Radiomics for the Prediction of Epilepsy in Patients With Frontal Glioma

Objective: To investigate the association between radiomic features and frontal gliomas associated epilepsy (GAE) and propose a reliable radiomics-based model to predict frontal GAE. Methods: This retrospective study consecutively enrolled 166 adult patients with frontal glioma (111 in the primary cohort and 55 in the testing cohort). A total 1130 features were extracted from T2-fluid attenuated inversion recovery images, including first-order statistics, 3D shape, texture, and wavelet features. Regions of interest, including the entire tumor and peritumoral edema, were drawn manually. Pearson correlation coefficient, 10-fold cross-validation, area under curve (AUC) analysis, and support vector machine were adopted to select the most relevant features to build a clinical model, a radiomic model and a clinic-radiomic model for GAE. The receiver operating characteristic curve (ROC) and AUC were used to evaluate the models’ classification performance in each cohort, and Delong’s test was used to compare the models’ performance. Two-sided t-test and Fisher’s exact test were used to compare the clinical variables. Statistical analysis was performed using SPSS software (version 22.0; IBM, Armonk, New York), and p < 0.05 set as threshold for significant. Results: The classification accuracy of seven scout models, except the Wavelet first order model (0.793) and Wavelet texture model (0.784), was <0.75 in cross-validation. The clinic-radiomic model, including 17 magnetic resonance imaging-based features selected among the 1130 radiomic features and two clinical features (patient age and tumor grade), achieved better discriminative performance for GAE prediction in both the training (AUC = 0.886, 95% confidence interval [CI] = 0.819–0.940) and testing cohorts (AUC = 0.836,95% CI= 0.707–0.937) than radiomic model (p=0.008) with 82.0 and 78.2% accuracy, respectively. Conclusion: Radiomics analysis can non-invasively predict GAE, thus allowing adequate treatment of frontal glioma. The clinical-radiomics model may enable a more precise prediction of frontal GAE. Further, age and pathology grade are important risk factors for GAE.