2011.100510. Kang KM, Song J, Choi Y, Park C, Park JE, Kim HS et al . MRI Scoring Systems for Predicting Isocitrate Dehydrogenase Mutation and Chromosome 1p/19q Codeletion in Adult-type Diffuse Glioma Lacking Contrast Enhancement. Radiology 2024, 311(2):e233120.http://doi.org/10.1148/radiol.233120. Moffet JJD, Fatunla OE, Freytag L, Kriel J, Jones JJ, Roberts-Thomson SJ et al . Spatial architecture of high-grade glioma reveals tumor heterogeneity within distinct domains. Neurooncol Adv 2023, 5(1):vdad142.http://doi.org/10.1093/noajnl/vdad142. Pruis IJ, Koene SR, van der Voort SR, Incekara F, Vincent A, van den Bent MJ et al . Noninvasive differentiation of molecular subtypes of adult nonenhancing glioma using MRI perfusion and diffusion parameters. Neurooncol Adv 2022, 4(1):vdac023.http://doi.org/10.1093/noajnl/vdac023. Arzanforoosh F, van der Voort SR, Incekara F, Vincent A, Van den Bent M, Kros JM et al . Microvasculature Features Derived from Hybrid EPI MRI in Non-Enhancing Adult-Type Diffuse Glioma Subtypes. Cancers (Basel) 2023, 15(7).http://doi.org/10.3390/cancers15072135. Wu M, Jiang T, Guo M, Duan Y, Zhuo Z, Weng J et al . Amide proton transfer-weighted imaging and derived radiomics in the classification of adult-type diffuse gliomas. Eur Radiol 2024, 34(5):2986-2996.http://doi.org/10.1007/s00330-023-10343-6. Patel SH, Poisson LM, Brat DJ, Zhou Y, Cooper L, Snuderl M et al . T2-FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project. Clin Cancer Res 2017, 23(20):6078-6085.http://doi.org/10.1158/1078-0432.Ccr-17-0560. Throckmorton P, Graber JJ. T2-FLAIR mismatch in isocitrate dehydrogenase mutant astrocytomas: Variability and evolution. Neurology 2020, 95(11):e1582-e1589.http://doi.org/10.1212/wnl.0000000000010324. Park JE, Kim D, Kim HS, Park SY, Kim JY, Cho SJ et al . Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. Eur Radiol 2020, 30(1):523-536.http://doi.org/10.1007/s00330-019-06360-z. Torres Hoyos F, Navarro RB, Vergara Villadiego J, Guerrero-Martelo M. Geometrical study of astrocytomas through fractals and scaling analysis. Appl Radiat Isot 2018, 141:250-256.http://doi.org/10.1016/j.apradiso.2018.05.020. Lennon FE, Cianci GC, Cipriani NA, Hensing TA, Zhang HJ, Chen CT et al . Lung cancer-a fractal viewpoint. Nat Rev Clin Oncol 2015, 12(11):664-675.http://doi.org/10.1038/nrclinonc.2015.108. Li M, Wang J, Chen X, Dong G, Zhang W, Shen S et al . The sinuous, wave-like intratumoral-wall sign is a sensitive and specific radiological biomarker for oligodendrogliomas. Eur Radiol 2023, 33(6):4440-4452.http://doi.org/10.1007/s00330-022-09314-0. Kocak B, Durmaz ES, Ates E, Sel I, Turgut Gunes S, Kaya OK et al . Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status. Eur Radiol 2020, 30(2):877-886.http://doi.org/10.1007/s00330-019-06492-2. Chu JP, Song YK, Tian YS, Qiu HS, Huang XH, Wang YL et al . Diffusion kurtosis imaging in evaluating gliomas: different region of interest selection methods on time efficiency, measurement repeatability, and diagnostic ability. Eur Radiol 2021, 31(2):729-739.http://doi.org/10.1007/s00330-020-07204-x. Lopes R, Betrouni N. Fractal and multifractal analysis: a review. Medical image analysis 2009, 13(4):634-649.http://doi.org/10.1016/j.media.2009.05.003. Petrujkić K, Milošević N, Rajković N, Stanisavljević D, Gavrilović S, Dželebdžić D et al . Computational quantitative MR image features - a potential useful tool in differentiating glioblastoma from solitary brain metastasis. Eur J Radiol 2019, 119:108634.http://doi.org/10.1016/j.ejrad.2019.08.003. Curtin L, Whitmire P, White H, Bond KM, Mrugala MM, Hu LS, Swanson KR. Shape matters: morphological metrics of glioblastoma imaging abnormalities as biomarkers of prognosis. Sci Rep 2021, 11(1):23202.http://doi.org/10.1038/s41598-021-02495-6. Kim S, Park YW, Park SH, Ahn SS, Chang JH, Kim SH, Lee SK. Comparison of Diagnostic Performance of Two-Dimensional and Three-Dimensional Fractal Dimension and Lacunarity Analyses for Predicting the Meningioma Grade. Brain Tumor Res Treat 2020, 8(1):36-42.http://doi.org/10.14791/btrt.2020.8.e3. Sun T, Liu J, Yuan H, Li X, Yan H. Construction of a risk prediction model for lung infection after chemotherapy in lung cancer patients based on the machine learning algorithm. Front Oncol 2024, 14:1403392.http://doi.org/10.3389/fonc.2024.1403392. Muhammad D, Bendechache M. Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis. Comput Struct Biotechnol J 2024, 24:542-560.http://doi.org/10.1016/j.csbj.2024.08.005. Dagher SA, Lochner RH, Ozkara BB, Schomer DF, Wintermark M, Fuller GN, Ucisik FE. The T2-FLAIR mismatch sign in oncologic neuroradiology: History, current use, emerging data, and future directions. Neuroradiol J 2024, 37(4):441-453.http://doi.org/10.1177/19714009231212375. Han Z, Chen Q, Zhang L, Mo X, You J, Chen L et al . Radiogenomic association between the T2-FLAIR mismatch sign and IDH mutation status in adult patients with lower-grade gliomas: an updated systematic review and meta-analysis. Eur Radiol 2022, 32(8):5339-5352.http://doi.org/10.1007/s00330-022-08607-8. Lee MD, Patel SH, Mohan S, Akbari H, Bakas S, Nasrallah MP et al . Association of partial T2-FLAIR mismatch sign and isocitrate dehydrogenase mutation in WHO grade 4 gliomas: results from the ReSPOND consortium. Neuroradiology 2023, 65(9):1343-1352.http://doi.org/10.1007/s00234-023-03196-9. Lasocki A, Buckland ME, Drummond KJ, Wei H, Xie J, Christie M et al . Conventional MRI features can predict the molecular subtype of adult grade 2-3 intracranial diffuse gliomas. Neuroradiology 2022, 64(12):2295-2305.http://doi.org/10.1007/s00234-022-02975-0. Cho NS, Sanvito F, Le VL, Oshima S, Teraishi A, Yao J et al . Quantification of T2-FLAIR Mismatch in Nonenhancing Diffuse Gliomas Using Digital Subtraction. AJNR Am J Neuroradiol 2024, 45(2):188-197.http://doi.org/10.3174/ajnr.A8094. Malik P, Soliman R, Chen YA, Munoz DG, Das S, Bharatha A, Mathur S. Patterns of T2-FLAIR discordance across a cohort of adult-type diffuse gliomas and deviations from the classic T2-FLAIR mismatch sign. Neuroradiology 2024, 66(4):521-530.http://doi.org/10.1007/s00234-024-03297-z. Sánchez J, Martín-Landrove M. Morphological and Fractal Properties of Brain Tumors. Front Physiol 2022, 13:878391.http://doi.org/10.3389/fphys.2022.878391. Wang J, Yi L, Kang QM, Zhou J, Chen TQ, Hugnot JP, Yu SC. Glioma invasion along white matter tracts: A dilemma for neurosurgeons. Cancer letters 2022, 526:103-111.http://doi.org/10.1016/j.canlet.2021.11.020. Mazurowski MA, Clark K, Czarnek NM, Shamsesfandabadi P, Peters KB, Saha A. Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data. J Neurooncol 2017, 133(1):27-35.http://doi.org/10.1007/s11060-017-2420-1. Nie S, Zhu Y, Yang J, Xin T, Xue S, Sun J et al . Clinicopathologic analysis of microscopic tumor extension in glioma for external beam radiotherapy planning. BMC medicine 2021, 19(1):269.http://doi.org/10.1186/s12916-021-02143-w. Smits M, van den Bent MJ. Imaging Correlates of Adult Glioma Genotypes. Radiology 2017, 284(2):316-331.http://doi.org/10.1148/radiol.2017151930. Park YW, Han K, Ahn SS, Bae S, Choi YS, Chang JH et al . Prediction of IDH1-Mutation and 1p/19q-Codeletion Status Using Preoperative MR Imaging Phenotypes in Lower Grade Gliomas. AJNR Am J Neuroradiol 2018, 39(1):37-42.http://doi.org/10.3174/ajnr.A5421. Yue S, Li S, Huang X, Liu J, Hou X, Zhao Y et al . Machine learning for the prediction of acute kidney injury in patients with sepsis. J Transl Med 2022, 20(1):215.http://doi.org/10.1186/s12967-022-03364-0. Truong NCD, Bangalore Yogananda CG, Wagner BC, Holcomb JM, Reddy D, Saadat N et al . Two-Stage Training Framework Using Multicontrast MRI Radiomics for IDH Mutation Status Prediction in Glioma. Radiology Artificial intelligence 2024, 6(4):e230218.http://doi.org/10.1148/ryai.230218. Kandemirli SG, Kocak B, Naganawa S, Ozturk K, Yip SSF, Chopra S et al . Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomics for Prediction of H3K27M Mutation in Midline Gliomas. World Neurosurg 2021, 151:e78-e85.http://doi.org/10.1016/j.wneu.2021.03.135. Yan Z, Wang J, Dong Q, Zhu L, Lin W, Jiang X. XGBoost algorithm and logistic regression to predict the postoperative 5-year outcome in patients with glioma. Ann Transl Med 2022, 10(16):860.http://doi.org/10.21037/atm-22-3384. Additional Declarations No competing interests reported. Supplementary Files Supplementarymaterials.docx Cite Share Download PDF Status: Published Journal Publication published 03 Jan, 2026 Read the published version in BMC Medical Imaging → Version 1 posted Editorial decision: Revision requested 09 Dec, 2025 Reviews received at journal 08 Dec, 2025 Reviews received at journal 06 Dec, 2025 Reviewers agreed at journal 06 Dec, 2025 Reviewers agreed at journal 16 Nov, 2025 Reviewers agreed at journal 16 Nov, 2025 Reviews received at journal 06 Nov, 2025 Reviewers agreed at journal 06 Oct, 2025 Reviewers invited by journal 26 Sep, 2025 Editor invited by journal 25 Sep, 2025 Editor assigned by journal 12 Aug, 2025 Submission checks completed at journal 12 Aug, 2025 First submitted to journal 09 Aug, 2025 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-7334338","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":525887398,"identity":"f700cb3a-cb04-4a78-9d9c-7fe5150c13b9","order_by":0,"name":"Yu Han","email":"","orcid":"","institution":"Tangdu Hospital, Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Han","suffix":""},{"id":525887399,"identity":"17c5419d-451a-4704-ba07-086375a0c3e8","order_by":1,"name":"Jin Zhang","email":"","orcid":"","institution":"Tangdu Hospital, Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Zhang","suffix":""},{"id":525887400,"identity":"2df31875-34f1-463d-9beb-9a4e4c9d3cf4","order_by":2,"name":"Yi-bin Xi","email":"","orcid":"","institution":"Xi'an People's Hospital (Xi'an Fourth Hospital)","correspondingAuthor":false,"prefix":"","firstName":"Yi-bin","middleName":"","lastName":"Xi","suffix":""},{"id":525887401,"identity":"80d0faa6-1dec-49e6-8d6c-e5911bacea9a","order_by":3,"name":"Si-jie Xiu","email":"","orcid":"","institution":"Tangdu Hospital, Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Si-jie","middleName":"","lastName":"Xiu","suffix":""},{"id":525887403,"identity":"889ea122-dcbe-495d-805e-bf789972b32d","order_by":4,"name":"Yang Yang","email":"","orcid":"","institution":"Tangdu Hospital, Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Yang","suffix":""},{"id":525887404,"identity":"8ec35d2d-9a17-45d0-88c6-804b8c6f7c78","order_by":5,"name":"Yu-yao Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYHACxgcJBv957BsONj9IqJCQkydCC7PBhwpmGQPGw8cMPpyxMDZsIKyFTXLGGWYbA+ZjCZIz2yoSGQ4QUG9wI8dAmreNjcec7YyBMe88iQTGBuaHj24Q0GLM28bDY9lzxuAx7zaJPHYGNmPjHDxazIBaknnbJHgYboBs2SZRzNjAwyZNSMth3jYDHob7b4AunCOR2HCAsBbDxhlnEngMDoC830CEFvszz4oZPlQc4JFsAAXyMQljw2YCfpFsT97+I8HggD0/Aygqa+rk5NmbHz7Gp4VBIMMATYQZn3IQ4D/+gJCSUTAKRsEoGOkAADM5UwjqRlq9AAAAAElFTkSuQmCC","orcid":"","institution":"Tangdu Hospital, Fourth Military Medical University","correspondingAuthor":true,"prefix":"","firstName":"Yu-yao","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-08-09 14:08:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7334338/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7334338/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12880-025-02140-y","type":"published","date":"2026-01-03T15:58:35+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93063042,"identity":"d9e1d87a-6246-4257-ac23-6945af63d085","added_by":"auto","created_at":"2025-10-08 