US 11,948,314 B2
Systems and methods for image processing
Shu Liao, Shanghai (CN); Yunhao Ge, Cambridge, MA (US); and Dongming Wei, Shanghai (CN)
Assigned to SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD., Shanghai (CN)
Filed by SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD., Shanghai (CN)
Filed on Feb. 20, 2022, as Appl. No. 17/651,806.
Application 17/651,806 is a continuation of application No. 16/729,303, filed on Dec. 28, 2019, granted, now 11,270,446.
Claims priority of application No. 201811622772.3 (CN), filed on Dec. 28, 2018.
Prior Publication US 2022/0172382 A1, Jun. 2, 2022
Int. Cl. G06T 7/30 (2017.01); G06T 7/55 (2017.01)
CPC G06T 7/30 (2017.01) [G06T 7/55 (2017.01); G06T 2207/10081 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/10116 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for image processing, comprising:
at least one storage device storing a set of instructions; and
at least one processor in communication with the at least one storage device, when executing the stored set of instructions, the at least one processor causes the system to perform operations including:
obtaining a first image of a first modality;
generating a second image of a second modality by processing, based on a trained machine learning model, the first image;
wherein the second modality is different from the first modality,
the trained machine learning model is a generative adversarial network (GAN) and includes a generative model, a first discriminative model, and a second discriminative model, and
in a process of training the machine learning model, the first discriminative model is used to evaluate a difference between a predicted image of the generative model and a reference image, the reference image is a desired predicted image, and the second discriminative model is used to evaluate a difference between at least one first shape extracted from the predicted image of the generative model and at least one second shape extracted from a sample input image of the generative model.