Preoperative Prediction of Thymoma Risk Classification with Machine Learning-Based Computed Tomography Radiomics Features

Preoperative Prediction of Thymoma Risk Classification with Machine Learning-Based Computed Tomography Radiomics Features | 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 Preoperative Prediction of Thymoma Risk Classification with Machine Learning-Based Computed Tomography Radiomics Features Kai Zhao, Yiming Liu, Honghao Xu, Wenhan Cai, Jiamei Jin, Leilei Shen, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9180024/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Background Thymomas are primarily assessed using chest computed tomography (CT); however, this method has inherent limitations such as an overlap between the semantic features of thymomas presenting as localized lesions and other histological subtypes. Therefore, this study aimed to develop a combined radiomics model, based on non-contrast CT, and investigate its potential clinical utility in preoperatively differentiating between the thymoma risk classification. Methods We retrospectively analyzed the clinical and imaging data of 436 patients with pathologically confirmed thymomas between January 2010 and October 2023. The cohort comprised 272 low-risk cases (types A, AB, and B1) and 164 high-risk cases (types B2 and B3), which were randomly divided into training (n = 306) and validation (n = 130) sets in a 7:3 ratio. Radiomic features were extracted from the volume of interest on non-contrast CT images. Feature selection was performed using principal component analysis, correlation analysis, least absolute shrinkage, and selection operator algorithms to identify the most discriminative features. A combined radiomics nomogram was developed by integrating significant clinical factors with radiomics scores. The discriminative performance of the model was assessed using receiver operating characteristic curve analysis. Results Two clinicoradiological and 11 radiomics features were identified and used to construct a radiomics nomogram. The diagnostic performance of the nomogram for thymoma risk stratification surpassed that of any single model. The nomogram yielded an area under the curve of 0.753 (accuracy, 71.2%; sensitivity, 62.4%; specificity, 76.7%) in the training cohort and 0.735 (accuracy, 70.8%; sensitivity, 58.8%; specificity, 78.5%) in the validation cohort. Conclusion The nomogram model integrating clinical factors and radiomics features accurately differentiated the histological subtypes of thymoma. This tool may be helpful in formulating personalized treatment plans in clinical practice and is worthy of clinical promotion and application. thymoma histopathological classification radiomics analysis computed tomography machine learning Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 1. Introduction Among anterior mediastinal masses, thymomas are the most common primary tumors accounting for 47% of all mediastinal tumors ( 1 ). The updated 2021 World Health Organization classification stratifies thymomas into five histological subtypes (types A, AB, B1, B2, and B3) based on the morphology of epithelial cells and the ratio of lymphocytes to epithelial cells ( 2 ). Specifically, type B2 and B3 thymomas are more invasive and associated with higher postoperative recurrence rates and lower survival rates than type A, AB, and B1 thymomas. Furthermore, A, AB, and B1 thymomas are completely surgically resected more frequently than B2 and B3 thymomas ( 3 , 4 ). Based on these distinct clinical behaviors, thymomas are often classified into two risk groups: low-risk (types A, AB, and B1) and high-risk (types B2 and B3) ( 5 – 7 ). Surgical resection is the primary treatment for thymoma, with complete resection being the goal for optimal survival. However, histological subtype is a key factor in planning therapeutic approaches. Patients with low-risk thymomas typically achieve high rates of complete resection and are often managed with surgery alone without neoadjuvant or adjuvant therapy. By contrast, high-risk thymomas are less amenable to complete resection and often require multimodal treatment ( 8 – 10 ). Consequently, accurate preoperative risk stratification is crucial for guiding surgical planning, informing decisions regarding neoadjuvant or adjuvant therapies, and ultimately improving patient prognosis. Radiomics has been widely used for the early diagnosis, screening, and prognostic assessment of tumors, facilitating the development of personalized treatment strategies. Currently, radiomics utilizes high-dimensional quantitative features extracted from medical images, such as computed tomography (CT) images, to noninvasively quantify tumor heterogeneity and elucidate the underlying malignant characteristics ( 11 ). Non-contrast chest CT is the primary imaging modality for thymoma assessment due to its widespread availability, high spatial resolution, and ability to provide information on tumor vascularity ( 12 , 13 ). However, chest CT images of patients with thymomas require evaluation by radiologists, leading to uncertainties that may affect the accurate classification of thymomas. For instance, the semantic features of thymomas presenting as localized lesions, especially those with no obvious invasion of the surrounding structures on CT images, may overlap with those of different histological subtypes. This overlap is unfavorable for preoperative thymoma risk classification ( 14 ). Additionally, owing to the rarity of thymomas, clinicians (including thoracic surgeons and radiologists) in some centers may have limited experience in evaluating thymomas. This highlights the need for a quantitative method to classify thymomas with high accuracy and objectivity, and to reduce reliance on radiologists' experience. Previous studies suggest that CT-based radiomics can aid in thymoma risk stratification; however, the clinical translation of this technology has been limited, primarily due to small sample sizes (often fewer than 200 patients), which have constrained the robustness and generalizability of the findings ( 9 , 15 , 16 ). Therefore, our study used a large cohort to develop a radiomics model based on non-contrast CT images using machine learning, which integrated radiomics features with clinical and radiological characteristics. This approach is expected to enhance the accuracy and clinical applicability of preoperative risk prediction for thymomas. 2. Materials and methods 2.1 Patient recruitment This retrospective study was approved by the Institutional Review Board of our hospital, and the requirement for informed consent was waived. This cohort study has been reported in line with the STROCSS 2024 guidelines ( 17 ). The study cohort comprised patients with pathologically confirmed thymomas who underwent surgical resection at our institution between January 2010 and October 2023. The inclusion criteria were as follows: ( 1 ) pathologically confirmed thymoma following surgical resection; ( 2 ) no prior anticancer treatment before surgery; ( 3 ) availability of a non-contrast chest CT scan performed within two weeks prior to surgery; and ( 4 ) complete clinical records. The exclusion criteria were as follows: ( 1 ) small tumor size (maximum diameter ≤ 9 mm); ( 2 ) poor image quality due to significant artifacts; ( 3 ) a history of other malignancies; and ( 4 ) incomplete clinical or imaging data. In total, 436 patients with thymomas were enrolled (Fig. 1 ). The cohort comprised 223 men and 213 women, aged 25–80 years with a mean age of 55.85 ± 10.99 years. Based on the postoperative pathology, the patients were categorized into a low-risk group (n = 272), consisting of type A (n = 32), AB (n = 155), and B1 (n = 85) thymomas, and a high-risk group (n = 164), consisting of type B2 (n = 115) and B3 (n = 49) thymomas. 2.2 Histopathological classification According to the 2021 World Health Organization classification, thymomas are categorized into five histological subtypes (A, AB, B1, B2, and B3) based on the morphology of epithelial cells and the lymphocyte to epithelial cell ratio. Type A thymoma is characterized by a population of spindle-shaped epithelial cells with minimal atypia and a notable absence of immature T-lymphocytes. Atypical type A thymoma meets the criteria for type A thymoma but also exhibits focal necrosis, mitotic activity (> 4 mitoses per 2 mm²), and nuclear crowding. Type AB thymoma demonstrates the morphological features of type A thymoma, but also contains abundant immature T cells, either locally or diffusely distributed. Type B1 thymomas most closely resemble the normal thymic architecture, featuring large areas of immature T cells, medullary differentiation (medullary islands), and scant aggregates of polygonal or dendritic epithelial cells (fewer than three adjacent cells). Type B2 thymomas show an increased proportion of polygonal or dendritic epithelial cells, appearing alone or in clusters, against a background of numerous immature T cells. Type B3 thymomas are composed of sheets of epithelial cells exhibiting mild to moderate atypia, with absent or inconspicuous intercellular bridges and a paucity of mature T lymphocytes. 2.3 CT examination and image analysis All patients underwent non-contrast CT using either a Philips (Amsterdam, the Netherlands) Brilliance iCT scanner or a Siemens (Erlangen, Germany) Somatom Definition scanner. The standard scanning range was extended from the lung apex to the costophrenic angle. In patients with ectopic neck thymomas, the range was adjusted to cover the upper edge of the aortic arch from the inferior border of the hyoid bone. The scanning parameters were as follows: tube voltage of 120 kV, automatic tube current modulation, matrix of 512×512, rotation time of 0.6 s, slice thickness of 5 mm for acquisition, and 1.25 mm for reconstruction. Images were reviewed using a mediastinal window setting (window width, 350 HU; level, 50 HU). Two radiologists, each with over 10 years of experience, independently assessed all images. Any discrepancies were resolved by a consensus discussion between the two radiologists. The following CT features were evaluated: tumor size (defined as the maximum axial diameter); location (left-sided, central, or right-sided); morphology (regular or irregular); margin (well-defined or ill-defined); and presence or absence of calcification, necrosis/cystic degeneration, invasion of adjacent structures, and distant metastasis. 2.4 Image segmentation and feature extraction The patients were randomly allocated to the training (n = 306) or validation sets (n = 130) in a 7:3 ratio. Original CT images in a DICOM format were retrieved from the Picture Archiving and Communication System. A two-dimensional image slice showing the largest tumor diameter was selected from each scan. All images were then resampled to a uniform voxel spacing of 1×1×1 mm³ to standardize the spatial resolution. Manual delineation of the volume of interest (VOI) was performed using the open-source software ITK-SNAP (version 3.6.0; Fig. 2 ). The initial contouring was performed by an experienced radiologist. A second radiologist independently reviewed all segmentations to ensure reliability. Any discrepancies were resolved through a consensus discussion between the two readers to finalize the VOIs, thereby enhancing the accuracy and reproducibility of subsequent feature extraction. During manual segmentation, caution was exercised to encompass the entire tumor volume while meticulously avoiding lesion boundaries, adjacent vascular structures, and internal cystic or necrotic areas. Subsequently, 1032 traditional radiomics features were extracted from each VOI using the PyRadiomics platform (version 3.1.0). The extracted feature set encompassed first-order statistics, shape-based features, texture features (derived from the gray-level co-occurrence matrix, gray-level run-length matrix, and gray-level size zone matrix), and higher-order features obtained through wavelet and Laplacian Gaussian filter transforms. The intraclass correlation coefficient was calculated for all features based on the segmentation to ensure feature stability and reproducibility. Only the features demonstrating excellent consistency (intraclass correlation coefficient > 0.75) were retained for subsequent analyses. 2.5 Radiomics feature selection The 1,032 radiomics features extracted from each VOI underwent feature selection. Briefly, Z-score normalization was applied to all features to eliminate scale differences. Class imbalance in the training set was addressed using the synthetic minority oversampling technique to generate synthetic samples and balance class distribution. Subsequently, feature dimensionality reduction was conducted using least absolute shrinkage and selection operator regression with a 10-fold cross-validation to determine the optimal penalty parameter (λ). The L1 regularization inherent in the least absolute shrinkage and selection operator shrinks the coefficients of irrelevant features to zero, resulting in the selection of a subset of features that are most predictive of the outcome. 2.6 Model construction and diagnostic efficacy evaluation Three distinct models were developed to differentiate between low- and high-risk thymomas. A clinicoradiological model was constructed using independent predictors identified using univariate and multivariate logistic regression analyses. Concurrently, a radiomics model was built and a radiomics score (Rad-score) was calculated for each patient. Finally, a combined nomogram integrating significant clinicoradiological factors and Rad-scores was established. The diagnostic performance of each model was evaluated and compared using the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Calibration of the combined nomogram was assessed using a calibration plot, and its clinical net benefit was quantified using decision curve analysis (Fig. 3 ). 