16:38:06","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142293,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/5fa8031b621ebe71d7647ca4.docx"},{"id":93063383,"identity":"ed6b0dbb-9264-4cc0-a64d-9dda2073cb32","added_by":"auto","created_at":"2025-10-08 16:38:15","extension":"tif","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4989086,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/9b08699f9c55ec1e5a00a382.tif"},{"id":93063391,"identity":"472f611b-2967-480c-b6d5-5897141915d2","added_by":"auto","created_at":"2025-10-08 16:38:16","extension":"tif","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11597862,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/9a4d89311d334502ee585b30.tif"},{"id":93063258,"identity":"c2f3b93d-1f2f-4784-acf5-98e4e3402e35","added_by":"auto","created_at":"2025-10-08 16:38:11","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32222,"visible":true,"origin":"","legend":"","description":"","filename":"Table.docx","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/e13767df15cc7e7ab42c3e33.docx"},{"id":93063346,"identity":"15eaf2c1-036c-41e8-81f9-567693af7229","added_by":"auto","created_at":"2025-10-08 16:38:13","extension":"tif","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2012522,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/5e83694971d59d2ef1634a4a.tif"},{"id":93062931,"identity":"d9206dd2-fd69-4656-90f2-33c6b8bc875a","added_by":"auto","created_at":"2025-10-08 16:38:05","extension":"tif","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6856364,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/58a27d36c5bab69ad0684209.tif"},{"id":93063204,"identity":"14194a9b-19ce-4ab0-ad21-fc80ab574001","added_by":"auto","created_at":"2025-10-08 16:38:09","extension":"json","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8051,"visible":true,"origin":"","legend":"","description":"","filename":"4e8c5de28f7a41f28a62524bcf4fe05e.json","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/a74fd9a145be18db760f7f72.json"},{"id":93065906,"identity":"ab138988-9a4a-4388-99a3-c9069a1a8562","added_by":"auto","created_at":"2025-10-08 16:46:07","extension":"tif","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24256398,"visible":true,"origin":"","legend":"","description":"","filename":"FigureS1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/8f98c2b87fd65b5a095a1018.tif"},{"id":93062838,"identity":"c75c9ce3-f0fd-41a5-a0e7-808a5a28e9f3","added_by":"auto","created_at":"2025-10-08 16:38:04","extension":"tif","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":455702,"visible":true,"origin":"","legend":"","description":"","filename":"FigureS2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/a6d7d03bfa49861a061b3760.tif"},{"id":93063451,"identity":"be2ee8c1-9eb0-45c6-bedc-5ff6497dfe1d","added_by":"auto","created_at":"2025-10-08 16:38:23","extension":"tif","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9585424,"visible":true,"origin":"","legend":"","description":"","filename":"FigureS3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/9df246a408eb7f9386fa1e83.tif"},{"id":93062892,"identity":"b3c4922a-0875-46b6-8377-0197e37e7595","added_by":"auto","created_at":"2025-10-08 16:38:05","extension":"docx","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1175652,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/db50c1b43d529ee262ed6621.docx"},{"id":93063063,"identity":"c9dfb94a-26df-4c5b-8b4a-d63c1de3cde7","added_by":"auto","created_at":"2025-10-08 16:38:07","extension":"xml","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159584,"visible":true,"origin":"","legend":"","description":"","filename":"4e8c5de28f7a41f28a62524bcf4fe05e1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/c168ba168cbe658c0785f0a5.xml"},{"id":93062990,"identity":"53ed0369-0c19-4afa-a116-82f91e40b4c3","added_by":"auto","created_at":"2025-10-08 16:38:06","extension":"tif","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4989086,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/8e1d2eaa4e37c9ccf21ea2df.tif"},{"id":93063060,"identity":"f9608303-9962-4f91-8660-9cd2876b9dd0","added_by":"auto","created_at":"2025-10-08 16:38:07","extension":"tif","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11597862,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/ac327dd1da08e2dec581ce11.tif"},{"id":93063244,"identity":"bc84a3b0-a516-4057-9ba0-40721c020254","added_by":"auto","created_at":"2025-10-08 16:38:10","extension":"tif","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2012522,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/c5f72ca68b9eadb3460c1dfb.tif"},{"id":93063374,"identity":"2af904f8-335e-4674-8b3a-b22dbc4e7f8c","added_by":"auto","created_at":"2025-10-08 16:38:14","extension":"tif","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6856364,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.tif","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/496ff26d4328a96e039c993f.tif"},{"id":93063376,"identity":"27db593a-b2ed-4704-b6b3-d8fe458d254d","added_by":"auto","created_at":"2025-10-08 16:38:14","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":743723,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/fbc60a9b033e0b2df591aa7c.png"},{"id":93062974,"identity":"6834e760-b1af-41e3-a9ce-64443c97f034","added_by":"auto","created_at":"2025-10-08 16:38:05","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":913839,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/4e1bbc0f7f9fb9eec8f6ea11.png"},{"id":93063424,"identity":"c43c1362-de11-473d-90e3-5bdfea27047c","added_by":"auto","created_at":"2025-10-08 16:38:18","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":201447,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/ebd86278eb01d93c355afbbb.png"},{"id":93062919,"identity":"0e0cb674-0c25-47a7-81cd-a0c0205cbcae","added_by":"auto","created_at":"2025-10-08 16:38:05","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":591287,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/717b9f4105a8bf8e2f4d290c.png"},{"id":93062896,"identity":"41a9e9ec-9a25-4b3e-9b69-7e2b4fddc2f5","added_by":"auto","created_at":"2025-10-08 16:38:05","extension":"xml","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156077,"visible":true,"origin":"","legend":"","description":"","filename":"4e8c5de28f7a41f28a62524bcf4fe05e1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/a72aef0b219de2b62fb1fa7d.xml"},{"id":93063052,"identity":"e6185033-d536-459f-b42d-f7f42003f782","added_by":"auto","created_at":"2025-10-08 16:38:07","extension":"html","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167805,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/a2d29064855195cd1af77d6d.html"},{"id":93063359,"identity":"898a6cf8-c6de-4cbf-a345-6cb2fab2296f","added_by":"auto","created_at":"2025-10-08 16:38:14","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":10319313,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePatient selection flowchart.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/8db437c3c8611667541e2e22.png"},{"id":93062814,"identity":"587d49fc-a91f-4ea8-b930-07f107760572","added_by":"auto","created_at":"2025-10-08 16:38:03","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":22866990,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSankey plots (left column) of RT2FM distribution across histopathology subtypes and radar plots (right column) of RT2FM performance for IDH mutation prediction in cohort A (A) and B (B).\u003c/strong\u003e \u003cstrong\u003eAbbreviations\u003c/strong\u003e: IDH = isocitrate dehydrogenase, T2WI = T2 weighted image, FLAIR = fluid-attenuated inversion recovery, RT2FM = relaxed T2-FLAIR mismatch, PRE = presence, SEN = sensitivity, SPE = specificity, PPV = positive predictive value, NPV = negative predictive value, ACC = accuracy.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/167750ed1c61afa7561cfd03.png"},{"id":93063344,"identity":"2f223641-44b2-48b8-9c92-c40538368c91","added_by":"auto","created_at":"2025-10-08 16:38:13","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":3011551,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFractal analysis.\u003c/strong\u003e (A) Representative cases: images from left column to right column are as follows: axial T2WI, FLAIR and outline image of maximum cross-sectional tumor diameter. (B) Violin plot comparing FD between IDHwt and IDHmut groups. (C) Violin plot comparing FD for IDHmut-Noncodel, IDHmut-Codel and IDHwt groups. (D) The ROC curve of FD for predicting IDH mutation status.\u003cstrong\u003e Abbreviations\u003c/strong\u003e: IDH = isocitrate dehydrogenase, IDHmut = IDH mutant, IDHwt = IDH wild type (glioblastoma), IDHmut-Noncodel = IDH mutant and 1p/19q noncodeletion astrocytoma, IDHmut-Codel = IDH mutant and 1p/19q codeletion (oligodendroglioma), T2WI = T2 weighted imaging, FLAIR = fluid-attenuated inversion recovery, FD = fractal dimension, ROC = receiver operating characteristic, AUC = area under curve, NS = no significance, \u003cstrong\u003e****\u003c/strong\u003e,\u003cem\u003eP \u003c/em\u003e\u0026lt; 0.001.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/ac6588c9b02fe4c5baef80ff.png"},{"id":93063228,"identity":"cd64ddc9-b300-44a6-a258-0398cc25ee60","added_by":"auto","created_at":"2025-10-08 16:38:10","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":14624445,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance evaluation of XGBoost model.\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e(A)\u003cstrong\u003e \u003c/strong\u003eCalibration curves and decision curve analysis of XGBoost model for IDH mutation prediction across the training, internal validation, and external testing sets. (B) Bee swarm plot of SHAP analysis for XGBoost model. (C) Feature importance ranking plot of the XGBoost model. \u003cstrong\u003eAbbreviations\u003c/strong\u003e: DCA = decision curve analysis, IDH = isocitrate dehydrogenase, T2WI = T2 weighted imaging, FLAIR = fluid-attenuated inversion recovery, RT2FM = relaxed T2-FLAIR mismatch, FD = fractal dimension, XGBoost = extreme gradient boosting, SHAP = SHapley Additive exPlanations.\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/2384d405ef88fcfc0b4df08b.png"},{"id":99545401,"identity":"fa0662a2-892d-4044-b083-4c1af9a77ce5","added_by":"auto","created_at":"2026-01-05 16:07:06","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":47474249,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/89a174ff-d70b-4a5b-a1c9-56c40827ffe1.pdf"},{"id":93062822,"identity":"d0e1b62f-ca0b-45bd-9dba-d15eb6bb1957","added_by":"auto","created_at":"2025-10-08 16:38:03","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1175652,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7334338/v1/503d8dca3854fb60c3848f46.