Meeting Banner
Abstract #4459

Predicting tumor recurrence in patients with gliomas via deep learning-based analysis of structural and amide proton transfer weighted MRI

Pengfei Guo1,2, Mathias Unberath2, Jinyuan Zhou1, Hye-Young Heo1, Charles G. Eberhart3, Michael Lim4, Jaishri O. Blakeley5, Peter van Zijl1,6, and Shanshan Jiang1
1Department of Radiology, Johns Hopkins University, Baltimore, MD, United States, 2Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States, 3Department of Pathology, Johns Hopkins University, Baltimore, MD, United States, 4Department of Neurosurgery, Johns Hopkins University, Baltimore, MD, United States, 5Department of Neurology, Johns Hopkins University, Baltimore, MD, United States, 6F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, United States

Synopsis

Amide protein transfer weighted (APTw) MRI has been validated to accurately detect recurrent malignant gliomas across different studies. However, APTw image interpretation is time consuming and requires professional knowledge. Therefore, reliable, automated imaging diagnostic tools to assess malignant glioma response to therapies are urgently needed. Here, we develop and verify a CNN-based deep-learning algorithm to identify tumor progression versus response by adding APTw MRI data to structural MR images as the proposed model input. Our results suggest that the use of APTw images can increase the diagnostic accuracy to structural MRI for the treatment response assessment.

This abstract and the presentation materials are available to members only; a login is required.

Join Here