US 11,966,454 B2
Self-contrastive learning for image processing
Zhang Chen, Brookline, MA (US); Xiao Chen, Lexington, MA (US); Yikang Liu, Cambridge, MA (US); Terrence Chen, Lexington, MA (US); and Shanhui Sun, Lexington, MA (US)
Assigned to Shanghai United Imaging Intelligence Co., Ltd., Shanghai (CN)
Filed by Shanghai United Imaging Intelligence Co., Ltd., Shanghai (CN)
Filed on Oct. 28, 2021, as Appl. No. 17/513,493.
Prior Publication US 2023/0138380 A1, May 4, 2023
Int. Cl. G06K 9/00 (2022.01); G01R 33/56 (2006.01); G06F 18/214 (2023.01); G06N 3/08 (2023.01); G06T 3/40 (2006.01); G06T 5/70 (2024.01); G06T 7/00 (2017.01); G06T 11/00 (2006.01); G06V 10/94 (2022.01); G16H 30/20 (2018.01)
CPC G06F 18/2148 (2023.01) [G01R 33/5608 (2013.01); G06N 3/08 (2013.01); G06T 3/40 (2013.01); G06T 5/70 (2024.01); G06T 7/0014 (2013.01); G06T 11/008 (2013.01); G06V 10/95 (2022.01); G16H 30/20 (2018.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30004 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An apparatus comprising one or more processors and one or more storage devices, the one or more storage devices configured to store instructions that, when executed by the one or more processors, cause the one or more processors to:
receive an input image of an anatomical structure, the input image produced by a medical imaging modality; and
generate, using one or more artificial neural networks, an output image based on the input image, wherein:
the one or more artificial neural networks are configured to implement a model for generating the output image based on the input image; and
the model is learned through a training process during which parameters associated with the model are adjusted so as to maximize a difference between a first image predicted using first parameter values of the model and a second image predicted using second parameter values of the model, and to minimize a difference between the second image and a ground truth image.