ALEXANDRIA, Va., Oct. 6 -- United States Patent no. 12,755,462, issued on Oct. 6, was assigned to The Chinese University of Hong Kong (Shatin, China).
"Deep learning based accelerated MRI reconstruction using mixed CNN and vision transformer" was invented by Hongjian Kang (Tai Po, China) and Weitian Chen (Ma On Shan, China).
According to the abstract* released by the U.S. Patent & Trademark Office: "Described herein are systems, methods, and other techniques for operating and training a dual-branch image reconstruction network having a transformer branch and a CNN branch. A zero-filled image is provided to the network, the zero-filled image having been generated using zero-filled k-space data. A set of CNN output features are generated us...