MRI-Based Deep-Learning Method for Determining Glioma MGMT Promoter Methylation Status.

Chandan Ganesh Bhavya R Shah Sahil S Nalawade Gowtham K Murugesan Fang Frank Yu Marco Aurélio Pinho de Oliveira Benjamin C Wagner B Mickey Toral R Patel Baowei Fei Ananth J Madhuranthakam Joseph A Maldjian

Published in: AJNR. American journal of neuroradiology (2021)

We demonstrate high classification accuracy in predicting MGMT 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.

Keyphrases

dna methylation
deep learning
contrast enhanced
genome wide
gene expression
transcription factor
machine learning
magnetic resonance imaging
artificial intelligence
convolutional neural network
computed tomography
magnetic resonance