Meeting Banner
Abstract #0407

Deep learning super-resolution of MR images of the distal tibia improves image quality and assessment of bone microstructure

Trevor Chan1,2, Nada Kamona1,2, Brian-Tinh Vu1,2, Felix Wehrli1,2, and Chamith Rajapakse1,2
1Radiology, University of Pennsylvania, Philadelphia, PA, United States, 2Bioengineering, University of Pennsylvania, Philadelphia, PA, United States


We apply a probabilistic deep learning model to perform image super-resolution on magnetic resonance (MR) images. Our results show that the model is capable of high performance in MR; we upsample low resolution images of the distal tibia to 2x initial spatial resolution–equivalent to capturing 4x fewer samples in K-space–with the goal of reconstructing details in the trabecular architecture. We validate our results by comparing trabecular bone microstructure metrics across high-resolution ground truth, model-reconstructed, and low-resolution input images. By drastically reducing scan time for high-resolution imaging, these methods have the potential to make MRI assessment of bone strength clinically viable.

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

Join Here