MRI-Based Deep-Learning Method for Determining Glioma <i>MGMT</i> Promoter Methylation Status
Chandan Ganesh Bangalore Yogananda, Bhavya Shah, Sahil Nalawade, Gowtham Krishnan Murugesan, Fang Yu, Marco C. Pinho, Benjamin Wagner, Bruce Mickey, Toral Patel, Baowei Fei, Ananth J. Madhuranthakam, Joseph A. Maldjian
Abstract
<h3>BACKGROUND AND PURPOSE:</h3> <i>O<sup>6</sup>-Methylguanine-DNA methyltransferase</i> (<i>MGMT</i>) promoter methylation confers an improved prognosis and treatment response in gliomas. We developed a deep learning network for determining <i>MGMT</i> promoter methylation status using T2 weighted Images (T2WI) only. <h3>MATERIALS AND METHODS:</h3> Brain MR imaging and corresponding genomic information were obtained for 247 subjects from The Cancer Imaging Archive and The Cancer Genome Atlas. One hundred sixty-three subjects had a methylated <i>MGMT</i> promoter. A T2WI-only network (<i>MGMT</i>-net) was developed to determine <i>MGMT</i> promoter methylation status and simultaneous single-label tumor segmentation. The network was trained using 3D-dense-UNets. Three-fold cross-validation was performed to generalize the performance of the networks. Dice scores were computed to determine tumor-segmentation accuracy. <h3>RESULTS:</h3> The <i>MGMT</i>-net demonstrated a mean cross-validation accuracy of 94.73% across the 3 folds (95.12%, 93.98%, and 95.12%, [SD, 0.66%]) in predicting <i>MGMT</i> methylation status with a sensitivity and specificity of 96.31% [SD, 0.04%] and 91.66% [SD, 2.06%], respectively, and a mean area under the curve of 0.93 [SD, 0.01]. The whole tumor-segmentation mean Dice score was 0.82 [SD, 0.008]. <h3>CONCLUSIONS:</h3> We demonstrate high classification accuracy in predicting <i>MGMT</i> promoter methylation status using only T2WI. Our network surpasses the sensitivity, specificity, and accuracy of histologic and molecular methods. This result represents an important milestone toward using MR imaging to predict prognosis and treatment response.