2.7 Statistical analysis All statistical analyses were performed using the SPSS software (version 26.0). The normality of continuous variables was assessed using the Shapiro–Wilk test. Data conforming to a normal distribution were compared using the independent samples t-test, whereas non-normally distributed data were compared using the Mann–Whitney U test. Categorical variables were compared using the chi-squared test or Fisher's exact test, as appropriate. The independent predictors were identified using univariate and multivariate logistic regression analyses. Spearman’s correlation analysis, least absolute shrinkage, and selection operator regression were employed for dimensionality reduction for radiomics feature selection. Predictive models were constructed using machine-learning algorithms. Model performance was evaluated using the AUC, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The DeLong test was used to compare the AUCs of different models. Calibration curves and decision curve analysis were used to assess the calibration and clinical utility of the models, respectively. Statistical significance was set at a two-sided P < 0.05. 3. Results 3.1 Clinical and radiological features This study enrolled 436 patients with thymomas, who were randomly allocated to a training cohort (n = 306) or a validation cohort (n = 130) in a 7:3 ratio. Baseline characteristics, including age and sex, were well balanced between the two cohorts (all P > 0.05, Table 1 ). The cohort comprised 272 low-risk thymomas (types A, AB, and B1) and 164 high-risk thymomas (types B2 and B3). The distributions of these risk categories were consistent between the training (low-risk, n = 189; high-risk, n = 117) and validation (low-risk, n = 83; high-risk, n = 47) cohorts. Comparative analysis revealed that tumor morphology, margin definition, and invasion of the surrounding tissues were significantly different between the low- and high-risk groups (all P < 0.05; Table 2 ). Table 1 Comparison of clinical and imaging features of thymomas between the training and validation cohorts Baseline Characteristics Training cohort (n = 306) Validation cohort (n = 130) P-value Sex (case) 0.836 Male 158 65 Female 148 65 Age (years) 0.332 ≤ 50 149 56 > 50 157 74 Diameter (cm) 0.174 ≤ 5 139 69 > 5 167 61 Location 0.073 Left 118 44 Middle 59 38 Right 129 48 Morphology 0.745 Regular 181 74 Irregular 125 56 Margin 0.594 Clear 183 82 Unclear 123 48 Calcification 0.119 Yes 47 12 No 259 118 Necrosis and cystic degeneration 0.689 Yes 56 21 No 250 109 Invasion of surrounding tissues 0.536 Yes 141 55 No 165 75 Distant metastasis 0.768 Yes 33 16 No 273 114 Table 2 Comparison of clinical and imaging features between low-risk and high-risk thymomas Baseline characteristics Training cohort Validation cohort Low-risk group (n = 189) High-risk group (n = 117) P-value Low-risk group (n = 83) High-risk group (n = 47) P-value Sex (case) 0.467 0.273 Male 94 64 45 20 Female 95 53 38 27 Age (years) 0.124 0.230 ≤ 50 85 64 32 24 > 50 104 53 51 23 Diameter (cm) 0.947 0.767 ≤ 5 86 53 44 25 > 5 103 64 39 22 Location 0.176 0.328 Left 70 48 28 16 Middle 32 27 34 17 Right 87 42 21 14 Morphology < 0.001 0.644 Regular 130 51 49 25 Irregular 59 66 34 22 Margin 0.003 0.417 Clear 126 57 55 27 Unclear 63 60 28 20 Calcification 0.863 0.597 Yes 28 19 9 3 No 161 98 74 44 Necrosis and cystic degeneration 0.781 0.125 Yes 36 20 17 4 No 153 97 66 43 Invasion of surrounding tissues < 0.001 < 0.001 Yes 70 71 24 31 No 119 46 59 16 Distant metastasis 0.998 0.691 Yes 20 13 9 7 No 169 104 74 20 3.2 Clinical feature selection and model construction Univariate and multivariate logistic regression analyses of clinical and radiological features identified tumor morphology and invasion of surrounding tissues as independent predictors of thymoma risk (all P < 0.05; Table 3 ). The clinicoradiological model, constructed using these independent factors, demonstrated an AUC of 0.668 (95% confidence interval [CI]: 0.613–0.721), accuracy of 68.3%, sensitivity of 46.2%, and specificity of 82.0% in the training cohort, and an AUC of 0.646 (95% CI: 0.557–0.728), accuracy of 63.8%, sensitivity of 38.3%, and specificity of 78.3% in the validation cohort (Table 4 ). Table 3 Univariate and Multivariate Analyses used to identify independent predictors of thymoma risk Univariate analysis Multivariate analysis OR 95%CI P-value OR 95% P-value Sex 0.995 0.675–1.467 0.981 NA NA NA Age 0.652 0.442–0.963 0.650 NA NA NA Diameter 1.009 0.685–1.488 0.962 NA NA NA Location 1.079 0.835–1.394 0.561 NA NA NA Morphology 2.229 1.500–3.312 < 0.001 2.042 1.198–3.480 0.009 Margin 1.894 1.274–2.816 0.002 0.565 0.300–1.062 0.076 Calcification 1.016 0.576–1.792 0.956 NA NA NA Necrosis and cystic degeneration 1.412 0.834–2.391 0.200 NA NA NA Invasion of surrounding tissues 3.115 2.083–4.659 < 0.001 3.366 2.014–5.626 < 0.001 Distant metastasis 0.859 0.469–1.575 0.624 NA NA NA OR, odds ratio; CI, confidence interval; NA, not applicable Table 4 Predictive performance of the training and validation cohorts for different models Models AUC 95%CI Accuracy Sensitivity Specificity PPV NPV Training cohort Clinicoradiological model 0.668 0.613–0.721 0.683 0.462 0.820 0.614 0.711 Radiomics model 0.751 0.698–0.798 0.725 0.735 0.720 0.619 0.814 Nomogram model 0.753 0.700–0.800 0.712 0.624 0.767 0.624 0.767 Validation cohort Clinicoradiological model 0.646 0.557–0.728 0.638 0.383 0.783 0.500 0.691 Radiomics model 0.725 0.640–0.800 0.677 0.766 0.627 0.537 0.825 Nomogram model 0.735 0.651–0.809 0.708 0.588 0.785 0.638 0.747 AUC, area under the receiver operating characteristic curve; CI, confidence interval; PPV, positive predictive value; NPV, negative predictive value 3.4 Construction of radiomics prediction model A total of 1032 radiomics features were extracted from each VOI, capturing comprehensive information on the geometry, intensity, and textural heterogeneity of the tumors. Dimensionality reduction was performed using PCA, least absolute shrinkage, and selection operator regression to mitigate the risk of overfitting from high-dimensional data. This process identified 11 key predictive features (Fig. 4 ) that were used to construct the radiomics model. In the training cohort, the model achieved an AUC of 0.751 (95% CI: 0.698–0.798), accuracy of 75.2%, sensitivity of 73.5%, and specificity of 72.0%. In the validation cohort, the AUC was 0.725 (95% CI: 0.640–0.800), with accuracy of 67.7%, sensitivity of 76.6%, and specificity of 62.7% (Table 4 ). 3.4 Model efficacy evaluation A combined radiomics nomogram was developed using logistic regression analysis to preoperatively predict thymoma risk by integrating significant clinical features (tumor morphology and invasion of surrounding tissues) with the radiomics signature (Fig. 5 ). In the training cohort, the nomogram achieved an AUC of 0.753 (95% CI, 0.700–0.800), with accuracy of 71.2%, sensitivity of 62.4%, and specificity of 76.7%. When evaluated in the independent validation cohort, it yielded an AUC of 0.735 (95% CI: 0.651–0.809), with accuracy of 70.8%, sensitivity of 58.8%, and specificity of 78.5% (Table 4 ). Notably, the combined radiomics nomogram demonstrated higher AUC values than the clinicoradiological and standalone radiomics models in the training and validation cohorts. The DeLong test revealed that in the training cohort, the nomogram performed significantly better than the clinicoradiological model (P < 0.001) and the standalone radiomics model (P = 0.012). Although the AUC of the nomogram was higher than that of the standalone radiomic model, the difference was not statistically significant (P = 0.863). In the validation cohort, the superior performance of the nomogram compared to the clinicoradiological model remained significant (P = 0.016). However, the differences between the nomogram and standalone radiomics model and between the standalone radiomics model and clinicoradiological model were not statistically significant (both P > 0.05). Collectively, these results indicate that the combined nomogram offers a more robust predictive advantage for thymoma risk stratification compared to other models (Table 5 , Fig. 6 ). Table 5 Comparison of prediction with the combined radiomics nomogram, clinicoradiological model, and radiomics models Group Model 1 Model 2 P-value Training cohort Nomogram Radiomics 0.863 Nomogram Clinicoradiological < 0.001 Radiomics Clinicoradiological 0.012 Validation cohort Nomogram Radiomics 0.509 Nomogram Clinicoradiological 0.016 Radiomics Clinicoradiological 0.109 The reliability and clinical value of the prediction models were assessed. The calibration curve indicated excellent agreement between the predicted probabilities of the combined radiomics nomogram and the actual observed outcomes in the training and validation cohorts, which was confirmed by the non-significant Hosmer–Lemeshow test results (all P > 0.05) (Fig. 5 ). Decision curve analysis further demonstrated that the application of this combined nomogram provided a higher net benefit across a wide range of threshold probabilities than the clinicoradiological and standalone radiomics models (Fig. 6 ). These findings collectively confirm the favorable calibration and clinical utility of the combined radiomics nomogram for thymoma risk stratification. 4. Discussion Radiomics enables the quantitative analysis of medical images and captures disease-specific features that may not be discernible through conventional visual assessment. The increasing application of radiomics in oncology has demonstrated a promising potential for augmenting traditional imaging analysis and supporting personalized treatment strategies. In this study, we developed a radiomics model based on non-contrast CT images to predict the histological risk of thymomas preoperatively. The standalone radiomics model showed superior predictive performance compared with the model based solely on clinicoradiological features. Furthermore, the combined nomogram that integrated radiomics and clinicoradiological factors demonstrated the best overall performance in differentiating high-risk thymomas from low-risk ones, with an efficacy comparable to that of the standalone radiomics model, while incorporating clinically relevant variables. The proposed nomogram shows potential as a practical tool to aid clinical decision-making for the individualized management of patients with thymoma. The results of this study indicate that high-risk thymomas predominantly exhibit an irregular shape, unclear boundaries, and invasion of surrounding tissues, whereas low-risk thymomas are more frequently round or oval, with clear boundaries and no invasion. These findings were consistent with those of previous reports ( 18 – 20 ). The irregular morphology commonly observed in high-risk tumors may be attributed to their higher malignant potential, greater cellular atypia, and heterogeneous growth patterns, leading to asymmetrical expansion. Thus, tumor shape serves as a key radiological indicator for risk stratification. Although the univariate analysis indicated an association between blurred margins and high-risk thymoma, this feature was not retained as an independent predictor in the multivariate model. This suggests that, while margin characteristics possess some discriminatory value, their predictive power may be subordinate to other stronger indicators, such as invasion or shape, when evaluated collectively. Consequently, the diagnostic utility of tumor margins might be better elucidated through future studies with larger cohorts or by analyzing enhanced CT images that provide superior soft tissue contrast. Consistent with the existing literature ( 21 – 23 ), our study confirmed that invasion into adjacent structures is a hallmark of high-risk thymomas, with a significantly higher incidence than that of low-risk tumors. This reinforces the value of peritumoral invasion as a critical imaging marker for evaluating the biological aggressiveness of thymomas. CT is an established first-line imaging modality for the evaluation of anterior mediastinal masses. Consequently, multiple studies have investigated CT-based strategies for distinguishing between low-and high-risk thymomas ( 19 , 24 ). Liang et al. ( 25 ) found that radiomics based on enhanced CT could be used to identify the histological subtypes of thymomas. The AUC of the radiomics nomogram and radiomics model for distinguishing between low-and high-risk thymomas was higher than that of the clinical model. Thus, the enhanced CT-based radiomics model and radiomics nomogram, integrating clinical factors, CT features, and radiomics features, are useful for identifying thymoma histological subtypes. Liu et al. ( 26 ) evaluated 30 patients with high-risk thymomas and 117 patients with low-risk thymomas to identify the key CT features for risk stratification. The results confirmed that high-risk thymomas had more irregular shapes and contours and a higher incidence of invasion into surrounding tissues and organs on CT images compared to low-risk thymomas. Han et al. ( 27 ) constructed and validated an imaging model combining clinical factors and non-contrast CT features to distinguish between high-risk and low-risk thymomas. They found that CT imaging features showed no significant differences between patients of different sexes or ages; however, multiple statistically significant differences in the imaging features were observed between the high- and low-risk groups. Sadohara et al. ( 20 ) proposed that combining the features of CT and magnetic resonance imaging (such as tumor contour, capsule, septation, and enhancement uniformity) is helpful in distinguishing low-and high-risk thymomas. Furthermore, Xiao et al. ( 28 ) showed the good performance of a combined radiomics nomogram that integrated magnetic resonance imaging with tumor shape, ADC coefficient, and radiomics features. Nakajo et al. ( 29 ) reported the good predictive efficacy of machine-learning methods based on deep-learning features from 18F-FDG-PET radiomics. The experimental results of this study demonstrate that radiomics based on non-contrast CT exhibits favorable predictive efficacy for distinguishing between low- and high-risk thymomas. In the training cohort, the combined radiomics and standalone radiomics models achieved significantly higher AUC values than the clinicoradiological