Meeting Banner
Abstract #2216

Rapid myocardial perfusion MRI reconstruction using deep learning networks

Eric Kenneth Gibbons1,2, Ye Tian3, Qi Huang4, Akshay Chaudhari5, and Edward DiBella2,4
1Electrical and Computer Engineering, Weber State University, Ogden, UT, United States, 2Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT, United States, 3Physics, University of Utah, Salt Lake City, UT, United States, 4Biomedical Engineering, University of Utah, Salt Lake City, UT, United States, 5Radiology, Stanford University, Stanford, CA, United States

Current acquisition strategies in cardiac perfusion MRI rely on non-uniform sampling that is highly undersampled in spatial and temporal domains. While iterative reconstruction methods are able to reconstruct such data reasonably well, reconstruction speeds are prohibitively long. This abstract applies novel deep learning approaches to accelerate reconstruction speeds relative to iterative algorithms with comparable image quality. Validation is performed through the calculation of a perfusion index.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here