Abstract #2594

Deep subspace unrolling network for accelerating non-Cartesian sampled CMR Multitasking imaging

Jiaying Zhao^1,2, Sen Jia³, Qi Liu⁴, Junpu Hu⁵, Jing Cheng³, Yining Wang⁶, Jian Xu⁷, Dong Liang^1,3, and Ye Li³

¹Medical AI Research Center, Shenzhen Institutes of Advanced Technology, Shenzhen, China, ²University of Chinese Academy of Sciences, Beijing, China, ³Paul C. Lauterbur Research Center for Biomedical lmaging, Shenzhen Institute of Advanced Technology, Shenzhen, China, ⁴UIH America, Inc, Houston, TX, United States, ⁵Shanghai United Imaging Healthcare Advanced Technology Research Institute Co., Ltd, Shanghai, China, ⁶Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China, ⁷UIH America, Inc., Houston, TX, United States

Synopsis

Keywords: Machine Learning/Artificial Intelligence, Quantitative Imaging, Multitasking

Motivation: The prolonged imaging time of CMR Multitasking limits its clinical application.

Goal(s): Developing deep learning method to improve the imaging speed while ensuring the reconstruction and quantification accuracy.

Approach: Developing a deep subspace unrolling network with an Unet as density compensation to accelerate convergence.

Results: The proposed unrolling network achieved the iterative reconstruction in 5 iterations.

Impact: The proposed method reduces the imaging time of CMR multitasking from 71 minutes (MATLAB) to 5 minutes (GPU), providing possible clinical applications.

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.