model (P < 0.05). In the validation cohort, the superiority of the combined radiomics model over the clinicoradiological model remained significant (P = 0.016). Although the combined model also yielded a higher AUC than the standalone radiomics model (which outperformed the clinicoradiological model), the differences were not statistically significant (P > 0.05). Given that traditional radiological parameters (e.g., tumor capsule integrity and degree of necrosis) remained clinically valuable and considering that the combined model demonstrated a superior performance compared to the individual models, we propose the integrated radiomics nomogram as the final predictive tool for clinical translation. Nonetheless, this study has some limitations. First, the single-center retrospective study design may have introduced selection bias and limited the generalizability of our findings, as patient demographics and clinical practices can vary across institutions. Second, the exclusive use of non-contrast CT images lacks the functional information available from contrast-enhanced CT, magnetic resonance imaging (particularly diffusion-weighted imaging sequences), or positron emission tomography-CT, despite providing anatomical details. The incorporation of multiparametric data in future studies may yield more discriminative features. Third, the absence of genomic data represents a significant limitation as it could offer crucial insights into the underlying biology of thymomas. Consequently, multicenter prospective studies are required in the future to validate and refine the model as our results demonstrate that integrating radiological, clinical, and genomic data is essential for developing a more comprehensive understanding of thymomas and for building robust predictive models to guide personalized treatment. In conclusion, this study developed and validated a non-contrast CT-based radiomics model as a noninvasive, reliable, and reproducible tool for predicting the histological subtypes of thymoma. The radiomics model demonstrated a superior predictive performance compared with the traditional clinicoradiological model. These results suggest that the proposed approach can assist clinicians in formulating personalized treatment strategies for patients with early stage thymoma, thereby optimizing therapeutic efficacy and improving clinical outcomes, and showing promise for broader clinical applications. Abbreviations Computed tomography (CT) Volume of interest (VOI) Area under the receiver operating characteristic curve (AUC) Confidence interval (CI) Declarations Conflict of Interest The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. Author Contributions K.Z. participated in research design, data collection, data analysis, and writing of the paper. Y.L. participated in research design and data analysis. H.X. participated in research design and data analysis. W.C. participated in research design and data analysis. J.J., L.S., Z.Z., and H.H. participated in research design and proofreading of the article. M.H. participated in research design. Q.L. participated in research design and data analysis. Z.X. participated in research design, data analysis, contribution of new analytic tools, writing, and study supervision. Funding This study was supported by the Research and Development Project on Medical Big Data and Artificial Intelligence of the PLA General Hospital (2019MBD-017) and Shaanxi Province Key Core Technology Tackling Project (2024SF-GJHX-27). These funding agencies were not involved in study design, analysis, or reporting. Acknowledgments N\A Data Availability Statement The data supporting the findings of this study were retrieved from the clinical database of PLA General Hospital, a secure institutional database housing de-identified clinical records of patients treated at the hospital. Ethics Approval and Consent to Participate This retrospective study was conducted in accordance with the ethical standards of the Declaration of Helsinki and its later amendments. Ethical approval was obtained from the Institutional Review Board (IRB) of Hainan Hospital of Chinese PLA General Hospital (IRB approval number: S2025-11-01). Human Ethics and Consent to Participate declarations: The requirement for written informed consent was waived by the IRB due to the retrospective nature of the study. All patient data were anonymized and de-identified prior to analysis, and no interventions were performed that would affect clinical care or patient outcomes. References Scorsetti M, Leo F, Trama A, D’Angelillo R, Serpico D, Macerelli M et al. Thymoma and thymic carcinomas. Crit Rev Oncol Hematol (2016) 99:332 – 50. 10.1016/j.critrevonc.2016.01.012 Marx A, Chan JKC, Chalabreysse L, Dacic S, Detterbeck F, French CA, et al. The 2021 WHO classification of tumors of the Thymus and mediastinum: what is new in thymic epithelial, germ cell, and mesenchymal tumors? J Thorac Oncol. 2022;17:200–13. 10.1016/j.jtho.2021.10.010 . Koçer B, Kaplan T, Günal N, Koçer BG, Akkaş Y, Yazkan R, et al. Long-term survival after R0 resection of thymoma. Asian Cardiovasc Thorac Ann. 2018;26:461–6. 10.1177/0218492318778634 . Lee GD, Kim HR, Choi SH, Kim YH, Kim DK, Park SI. Prognostic stratification of thymic epithelial tumors based on both Masaoka-Koga stage and WHO classification systems. J Thorac Dis (2016) 8:901 – 10. 10.21037/jtd.2016.03.53 Roden AC, Yi ES, Jenkins SM, Edwards KK, Donovan JL, Lewis JE, et al. Reproducibility of 3 histologic classifications and 3 staging systems for thymic epithelial neoplasms and its effect on prognosis. Am J Surg Pathol. 2015;39:427–41. 10.1097/PAS.0000000000000391 . Multidisciplinary Committee of Oncology, Chinese Physicians Association. [Chinese guideline for clinical diagnosis and treatment of thymic epithelial tumors (2021 Edition)]. Zhonghua Zhong Liu Za Zhi. 2021;43:395–404. 10.3760/cma.j.cn112152-20210313-00226 . Osserman KE, Genkins G. Studies in myasthenia gravis: review of a twenty-year experience in over 1200 patients. Mt Sinai J Med. 1971;38:497–537. Wang X, Sun W, Liang H, Mao X, Lu Z. Radiomics signatures of computed tomography imaging for predicting risk categorization and clinical stage of thymomas. BioMed Res Int. 2019;2019:3616852. 10.1155/2019/3616852 . Dong W, Xiong S, Lei P, Wang X, Liu H, Liu Y, et al. Application of a combined radiomics nomogram based on CE-CT in the preoperative prediction of thymomas risk categorization. Front Oncol. 2022;12:944005. 10.3389/fonc.2022.944005 . Sacks D, Baxter B, Campbell BCV, Carpenter JS, Cognard C, Dippel D, et al. Multisociety consensus quality improvement revised consensus statement for endovascular therapy of acute ischemic stroke: From the American Association of Neurological Surgeons (AANS), American Society of Neuroradiology (ASNR), Cardiovascular and Interventional Radiology Society of Europe (CIRSE), Canadian Interventional Radiology Association (CIRA), Congress of Neurological Surgeons (CNS), European Society of Minimally Invasive Neurological Therapy (ESMINT), European Society of Neuroradiology (ESNR), European Stroke Organization (ESO), Society for Cardiovascular Angiography and Interventions (SCAI), Society of Interventional Radiology (SIR), Society of NeuroInterventional Surgery (SNIS), and World Stroke Organization (WSO). J Vasc Interv Radiol. 2018;29:441–53. 10.1016/j.jvir.2017.11.026 . Ganeshan B, Miles KA. Quantifying tumour heterogeneity with CT. Cancer Imaging. 2013;13:140–9. 10.1102/1470-7330.2013.0015 . Takahashi K, Al-Janabi NJ. Computed tomography and magnetic resonance imaging of mediastinal tumors. J Magn Reson Imaging. 2010;32:1325–39. 10.1002/jmri.22377 . Ried M, Marx A, Götz A, Hamer O, Schalke B, Hofmann HS. State of the art: diagnostic tools and innovative therapies for treatment of advanced thymoma and thymic carcinoma. Eur J Cardiothorac Surg. 2016;49:1545–52. 10.1093/ejcts/ezv426 . Ozawa Y, Hara M, Shimohira M, Sakurai K, Nakagawa M, Shibamoto Y. Associations between computed tomography features of thymomas and their pathological classification. Acta Radiol. 2016;57:1318–25. 10.1177/0284185115590288 . Yu C, Li T, Yang X, Zhang R, Xin L, Zhao Z, et al. Contrast-enhanced CT-based radiomics model for differentiating risk subgroups of thymic epithelial tumors. BMC Med Imaging. 2022;22:37. 10.1186/s12880-022-00768-8 . Tian D, Yan HJ, Shiiya H, Sato M, Shinozaki-Ushiku A, Nakajima J. Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: predicting pathological and survival outcomes. J Thorac Cardiovasc Surg (2023) 165:502 – 16.e9. 10.1016/j.jtcvs.2022.05.046 Agha RA, Mathew G, Rashid R, Kerwan A, Al-Jabir A, Sohrabi C, et al. Revised Strengthening the reporting of cohort, cross-sectional and case-control studies in surgery (STROCSS) Guideline: an update for the age of Artificial Intelligence. Premier J Sci. 2025;10:100081. 10.70389/PJS.100081 . Xu J, Jian Z, Yi W, et al. Clinical application value of CT deep learning in identifying histological types of thymoma. J Qiqihar Med Univ. 2024;45:458–64. Wu S, Fan L, Wu Y, Xu J, Guo Y, Zhang H, et al. Deep transfer learning radiomics combined with explainable machine learning for preoperative thymoma risk prediction based on CT. Eur J Radiol. 2025;190:112266. 10.1016/j.ejrad.2025.112266 . Yamazaki M, Oyanagi K, Umezu H, Yagi T, Ishikawa H, Yoshimura N, et al. Quantitative 3D shape analysis of CT images of thymoma: A comparison with histological types. AJR Am J Roentgenol. 2020;214:341–7. 10.2214/AJR.19.21844 . Sadohara J, Fujimoto K, Müller NL, Kato S, Takamori S, Ohkuma K, et al. Thymic epithelial tumors: comparison of CT and MR imaging findings of low-risk thymomas, high-risk thymomas, and thymic carcinomas. Eur J Radiol. 2006;60:70–9. 10.1016/j.ejrad.2006.05.003 . Yakushiji S, Tateishi U, Nagai S, Matsuno Y, Nakagawa K, Asamura H, et al. Computed tomographic findings and prognosis in thymic epithelial tumor patients. J Comput Assist Tomogr. 2008;32:799–805. 10.1097/RCT.0b013e31815896df . Strange CD, Ahuja J, Shroff GS, Truong MT, Marom EM. Imaging evaluation of thymoma and thymic carcinoma. Front Oncol. 2021;11:810419. 10.3389/fonc.2021.810419 . Gao C, Yang L, Xu Y, Wang T, Ding H, Gao X, et al. Differentiating low-risk thymomas from high-risk thymomas: preoperative radiomics nomogram based on contrast enhanced CT to minimize unnecessary invasive thoracotomy. BMC Med Imaging. 2024;24:197. 10.1186/s12880-024-01367-5 . Liang Z, Li J, Tang Y, Zhang Y, Chen C, Li S, et al. Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences. Sci Rep. 2024;14:19215. 10.1038/s41598-024-69735-3 . Liu W, Wang W, Guo R, Zhang H, Guo M. Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images. BMC Cancer. 2024;24:651. 10.1186/s12885-024-12394-4 . Han X, Gao W, Chen Y, Du L, Duan J, Yu H, et al. Relationship between computed tomography imaging features and clinical characteristics, masaoka-koga stages, and World Health Organization histological classifications of thymoma. Front Oncol. 2019;9:1041. 10.3389/fonc.2019.01041 . Xiao G, Hu YC, Ren JL, Qin P, Han JC, Qu XY, et al. MR imaging of thymomas: a combined radiomics nomogram to predict histologic subtypes. Eur Radiol. 2021;31:447–57. 10.1007/s00330-020-07074-3 . Nakajo M, Takeda A, Katsuki A, Jinguji M, Ohmura K, Tani A, et al. The efficacy of 18 F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors. Br J Radiol. 2022;95:20211050. 10.1259/bjr.20211050 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 18 May, 2026 Reviews received at journal 05 May, 2026 Reviewers agreed at journal 26 Apr, 2026 Reviews received at journal 21 Apr, 2026 Reviewers agreed at journal 20 Apr, 2026 Reviewers agreed at journal 20 Apr, 2026 Reviewers invited by journal 20 Apr, 2026 Editor assigned by journal 30 Mar, 2026 Submission checks completed at journal 23 Mar, 2026 First submitted to journal 20 Mar, 2026 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-9180024","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":629759861,"identity":"4f20f553-077e-4aef-b799-5a1b1d140815","order_by":0,"name":"Kai Zhao","email":"","orcid":"","institution":"Hainan Hospital of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Zhao","suffix":""},{"id":629759862,"identity":"42c51507-31cd-4e37-8ac5-64a771176dfd","order_by":1,"name":"Yiming Liu","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yiming","middleName":"","lastName":"Liu","suffix":""},{"id":629759863,"identity":"a49190a8-7f26-4275-bb8a-935717715b76","order_by":2,"name":"Honghao Xu","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Honghao","middleName":"","lastName":"Xu","suffix":""},{"id":629759864,"identity":"98ae0bc4-b19e-4400-84e2-28608408ecd7","order_by":3,"name":"Wenhan Cai","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Wenhan","middleName":"","lastName":"Cai","suffix":""},{"id":629759865,"identity":"8be7041a-f6f3-4e4c-bd08-a2cbf0011602","order_by":4,"name":"Jiamei Jin","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jiamei","middleName":"","lastName":"Jin","suffix":""},{"id":629759866,"identity":"ea19a5ff-3688-4d2e-8836-a16946d1dd91","order_by":5,"name":"Leilei Shen","email":"","orcid":"","institution":"Hainan Hospital of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Leilei","middleName":"","lastName":"Shen","suffix":""},{"id":629759869,"identity":"69aeae5e-ea9a-41cb-8c8d-fafca64eea53","order_by":6,"name":"Zirui Zhu","email":"","orcid":"","institution":"Hainan Hospital of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zirui","middleName":"","lastName":"Zhu","suffix":""},{"id":629759875,"identity":"faa95cba-2417-44d4-996a-5140db877671","order_by":7,"name":"Herui Han","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Herui","middleName":"","lastName":"Han","suffix":""},{"id":629759876,"identity":"f7f5fa73-49d7-4979-9d8c-152d6f90c330","order_by":8,"name":"Mingchuan Hu","email":"","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Mingchuan","middleName":"","lastName":"Hu","suffix":""},{"id":629759877,"identity":"247f6c3b-e188-4521-85b0-d08d7e9dcc94","order_by":9,"name":"Qiang Lu","email":"","orcid":"","institution":"Tangdu Hospital, Air Force Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Lu","suffix":""},{"id":629759878,"identity":"76551202-844a-468a-89d6-eaffe9d41db7","order_by":10,"name":"Zhiqiang Xue","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIie3RsYrCMBjA8ZRAXb6ja4Ll7hU+6ahcfZRAwS4F+wiFDi4+QMX3uLnSweU4HQM6FAo3R1wdTKCrsaNg/ksofL82aQhxuV40SpCAWVuBMwhGxXDio8oXIV/XQ0gfr1QzQzm3j6NMmmueT8NguzpGgAcgknjqkj0mvFqIqMIU2Pk37wBP4G0Lyjc/j0nAMkwAG/3yTESG0LD26YeF+GypGkO+NBkD/oHPhJ3or3ilISjTmldYAzwjfP0fUdBnmchM/2S9SQa70noW3CfdFW7T+FOmXStu33G8L3fqYiF95moA+weveDrfk1E7ZNLlcrnesDvCC00AQ0Uc6wAAAABJRU5ErkJggg==","orcid":"","institution":"The First Medical Center of Chinese PLA General Hospital","correspondingAuthor":true,"prefix":"","firstName":"Zhiqiang","middleName":"","lastName":"Xue","suffix":""}],"badges":[],"createdAt":"2026-03-20 14:53:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9180024/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9180024/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108097546,"identity":"f9f83c2e-4272-4e24-b297-a7398b45b85d","added_by":"auto","created_at":"2026-04-29 10:14:35","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":82644,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the patient selection process.