US 11,693,919 B2
Anatomy-aware motion estimation
Xiao Chen, Lexington, MA (US); Pingjun Chen, Gainesville, FL (US); Zhang Chen, Brookline, 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 Jun. 22, 2020, as Appl. No. 16/908,148.
Prior Publication US 2021/0397886 A1, Dec. 23, 2021
Int. Cl. G06F 18/213 (2023.01); G16H 50/50 (2018.01); G16H 30/20 (2018.01); G16H 50/70 (2018.01); G16H 50/20 (2018.01); G16H 30/40 (2018.01); G06V 40/20 (2022.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01)
CPC G06F 18/213 (2023.01) [G06F 18/2148 (2023.01); G06N 3/08 (2013.01); G06V 40/20 (2022.01); G16H 30/20 (2018.01); G16H 30/40 (2018.01); G16H 50/20 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01); G06V 2201/031 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A neural network system 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 a first medical image and a second medical image, wherein the first medical image comprises a first visual representation of an anatomical structure and the second medical image comprises a second visual representation of the anatomical structure;
extract a first plurality of features from the first medical image and a second plurality of features from the second medical image;
determine a first motion of the anatomical structure between the first medical image and the second medical image based on the first plurality of features and the second plurality of features respectively extracted from the first medical image and the second medical image; and
generate a first flow field indicating the first motion;
wherein the neural network system is trained at least partially using a variational autoencoder (VAE) as a supervisor of the training, the VAE being pre-trained to generate a refined segmentation mask for the anatomical structure based on a shape prior of the anatomical structure, and wherein, during the training of the neural network system, the neural network system is configured to generate a coarse segmentation mask for the anatomical structure based on a first plurality of features extracted from a first training image or based on a second plurality of features extracted from a second training image, and adjust one or more operating parameters of the neural network system based on a first loss calculated from the coarse segmentation mask and the refined segmentation mask.