US 11,666,210 B2
System for recognizing diabetic retinopathy
Juan Wang, Shenzhen (CN); Bin Xia, Shenzhen (CN); Yujing Bai, Shenzhen (CN); Xiaoxin Li, Shenzhen (CN); Zhigang Hu, Shenzhen (CN); and Yu Zhao, Shenzhen (CN)
Assigned to SHENZHEN SIBIONICS TECHNOLOGY CO., LTD., Shenzhen (CN); and SHENZHEN SIBRIGHT TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed by SHENZHEN SIBIONICS TECHNOLOGY CO., LTD., Shenzhen (CN); and SHENZHEN SIBRIGHT TECHNOLOGY CO., LTD., Shenzhen (CN)
Filed on Nov. 19, 2021, as Appl. No. 17/455,795.
Application 17/455,795 is a continuation of application No. 16/609,213, granted, now 11,213,197, previously published as PCT/CN2017/095909, filed on Aug. 4, 2017.
Claims priority of application No. 201710306096.8 (CN), filed on May 4, 2017.
Prior Publication US 2022/0079430 A1, Mar. 17, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 3/00 (2006.01); G06N 20/20 (2019.01); G06N 20/10 (2019.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06N 3/045 (2023.01)
CPC A61B 3/0025 (2013.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06T 7/0012 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01); G06T 2207/30096 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for recognizing a diabetic retinopathy, comprising:
a first neural network configured to generate a first advanced feature set from a target retinal fundus image;
a second neural network configured to generate a second advanced feature set from a reference retinal fundus image;
a feature combination module configured to combine the first advanced feature set and the second advanced feature set to form a feature combination set; and
a third neural network configured to generate a diagnosis result according to the feature combination set;
wherein:
the target retinal fundus image and the reference retinal fundus image are taken from one person; and
fundus images of a same resolution are used during a training process of the system.