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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.