Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status

Panagiotis Korfiatis, Timothy L. Kline, Daniel H. Lachance, Ian F. Parney, Jan C. Buckner, Bradley J. Erickson

Research output: Contribution to journalArticlepeer-review

58 Scopus citations


Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate their ability in predicting MGMT methylation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture was the best performing model, achieving an accuracy of 94.90% (+/− 3.92%) for the test set (classification of a slice as no tumor, methylated MGMT, or non-methylated). ResNet34 (34 layers) achieved 80.72% (+/− 13.61%) while ResNet18 (18 layers) accuracy was 76.75% (+/− 20.67%). ResNet50 performance was statistically significantly better than both ResNet18 and ResNet34 architectures (p < 0.001). We report a method that alleviates the need of extensive preprocessing and acts as a proof of concept that deep neural architectures can be used to predict molecular biomarkers from routine medical images.

Original languageEnglish (US)
Pages (from-to)622-628
Number of pages7
JournalJournal of Digital Imaging
Issue number5
StatePublished - Oct 1 2017


  • Deep learning
  • MGMT methylation
  • MRI

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications


Dive into the research topics of 'Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status'. Together they form a unique fingerprint.

Cite this