ALEXANDRIA, Va., May 26 -- United States Patent no. 12,639,834, issued on May 26, was assigned to The Hong Kong Polytechnic University (Hong Kong).

"Training method of a neural network model for CT image registration" was invented by Jing Qin (Hong Kong) and Jing Zou (Hong Kong).

According to the abstract* released by the U.S. Patent & Trademark Office: "A training method of a deep neural network model for CT image registration, comprising the following steps: providing features of a source image and features of a corresponding target image; generating a deformation field from the source image to the target image; decomposing the generated deformation field into a first deformation field part and a second deformation field part; obtaining...