Screening and evaluation of diabetic retinopathy via a deep learning network model: A prospective study.

IF 4.2 3区 医学 Q1 ENDOCRINOLOGY & METABOLISM
Li Yao, Chan-Yuan Cao, Guo-Xiao Yu, Xu-Peng Shu, Xiao-Nan Fan, Yi-Fan Zhang
{"title":"Screening and evaluation of diabetic retinopathy <i>via</i> a deep learning network model: A prospective study.","authors":"Li Yao, Chan-Yuan Cao, Guo-Xiao Yu, Xu-Peng Shu, Xiao-Nan Fan, Yi-Fan Zhang","doi":"10.4239/wjd.v15.i12.2302","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Diabetic retinopathy (DR) is one of the most common serious complications in diabetic patients, and early screening and diagnosis are essential to prevent visual impairment. With the rapid development of deep learning technology, network models based on attention mechanisms have shown significant advantages in medical image analysis, which can improve the accuracy and efficiency of screening.</p><p><strong>Aim: </strong>To evaluate the efficacy of an attention mechanism-based deep learning network model in screening for DR in natural and diabetic populations, as well as in screening with unilateral and bilateral fundus photography.</p><p><strong>Methods: </strong>From January 2023 to June 2024, a stratified multistage cluster sampling method was adopted to select a representative sample of permanent residents aged 18-70 years from our hospital. A total of 948 fundus images from 474 participants were included in the \"deep learning model\" system for scoring. The fundus images were graded <i>via</i> the early treatment of DR [Early Treatment Diabetic Retinopathy Study (ETDRS)] scoring system as the gold standard for the diagnosis of DR. With \"DR to be referred (ETDRS > 31)\" as the reference variable, a receiver operating characteristic curve was drawn to evaluate the area under the curve (AUC), sensitivity and specificity of the \"deep learning model\" to determine the screening efficiency of the system.</p><p><strong>Results: </strong>For each subject, in the natural population, the AUC of using the \"deep learning model system\" to screen \"DR-requiring referral\" was 0.941, and the sensitivity and specificity were 98.15% and 90.08%, respectively. The sensitivity and specificity of two-directional fundus photography were 100% and 86.91%, respectively. In the diabetic population, the AUC, sensitivity and specificity were 0.901, 98.08% and 82.10%, respectively, when \"wise eye sugar net\" unilateral fundus photography was used to screen for \"DR-requiring referrals\".</p><p><strong>Conclusion: </strong>In both the natural population and the diabetic population, the deep learning model system has shown high sensitivity and specificity and can be used as an auxiliary means of DR screening.</p>","PeriodicalId":48607,"journal":{"name":"World Journal of Diabetes","volume":"15 12","pages":"2302-2310"},"PeriodicalIF":4.2000,"publicationDate":"2024-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11580591/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"World Journal of Diabetes","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.4239/wjd.v15.i12.2302","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Diabetic retinopathy (DR) is one of the most common serious complications in diabetic patients, and early screening and diagnosis are essential to prevent visual impairment. With the rapid development of deep learning technology, network models based on attention mechanisms have shown significant advantages in medical image analysis, which can improve the accuracy and efficiency of screening.

Aim: To evaluate the efficacy of an attention mechanism-based deep learning network model in screening for DR in natural and diabetic populations, as well as in screening with unilateral and bilateral fundus photography.

Methods: From January 2023 to June 2024, a stratified multistage cluster sampling method was adopted to select a representative sample of permanent residents aged 18-70 years from our hospital. A total of 948 fundus images from 474 participants were included in the "deep learning model" system for scoring. The fundus images were graded via the early treatment of DR [Early Treatment Diabetic Retinopathy Study (ETDRS)] scoring system as the gold standard for the diagnosis of DR. With "DR to be referred (ETDRS > 31)" as the reference variable, a receiver operating characteristic curve was drawn to evaluate the area under the curve (AUC), sensitivity and specificity of the "deep learning model" to determine the screening efficiency of the system.

Results: For each subject, in the natural population, the AUC of using the "deep learning model system" to screen "DR-requiring referral" was 0.941, and the sensitivity and specificity were 98.15% and 90.08%, respectively. The sensitivity and specificity of two-directional fundus photography were 100% and 86.91%, respectively. In the diabetic population, the AUC, sensitivity and specificity were 0.901, 98.08% and 82.10%, respectively, when "wise eye sugar net" unilateral fundus photography was used to screen for "DR-requiring referrals".

Conclusion: In both the natural population and the diabetic population, the deep learning model system has shown high sensitivity and specificity and can be used as an auxiliary means of DR screening.

求助全文
约1分钟内获得全文 求助全文
来源期刊
World Journal of Diabetes
World Journal of Diabetes ENDOCRINOLOGY & METABOLISM-
自引率
2.40%
发文量
909
期刊介绍: The WJD is a high-quality, peer reviewed, open-access journal. The primary task of WJD is to rapidly publish high-quality original articles, reviews, editorials, and case reports in the field of diabetes. In order to promote productive academic communication, the peer review process for the WJD is transparent; to this end, all published manuscripts are accompanied by the anonymized reviewers’ comments as well as the authors’ responses. The primary aims of the WJD are to improve diagnostic, therapeutic and preventive modalities and the skills of clinicians and to guide clinical practice in diabetes. Scope: Diabetes Complications, Experimental Diabetes Mellitus, Type 1 Diabetes Mellitus, Type 2 Diabetes Mellitus, Diabetes, Gestational, Diabetic Angiopathies, Diabetic Cardiomyopathies, Diabetic Coma, Diabetic Ketoacidosis, Diabetic Nephropathies, Diabetic Neuropathies, Donohue Syndrome, Fetal Macrosomia, and Prediabetic State.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信