\u003c/p\u003e\n\u003cp\u003eCT, computed tomography\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/ebaedf70224cd44eec818a43.png"},{"id":108181674,"identity":"24fea674-3e03-4cca-a4bd-40ef6cf6f95d","added_by":"auto","created_at":"2026-04-30 08:58:49","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":159748,"visible":true,"origin":"","legend":"\u003cp\u003eImage segmentation. (a) the outlined ROI (b) the combined three-dimensional VOI.\u003c/p\u003e\n\u003cp\u003eROI, region of interest; VOI, volume of interest\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/be468ea5cb2770825df237af.png"},{"id":108181621,"identity":"04682ab2-fbc9-4970-b98d-9351350dc6c0","added_by":"auto","created_at":"2026-04-30 08:58:48","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":126133,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the model construction process.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/349bc60d5f41ed8328318c67.png"},{"id":108097548,"identity":"68b35a95-ef6c-4937-bd57-f536f4f63ccf","added_by":"auto","created_at":"2026-04-29 10:14:35","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":180240,"visible":true,"origin":"","legend":"\u003cp\u003e(a–c) The 10-fold cross-validation process of LASSO regression. (a) Determination of the optimal hyperparameter λ (lambda) for the LASSO model through 10-fold cross-validation. (b) Curve showing the changes in feature coefficients with varying λ values; each colored line represents the variation in the coefficient of a specific feature. (c) Selected optimal features with their corresponding weights.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/5946dbdd623d4a7b2b2e7bff.png"},{"id":108181504,"identity":"bdddd86d-437a-4089-b661-68586bdba639","added_by":"auto","created_at":"2026-04-30 08:58:42","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":136239,"visible":true,"origin":"","legend":"\u003cp\u003eCombined radiomics nomogram for thymoma risk stratification. (a) A radiomics nomogram for thymoma risk stratification was developed in the training cohort, incorporating clinical features (tumor morphology and surrounding tissue invasion) and radiomics features. (b, c) Calibration curve analyses of the clinicoradiological model, radiomics model, and radiomics nomogram in the training and validation cohorts (b: training cohort, n=306; c: validation cohort, n=130). The 45° line represents a perfect match between the actual outcomes (Y-axis) and the probabilities from differential diagnosis, the clinicoradiological model, the radiomics model, and the radiomics nomogram (X-axis).\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/ec90299555f90105e0019e90.png"},{"id":108097551,"identity":"84304412-542b-4f5d-a66b-93a77ffce18b","added_by":"auto","created_at":"2026-04-29 10:14:35","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":130817,"visible":true,"origin":"","legend":"\u003cp\u003eThe AUC values of the clinicoradiological model, radiomics model, and radiomics nomogram in the training cohort and validation cohort (a: training cohort, n=306; b validation cohort, n=130). Decision curve analysis of the clinicoradiological model, radiomics model, and radiomics nomogram (c)\u003c/p\u003e\n\u003cp\u003eAUC, area under the receiver operating characteristic curve\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/dde5e6bc4fe7c0027b48ad7f.png"},{"id":108183745,"identity":"c2fb7bd6-c783-4c1f-8659-3d88974fe833","added_by":"auto","created_at":"2026-04-30 09:02:38","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1267746,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9180024/v1/851098ba-cf81-4378-932b-795dc1c52337.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Preoperative Prediction of Thymoma Risk Classification with Machine Learning-Based Computed Tomography Radiomics Features","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eAmong anterior mediastinal masses, thymomas are the most common primary tumors accounting for 47% of all mediastinal tumors (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). The updated 2021 World Health Organization classification stratifies thymomas into five histological subtypes (types A, AB, B1, B2, and B3) based on the morphology of epithelial cells and the ratio of lymphocytes to epithelial cells (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). Specifically, type B2 and B3 thymomas are more invasive and associated with higher postoperative recurrence rates and lower survival rates than type A, AB, and B1 thymomas. Furthermore, A, AB, and B1 thymomas are completely surgically resected more frequently than B2 and B3 thymomas (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e). Based on these distinct clinical behaviors, thymomas are often classified into two risk groups: low-risk (types A, AB, and B1) and high-risk (types B2 and B3) (\u003cspan additionalcitationids=\"CR6\" citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e). Surgical resection is the primary treatment for thymoma, with complete resection being the goal for optimal survival. However, histological subtype is a key factor in planning therapeutic approaches. Patients with low-risk thymomas typically achieve high rates of complete resection and are often managed with surgery alone without neoadjuvant or adjuvant therapy. By contrast, high-risk thymomas are less amenable to complete resection and often require multimodal treatment (\u003cspan additionalcitationids=\"CR9\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). Consequently, accurate preoperative risk stratification is crucial for guiding surgical planning, informing decisions regarding neoadjuvant or adjuvant therapies, and ultimately improving patient prognosis.\u003c/p\u003e \u003cp\u003eRadiomics has been widely used for the early diagnosis, screening, and prognostic assessment of tumors, facilitating the development of personalized treatment strategies. Currently, radiomics utilizes high-dimensional quantitative features extracted from medical images, such as computed tomography (CT) images, to noninvasively quantify tumor heterogeneity and elucidate the underlying malignant characteristics (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e). Non-contrast chest CT is the primary imaging modality for thymoma assessment due to its widespread availability, high spatial resolution, and ability to provide information on tumor vascularity (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e). However, chest CT images of patients with thymomas require evaluation by radiologists, leading to uncertainties that may affect the accurate classification of thymomas. For instance, the semantic features of thymomas presenting as localized lesions, especially those with no obvious invasion of the surrounding structures on CT images, may overlap with those of different histological subtypes. This overlap is unfavorable for preoperative thymoma risk classification (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e). Additionally, owing to the rarity of thymomas, clinicians (including thoracic surgeons and radiologists) in some centers may have limited experience in evaluating thymomas. This highlights the need for a quantitative method to classify thymomas with high accuracy and objectivity, and to reduce reliance on radiologists' experience.\u003c/p\u003e \u003cp\u003ePrevious studies suggest that CT-based radiomics can aid in thymoma risk stratification; however, the clinical translation of this technology has been limited, primarily due to small sample sizes (often fewer than 200 patients), which have constrained the robustness and generalizability of the findings (\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e). Therefore, our study used a large cohort to develop a radiomics model based on non-contrast CT images using machine learning, which integrated radiomics features with clinical and radiological characteristics. This approach is expected to enhance the accuracy and clinical applicability of preoperative risk prediction for thymomas.\u003c/p\u003e"},{"header":"2. Materials and methods","content":"\u003cp\u003e2.1 Patient recruitment\u003c/p\u003e\n\u003cp\u003eThis retrospective study was approved by the Institutional Review Board of our hospital, and the requirement for informed consent was waived. This cohort study has been reported in line with the STROCSS 2024 guidelines (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e). The study cohort comprised patients with pathologically confirmed thymomas who underwent surgical resection at our institution between January 2010 and October 2023. The inclusion criteria were as follows: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) pathologically confirmed thymoma following surgical resection; (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) no prior anticancer treatment before surgery; (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) availability of a non-contrast chest CT scan performed within two weeks prior to surgery; and (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e) complete clinical records. The exclusion criteria were as follows: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) small tumor size (maximum diameter\u0026thinsp;\u0026le;\u0026thinsp;9 mm); (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) poor image quality due to significant artifacts; (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) a history of other malignancies; and (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e) incomplete clinical or imaging data. In total, 436 patients with thymomas were enrolled (Fig. \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The cohort comprised 223 men and 213 women, aged 25\u0026ndash;80 years with a mean age of 55.85\u0026thinsp;\u0026plusmn;\u0026thinsp;10.99 years. Based on the postoperative pathology, the patients were categorized into a low-risk group (n\u0026thinsp;=\u0026thinsp;272), consisting of type A (n\u0026thinsp;=\u0026thinsp;32), AB (n\u0026thinsp;=\u0026thinsp;155), and B1 (n\u0026thinsp;=\u0026thinsp;85) thymomas, and a high-risk group (n\u0026thinsp;=\u0026thinsp;164), consisting of type B2 (n\u0026thinsp;=\u0026thinsp;115) and B3 (n\u0026thinsp;=\u0026thinsp;49) thymomas.\u003c/p\u003e\n\u003cp\u003e2.2 Histopathological classification\u003c/p\u003e\n\u003cp\u003eAccording to the 2021 World Health Organization classification, thymomas are categorized into five histological subtypes (A, AB, B1, B2, and B3) based on the morphology of epithelial cells and the lymphocyte to epithelial cell ratio. Type A thymoma is characterized by a population of spindle-shaped epithelial cells with minimal atypia and a notable absence of immature T-lymphocytes. Atypical type A thymoma meets the criteria for type A thymoma but also exhibits focal necrosis, mitotic activity (\u0026gt;\u0026thinsp;4 mitoses per 2 mm\u0026sup2;), and nuclear crowding. Type AB thymoma demonstrates the morphological features of type A thymoma, but also contains abundant immature T cells, either locally or diffusely distributed. Type B1 thymomas most closely resemble the normal thymic architecture, featuring large areas of immature T cells, medullary differentiation (medullary islands), and scant aggregates of polygonal or dendritic epithelial cells (fewer than three adjacent cells). Type B2 thymomas show an increased proportion of polygonal or dendritic epithelial cells, appearing alone or in clusters, against a background of numerous immature T cells. Type B3 thymomas are composed of sheets of epithelial cells exhibiting mild to moderate atypia, with absent or inconspicuous intercellular bridges and a paucity of mature T lymphocytes.\u003c/p\u003e\n\u003cp\u003e2.3 CT examination and image analysis\u003c/p\u003e\n\u003cp\u003eAll patients underwent non-contrast CT using either a Philips (Amsterdam, the Netherlands) Brilliance iCT scanner or a Siemens (Erlangen, Germany) Somatom Definition scanner. The standard scanning range was extended from the lung apex to the costophrenic angle. In patients with ectopic neck thymomas, the range was adjusted to cover the upper edge of the aortic arch from the inferior border of the hyoid bone. The scanning parameters were as follows: tube voltage of 120 kV, automatic tube current modulation, matrix of 512\u0026times;512, rotation time of 0.6 s, slice thickness of 5 mm for acquisition, and 1.25 mm for reconstruction. Images were reviewed using a mediastinal window setting (window width, 350 HU; level, 50 HU).\u003c/p\u003e\n\u003cp\u003eTwo radiologists, each with over 10 years of experience, independently assessed all images. Any discrepancies were resolved by a consensus discussion between the two radiologists. The following CT features were evaluated: tumor size (defined as the maximum axial diameter); location (left-sided, central, or right-sided); morphology (regular or irregular); margin (well-defined or ill-defined); and presence or absence of calcification, necrosis/cystic degeneration, invasion of adjacent structures, and distant metastasis.