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"IDH mutation prediction in non-enhancing gliomas with relaxed T2-FLAIR mismatch and fractal dimension: a two-center study","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eDiffuse glioma is the most common primary malignant brain tumor in adults. The 2021 World Health Organization (WHO) classification of tumors of central nervous system integrates molecular profiling with histopathology for the precise classification of diffuse glioma[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Isocitrate dehydrogenase (IDH) mutation status is established as a pivotal molecular biomarker for therapeutic decision-making and prognostic stratification[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eMagnetic resonance imaging (MRI) is an important tool for gliomas diagnosis, with contrast enhancement on contrast-enhanced T1-weighted imaging (T1CE) serving as a radiographic biomarker indicative of aggressive biological behavior[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. However, subsequent evidence has confirmed that non-enhancing gliomas are a large and heterogeneous group. Of these, approximately 18% are IDH wild-type (IDHwt)[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e], and exhibiting aggressive biological behavior. Therefore, preoperative prediction of IDH mutation is important in non-enhancing adult-type gliomas.\u003c/p\u003e\u003cp\u003eGlioma IDH mutation status drives tumor cell proliferative heterogeneity and spatial architecture[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e], radiologically manifesting as MRI signal heterogeneity and irregular contours. Consequently, accurate quantification of these MRI-derived heterogeneity and morphological irregularity is essential for predicting IDH mutation status.\u003c/p\u003e\u003cp\u003eFunctional MRI enables IDH mutation prediction through quantification of intratumoral heterogeneity including cellular density, perfusion, and metabolite products[\u003cspan additionalcitationids=\"CR8\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Its clinical implementation is constrained by prolonged acquisition times, economic burdens, and inter-institutional heterogeneity in acquisition parameters and post-processing protocols. In contrast, the T2-fluid-attenuated inversion recovery mismatch (T2FM) sign is a promising radiogenomic biomarker detected on routine MRI with 100% specificity for predicting IDH mutant (IDHmut) astrocytomas[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. However, its stringent diagnostic criteria result in limited predictive sensitivity and suboptimal interobserver agreement, significantly constraining clinical applicability[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eTraditional morphological parameters (e.g., tumor volume, maximal diameter) based on Euclidean geometry provide only coarse approximations of contour irregularity. While radiomic features like sphericity, compactness, and sphericity enable quantitative assessment, their limited intuitive biological interpretability and requirement for complex computational pipelines hinder clinical adoption[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. In contrast, the tumor-brain interface's inherent fractal properties offer an anatomically grounded framework[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e], where fractal dimension (FD) emerging as a computationally metric that effectively quantifies contour irregularity without sophisticated mathematical operations[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eIn summary, previous studies on glioma intratumoral heterogeneity offered limited clinical utility and lacked effective methods for assessing tumor margin irregularity. Consequently, developing an IDH mutation prediction framework that integrates internal heterogeneity and contour irregularity indices, while ensuring clinical feasibility and interpretability, is imperative. In our study, we optimized T2FM to enhance its sensitivity, quantified contour irregularity using FD, and constructed an IDH prediction model combining FD with T2FM, accounting for both \u0026ldquo;internal heterogeneity\u0026rdquo; and \u0026ldquo;marginal invasiveness\u0026rdquo;.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Patients\u003c/h2\u003e\u003cp\u003eThis study was approved by the institutional review board of *** Hospital (IRB No.********) and *** Hospital (IRB No.********). All procedures performed in this study involving human participants were in accordance with the ethical standards of the Declaration of Helsinki. Due to the retrospective nature of this study, the requirement for informed consent was waived.\u003c/p\u003e\u003cp\u003ePotentially eligible patients with pathologically confirmed gliomas were consecutively enrolled according to the inclusion and exclusion criteria. The inclusion criteria were: (i) age \u0026ge; 18 years; (ii) preoperative MRI scan was performed; (iii) clinicopathologic information was well documented, including age, gender, WHO grade and IDH mutation status. The exclusion criteria were: (i) patient underwent treatment before MRI; (ii) discernible enhancement in lesion was observed on T1CE; (iii) MRI image quality was unsatisfactory due to susceptibility or motion artifacts; (iv) missing in any of the four routine sequences, including T1 weighted imaging (T1WI), T2 weighted imaging (T2WI), FLAIR and T1CE.\u003c/p\u003e\u003cp\u003eFinally, 267 patients from the *** Hospital between March 2017 and May 2023 were included in the training and internal validation set, and 97 patients from the *** Hospital between February 2018 and May 2022 were used as the external testing set. The patient selection process is depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Histopathologic Analysis\u003c/h2\u003e\u003cp\u003eHistopathological and molecular analyses were in accordance with the 2021 WHO classification of tumors of the central nervous System. Sanger sequencing and next-generation sequencing were used to determine IDH mutation status. The lp/19q status was analyzed using fluorescent in situ hybridization or next-generation sequencing.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3 MRI Acquisitions\u003c/h2\u003e\u003cp\u003eMRI studies were performed at two institutions using either a 3.0 T or a 1.5 T unit from different scanners, with various parameters to reflect real inter-center heterogeneity. The brain tumor imaging protocol included T1WI, T2WI, FLAIR, and T1CE. The detailed acquisition parameters are provided in \u003cb\u003eSupplementary Table \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/b\u003e.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e2.4. Image Analysis\u003c/h2\u003e\u003cdiv id=\"Sec7\" class=\"Section3\"\u003e\u003ch2\u003e2.4.1 Relaxed T2FM (RT2FM) Definition\u003c/h2\u003e\u003cp\u003eDiagnostic criteria for the relaxed T2FM sign: A lesion is classified as T2FM-positive if it displays focal region of T2WI hyperintensity with corresponding FLAIR hypointensity. Crucially, two points merit specification: First, the extent of mismatch region does not require involvement of the entire tumor region, and heterogeneous T2WI within this area is permissible. Second, cystic gliomas are classified as T2FM-positive. Representative cases are shown in \u003cb\u003eFigure \u003cspan refid=\"MOESM1\" class=\"InternalRef\"\u003eS1\u003c/span\u003e\u003c/b\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section3\"\u003e\u003ch2\u003e2.4.2 MRI Semantic Feature Assessment\u003c/h2\u003e\u003cp\u003ePrior to feature assessment, all images were anonymized and radiologists were blinded to clinical history, pathological diagnosis, and molecular genotype of tumor. Two radiologists (*** and ***, with 5 and 8 years of brain tumor diagnostic experience, respectively) independently evaluated MRI semantic features including RT2FM, tumor location, multicentric/multifocal, T2WI homogeneity, deep white matter invasion, cyst, cortical involvement, tumor borders, and sinuous, wave-like intratumoral-wall (SWITW)[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. In cases of inter-reader discrepancy, consensus was achieved through consultation with a third board-certified radiologist (***, with 20 years\u0026rsquo; neuroimaging experience). Following a 3-month washout period, 30 randomly selected cases were reassessed for RT2FM sign by a senior radiologist. Intra- and inter-observer agreements of RT2FM were subsequently calculated.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e2.5 Tumor Segmentation and Fractal Analysis\u003c/h2\u003e\u003cp\u003eTwo radiologists (*** and ***, with 4 and 9 years of brain tumor diagnostic experience respectively) manually segmented tumor regions of interest (ROI) on axial FLAIR images, blinded to IDH mutation status. Previous studies demonstrated that tumor segmentation using fewer slices can effectively capture molecular subtype-associated heterogeneity in gliomas while reducing segmentation time and enhancing clinical feasibility[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. In this study, ROIs were delineated on three adjacent consecutive slices centered on the slice demonstrating the maximal tumor diameter using open-source software ITK-SNAP (version 4.0.1; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://itk-snap.org\u003c/span\u003e\u003cspan address=\"http://itk-snap.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThe 2D FD values were calculated from the segmented masks using box-counting algorithms via Python[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. As the optimal box size was unknown, a number of different 2D box sizes, ranging from 2\u003csup\u003e0\u003c/sup\u003e to 2\u003csup\u003e7\u003c/sup\u003e isotropic pixels, were adopted to compute the 2D FD[\u003cspan additionalcitationids=\"CR20\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The mean FD across the three slices was calculated per patient and utilized for subsequent analysis. Details of FD calculations are available in \u003cb\u003eSupplementary S1\u003c/b\u003e.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e2.6 Model Development and Validation for IDH Mutation Prediction\u003c/h2\u003e\u003cp\u003ePatients from *** Hospital were randomly allocated to the training and internal validation sets at a 7:3 ratio for model construction and evaluation, while cases from *** Hospital served as an independent external testing set. In the training set, clinical and MRI semantic features underwent dual feature selection via least absolute shrinkage and selection operator (LASSO) regression and Boruta algorithm, with intersecting features retained as IDH mutation-associated predictors[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Subsequently, intersecting features were used for machine learning models construction, including light gradient boosting machine (LightGBM), logistic regression (LR), extreme gradient boosting (XGBoost) and support vector machine (SVM). Random search and manual fine-tuning with 5-fold cross-validation were used to determine the optimal hyperparameters for each model. Finally, SHapley Additive exPlanations (SHAP) was used to assess the significance of each feature in the model[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e2.7 Statistical Analysis\u003c/h2\u003e\u003cp\u003eNormality of the variables was assessed using the Shapiro-Wilk test. Quantitative variables were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation for normal distribution or median with interquartile range (IQR) for non-normal distribution. Categorical variables were expressed as numbers and percentages. The Student\u0026rsquo;s \u003cem\u003et\u003c/em\u003e-test or one-way ANOVA test was used for continuous variables, and the Mann\u0026ndash;Whitney U-test or Kruskal\u0026ndash;Wallis H test was applied for nonparametric data. For comparative analyses of categorical variables in two groups, the chi-square test or Fisher\u0026rsquo;s exact test was used. Cohen\u0026rsquo;s Kappa analysis was used to assess the intra- and inter-observer agreement of RT2FM. Inter-class correlation coefficient (ICC) was calculated to evaluate the intra- and inter-observer agreement for FD. Receiver operating characteristic (ROC) curve was constructed to calculate area under the curve (AUC) and the optimal cut-off value was determined by the maximal Youden index. The performance of the IDH mutation prediction model was evaluated using multiple metrics, including AUC, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), F1 score, and Matthews correlation coefficient (MCC). The model\u0026rsquo;s fit was tested through calibration curve. The decision curve analysis (DCA) was utilized to assess the clinical utility of the model. Statistical analysis was performed using software (SPSS, version 26.0; MedCalc, version 15.0; R, version 4.3.2; Python, version 3.8.5). \u003cem\u003eP\u003c/em\u003e \u0026lt; 0.05 was considered a statistically significant difference.