Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma

Background In glioblastoma (GBM), promoter methylation of the DNA repair gene O‐methylguanine‐DNA methyltransferase (MGMT) is associated with beneficial chemotherapy. Purpose/Hypothesis To analyze radiomics features for utilizing the full potential of medical imaging as biomarkers of MGMT promoter methylation. Study Type Retrospective. Population/Subjects In all, 98 GBM patients with known MGMT (48 methylated and 50 unmethylated tumors). Field Strength/Sequence 3.0T magnetic resonance (MR) images, containing T1‐weighted image (T1WI), T2‐weighted image (T2WI), and enhanced T1WI. Assessment A region of interest (ROI) of the tumor was delineated. A total of 1665 radiomics features were extracted and quantized, and were reduced using least absolute shrinkage and selection operator (LASSO) regularization. Statistical Testing After the support vector machine construction, accuracy, sensitivity, and specificity were computed for different sequences. An independent validation cohort containing 20 GBM patients was utilized to further evaluate the radiomics model performance. Results Radiomics features of T1WI reached an accuracy of 67.54%. Enhanced T1WI features reached an accuracy of 82.01%, while T2WI reached an accuracy of 69.25%. The best classification system for predicting MGMT promoter methylation status originated from the combination of 36 T1WI, T2WI, and enhanced T1WI images features, with an accuracy of 86.59%. Further validation on the independent cohort of 20 patients produced similar results, with an accuracy of 80%. Data Conclusion Our results provide further evidence that radiomics MR features could predict MGMT methylation status in preoperative GBM. Multiple imaging modalities together can yield putative noninvasive biomarkers for the identification of MGMT. Level of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:1380–1387.