\u003c/p\u003e\n\u003cp\u003e2.4 Image segmentation and feature extraction\u003c/p\u003e\n\u003cp\u003eThe patients were randomly allocated to the training (n\u0026thinsp;=\u0026thinsp;306) or validation sets (n\u0026thinsp;=\u0026thinsp;130) in a 7:3 ratio. Original CT images in a DICOM format were retrieved from the Picture Archiving and Communication System. A two-dimensional image slice showing the largest tumor diameter was selected from each scan. All images were then resampled to a uniform voxel spacing of 1\u0026times;1\u0026times;1 mm\u0026sup3; to standardize the spatial resolution. Manual delineation of the volume of interest (VOI) was performed using the open-source software ITK-SNAP (version 3.6.0; Fig. \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The initial contouring was performed by an experienced radiologist. A second radiologist independently reviewed all segmentations to ensure reliability. Any discrepancies were resolved through a consensus discussion between the two readers to finalize the VOIs, thereby enhancing the accuracy and reproducibility of subsequent feature extraction. During manual segmentation, caution was exercised to encompass the entire tumor volume while meticulously avoiding lesion boundaries, adjacent vascular structures, and internal cystic or necrotic areas.\u003c/p\u003e\n\u003cp\u003eSubsequently, 1032 traditional radiomics features were extracted from each VOI using the PyRadiomics platform (version 3.1.0). The extracted feature set encompassed first-order statistics, shape-based features, texture features (derived from the gray-level co-occurrence matrix, gray-level run-length matrix, and gray-level size zone matrix), and higher-order features obtained through wavelet and Laplacian Gaussian filter transforms. The intraclass correlation coefficient was calculated for all features based on the segmentation to ensure feature stability and reproducibility. Only the features demonstrating excellent consistency (intraclass correlation coefficient\u0026thinsp;\u0026gt;\u0026thinsp;0.75) were retained for subsequent analyses.\u003c/p\u003e\n\u003cp\u003e2.5 Radiomics feature selection\u003c/p\u003e\n\u003cp\u003eThe 1,032 radiomics features extracted from each VOI underwent feature selection. Briefly, Z-score normalization was applied to all features to eliminate scale differences. Class imbalance in the training set was addressed using the synthetic minority oversampling technique to generate synthetic samples and balance class distribution. Subsequently, feature dimensionality reduction was conducted using least absolute shrinkage and selection operator regression with a 10-fold cross-validation to determine the optimal penalty parameter (\u0026lambda;). The L1 regularization inherent in the least absolute shrinkage and selection operator shrinks the coefficients of irrelevant features to zero, resulting in the selection of a subset of features that are most predictive of the outcome.\u003c/p\u003e\n\u003cp\u003e2.6 Model construction and diagnostic efficacy evaluation\u003c/p\u003e\n\u003cp\u003eThree distinct models were developed to differentiate between low- and high-risk thymomas. A clinicoradiological model was constructed using independent predictors identified using univariate and multivariate logistic regression analyses. Concurrently, a radiomics model was built and a radiomics score (Rad-score) was calculated for each patient. Finally, a combined nomogram integrating significant clinicoradiological factors and Rad-scores was established. The diagnostic performance of each model was evaluated and compared using the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Calibration of the combined nomogram was assessed using a calibration plot, and its clinical net benefit was quantified using decision curve analysis (Fig. \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\n\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\n \u003ch2\u003e2.7 Statistical analysis\u003c/h2\u003e\n \u003cp\u003eAll statistical analyses were performed using the SPSS software (version 26.0). The normality of continuous variables was assessed using the Shapiro\u0026ndash;Wilk test. Data conforming to a normal distribution were compared using the independent samples t-test, whereas non-normally distributed data were compared using the Mann\u0026ndash;Whitney U test. Categorical variables were compared using the chi-squared test or Fisher\u0026apos;s exact test, as appropriate. The independent predictors were identified using univariate and multivariate logistic regression analyses. Spearman\u0026rsquo;s correlation analysis, least absolute shrinkage, and selection operator regression were employed for dimensionality reduction for radiomics feature selection. Predictive models were constructed using machine-learning algorithms. Model performance was evaluated using the AUC, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The DeLong test was used to compare the AUCs of different models. Calibration curves and decision curve analysis were used to assess the calibration and clinical utility of the models, respectively. Statistical significance was set at a two-sided P\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"3. Results","content":"\u003cp\u003e3.1 Clinical and radiological features\u003c/p\u003e\n\u003cp\u003eThis study enrolled 436 patients with thymomas, who were randomly allocated to a training cohort (n\u0026thinsp;=\u0026thinsp;306) or a validation cohort (n\u0026thinsp;=\u0026thinsp;130) in a 7:3 ratio. Baseline characteristics, including age and sex, were well balanced between the two cohorts (all P\u0026thinsp;\u0026gt;\u0026thinsp;0.05, Table \u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The cohort comprised 272 low-risk thymomas (types A, AB, and B1) and 164 high-risk thymomas (types B2 and B3). The distributions of these risk categories were consistent between the training (low-risk, n\u0026thinsp;=\u0026thinsp;189; high-risk, n\u0026thinsp;=\u0026thinsp;117) and validation (low-risk, n\u0026thinsp;=\u0026thinsp;83; high-risk, n\u0026thinsp;=\u0026thinsp;47) cohorts. Comparative analysis revealed that tumor morphology, margin definition, and invasion of the surrounding tissues were significantly different between the low- and high-risk groups (all P\u0026thinsp;\u0026lt;\u0026thinsp;0.05; Table \u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u0026nbsp;\u003c/p\u003e\n\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of clinical and imaging features of thymomas between the training and validation cohorts\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eBaseline Characteristics\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eTraining cohort (n\u0026thinsp;=\u0026thinsp;306)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eValidation cohort (n\u0026thinsp;=\u0026thinsp;130)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eSex (case)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.836\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e158\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e148\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eAge (years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.332\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026le;\u0026thinsp;50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e149\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026gt;\u0026thinsp;50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e157\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDiameter (cm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.174\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026le;\u0026thinsp;5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e139\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026gt;\u0026thinsp;5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e167\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eLocation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.073\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eLeft\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e118\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMiddle\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e129\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMorphology\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.745\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRegular\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e181\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eIrregular\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e125\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMargin\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.594\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eClear\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e183\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eUnclear\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e123\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eCalcification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.119\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e47\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e259\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e118\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNecrosis and cystic degeneration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.689\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e250\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eInvasion of surrounding tissues\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.536\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e141\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e165\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDistant metastasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\n \u003cp\u003e0.768\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\n \u003cp\u003e273\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\n \u003cp\u003e114\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of clinical and imaging features between low-risk and high-risk thymomas\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\n \u003cp\u003eBaseline characteristics\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e\n \u003cp\u003eTraining cohort\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"9\" nameend=\"c13\" namest=\"c5\"\u003e\n \u003cp\u003eValidation cohort\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eLow-risk group\u003c/p\u003e\n \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;189)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eHigh-risk group\u003c/p\u003e\n \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;117)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"3\" nameend=\"c6\" namest=\"c4\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eLow-risk group (n\u0026thinsp;=\u0026thinsp;83)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c10\" namest=\"c9\"\u003e\n \u003cp\u003eHigh-risk group (n\u0026thinsp;=\u0026thinsp;47)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c12\" namest=\"c11\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"1\" nameend=\"c13\" namest=\"c13\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eSex (case)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.467\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.273\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eAge (years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.124\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.230\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026le;\u0026thinsp;50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026gt;\u0026thinsp;50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e104\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDiameter (cm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.947\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.767\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026le;\u0026thinsp;5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003e\u0026gt;\u0026thinsp;5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e103\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eLocation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.176\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.328\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eLeft\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMiddle\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMorphology\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.644\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRegular\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e130\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eIrregular\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMargin\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.003\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.417\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eClear\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e126\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eUnclear\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eCalcification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.863\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.597\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e161\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNecrosis and cystic\u003c/p\u003e\n \u003cp\u003edegeneration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.781\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.125\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e153\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eInvasion of surrounding tissues\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDistant metastasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\n \u003cp\u003e0.998\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\n \u003cp\u003e0.691\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e169\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e104\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\n \u003cp\u003e74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\n \u003cp\u003e20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c13\" namest=\"c12\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e3.2 Clinical feature selection and model construction\u003c/p\u003e\n\u003cp\u003eUnivariate and multivariate logistic regression analyses of clinical and radiological features identified tumor morphology and invasion of surrounding tissues as independent predictors of thymoma risk (all P\u0026thinsp;\u0026lt;\u0026thinsp;0.05; Table \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The clinicoradiological model, constructed using these independent factors, demonstrated an AUC of 0.668 (95% confidence interval [CI]: 0.613\u0026ndash;0.721), accuracy of 68.3%, sensitivity of 46.2%, and specificity of 82.0% in the training cohort, and an AUC of 0.646 (95% CI: 0.557\u0026ndash;0.728), accuracy of 63.8%, sensitivity of 38.3%, and specificity of 78.3% in the validation cohort (Table \u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u0026nbsp;\u003c/p\u003e\n\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eUnivariate and Multivariate Analyses used to identify independent predictors of thymoma risk\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"4\" nameend=\"c5\" namest=\"c2\"\u003e\n \u003cp\u003eUnivariate analysis\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"4\" nameend=\"c11\" namest=\"c8\"\u003e\n \u003cp\u003eMultivariate analysis\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e95%CI\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eOR\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003e95%\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eSex\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.995\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.675\u0026ndash;1.467\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.981\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eAge\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.652\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.442\u0026ndash;0.963\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.650\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDiameter\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e1.009\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.685\u0026ndash;1.488\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.962\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eLocation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e1.079\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.835\u0026ndash;1.394\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.561\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMorphology\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e2.229\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e1.500\u0026ndash;3.312\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003e2.042\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003e1.198\u0026ndash;3.480\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003e0.009\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eMargin\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e1.894\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e1.274\u0026ndash;2.816\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003e0.565\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003e0.300\u0026ndash;1.062\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003e0.076\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eCalcification\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e1.016\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.576\u0026ndash;1.792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.956\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNecrosis and cystic degeneration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e1.412\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.834\u0026ndash;2.391\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.200\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eInvasion of surrounding tissues\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e3.115\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e2.083\u0026ndash;4.659\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003e3.366\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003e2.014\u0026ndash;5.626\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eDistant metastasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.859\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.469\u0026ndash;1.575\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.624\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c9\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c10\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colspan=\"1\" nameend=\"c11\" namest=\"c11\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"11\"\u003eOR, odds ratio; CI, confidence interval; NA, not applicable\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003ePredictive performance of the training and validation cohorts for different models\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eModels\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eAUC\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e95%CI\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003eAccuracy\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003eSensitivity\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003eSpecificity\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003ePPV\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003eNPV\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eTraining cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eClinicoradiological model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.668\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.613\u0026ndash;0.721\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.683\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.462\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.820\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.614\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.711\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRadiomics model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.751\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.698\u0026ndash;0.798\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.725\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.735\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.720\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.619\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.814\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNomogram model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.753\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.700\u0026ndash;0.800\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.712\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.624\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.767\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.624\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.767\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eValidation cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eClinicoradiological model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.646\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.557\u0026ndash;0.728\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.638\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.383\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.783\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.500\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.691\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eRadiomics model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.725\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.640\u0026ndash;0.800\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.677\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.766\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.627\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.537\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.825\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eNomogram model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003e0.735\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003e0.651\u0026ndash;0.809\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.708\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c5\"\u003e\n \u003cp\u003e0.588\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c6\"\u003e\n \u003cp\u003e0.785\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c7\"\u003e\n \u003cp\u003e0.638\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c8\"\u003e\n \u003cp\u003e0.747\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"8\"\u003eAUC, area under the receiver operating characteristic curve; CI, confidence interval; PPV, positive predictive value; NPV, negative predictive value\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e3.4 Construction of radiomics prediction model\u003c/p\u003e\n\u003cp\u003eA total of 1032 radiomics features were extracted from each VOI, capturing comprehensive information on the geometry, intensity, and textural heterogeneity of the tumors. Dimensionality reduction was performed using PCA, least absolute shrinkage, and selection operator regression to mitigate the risk of overfitting from high-dimensional data. This process identified 11 key predictive features (Fig. \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e) that were used to construct the radiomics model. In the training cohort, the model achieved an AUC of 0.751 (95% CI: 0.698\u0026ndash;0.798), accuracy of 75.2%, sensitivity of 73.5%, and specificity of 72.0%. In the validation cohort, the AUC was 0.725 (95% CI: 0.640\u0026ndash;0.800), with accuracy of 67.7%, sensitivity of 76.6%, and specificity of 62.7% (Table \u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\n\u003cp\u003e3.4 Model efficacy evaluation\u003c/p\u003e\n\u003cp\u003eA combined radiomics nomogram was developed using logistic regression analysis to preoperatively predict thymoma risk by integrating significant clinical features (tumor morphology and invasion of surrounding tissues) with the radiomics signature (Fig. \u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e). In the training cohort, the nomogram achieved an AUC of 0.753 (95% CI, 0.700\u0026ndash;0.800), with accuracy of 71.2%, sensitivity of 62.4%, and specificity of 76.7%. When evaluated in the independent validation cohort, it yielded an AUC of 0.735 (95% CI: 0.651\u0026ndash;0.809), with accuracy of 70.8%, sensitivity of 58.8%, and specificity of 78.5% (Table \u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). Notably, the combined radiomics nomogram demonstrated higher AUC values than the clinicoradiological and standalone radiomics models in the training and validation cohorts. The DeLong test revealed that in the training cohort, the nomogram performed significantly better than the clinicoradiological model (P\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and the standalone radiomics model (P\u0026thinsp;=\u0026thinsp;0.012). Although the AUC of the nomogram was higher than that of the standalone radiomic model, the difference was not statistically significant (P\u0026thinsp;=\u0026thinsp;0.863). In the validation cohort, the superior performance of the nomogram compared to the clinicoradiological model remained significant (P\u0026thinsp;=\u0026thinsp;0.016). However, the differences between the nomogram and standalone radiomics model and between the standalone radiomics model and clinicoradiological model were not statistically significant (both P\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Collectively, these results indicate that the combined nomogram offers a more robust predictive advantage for thymoma risk stratification compared to other models (Table \u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, Fig. \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e).\u0026nbsp;\u003c/p\u003e\n\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eComparison of prediction with the combined radiomics nomogram, clinicoradiological model, and radiomics models\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eGroup\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eModel 1\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eModel 2\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003eP-value\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eTraining cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eNomogram\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eRadiomics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.863\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eNomogram\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eClinicoradiological\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eRadiomics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eClinicoradiological\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.012\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\n \u003cp\u003eValidation cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eNomogram\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eRadiomics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.509\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eNomogram\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eClinicoradiological\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.016\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c2\"\u003e\n \u003cp\u003eRadiomics\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c3\"\u003e\n \u003cp\u003eClinicoradiological\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\" colname=\"c4\"\u003e\n \u003cp\u003e0.109\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cp\u003eThe reliability and clinical value of the prediction models were assessed. The calibration curve indicated excellent agreement between the predicted probabilities of the combined radiomics nomogram and the actual observed outcomes in the training and validation cohorts, which was confirmed by the non-significant Hosmer\u0026ndash;Lemeshow test results (all P\u0026thinsp;\u0026gt;\u0026thinsp;0.05) (Fig. \u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e). Decision curve analysis further demonstrated that the application of this combined nomogram provided a higher net benefit across a wide range of threshold probabilities than the clinicoradiological and standalone radiomics models (Fig. \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e). These findings collectively confirm the favorable calibration and clinical utility of the combined radiomics nomogram for thymoma risk stratification.