Development and Validation of MRI-Based Radiomics Models for Diagnosing Juvenile Myoclonic Epilepsy

• Published in: Korean journal of radiology Vol. 23; no. 12; pp. 1281 - 1289
• Main Authors: Kim, Kyung Min, Hwang, Heewon, Sohn, Beomseok, Park, Kisung, Han, Kyunghwa, Ahn, Sung Soo, Lee, Wonwoo, Chu, Min Kyung, Heo, Kyoung, Lee, Seung-Koo
• Format: Journal Article
• Language: English
• Published: Korea (South) The Korean Society of Radiology 01.12.2022
• Subjects: Adult; Age; Area Under Curve; Automation; Brain - diagnostic imaging; Brain research; Convulsions & seizures; Electroencephalography; Epilepsy; Female; Humans; Machine learning; Magnetic Resonance Imaging; Male; Morphology; Myoclonic Epilepsy, Juvenile - diagnostic imaging; Neuroimaging and Head & Neck; Patients; Regression analysis; Software; Idiopathic generalized epilepsy; Texture analysis; Magnetic resonance imaging; Juvenile myoclonic epilepsy; Radiomics
• DOI: 10.3348/kjr.2022.0539
• ISSN: 1229-6929

Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Radiomic models using MRI were able to differentiate JME from HCs.