\u003c/p\u003e\u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Patient Characteristics\u003c/h2\u003e\u003cp\u003eBaseline characteristics is detailed in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. In cohort A, 267 patients (median age, 44 years; IQR, 36\u0026ndash;52 years; 157 males) were included, comprising 129 astrocytomas, 98 oligodendrogliomas and 40 glioblastomas. Cohort B included 97 patients (median age, 42 years, IQR, 33\u0026ndash;51 years; 56 males) with 66 IDHmut gliomas (25 astrocytomas, 41 oligodendrogliomas) and 31 glioblastomas. IDHmut gliomas exhibited a younger age compared to IDHwt group (cohort A, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.002; cohort B, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePatient characteristics.\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=\"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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eCharacteristics\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e\u003cp\u003eCohort A: Training set \u0026amp; Internal validation set\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c8\" namest=\"c6\"\u003e\u003cp\u003eCohort B: External testing set\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIDHmut (n\u0026thinsp;=\u0026thinsp;227)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIDHwt (n\u0026thinsp;=\u0026thinsp;40)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIDHmut (n\u0026thinsp;=\u0026thinsp;66)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIDHwt (n\u0026thinsp;=\u0026thinsp;31)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAge(y)\u003c/b\u003e \u003csup\u003e\u0026sect;\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e44 (36, 51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e52 (39, 61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.002\u003csup\u003e\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e39 (31,47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e51 (42, 62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003e\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGender\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.380\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.403\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e136 (59.91)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e21 (52.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e40 (60.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e16 (51.61)\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\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e91 (40.09)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19 (47.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e26 (39.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e15 (48.39)\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\u003e\u003cb\u003eHistopathology\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eNA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eNA\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGlioblastoma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e40 (100.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e31 (100.00)\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\u003eAstrocytoma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e129 (56.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e25 (37.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0 (0.00)\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\u003eOligodendroglioma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e98 (43.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e41 (62.12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0 (0.00)\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\u003e\u003cb\u003eWHO Grade\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrade 2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e164 (72.25)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e42 (63.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0 (0.00)\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\u003eGrade 3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e54 (23.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e22 (33.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0 (0.00)\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\u003eGrade 4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e9 (3.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e40 (100.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e2 (3.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e31 (100.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003eNote. \u0026mdash; Unless otherwise indicated, data are numbers of patients, and data in parentheses are percentages. IDH\u0026thinsp;=\u0026thinsp;isocitrate dehydrogenase, IDHmut\u0026thinsp;=\u0026thinsp;IDH mutant, IDHwt\u0026thinsp;=\u0026thinsp;IDH wild type, NA\u0026thinsp;=\u0026thinsp;not available.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e\u003csup\u003e\u0026sect;\u003c/sup\u003eData are the median, and data in parentheses are the interquartile range.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e\u003csup\u003e\u0026Dagger;\u003c/sup\u003eMann-Whitney U test.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e\u003csup\u003eΨ\u003c/sup\u003ePearson's Chi-squared test.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e3.2 MRI Semantic Features\u003c/h2\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents MRI semantic feature differences between IDHmut and IDHwt groups across cohorts A and B. In cohort A, IDHmut gliomas exhibited frontal lobe predilection, well-defined tumor border, cortical involvement, heterogeneous T2WI, hyperintensity on T1WI and a positive SWITW sign. In contrast, IDHwt gliomas tended to show blurred borders, multifocal/multicentric and deep white matter invasion. Similar trends were observed in cohort B. No statistically differences were observed in cyst between IDHmut and IDHwt groups across both cohorts (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMRI semantic feature comparisons between IDHmut and IDHwt groups.\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=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" 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=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eCharacteristics\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e\u003cp\u003eCohort A: Training set \u0026amp; Internal validation set\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c8\" namest=\"c6\"\u003e\u003cp\u003eCohort B: External testing set\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIDHmut (n\u0026thinsp;=\u0026thinsp;227)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIDHwt (n\u0026thinsp;=\u0026thinsp;40)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eIDHmut (n\u0026thinsp;=\u0026thinsp;66)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIDHwt (n\u0026thinsp;=\u0026thinsp;31)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLocation\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrontal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e157 (69.16)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10 (25.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e42 (63.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (29.03)\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\u003eTemporal-insular\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e56 (24.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6 (15.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e19 (28.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (19.35)\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\u003eParieto-occipital\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e12 (5.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5 (12.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4 (6.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e7 (22.58)\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\u003eOther\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2 (0.88)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e19 (47.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1 (1.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e9 (29.04)\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\u003e\u003cb\u003eRT2FM\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e220 (96.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e14 (35.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e61 (92.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e18 (58.06)\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\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7 (3.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26 (65.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e5 (7.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e13 (41.94)\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\u003e\u003cb\u003eMultifocal/Multicentric\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e8 (3.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e22 (55.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e5 (7.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e11 (35.48)\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\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e219 (96.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18 (45.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e61 (92.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e20 (64.52)\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\u003e\u003cb\u003eDeep WM invasion\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10 (4.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e14 (35.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7 (10.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e12 (38.71)\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\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e217 (95.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26 (65.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e59 (89.