US 12,089,915 B2
Method and system for prostate multi-modal MR image classification based on foveated residual network
Xuming Zhang, Hubei (CN); and Tuo Wang, Hubei (CN)
Assigned to HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY, Hubei (CN)
Appl. No. 18/554,680
Filed by HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY, Hubei (CN)
PCT Filed May 10, 2021, PCT No. PCT/CN2021/092541
§ 371(c)(1), (2) Date Oct. 10, 2023,
PCT Pub. No. WO2022/227108, PCT Pub. Date Nov. 3, 2022.
Claims priority of application No. 202110450651.0 (CN), filed on Apr. 25, 2021.
Prior Publication US 2024/0081648 A1, Mar. 14, 2024
Int. Cl. A61B 5/055 (2006.01); A61B 5/00 (2006.01); G06N 3/084 (2023.01); G06T 7/00 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC A61B 5/004 (2013.01) [A61B 5/055 (2013.01); A61B 5/7267 (2013.01); G06N 3/084 (2013.01); G06T 7/0012 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30081 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 2201/031 (2022.01)] 9 Claims
OG exemplary drawing
 
1. A method for prostate multi-modal MR image classification based on a foveated residual network, the method comprising:
classifying, using a foveated residual network, a prostate multi-modal MR image to be classified, to obtain a classification result;
a construction and training of the foveated residual network comprises:
replacing convolution kernels of a residual network using blur kernels in a foveation operator, thereby constructing a foveated residual network; and
training the foveated residual network using prostate multi-modal MR images having category labels, so as to obtain a trained foveated residual network.