US 12,343,191 B2
Medical image synthesis for motion correction using generative adversarial networks
Brendan Thomas Crabb, Salt Lake City, UT (US); Frederic Nicolas Firmin Noo, Midvale, UT (US); and Gabriel Chaim Fine, Salt Lake City, UT (US)
Assigned to University of Utah Research Foundation, Salt Lake City, UT (US)
Appl. No. 17/781,037
Filed by University of Utah Research Foundation, Salt Lake City, UT (US)
PCT Filed Dec. 1, 2020, PCT No. PCT/US2020/062699
§ 371(c)(1), (2) Date May 30, 2022,
PCT Pub. No. WO2021/113235, PCT Pub. Date Jun. 10, 2021.
Claims priority of provisional application 63/085,491, filed on Sep. 30, 2020.
Claims priority of provisional application 62/942,675, filed on Dec. 2, 2019.
Prior Publication US 2022/0409161 A1, Dec. 29, 2022
Int. Cl. A61B 6/00 (2024.01); G06V 10/32 (2022.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01)
CPC A61B 6/5264 (2013.01) [G06V 10/32 (2022.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer system for removing motion artifacts in medical images using a generative adversarial network (GAN) comprising:
one or more processors; and
one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform at least the following:
instantiate the generative adversarial network (GAN) having one or more generative network(s) and one or more discriminative network(s) that are pitted against each other to train a generative model and a discriminative model,
wherein the training of the generative network(s) and the discriminative network(s) uses a training dataset comprising a first plurality of medical images that are previously classified as without significant motion artifacts for diagnostic purposes;
wherein the discriminative model is trained to classify medical images as artificially generated or real; and
wherein the generative model is trained to enhance the quality of a medical image and remove motion artifacts by producing an image without the use of a pre-contrast mask.