\u003c/p\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eRadiomics enables the quantitative analysis of medical images and captures disease-specific features that may not be discernible through conventional visual assessment. The increasing application of radiomics in oncology has demonstrated a promising potential for augmenting traditional imaging analysis and supporting personalized treatment strategies. In this study, we developed a radiomics model based on non-contrast CT images to predict the histological risk of thymomas preoperatively. The standalone radiomics model showed superior predictive performance compared with the model based solely on clinicoradiological features. Furthermore, the combined nomogram that integrated radiomics and clinicoradiological factors demonstrated the best overall performance in differentiating high-risk thymomas from low-risk ones, with an efficacy comparable to that of the standalone radiomics model, while incorporating clinically relevant variables. The proposed nomogram shows potential as a practical tool to aid clinical decision-making for the individualized management of patients with thymoma.\u003c/p\u003e\n\u003cp\u003eThe results of this study indicate that high-risk thymomas predominantly exhibit an irregular shape, unclear boundaries, and invasion of surrounding tissues, whereas low-risk thymomas are more frequently round or oval, with clear boundaries and no invasion. These findings were consistent with those of previous reports (\u003cspan additionalcitationids=\"CR19\" citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e). The irregular morphology commonly observed in high-risk tumors may be attributed to their higher malignant potential, greater cellular atypia, and heterogeneous growth patterns, leading to asymmetrical expansion. Thus, tumor shape serves as a key radiological indicator for risk stratification. Although the univariate analysis indicated an association between blurred margins and high-risk thymoma, this feature was not retained as an independent predictor in the multivariate model. This suggests that, while margin characteristics possess some discriminatory value, their predictive power may be subordinate to other stronger indicators, such as invasion or shape, when evaluated collectively. Consequently, the diagnostic utility of tumor margins might be better elucidated through future studies with larger cohorts or by analyzing enhanced CT images that provide superior soft tissue contrast. Consistent with the existing literature (\u003cspan additionalcitationids=\"CR22\" citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e), our study confirmed that invasion into adjacent structures is a hallmark of high-risk thymomas, with a significantly higher incidence than that of low-risk tumors. This reinforces the value of peritumoral invasion as a critical imaging marker for evaluating the biological aggressiveness of thymomas.\u003c/p\u003e\n\u003cp\u003eCT is an established first-line imaging modality for the evaluation of anterior mediastinal masses. Consequently, multiple studies have investigated CT-based strategies for distinguishing between low-and high-risk thymomas (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e). Liang et al. (\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e) found that radiomics based on enhanced CT could be used to identify the histological subtypes of thymomas. The AUC of the radiomics nomogram and radiomics model for distinguishing between low-and high-risk thymomas was higher than that of the clinical model. Thus, the enhanced CT-based radiomics model and radiomics nomogram, integrating clinical factors, CT features, and radiomics features, are useful for identifying thymoma histological subtypes. Liu et al. (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e) evaluated 30 patients with high-risk thymomas and 117 patients with low-risk thymomas to identify the key CT features for risk stratification. The results confirmed that high-risk thymomas had more irregular shapes and contours and a higher incidence of invasion into surrounding tissues and organs on CT images compared to low-risk thymomas. Han et al. (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e) constructed and validated an imaging model combining clinical factors and non-contrast CT features to distinguish between high-risk and low-risk thymomas. They found that CT imaging features showed no significant differences between patients of different sexes or ages; however, multiple statistically significant differences in the imaging features were observed between the high- and low-risk groups. Sadohara et al. (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e) proposed that combining the features of CT and magnetic resonance imaging (such as tumor contour, capsule, septation, and enhancement uniformity) is helpful in distinguishing low-and high-risk thymomas. Furthermore, Xiao et al. (\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e) showed the good performance of a combined radiomics nomogram that integrated magnetic resonance imaging with tumor shape, ADC coefficient, and radiomics features. Nakajo et al. (\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e) reported the good predictive efficacy of machine-learning methods based on deep-learning features from 18F-FDG-PET radiomics.\u003c/p\u003e\n\u003cp\u003eThe experimental results of this study demonstrate that radiomics based on non-contrast CT exhibits favorable predictive efficacy for distinguishing between low- and high-risk thymomas. In the training cohort, the combined radiomics and standalone radiomics models achieved significantly higher AUC values than the clinicoradiological model (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05). In the validation cohort, the superiority of the combined radiomics model over the clinicoradiological model remained significant (P\u0026thinsp;=\u0026thinsp;0.016). Although the combined model also yielded a higher AUC than the standalone radiomics model (which outperformed the clinicoradiological model), the differences were not statistically significant (P\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Given that traditional radiological parameters (e.g., tumor capsule integrity and degree of necrosis) remained clinically valuable and considering that the combined model demonstrated a superior performance compared to the individual models, we propose the integrated radiomics nomogram as the final predictive tool for clinical translation.\u003c/p\u003e\n\u003cp\u003eNonetheless, this study has some limitations. First, the single-center retrospective study design may have introduced selection bias and limited the generalizability of our findings, as patient demographics and clinical practices can vary across institutions. Second, the exclusive use of non-contrast CT images lacks the functional information available from contrast-enhanced CT, magnetic resonance imaging (particularly diffusion-weighted imaging sequences), or positron emission tomography-CT, despite providing anatomical details. The incorporation of multiparametric data in future studies may yield more discriminative features. Third, the absence of genomic data represents a significant limitation as it could offer crucial insights into the underlying biology of thymomas. Consequently, multicenter prospective studies are required in the future to validate and refine the model as our results demonstrate that integrating radiological, clinical, and genomic data is essential for developing a more comprehensive understanding of thymomas and for building robust predictive models to guide personalized treatment.\u003c/p\u003e\n\u003cp\u003eIn conclusion, this study developed and validated a non-contrast CT-based radiomics model as a noninvasive, reliable, and reproducible tool for predicting the histological subtypes of thymoma. The radiomics model demonstrated a superior predictive performance compared with the traditional clinicoradiological model. These results suggest that the proposed approach can assist clinicians in formulating personalized treatment strategies for patients with early stage thymoma, thereby optimizing therapeutic efficacy and improving clinical outcomes, and showing promise for broader clinical applications.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eComputed tomography (CT)\u003c/p\u003e\n\u003cp\u003eVolume of interest (VOI)\u003c/p\u003e\n\u003cp\u003eArea under the receiver operating characteristic curve (AUC)\u003c/p\u003e\n\u003cp\u003eConfidence interval (CI)\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eConflict of Interest\u003c/h2\u003e\n\u003cp\u003eThe authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.\u003c/p\u003e\n\u003ch2\u003eAuthor Contributions\u003c/h2\u003e\n\u003cp\u003eK.Z. participated in research design, data collection, data analysis, and writing of the paper. Y.L. participated in research design and data analysis. H.X. participated in research design and data analysis. W.C. participated in research design and data analysis. J.J., L.S., Z.Z., and H.H. participated in research design and proofreading of the article. M.H. participated in research design. Q.L. participated in research design and data analysis. Z.X. participated in research design, data analysis, contribution of new analytic tools, writing, and study supervision.\u003c/p\u003e\n\u003ch2\u003eFunding\u003c/h2\u003e\n\u003cp\u003eThis study was supported by the Research and Development Project on Medical Big Data and Artificial Intelligence of the PLA General Hospital (2019MBD-017) and Shaanxi Province Key Core Technology Tackling Project (2024SF-GJHX-27). These funding agencies were not involved in study design, analysis, or reporting.\u003c/p\u003e\n\u003ch2\u003eAcknowledgments\u003c/h2\u003e\n\u003cp\u003eN\\A\u003c/p\u003e\n\u003ch2\u003eData Availability Statement\u003c/h2\u003e\n\u003cp\u003eThe data supporting the findings of this study were retrieved from the clinical database of PLA General Hospital, a secure institutional database housing de-identified clinical records of patients treated at the hospital.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis retrospective study was conducted in accordance with the ethical standards of the Declaration of Helsinki and its later amendments. Ethical approval was obtained from the Institutional Review Board (IRB) of Hainan Hospital of Chinese PLA General Hospital (IRB approval number: S2025-11-01).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHuman Ethics and Consent to Participate declarations: The requirement for written informed consent was waived by the IRB due to the retrospective nature of the study. All patient data were anonymized and de-identified prior to analysis, and no interventions were performed that would affect clinical care or patient outcomes.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eScorsetti M, Leo F, Trama A, D\u0026rsquo;Angelillo R, Serpico D, Macerelli M et al. Thymoma and thymic carcinomas. Crit Rev Oncol Hematol (2016) 99:332\u0026thinsp;\u0026ndash;\u0026thinsp;50. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.critrevonc.2016.01.012\u003c/span\u003e\u003cspan address=\"10.1016/j.critrevonc.2016.01.012\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMarx A, Chan JKC, Chalabreysse L, Dacic S, Detterbeck F, French CA, et al. The 2021 WHO classification of tumors of the Thymus and mediastinum: what is new in thymic epithelial, germ cell, and mesenchymal tumors? J Thorac Oncol. 2022;17:200\u0026ndash;13. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jtho.2021.10.010\u003c/span\u003e\u003cspan address=\"10.1016/j.jtho.2021.10.010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKo\u0026ccedil;er B, Kaplan T, G\u0026uuml;nal N, Ko\u0026ccedil;er BG, Akkaş Y, Yazkan R, et al. Long-term survival after R0 resection of thymoma. Asian Cardiovasc Thorac Ann. 2018;26:461\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0218492318778634\u003c/span\u003e\u003cspan address=\"10.1177/0218492318778634\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee GD, Kim HR, Choi SH, Kim YH, Kim DK, Park SI. Prognostic stratification of thymic epithelial tumors based on both Masaoka-Koga stage and WHO classification systems. J Thorac Dis (2016) 8:901\u0026thinsp;\u0026ndash;\u0026thinsp;10. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21037/jtd.2016.03.53\u003c/span\u003e\u003cspan address=\"10.21037/jtd.2016.03.53\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoden AC, Yi ES, Jenkins SM, Edwards KK, Donovan JL, Lewis JE, et al. Reproducibility of 3 histologic classifications and 3 staging systems for thymic epithelial neoplasms and its effect on prognosis. Am J Surg Pathol. 2015;39:427\u0026ndash;41. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/PAS.0000000000000391\u003c/span\u003e\u003cspan address=\"10.1097/PAS.0000000000000391\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMultidisciplinary Committee of Oncology, Chinese Physicians Association. [Chinese guideline for clinical diagnosis and treatment of thymic epithelial tumors (2021 Edition)]. Zhonghua Zhong Liu Za Zhi. 2021;43:395\u0026ndash;404. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3760/cma.j.cn112152-20210313-00226\u003c/span\u003e\u003cspan address=\"10.3760/cma.j.cn112152-20210313-00226\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOsserman KE, Genkins G. Studies in myasthenia gravis: review of a twenty-year experience in over 1200 patients. Mt Sinai J Med. 1971;38:497\u0026ndash;537.