Detection of Fuchs' Uveitis Syndrome From Slit-Lamp Images Using Deep Convolutional Neural Networks in a Chinese Population

作者全名："Zhang, Wanyun; Chen, Zhijun; Zhang, Han; Su, Guannan; Chang, Rui; Chen, Lin; Zhu, Ying; Cao, Qingfeng; Zhou, Chunjiang; Wang, Yao; Yang, Peizeng"

作者地址："[Zhang, Wanyun; Chen, Zhijun; Su, Guannan; Chang, Rui; Chen, Lin; Zhu, Ying; Cao, Qingfeng; Zhou, Chunjiang; Wang, Yao; Yang, Peizeng] Chongqing Med Univ, Chongqing Key Lab Ophthalmol, Affiliated Hosp 1, Chongqing, Peoples R China; [Zhang, Wanyun; Chen, Zhijun; Su, Guannan; Chang, Rui; Chen, Lin; Zhu, Ying; Cao, Qingfeng; Zhou, Chunjiang; Wang, Yao; Yang, Peizeng] Chongqing Eye Inst, Natl Clin Res Ctr Ocular Dis, Chongqing Branch, Chongqing, Peoples R China; [Zhang, Han] Harbin Inst Technol, Sch Comp Sci & Technol, Harbin, Peoples R China"

通信作者："Yang, PZ (corresponding author), Chongqing Med Univ, Chongqing Key Lab Ophthalmol, Affiliated Hosp 1, Chongqing, Peoples R China.; Yang, PZ (corresponding author), Chongqing Eye Inst, Natl Clin Res Ctr Ocular Dis, Chongqing Branch, Chongqing, Peoples R China."

来源：FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY

ESI学科分类：MOLECULAR BIOLOGY & GENETICS

WOS号：WOS:000668940700001

JCR分区：Q1

影响因子：5.5

年份：2021

卷号：9

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Fuchs' uveitis syndrome; diffuse iris depigmentation; slit-lamp images; deep convolutional neural model; deep learning

摘要："Fuchs' uveitis syndrome (FUS) is one of the most under- or misdiagnosed uveitis entities. Many undiagnosed FUS patients are unnecessarily overtreated with anti-inflammatory drugs, which may lead to serious complications. To offer assistance for ophthalmologists in the screening and diagnosis of FUS, we developed seven deep convolutional neural networks (DCNNs) to detect FUS using slit-lamp images. We also proposed a new optimized model with a mixed ""attention"" module to improve test accuracy. In the same independent set, we compared the performance between these DCNNs and ophthalmologists in detecting FUS. Seven different network models, including Xception, Resnet50, SE-Resnet50, ResNext50, SE-ResNext50, ST-ResNext50, and SET-ResNext50, were used to predict FUS automatically with the area under the receiver operating characteristic curves (AUCs) that ranged from 0.951 to 0.977. Our proposed SET-ResNext50 model (accuracy = 0.930; Precision = 0.918; Recall = 0.923; F1 measure = 0.920) with an AUC of 0.977 consistently outperformed the other networks and outperformed general ophthalmologists by a large margin. Heat-map visualizations of the SET-ResNext50 were provided to identify the target areas in the slit-lamp images. In conclusion, we confirmed that a trained classification method based on DCNNs achieved high effectiveness in distinguishing FUS from other forms of anterior uveitis. The performance of the DCNNs was better than that of general ophthalmologists and could be of value in the diagnosis of FUS."

基金机构：Chongqing Outstanding Scientists Project (2019); Chongqing Key Laboratory of Ophthalmology (CSTC)Natural Science Foundation Project of CQ CSTC [2008CA5003]; Chongqing Science and Technology Platform and Base Construction Program [cstc2014pt-sy10002]; Chongqing Chief Medical Scientist Project (2018)

基金资助正文："The work was supported by Chongqing Outstanding Scientists Project (2019), Chongqing Key Laboratory of Ophthalmology (CSTC, 2008CA5003), Chongqing Science and Technology Platform and Base Construction Program (cstc2014pt-sy10002), and the Chongqing Chief Medical Scientist Project (2018)."