T2-weighted MR imaging is the standardized protocol in clinical evaluation of rectal cancer and anatomic structures. Usually, spasmolytic agent injection is required before the examination to reduce the imaging artifacts caused by the rectum peristalsis. In this work, we propose a novel dynamic imaging approach that with a complementary k-space sampling strategy and deep learning-based image reconstruction method to illustrate the anatomical structures of the rectum without any agent injection. Experimental results demonstrate the superior performance of the proposed approach.
This abstract and the presentation materials are available to members only; a login is required.