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang X, Sun W, Liang H, Mao X, Lu Z. Radiomics signatures of computed tomography imaging for predicting risk categorization and clinical stage of thymomas. BioMed Res Int. 2019;2019:3616852. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1155/2019/3616852\u003c/span\u003e\u003cspan address=\"10.1155/2019/3616852\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDong W, Xiong S, Lei P, Wang X, Liu H, Liu Y, et al. Application of a combined radiomics nomogram based on CE-CT in the preoperative prediction of thymomas risk categorization. Front Oncol. 2022;12:944005. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fonc.2022.944005\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2022.944005\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSacks D, Baxter B, Campbell BCV, Carpenter JS, Cognard C, Dippel D, et al. Multisociety consensus quality improvement revised consensus statement for endovascular therapy of acute ischemic stroke: From the American Association of Neurological Surgeons (AANS), American Society of Neuroradiology (ASNR), Cardiovascular and Interventional Radiology Society of Europe (CIRSE), Canadian Interventional Radiology Association (CIRA), Congress of Neurological Surgeons (CNS), European Society of Minimally Invasive Neurological Therapy (ESMINT), European Society of Neuroradiology (ESNR), European Stroke Organization (ESO), Society for Cardiovascular Angiography and Interventions (SCAI), Society of Interventional Radiology (SIR), Society of NeuroInterventional Surgery (SNIS), and World Stroke Organization (WSO). J Vasc Interv Radiol. 2018;29:441\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jvir.2017.11.026\u003c/span\u003e\u003cspan address=\"10.1016/j.jvir.2017.11.026\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaneshan B, Miles KA. Quantifying tumour heterogeneity with CT. Cancer Imaging. 2013;13:140\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1102/1470-7330.2013.0015\u003c/span\u003e\u003cspan address=\"10.1102/1470-7330.2013.0015\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTakahashi K, Al-Janabi NJ. Computed tomography and magnetic resonance imaging of mediastinal tumors. J Magn Reson Imaging. 2010;32:1325\u0026ndash;39. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/jmri.22377\u003c/span\u003e\u003cspan address=\"10.1002/jmri.22377\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRied M, Marx A, G\u0026ouml;tz A, Hamer O, Schalke B, Hofmann HS. State of the art: diagnostic tools and innovative therapies for treatment of advanced thymoma and thymic carcinoma. Eur J Cardiothorac Surg. 2016;49:1545\u0026ndash;52. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/ejcts/ezv426\u003c/span\u003e\u003cspan address=\"10.1093/ejcts/ezv426\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOzawa Y, Hara M, Shimohira M, Sakurai K, Nakagawa M, Shibamoto Y. Associations between computed tomography features of thymomas and their pathological classification. Acta Radiol. 2016;57:1318\u0026ndash;25. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0284185115590288\u003c/span\u003e\u003cspan address=\"10.1177/0284185115590288\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu C, Li T, Yang X, Zhang R, Xin L, Zhao Z, et al. Contrast-enhanced CT-based radiomics model for differentiating risk subgroups of thymic epithelial tumors. BMC Med Imaging. 2022;22:37. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12880-022-00768-8\u003c/span\u003e\u003cspan address=\"10.1186/s12880-022-00768-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTian D, Yan HJ, Shiiya H, Sato M, Shinozaki-Ushiku A, Nakajima J. Machine learning-based radiomic computed tomography phenotyping of thymic epithelial tumors: predicting pathological and survival outcomes. J Thorac Cardiovasc Surg (2023) 165:502\u0026thinsp;\u0026ndash;\u0026thinsp;16.e9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jtcvs.2022.05.046\u003c/span\u003e\u003cspan address=\"10.1016/j.jtcvs.2022.05.046\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAgha RA, Mathew G, Rashid R, Kerwan A, Al-Jabir A, Sohrabi C, et al. Revised Strengthening the reporting of cohort, cross-sectional and case-control studies in surgery (STROCSS) Guideline: an update for the age of Artificial Intelligence. Premier J Sci. 2025;10:100081. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.70389/PJS.100081\u003c/span\u003e\u003cspan address=\"10.70389/PJS.100081\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXu J, Jian Z, Yi W, et al. Clinical application value of CT deep learning in identifying histological types of thymoma. J Qiqihar Med Univ. 2024;45:458\u0026ndash;64.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu S, Fan L, Wu Y, Xu J, Guo Y, Zhang H, et al. Deep transfer learning radiomics combined with explainable machine learning for preoperative thymoma risk prediction based on CT. Eur J Radiol. 2025;190:112266. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.ejrad.2025.112266\u003c/span\u003e\u003cspan address=\"10.1016/j.ejrad.2025.112266\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYamazaki M, Oyanagi K, Umezu H, Yagi T, Ishikawa H, Yoshimura N, et al. Quantitative 3D shape analysis of CT images of thymoma: A comparison with histological types. AJR Am J Roentgenol. 2020;214:341\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2214/AJR.19.21844\u003c/span\u003e\u003cspan address=\"10.2214/AJR.19.21844\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSadohara J, Fujimoto K, M\u0026uuml;ller NL, Kato S, Takamori S, Ohkuma K, et al. Thymic epithelial tumors: comparison of CT and MR imaging findings of low-risk thymomas, high-risk thymomas, and thymic carcinomas. Eur J Radiol. 2006;60:70\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.ejrad.2006.05.003\u003c/span\u003e\u003cspan address=\"10.1016/j.ejrad.2006.05.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYakushiji S, Tateishi U, Nagai S, Matsuno Y, Nakagawa K, Asamura H, et al. Computed tomographic findings and prognosis in thymic epithelial tumor patients. J Comput Assist Tomogr. 2008;32:799\u0026ndash;805. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/RCT.0b013e31815896df\u003c/span\u003e\u003cspan address=\"10.1097/RCT.0b013e31815896df\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStrange CD, Ahuja J, Shroff GS, Truong MT, Marom EM. Imaging evaluation of thymoma and thymic carcinoma. Front Oncol. 2021;11:810419. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fonc.2021.810419\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2021.810419\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGao C, Yang L, Xu Y, Wang T, Ding H, Gao X, et al. Differentiating low-risk thymomas from high-risk thymomas: preoperative radiomics nomogram based on contrast enhanced CT to minimize unnecessary invasive thoracotomy. BMC Med Imaging. 2024;24:197. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12880-024-01367-5\u003c/span\u003e\u003cspan address=\"10.1186/s12880-024-01367-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiang Z, Li J, Tang Y, Zhang Y, Chen C, Li S, et al. Predicting the risk category of thymoma with machine learning-based computed tomography radiomics signatures and their between-imaging phase differences. Sci Rep. 2024;14:19215. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41598-024-69735-3\u003c/span\u003e\u003cspan address=\"10.1038/s41598-024-69735-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu W, Wang W, Guo R, Zhang H, Guo M. Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images. BMC Cancer. 2024;24:651. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12885-024-12394-4\u003c/span\u003e\u003cspan address=\"10.1186/s12885-024-12394-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHan X, Gao W, Chen Y, Du L, Duan J, Yu H, et al. Relationship between computed tomography imaging features and clinical characteristics, masaoka-koga stages, and World Health Organization histological classifications of thymoma. Front Oncol. 2019;9:1041. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fonc.2019.01041\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2019.01041\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXiao G, Hu YC, Ren JL, Qin P, Han JC, Qu XY, et al. MR imaging of thymomas: a combined radiomics nomogram to predict histologic subtypes. Eur Radiol. 2021;31:447\u0026ndash;57. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00330-020-07074-3\u003c/span\u003e\u003cspan address=\"10.1007/s00330-020-07074-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNakajo M, Takeda A, Katsuki A, Jinguji M, Ohmura K, Tani A, et al. The efficacy of \u003csup\u003e18\u003c/sup\u003eF-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors. Br J Radiol. 2022;95:20211050. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1259/bjr.20211050\u003c/span\u003e\u003cspan address=\"10.1259/bjr.20211050\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"world-journal-of-surgical-oncology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wjso","sideBox":"Learn more about [World Journal of Surgical Oncology](http://wjso.biomedcentral.com)","snPcode":"12957","submissionUrl":"https://submission.nature.com/new-submission/12957/3","title":"World Journal of Surgical Oncology","twitterHandle":"@OncoBioMed","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"thymoma, histopathological classification, radiomics analysis, computed tomography, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-9180024/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9180024/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eThymomas are primarily assessed using chest computed tomography (CT); however, this method has inherent limitations such as an overlap between the semantic features of thymomas presenting as localized lesions and other histological subtypes. Therefore, this study aimed to develop a combined radiomics model, based on non-contrast CT, and investigate its potential clinical utility in preoperatively differentiating between the thymoma risk classification.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe retrospectively analyzed the clinical and imaging data of 436 patients with pathologically confirmed thymomas between January 2010 and October 2023. The cohort comprised 272 low-risk cases (types A, AB, and B1) and 164 high-risk cases (types B2 and B3), which were randomly divided into training (n\u0026thinsp;=\u0026thinsp;306) and validation (n\u0026thinsp;=\u0026thinsp;130) sets in a 7:3 ratio. Radiomic features were extracted from the volume of interest on non-contrast CT images. Feature selection was performed using principal component analysis, correlation analysis, least absolute shrinkage, and selection operator algorithms to identify the most discriminative features. A combined radiomics nomogram was developed by integrating significant clinical factors with radiomics scores. The discriminative performance of the model was assessed using receiver operating characteristic curve analysis.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eTwo clinicoradiological and 11 radiomics features were identified and used to construct a radiomics nomogram. The diagnostic performance of the nomogram for thymoma risk stratification surpassed that of any single model. The nomogram yielded an area under the curve of 0.753 (accuracy, 71.2%; sensitivity, 62.4%; specificity, 76.7%) in the training cohort and 0.735 (accuracy, 70.8%; sensitivity, 58.8%; specificity, 78.5%) in the validation cohort.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe nomogram model integrating clinical factors and radiomics features accurately differentiated the histological subtypes of thymoma. This tool may be helpful in formulating personalized treatment plans in clinical practice and is worthy of clinical promotion and application.\u003c/p\u003e","manuscriptTitle":"Preoperative Prediction of Thymoma Risk Classification with Machine Learning-Based Computed Tomography Radiomics Features","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-29 10:14:30","doi":"10.21203/rs.3.rs-9180024/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-18T17:31:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T00:28:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"84177837894114699911001461889226948073","date":"2026-04-26T14:04:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-22T01:42:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"122538589703881070036243442259621086208","date":"2026-04-20T22:48:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"124771084460637493905557647162970960997","date":"2026-04-20T14:45:47+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-20T09:12:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-30T17:10:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-23T23:16:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Journal of Surgical Oncology","date":"2026-03-20T14:36:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"world-journal-of-surgical-oncology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wjso","sideBox":"Learn more about [World Journal of Surgical Oncology](http://wjso.biomedcentral.com)","snPcode":"12957","submissionUrl":"https://submission.nature.com/new-submission/12957/3","title":"World Journal of Surgical Oncology","twitterHandle":"@OncoBioMed","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"26aa154d-c3ec-44e6-a145-203094bebd03","owner":[],"postedDate":"April 29th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-18T17:31:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-06T00:28:05+00:00","index":86,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T17:38:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-29 10:14:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9180024","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9180024","identity":"rs-9180024","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}