MR Contrast-Invariant Deep Learning Method for Synthetic CT Generation

Motivation: Deep learning models are sensitive to image contrast variations. We explore the feasibility of training a single model to process multiple MR contrasts. Goal(s): To generate synthetic CT images from different MR image contrasts using a image contrast agnostic model. Approach: A multi-task deep convolutional neural network has been trained using a variety of MR image contrasts. Results: We demonstrate generation of synthetic CT images from multiple MR images with superior qualitative accuracy and encouraging quantitative accuracy. Impact: The ability to generate synthetic CT from a variety of MR contrasts brings flexibility of choice of MR sequence in MR guided radiation therapy clinical setup. It improves the model robustness to scan parameter variations leading to a consistent outcome.