Abstract #3976

Deep network training based sparsity model for reconstruction

Jiahao Lin^1,2, Stamatios Lefkimmiatis³, and Kyunghyun Sung²

¹Electrical Engineering, University of California, Los Angeles, Los Angeles, CA, United States, ²Radiology, University of California, Los Angeles, Los Angeles, CA, United States, ³Skolkovo Institute of Science and Technology, Moscow, Russian Federation

One challenge for MR reconstruction is to heuristically select the appropriate regularizer for the optimization problem. This abstract proposes a novel deep learning based reconstruction approach for accelerated MR imaging. With the training using clinical MR images and their retrospectively undersampled noisy images, this algorithm learns the specific parameters of a general regularizer for the optimization problem, and uses this regularizer in the iterative reconstruction to achieves high image quality with high acceleration factors.

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

Join Here