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e19 (61.29)\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\u003e\u003cb\u003eCyst (s)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.642\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.708\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e47 (20.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7 (17.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e5 (7.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e3 (9.68)\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\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e180 (79.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e33 (82.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e61 (92.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e28 (90.32)\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\u003e\u003cb\u003eCortical involvement\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.032\u003csup\u003eξ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e224 (98.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e31 (77.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e64 (96.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e26 (83.87)\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\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e3 (1.32)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9 (22.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2 (3.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e5 (16.13)\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\u003e\u003cb\u003eT2WI homogeneity\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.046\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHomogeneous\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e23 (10.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13 (32.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e13 (19.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e12 (38.71)\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\u003eHeterogeneous\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e204 (89.87)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e27 (67.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e53 (80.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e19 (61.29)\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\u003e\u003cb\u003eTumor border\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.001\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWell defined\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e96 (42.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4 (10.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e36 (54.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e6 (19.35)\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\u003ePoorly defined\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e131 (57.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e36 (90.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e30 (45.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e25 (80.65)\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\u003e\u003cb\u003eHyperintensity on T1WI\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.032\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\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\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e65 (28.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5 (12.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e21 (31.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1 (3.23)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.002\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e162 (71.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e35 (87.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e45 (68.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e30 (96.77)\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\u003e\u003cb\u003eSWITW\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.016\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\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\u003ePresent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e56 (24.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3 (7.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e22 (33.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e4 (12.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.034\u003csup\u003eΨ\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAbsent\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e171 (75.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e37 (92.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e44 (66.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e27 (87.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003eNote. \u0026mdash; Unless otherwise indicated, data are numbers of patients, and data in parentheses are percentages. IDH\u0026thinsp;=\u0026thinsp;isocitrate dehydrogenase, IDHmut\u0026thinsp;=\u0026thinsp;IDH mutant, IDHwt\u0026thinsp;=\u0026thinsp;IDH wild type, T1WI\u0026thinsp;=\u0026thinsp;T1 weighted imaging, T2WI\u0026thinsp;=\u0026thinsp;T2 weighted imaging, FLAIR\u0026thinsp;=\u0026thinsp;fluid-attenuated inversion recovery, RT2FM\u0026thinsp;=\u0026thinsp;relaxed T2-FLAIR mismatch, Deep WM invasion\u0026thinsp;=\u0026thinsp;deep white matter invasion, SWITW\u0026thinsp;=\u0026thinsp;sinuous wave-like intratumoral-wall.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e\u003csup\u003eξ\u003c/sup\u003eFisher's exact test.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e\u003csup\u003eΨ\u003c/sup\u003ePearson's Chi-squared test.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003e3.3 RT2FM for IDH Mutation Prediction\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003e depicts RT2FM distribution across histopathology subtypes (Sankey plot, left) and its diagnostic performance for predicting IDH mutation status (Radar chart, right). In cohort A, 234 cases showed positive RT2FM (astrocytoma, 127/129; oligodendroglioma, 93/98; glioblastoma, 14/40), while 33 cases were negative (astrocytoma, 2/129; oligodendroglioma, 5/98; glioblastoma, 26/40). In cohort B, positive RT2FM was observed in 79 cases (astrocytoma, 24/25; oligodendroglioma, 37/41; glioblastoma, 18/31), and 18 cases were negative (astrocytoma, 1/25; oligodendroglioma, 4/41; glioblastoma, 13/31). The presence, sensitivity, specificity, and accuracy of RT2FM for predicting IDH mutation were 0.876, 0.969, 0.650, and 0.921 in cohort A, and 0.814, 0.924, 0.419, and 0.762 in cohort B, respectively. The intra-observer and inter-observer agreement for RT2FM was almost perfect, with κ values of 0.867 and 0.824, respectively.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003e3.4 FD for IDH Mutation Prediction\u003c/h2\u003e\u003cp\u003eRepresentative cases of fractal analysis are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e3\u003c/span\u003eA. The FD measurements demonstrated excellent consistency, with intra-observer and inter-observer ICCs of 0.957 and 0.909, respectively (\u003cb\u003eFigure \u003cspan refid=\"MOESM2\" class=\"InternalRef\"\u003eS2\u003c/span\u003e\u003c/b\u003e). In cohort A, IDHwt gliomas exhibited higher FD than the IDHmut group (IDHwt, 1.264 vs. IDHmut, 1.190; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e3\u003c/span\u003eB). Further subgroup analysis revealed no significant difference in FD was observed between oligodendrogliomas (IDHmut-Noncodel) and astrocytomas (IDHmut-Codel) (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e3\u003c/span\u003eC). When the cut-off value was set at 1.225, the AUC for predicting IDH mutation was 0.884, with a sensitivity of 0.837 and a specificity of 0.850 (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e3\u003c/span\u003eD).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e3.5 Model Performance for IDH Mutation Prediction\u003c/h2\u003e\u003cp\u003e\u003cb\u003eFigure \u003cspan refid=\"MOESM3\" class=\"InternalRef\"\u003eS3\u003c/span\u003e\u003c/b\u003e illustrates the intersectional feature selection by LASSO and Boruta algorithm, identifying four critical features: FD, tumor location, multicentric/multifocal, and RT2FM. Utilizing these features, LightGBM, LR, XGBoost, and SVM were subsequently developed. As detailed in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, XGBoost model exhibited superior performance, with AUCs of 0.974/0.968/0.895 and ACCs of 0.952/0.950/0.876 across training/internal validation/external testing sets. The XGBoost model demonstrated good calibration and net benefit in the training set, internal validation set, and external testing set (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e4\u003c/span\u003eA). Figure\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e4\u003c/span\u003eB-C displays SHAP-based feature rankings in the XGBoost model: FD\u0026thinsp;\u0026gt;\u0026thinsp;RT2FM\u0026thinsp;\u0026gt;\u0026thinsp;multifocal/multicentric\u0026thinsp;\u0026gt;\u0026thinsp;location. Specifically, lower FD, positive RT2FM, and negative multifocal/multicentric status were significantly associated with IDH mutation.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparisons of model performance for IDH mutation prediction across training, internal validation and external testing set.\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=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" 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=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAUC (95%CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSEN\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSPE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eACC\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eMCC\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.974 (0.936-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.956\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.929\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.987\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.788\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.952\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.971\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.825\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInternal validation set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.968 (0.925-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.941\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.833\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.970\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.714\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.950\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.955\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.728\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExternal testing set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.895 (0.820\u0026ndash;0.970)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.955\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.710\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.875\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.880\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.876\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.913\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.708\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLightGBM\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\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=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.969 (0.941\u0026ndash;0.996)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.893\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.893\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.979\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.595\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.893\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.934\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.672\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInternal validation set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.954 (0.901-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.912\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.833\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.969\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.900\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.939\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.665\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExternal testing set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.893 (0.826\u0026ndash;0.959)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.803\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.774\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.883\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.649\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.794\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.841\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.599\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSVM\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\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=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.955 (0.909-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.994\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.821\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.969\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.958\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.968\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.981\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.870\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInternal validation set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.850 (0.702\u0026ndash;0.998)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.985\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.583\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.931\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.875\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.925\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.957\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.677\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExternal testing set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.883 (0.810\u0026ndash;0.957)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.984\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.580\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.833\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.947\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.856\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.903\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.664\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLR\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\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=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTraining set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.946 (0.892-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.975\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.857\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.975\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.857\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.957\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.974\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.832\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInternal validation set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.968 (0.922-1.000)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.985\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.667\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.944\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.889\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.938\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.964\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.737\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExternal testing set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.876 (0.801\u0026ndash;0.951)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.985\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.548\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.823\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.944\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.845\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0.897\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0.640\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"9\"\u003eNote. \u0026mdash; AUC\u0026thinsp;=\u0026thinsp;area under the receiver operating characteristic curve, CI\u0026thinsp;=\u0026thinsp;confidence interval, SEN\u0026thinsp;=\u0026thinsp;sensitivity, SPE\u0026thinsp;=\u0026thinsp;specificity, PPV\u0026thinsp;=\u0026thinsp;positive predictive value, NPV\u0026thinsp;=\u0026thinsp;negative predictive value, ACC\u0026thinsp;=\u0026thinsp;accuracy, MCC\u0026thinsp;=\u0026thinsp;matthews correlation coefficient, XGBoost\u0026thinsp;=\u0026thinsp;extreme gradient boosting, LightGBM\u0026thinsp;=\u0026thinsp;light gradient boosting machine, SVM\u0026thinsp;=\u0026thinsp;support vector machine, LR\u0026thinsp;=\u0026thinsp;logistic regression.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eExploration of a noninvasive tool to predict IDH mutation status is important to guide clinical decision-making in non-enhancing adult-type diffuse gliomas. Radiologically, gliomas with distinct IDH mutation status exhibit differences in intratumoral signal and contour irregularity. In our study, we employed RT2FM and other MRI semantic features to classify intratumoral heterogeneity while utilizing FD to quantify contour irregularity. Ultimately, four models were constructed to predict IDH mutation status by integrating RT2FM, FD and MRI semantic features. XGBoost model exhibited optimal diagnostic performance, with AUCs of 0.974/0.968/0.895 across training/internal validation/external testing sets.\u003c/p\u003e\u003cp\u003eThe classical T2FM requires a homogeneous T2WI signal and complete FLAIR signal attenuation (except for the high signal edge), resulting in reduced sensitivity for IDH mutation prediction in the real-world cohorts[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. In this study, we applied a relaxed T2FM criterion that neither confines mismatch region to the entire tumor area nor requires homogeneous T2WI signal. Notably, for tumors exhibiting prominent cystic gliomas, we adopted the criteria established by Lee et al[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] to classify these cases as T2FM-positive, corresponding to IDHmut status. Following the aforementioned adjustments, our RT2FM demonstrated sensitivities of 0.969 and 0.924 in IDH mutation prediction across cohorts A and B, respectively. In alignment with our study design, Throckmorton et al.[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] demonstrated that incorporating T2WI heterogeneity (without restricting T2WI homogeneity) improved the sensitivity of T2FM for IDH prediction from 34\u0026ndash;74%. Subsequent studies by Lasoki et al.[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] and Cho et al.[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] further quantified the spatial extent of mismatch involvement. By defining T2FM positive as a mismatch region involvement extent of \u0026ge;\u0026thinsp;25% of tumor, these studies achieved sensitivities of 0.33\u0026ndash;0.63 for IDH prediction while maintaining high specificity (0.92\u0026ndash;1.00). However, the quantitative assessment of mismatch extent in these studies required complex postprocessing, and substantial interobserver variability, which may limit their clinical applicability. Although RT2FM improved the sensitivity for IDH mutation prediction, its specificity remained suboptimal, with values of 0.650 and 0.419 in cohorts A and B, respectively, likely attributable to local mismatch sign observed in glioblastoma[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Nevertheless, parameter complementarity in the multiparametric modeling framework mitigated this limitation. SHAP analysis further validated RT2FM as a critical predictive marker for IDH mutation prediction.\u003c/p\u003e\u003cp\u003eIt is well known that irregular morphology of gliomas arises from both heterogeneous distributions of tumor cells with differential proliferative capacities[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e] and their selective, non-isotropic infiltration patterns along nerve bundles[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. This makes tumors tend to exhibit more irregular geometries. Previous studies have reported that the contour of gliomas conforms to fractal geometry. Consequently, our study utilized FD to quantify irregularity of gliomas. Our results showed a higher median FD value of glioblastomas compared to the IDHmut gliomas, indicating a more irregular morphology. Similar to our findings, Saha et al.[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e] found that IDHwt gliomas are more irregular compared to IDHmut gliomas based on morphological parameters. Indeed, pathological studies also suggest that the spatial heterogeneity and invasiveness of tumor cells are more pronounced in IDHwt gliomas than in IDHmut gliomas, thereby facilitating their anisotropic growth and potentially contributing to irregular morphology[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. Considering clinical applicability, our study employed manual segmentation limited to three consecutive slices centered on tumor\u0026rsquo;s largest cross-sectional area. This approach not only reduced radiologists\u0026rsquo;time expenditure but also ensured reproducibility, thereby supporting potential clinical translation. Furthermore, SHAP-based feature rankings in the XGBoost model identified FD as the most critical variable for predicting IDH mutation in gliomas.