Abstract #1778

Exploiting deep convolutional neural network for fast magnetic resonance imaging

Shanshan Wang¹, Zhenghang Su^1,2, Leslie Ying³, Xi Peng¹, and Dong Liang¹

¹Shenzhen Institutes of Advanced Technologies, Shenzhen, China, People's Republic of, ²School of Information Technologies, Guangdong University of Technology, Guangzhou, China, People's Republic of, ³Department of Biomedical Engineering and Department of Electrical Engineering, The State University of New York, Buffalo, NY, United States

This paper proposes a deep learning based approach for accelerating MR imaging. With the utilization of a large number of existing high-quality MR images, we train an off-line convolutional neural network (CNN) to identify the mapping relationship between MR images obtained from zero-filled and fully-sampled k-space data. Then the trained CNN is employed to predict an image from undersampled data, which is used as the reference in solving an online constrained imaging problem. Results on in vivo datasets show that the proposed approach is capable of restoring fine details and presents great potential for efficient and effective MR imaging.

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

Join Here