Abstract #3219

Parallel Imaging Reconstruction from Undersampled K-space Data via Iterative Feature Refinement

Jing Cheng¹, Leslie Ying², Shanshan Wang¹, Xi Peng¹, Yuanyuan Liu¹, Jing Yuan³, and Dong Liang¹

¹Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences, shenzhen, China, People's Republic of, ²University at Buffalo,The State University of New York, New york, NY, United States, ³Medical Physics and Research Department, Hong Kong Sanatorium & Hospital, Hong Kong, Hong Kong

Compressed sensing based parallel imaging is an essential technique for accelerating MRI scan. However, most existing methods are still suffering from fine structure loss. This paper proposes an iterative feature refinement scheme for improving the reconstruction accuracy. We have incorporated the feature descriptor into the self-feeding sparse SENSE (SFSS) framework. Results on in-vivo MR dataset have shown that the descriptor is capable of capturing image structures and details that are discarded by SFSS and thus presents great potential for more effective parallel imaging.

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

Join Here