\u003c/p\u003e\u003cp\u003eDuring model construction, we incorporated two MRI semantic features, tumor location and multicentric/multifocal presentation, alongside RT2FM and FD. Our findings indicated that IDHmut gliomas were predominantly located in the frontal lobe, whereas multicentric/multifocal lesions were more common in IDHwt cases, aligning with previous studies[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. Among the four constructed models for IDH mutation prediction, XGBoost achieved the highest performance, likely due to its gradient-boosted decision tree architecture, which efficiently handles nonlinear relationships, mitigates class imbalance, and ensures stable classification accuracy[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. This algorithm has been widely implemented in artificial intelligence applications and is increasingly utilized for tumor molecular subtyping and prognostic prediction[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e, \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThis study has several limitations. First, despite utilizing data from two independent medical institutions, the retrospective design inherently carries potential selection bias, and findings should be interpreted with caution. Second, the modest sample size necessitates future multicenter studies with larger cohorts to validate the findings. Third, although RT2FM demonstrated high sensitivity for IDH mutation prediction, sole reliance on RT2FM for diagnosis requires refined classification frameworks, which will be a focus of our future research.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eIn our study, RT2FM significantly improved sensitivity for preoperative IDH mutation prediction in non-enhancing adult-type diffuse gliomas. Additionally, IDHwt gliomas exhibited higher FD compared to IDHmut counterparts. Furthermore, the XGBoost model integrating RT2FM, FD, and other MRI semantic features showed potential for IDH mutation prediction. However, validation for our findings in a prospective, multicenter cohort is warranted.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eAUC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003earea under the curve\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eFD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003efractal dimension\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eFLAIR \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003efluid-attenuated inversion recovery\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eIDH\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003eisocitrate dehydrogenase\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eIQR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003einterquartile range\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eLASSO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003eleast absolute shrinkage and selection operator\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eMCC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003ematthews correlation coefficient\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eSHAP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003eSHapley Additive exPlanations\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eROC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003ereceiver operating characteristic\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eT1CE\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003econtrast-enhanced T1WI\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eRT2FM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003erelaxed T2-FLAIR mismatch\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 37.613%;\"\u003e\n \u003cp\u003eWHO\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62.387%;\"\u003e\n \u003cp\u003eworld health organization\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have no acknowledgements to declare.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eYu Han:\u003c/strong\u003e Writing \u0026ndash; review \u0026amp; editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. \u003cstrong\u003eJin Zhang:\u0026nbsp;\u003c/strong\u003eWriting \u0026ndash; review \u0026amp; editing, Writing \u0026ndash; original draft, Methodology, Conceptualization. \u003cstrong\u003eYi-bin Xi:\u003c/strong\u003e Writing \u0026ndash; review \u0026amp; editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. \u003cstrong\u003eSi-jie Xiu:\u0026nbsp;\u003c/strong\u003eWriting \u0026ndash; review \u0026amp; editing, Visualization, Validation, Software, Resources, Methodology, Investigation, Formal analysis, Data curation, Conceptualization. \u003cstrong\u003eYang Yang:\u003c/strong\u003e Writing \u0026ndash; review \u0026amp; editing, Supervision, Project administration, Methodology, Conceptualization. \u003cstrong\u003eYu-yao Wang:\u003c/strong\u003e Writing \u0026ndash; review \u0026amp; editing, Writing \u0026ndash; original draft, Visualization, Validation, Supervision, Software, Resources, Project administration, Methodology, Investigation, Formal analysis, Data curation, Conceptualization.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study received financial support from the National Natural Science Foundation of China (No. 82102127 to YY and No. 82371936 to YBX).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets generated or analyzed during the study are not publicly available but are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was approved by the institutional review board of Tangdu Hospital (IRB No. K-HG-202507-05) and Xi\u0026apos;an People\u0026apos;s Hospital (IRB No.20230904). All procedures performed in this study involving human participants were in accordance with the ethical standards of the Declaration of Helsinki. Due to the retrospective nature of this study, the requirement for informed consent was waived.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no conflicts of interest.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eAuthor details\u003c/strong\u003e\u003c/p\u003e\n\u003col\u003e\n \u003cli\u003eDepartment of Radiology \u0026amp; Functional and Molecular Imaging Key Lab of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University, Xi\u0026apos;an, Shaanxi, P.R. China, 710038\u003c/li\u003e\n \u003cli\u003eDepartment of Radiology, Xi\u0026apos;an People\u0026apos;s Hospital (Xi\u0026apos;an Fourth Hospital), Xi\u0026apos;an, Shaanxi, P.R. China, 710199\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eLouis DN, Perry A, Wesseling P, Brat DJ, Cree IA, Figarella-Branger D\u003cem\u003e et al\u003c/em\u003e. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary. \u003cem\u003eNeuro Oncol \u003c/em\u003e2021, 23(8):1231-1251.http://doi.org/10.1093/neuonc/noab106.\u003c/li\u003e\n\u003cli\u003eBerger TR, Wen PY, Lang-Orsini M, Chukwueke UN. World Health Organization 2021 Classification of Central Nervous System Tumors and Implications for Therapy for Adult-Type Gliomas: A Review. \u003cem\u003eJAMA Oncol \u003c/em\u003e2022, 8(10):1493-1501.http://doi.org/10.1001/jamaoncol.2022.2844.\u003c/li\u003e\n\u003cli\u003eBrindle KM, Izquierdo-Garc\u0026iacute;a JL, Lewis DY, Mair RJ, Wright AJ. Brain Tumor Imaging. \u003cem\u003eJ Clin Oncol \u003c/em\u003e2017, 35(21):2432-2438.http://doi.org/10.1200/jco.2017.72.7636.\u003c/li\u003e\n\u003cli\u003eGarz\u0026oacute;n B, Emblem KE, Mouridsen K, Nedregaard B, Due-T\u0026oslash;nnessen P, Nome T\u003cem\u003e et al\u003c/em\u003e. Multiparametric analysis of magnetic resonance images for glioma grading and patient survival time prediction. \u003cem\u003eActa Radiol \u003c/em\u003e2011, 52(9):1052-1060.http://doi.org/10.1258/ar.2011.100510.\u003c/li\u003e\n\u003cli\u003eKang KM, Song J, Choi Y, Park C, Park JE, Kim HS\u003cem\u003e et al\u003c/em\u003e. MRI Scoring Systems for Predicting Isocitrate Dehydrogenase Mutation and Chromosome 1p/19q Codeletion in Adult-type Diffuse Glioma Lacking Contrast Enhancement. \u003cem\u003eRadiology \u003c/em\u003e2024, 311(2):e233120.http://doi.org/10.1148/radiol.233120.\u003c/li\u003e\n\u003cli\u003eMoffet JJD, Fatunla OE, Freytag L, Kriel J, Jones JJ, Roberts-Thomson SJ\u003cem\u003e et al\u003c/em\u003e. Spatial architecture of high-grade glioma reveals tumor heterogeneity within distinct domains. \u003cem\u003eNeurooncol Adv \u003c/em\u003e2023, 5(1):vdad142.http://doi.org/10.1093/noajnl/vdad142.\u003c/li\u003e\n\u003cli\u003ePruis IJ, Koene SR, van der Voort SR, Incekara F, Vincent A, van den Bent MJ\u003cem\u003e et al\u003c/em\u003e. Noninvasive differentiation of molecular subtypes of adult nonenhancing glioma using MRI perfusion and diffusion parameters. \u003cem\u003eNeurooncol Adv \u003c/em\u003e2022, 4(1):vdac023.http://doi.org/10.1093/noajnl/vdac023.\u003c/li\u003e\n\u003cli\u003eArzanforoosh F, van der Voort SR, Incekara F, Vincent A, Van den Bent M, Kros JM\u003cem\u003e et al\u003c/em\u003e. Microvasculature Features Derived from Hybrid EPI MRI in Non-Enhancing Adult-Type Diffuse Glioma Subtypes. \u003cem\u003eCancers (Basel) \u003c/em\u003e2023, 15(7).http://doi.org/10.3390/cancers15072135.\u003c/li\u003e\n\u003cli\u003eWu M, Jiang T, Guo M, Duan Y, Zhuo Z, Weng J\u003cem\u003e et al\u003c/em\u003e. Amide proton transfer-weighted imaging and derived radiomics in the classification of adult-type diffuse gliomas. \u003cem\u003eEur Radiol \u003c/em\u003e2024, 34(5):2986-2996.http://doi.org/10.1007/s00330-023-10343-6.\u003c/li\u003e\n\u003cli\u003ePatel SH, Poisson LM, Brat DJ, Zhou Y, Cooper L, Snuderl M\u003cem\u003e et al\u003c/em\u003e. T2-FLAIR Mismatch, an Imaging Biomarker for IDH and 1p/19q Status in Lower-grade Gliomas: A TCGA/TCIA Project. \u003cem\u003eClin Cancer Res \u003c/em\u003e2017, 23(20):6078-6085.http://doi.org/10.1158/1078-0432.Ccr-17-0560.\u003c/li\u003e\n\u003cli\u003eThrockmorton P, Graber JJ. T2-FLAIR mismatch in isocitrate dehydrogenase mutant astrocytomas: Variability and evolution. \u003cem\u003eNeurology \u003c/em\u003e2020, 95(11):e1582-e1589.http://doi.org/10.1212/wnl.0000000000010324.\u003c/li\u003e\n\u003cli\u003ePark JE, Kim D, Kim HS, Park SY, Kim JY, Cho SJ\u003cem\u003e et al\u003c/em\u003e. Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement. \u003cem\u003eEur Radiol \u003c/em\u003e2020, 30(1):523-536.http://doi.org/10.1007/s00330-019-06360-z.\u003c/li\u003e\n\u003cli\u003eTorres Hoyos F, Navarro RB, Vergara Villadiego J, Guerrero-Martelo M. Geometrical study of astrocytomas through fractals and scaling analysis. \u003cem\u003eAppl Radiat Isot \u003c/em\u003e2018, 141:250-256.http://doi.org/10.1016/j.apradiso.2018.05.020.\u003c/li\u003e\n\u003cli\u003eLennon FE, Cianci GC, Cipriani NA, Hensing TA, Zhang HJ, Chen CT\u003cem\u003e et al\u003c/em\u003e. Lung cancer-a fractal viewpoint. \u003cem\u003eNat Rev Clin Oncol \u003c/em\u003e2015, 12(11):664-675.http://doi.org/10.1038/nrclinonc.2015.108.\u003c/li\u003e\n\u003cli\u003eLi M, Wang J, Chen X, Dong G, Zhang W, Shen S\u003cem\u003e et al\u003c/em\u003e. The sinuous, wave-like intratumoral-wall sign is a sensitive and specific radiological biomarker for oligodendrogliomas. \u003cem\u003eEur Radiol \u003c/em\u003e2023, 33(6):4440-4452.http://doi.org/10.1007/s00330-022-09314-0.\u003c/li\u003e\n\u003cli\u003eKocak B, Durmaz ES, Ates E, Sel I, Turgut Gunes S, Kaya OK\u003cem\u003e et al\u003c/em\u003e. Radiogenomics of lower-grade gliomas: machine learning-based MRI texture analysis for predicting 1p/19q codeletion status. \u003cem\u003eEur Radiol \u003c/em\u003e2020, 30(2):877-886.http://doi.org/10.1007/s00330-019-06492-2.\u003c/li\u003e\n\u003cli\u003eChu JP, Song YK, Tian YS, Qiu HS, Huang XH, Wang YL\u003cem\u003e et al\u003c/em\u003e. Diffusion kurtosis imaging in evaluating gliomas: different region of interest selection methods on time efficiency, measurement repeatability, and diagnostic ability. \u003cem\u003eEur Radiol \u003c/em\u003e2021, 31(2):729-739.http://doi.org/10.1007/s00330-020-07204-x.\u003c/li\u003e\n\u003cli\u003eLopes R, Betrouni N. Fractal and multifractal analysis: a review. \u003cem\u003eMedical image analysis \u003c/em\u003e2009, 13(4):634-649.http://doi.org/10.1016/j.media.2009.05.003.\u003c/li\u003e\n\u003cli\u003ePetrujkić K, Milo\u0026scaron;ević N, Rajković N, Stanisavljević D, Gavrilović S, Dželebdžić D\u003cem\u003e et al\u003c/em\u003e. Computational quantitative MR image features - a potential useful tool in differentiating glioblastoma from solitary brain metastasis. \u003cem\u003eEur J Radiol \u003c/em\u003e2019, 119:108634.http://doi.org/10.1016/j.ejrad.2019.08.003.\u003c/li\u003e\n\u003cli\u003eCurtin L, Whitmire P, White H, Bond KM, Mrugala MM, Hu LS, Swanson KR. Shape matters: morphological metrics of glioblastoma imaging abnormalities as biomarkers of prognosis. \u003cem\u003eSci Rep \u003c/em\u003e2021, 11(1):23202.http://doi.org/10.1038/s41598-021-02495-6.\u003c/li\u003e\n\u003cli\u003eKim S, Park YW, Park SH, Ahn SS, Chang JH, Kim SH, Lee SK. Comparison of Diagnostic Performance of Two-Dimensional and Three-Dimensional Fractal Dimension and Lacunarity Analyses for Predicting the Meningioma Grade. \u003cem\u003eBrain Tumor Res Treat \u003c/em\u003e2020, 8(1):36-42.http://doi.org/10.14791/btrt.2020.8.e3.\u003c/li\u003e\n\u003cli\u003eSun T, Liu J, Yuan H, Li X, Yan H. Construction of a risk prediction model for lung infection after chemotherapy in lung cancer patients based on the machine learning algorithm. \u003cem\u003eFront Oncol \u003c/em\u003e2024, 14:1403392.http://doi.org/10.3389/fonc.2024.1403392.\u003c/li\u003e\n\u003cli\u003eMuhammad D, Bendechache M. Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis. \u003cem\u003eComput Struct Biotechnol J \u003c/em\u003e2024, 24:542-560.http://doi.org/10.1016/j.csbj.2024.08.005.\u003c/li\u003e\n\u003cli\u003eDagher SA, Lochner RH, Ozkara BB, Schomer DF, Wintermark M, Fuller GN, Ucisik FE. The T2-FLAIR mismatch sign in oncologic neuroradiology: History, current use, emerging data, and future directions. \u003cem\u003eNeuroradiol J \u003c/em\u003e2024, 37(4):441-453.http://doi.org/10.1177/19714009231212375.\u003c/li\u003e\n\u003cli\u003eHan Z, Chen Q, Zhang L, Mo X, You J, Chen L\u003cem\u003e et al\u003c/em\u003e. Radiogenomic association between the T2-FLAIR mismatch sign and IDH mutation status in adult patients with lower-grade gliomas: an updated systematic review and meta-analysis. \u003cem\u003eEur Radiol \u003c/em\u003e2022, 32(8):5339-5352.http://doi.org/10.1007/s00330-022-08607-8.\u003c/li\u003e\n\u003cli\u003eLee MD, Patel SH, Mohan S, Akbari H, Bakas S, Nasrallah MP\u003cem\u003e et al\u003c/em\u003e. Association of partial T2-FLAIR mismatch sign and isocitrate dehydrogenase mutation in WHO grade 4 gliomas: results from the ReSPOND consortium. \u003cem\u003eNeuroradiology \u003c/em\u003e2023, 65(9):1343-1352.http://doi.org/10.1007/s00234-023-03196-9.\u003c/li\u003e\n\u003cli\u003eLasocki A, Buckland ME, Drummond KJ, Wei H, Xie J, Christie M\u003cem\u003e et al\u003c/em\u003e. Conventional MRI features can predict the molecular subtype of adult grade 2-3 intracranial diffuse gliomas. \u003cem\u003eNeuroradiology \u003c/em\u003e2022, 64(12):2295-2305.http://doi.org/10.1007/s00234-022-02975-0.\u003c/li\u003e\n\u003cli\u003eCho NS, Sanvito F, Le VL, Oshima S, Teraishi A, Yao J\u003cem\u003e et al\u003c/em\u003e. Quantification of T2-FLAIR Mismatch in Nonenhancing Diffuse Gliomas Using Digital Subtraction. \u003cem\u003eAJNR Am J Neuroradiol \u003c/em\u003e2024, 45(2):188-197.http://doi.org/10.3174/ajnr.A8094.\u003c/li\u003e\n\u003cli\u003eMalik P, Soliman R, Chen YA, Munoz DG, Das S, Bharatha A, Mathur S. Patterns of T2-FLAIR discordance across a cohort of adult-type diffuse gliomas and deviations from the classic T2-FLAIR mismatch sign. \u003cem\u003eNeuroradiology \u003c/em\u003e2024, 66(4):521-530.http://doi.org/10.1007/s00234-024-03297-z.\u003c/li\u003e\n\u003cli\u003eS\u0026aacute;nchez J, Mart\u0026iacute;n-Landrove M. Morphological and Fractal Properties of Brain Tumors. \u003cem\u003eFront Physiol \u003c/em\u003e2022, 13:878391.http://doi.org/10.3389/fphys.2022.878391.\u003c/li\u003e\n\u003cli\u003eWang J, Yi L, Kang QM, Zhou J, Chen TQ, Hugnot JP, Yu SC. Glioma invasion along white matter tracts: A dilemma for neurosurgeons. \u003cem\u003eCancer letters \u003c/em\u003e2022, 526:103-111.http://doi.org/10.1016/j.canlet.2021.11.020.\u003c/li\u003e\n\u003cli\u003eMazurowski MA, Clark K, Czarnek NM, Shamsesfandabadi P, Peters KB, Saha A. Radiogenomics of lower-grade glioma: algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with The Cancer Genome Atlas data. \u003cem\u003eJ Neurooncol \u003c/em\u003e2017, 133(1):27-35.http://doi.org/10.1007/s11060-017-2420-1.\u003c/li\u003e\n\u003cli\u003eNie S, Zhu Y, Yang J, Xin T, Xue S, Sun J\u003cem\u003e et al\u003c/em\u003e. Clinicopathologic analysis of microscopic tumor extension in glioma for external beam radiotherapy planning. \u003cem\u003eBMC medicine \u003c/em\u003e2021, 19(1):269.http://doi.org/10.1186/s12916-021-02143-w.\u003c/li\u003e\n\u003cli\u003eSmits M, van den Bent MJ. Imaging Correlates of Adult Glioma Genotypes. \u003cem\u003eRadiology \u003c/em\u003e2017, 284(2):316-331.http://doi.org/10.1148/radiol.2017151930.\u003c/li\u003e\n\u003cli\u003ePark YW, Han K, Ahn SS, Bae S, Choi YS, Chang JH\u003cem\u003e et al\u003c/em\u003e. Prediction of IDH1-Mutation and 1p/19q-Codeletion Status Using Preoperative MR Imaging Phenotypes in Lower Grade Gliomas. \u003cem\u003eAJNR Am J Neuroradiol \u003c/em\u003e2018, 39(1):37-42.http://doi.org/10.3174/ajnr.A5421.\u003c/li\u003e\n\u003cli\u003eYue S, Li S, Huang X, Liu J, Hou X, Zhao Y\u003cem\u003e et al\u003c/em\u003e. Machine learning for the prediction of acute kidney injury in patients with sepsis. \u003cem\u003eJ Transl Med \u003c/em\u003e2022, 20(1):215.http://doi.org/10.1186/s12967-022-03364-0.\u003c/li\u003e\n\u003cli\u003eTruong NCD, Bangalore Yogananda CG, Wagner BC, Holcomb JM, Reddy D, Saadat N\u003cem\u003e et al\u003c/em\u003e. Two-Stage Training Framework Using Multicontrast MRI Radiomics for IDH Mutation Status Prediction in Glioma. \u003cem\u003eRadiology Artificial intelligence \u003c/em\u003e2024, 6(4):e230218.http://doi.org/10.1148/ryai.230218.\u003c/li\u003e\n\u003cli\u003eKandemirli SG, Kocak B, Naganawa S, Ozturk K, Yip SSF, Chopra S\u003cem\u003e et al\u003c/em\u003e. Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomics for Prediction of H3K27M Mutation in Midline Gliomas. \u003cem\u003eWorld Neurosurg \u003c/em\u003e2021, 151:e78-e85.http://doi.org/10.1016/j.wneu.2021.03.135.\u003c/li\u003e\n\u003cli\u003eYan Z, Wang J, Dong Q, Zhu L, Lin W, Jiang X. XGBoost algorithm and logistic regression to predict the postoperative 5-year outcome in patients with glioma. \u003cem\u003eAnn Transl Med \u003c/em\u003e2022, 10(16):860.http://doi.org/10.21037/atm-22-3384.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Isocitrate dehydrogenase, T2-FLAIR mismatch, Magnetic resonance imaging, Gliomas, Fractal analysis","lastPublishedDoi":"10.21203/rs.3.rs-7334338/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7334338/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eTo explore the relationship between relaxed T2-FLAIR mismatch (RT2FM) sign, fractal dimension (FD) of tumor contour and IDH mutation status, and construct models for IDH mutation prediction in non-enhancing gliomas.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eThis retrospective study enrolled 364 patients with non-enhancing gliomas from two independent cohorts: cohort A (n\u0026thinsp;=\u0026thinsp;267) for training \u0026amp; internal validation set and cohort B (n\u0026thinsp;=\u0026thinsp;97) for external testing set. RT2FM, FD, and other MRI semantic features were extracted. Boruta and least absolute shrinkage and selection operator algorithms were employed to select intersecting features. Four machine learning models were constructed using the intersecting features and their diagnostic performance was evaluated.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThe RT2FM sign predicted IDH mutation with an accuracy, sensitivity, and specificity of 0.969, 0.650, and 0.921 in cohort A, and 0.924, 0.419, and 0.762 in cohort B, respectively. In cohort A, FD were significantly higher in IDH wild-type than in IDH mutant groups (1.264 vs. 1.190; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Using an FD cutoff value of 1.225, the area under the curve (AUC) and accuracy for predicting IDH mutation were 0.884 and 0.839, respectively. Among models constructed using four intersecting features (FD, RT2FM, multifocal/multicentric, and tumor location), XGBoost demonstrated the optimal predictive performance, with AUCs of 0.974, 0.968 and 0.895 in the training, internal validation and external testing set, respectively.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eRT2FM and FD can provide informative imaging biomarkers for predicting IDH mutation. The XGBoost model constructed by these features demonstrated favorable diagnostic performance for IDH mutation prediction in non-enhancing gliomas.\u003c/p\u003e\u003ch2\u003eClinical trial number\u003c/h2\u003e\u003cp\u003eNot applicable\u003c/p\u003e","manuscriptTitle":"IDH mutation prediction in non-enhancing gliomas with relaxed T2-FLAIR mismatch and fractal dimension: a two-center study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-08 16:04:53","doi":"10.21203/rs.3.rs-7334338/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-10T04:30:11+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-08T20:47:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-07T01:29:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"236037341856679452829387442952778254737","date":"2025-12-06T18:48:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"108631167829024555399888308612075000709","date":"2025-11-17T02:42:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73284967530516919834730205599200129247","date":"2025-11-16T14:55:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-06T12:53:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"305887243621629194125763010451388980390","date":"2025-10-06T10:38:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-26T07:10:06+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-25T19:39:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-12T11:07:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-12T11:06:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2025-08-09T13:52:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f424f865-ebf1-4c81-bb7d-61b39fab829d","owner":[],"postedDate":"October 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-05T16:02:11+00:00","versionOfRecord":{"articleIdentity":"rs-7334338","link":"https://doi.org/10.1186/s12880-025-02140-y","journal":{"identity":"bmc-medical-imaging","isVorOnly":false,"title":"BMC Medical Imaging"},"publishedOn":"2026-01-03 15:58:35","publishedOnDateReadable":"January 3rd, 2026"},"versionCreatedAt":"2025-10-08 16:04:53","video":"","vorDoi":"10.1186/s12880-025-02140-y","vorDoiUrl":"https://doi.org/10.1186/s12880-025-02140-y","workflowStages":[]},"version":"v1","identity":"rs-7334338","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7334338","identity":"rs-7334338","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}