• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

跨相机人工智能软件在糖尿病视网膜病变诊断中的外部验证。

Cross-Camera External Validation for Artificial Intelligence Software in Diagnosis of Diabetic Retinopathy.

机构信息

Department of Ophthalmology, Taoyuan General Hospital, Ministry of Health and Welfare, Taoyuan, Taiwan.

Department of Ophthalmology, National Taiwan University Hospital, Taipei, Taiwan.

出版信息

J Diabetes Res. 2022 Mar 9;2022:5779276. doi: 10.1155/2022/5779276. eCollection 2022.

DOI:10.1155/2022/5779276
PMID:35308093
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8926465/
Abstract

AIMS

To investigate the applicability of deep learning image assessment software VeriSee DR to different color fundus cameras for the screening of diabetic retinopathy (DR).

METHODS

Color fundus images of diabetes patients taken with three different nonmydriatic fundus cameras, including 477 Topcon TRC-NW400, 459 Topcon TRC-NW8 series, and 471 Kowa nonmyd 8 series that were judged as "gradable" by one ophthalmologist were enrolled for validation. VeriSee DR was then used for the diagnosis of referable DR according to the International Clinical Diabetic Retinopathy Disease Severity Scale. Gradability, sensitivity, and specificity were calculated for each camera model.

RESULTS

All images (100%) from the three camera models were gradable for VeriSee DR. The sensitivity for diagnosing referable DR in the TRC-NW400, TRC-NW8, and non-myd 8 series was 89.3%, 94.6%, and 95.7%, respectively, while the specificity was 94.2%, 90.4%, and 89.3%, respectively. Neither the sensitivity nor the specificity differed significantly between these camera models and the original camera model used for VeriSee DR development ( = 0.40, = 0.065, respectively).

CONCLUSIONS

VeriSee DR was applicable to a variety of color fundus cameras with 100% agreement with ophthalmologists in terms of gradability and good sensitivity and specificity for the diagnosis of referable DR.

摘要

目的

研究深度学习图像评估软件 VeriSee DR 应用于不同眼底彩色相机筛查糖尿病视网膜病变(DR)的适用性。

方法

纳入一位眼科医生判断为“可评估”的三种不同非散瞳眼底相机(包括 477 台 Topcon TRC-NW400、459 台 Topcon TRC-NW8 系列和 471 台 Kowa 非散瞳 8 系列)拍摄的糖尿病患者眼底彩色图像,采用 VeriSee DR 根据国际临床糖尿病视网膜病变疾病严重程度量表进行可转诊 DR 的诊断。计算每个相机模型的可评估性、敏感性和特异性。

结果

三种相机模型的所有图像(100%)均适用于 VeriSee DR。TRC-NW400、TRC-NW8 和非散瞳 8 系列诊断可转诊 DR 的敏感性分别为 89.3%、94.6%和 95.7%,特异性分别为 94.2%、90.4%和 89.3%。这些相机模型与用于开发 VeriSee DR 的原始相机模型之间的敏感性或特异性均无显著差异(=0.40,=0.065)。

结论

VeriSee DR 适用于多种眼底彩色相机,在可评估性方面与眼科医生完全一致,对可转诊 DR 的诊断具有良好的敏感性和特异性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/098b/8926465/d8ab91f1d990/JDR2022-5779276.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/098b/8926465/d8ab91f1d990/JDR2022-5779276.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/098b/8926465/d8ab91f1d990/JDR2022-5779276.001.jpg

相似文献

1
Cross-Camera External Validation for Artificial Intelligence Software in Diagnosis of Diabetic Retinopathy.跨相机人工智能软件在糖尿病视网膜病变诊断中的外部验证。
J Diabetes Res. 2022 Mar 9;2022:5779276. doi: 10.1155/2022/5779276. eCollection 2022.
2
Head to head comparison of diagnostic performance of three non-mydriatic cameras for diabetic retinopathy screening with artificial intelligence.三种非散瞳相机与人工智能联合用于糖尿病视网膜病变筛查的诊断性能头对头比较。
Eye (Lond). 2024 Jun;38(9):1694-1701. doi: 10.1038/s41433-024-03000-9. Epub 2024 Mar 11.
3
Comparison of 21 artificial intelligence algorithms in automated diabetic retinopathy screening using handheld fundus camera.比较使用手持眼底相机的 21 种人工智能算法在自动化糖尿病性视网膜病变筛查中的应用。
Ann Med. 2024 Dec;56(1):2352018. doi: 10.1080/07853890.2024.2352018. Epub 2024 May 13.
4
Clinical validation of a smartphone-based retinal camera for diabetic retinopathy screening.基于智能手机的视网膜相机用于糖尿病视网膜病变筛查的临床验证。
Acta Diabetol. 2023 Aug;60(8):1075-1081. doi: 10.1007/s00592-023-02105-z. Epub 2023 May 7.
5
Validation of Artificial Intelligence Algorithm in the Detection and Staging of Diabetic Retinopathy through Fundus Photography: An Automated Tool for Detection and Grading of Diabetic Retinopathy.基于眼底照相的糖尿病视网膜病变检测和分期的人工智能算法验证:一种用于糖尿病视网膜病变检测和分级的自动化工具。
Middle East Afr J Ophthalmol. 2021 Sep 25;28(2):81-86. doi: 10.4103/meajo.meajo_406_20. eCollection 2021 Apr-Jun.
6
Automated diabetic retinopathy detection with two different retinal imaging devices using artificial intelligence: a comparison study.使用人工智能通过两种不同视网膜成像设备进行糖尿病视网膜病变的自动检测:一项比较研究。
Graefes Arch Clin Exp Ophthalmol. 2020 Dec;258(12):2647-2654. doi: 10.1007/s00417-020-04853-y. Epub 2020 Sep 16.
7
Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening.深度学习图像评估软件 VeriSee™ 在糖尿病视网膜病变筛查中的应用。
J Formos Med Assoc. 2021 Jan;120(1 Pt 1):165-171. doi: 10.1016/j.jfma.2020.03.024. Epub 2020 Apr 16.
8
Validation of handheld fundus camera with mydriasis for retinal imaging of diabetic retinopathy screening in China: a prospective comparison study.中国散瞳手持式眼底相机用于糖尿病视网膜病变筛查视网膜成像的验证:一项前瞻性比较研究。
BMJ Open. 2020 Oct 29;10(10):e040196. doi: 10.1136/bmjopen-2020-040196.
9
Convolutional Neural Networks Accurately Identify Ungradable Images in a Diabetic Retinopathy Telemedicine Screening Program.卷积神经网络在糖尿病视网膜病变远程医疗筛查项目中准确识别不可分级图像。
Telemed J E Health. 2023 Sep;29(9):1349-1355. doi: 10.1089/tmj.2022.0357. Epub 2023 Feb 2.
10
Application of artificial intelligence-based dual-modality analysis combining fundus photography and optical coherence tomography in diabetic retinopathy screening in a community hospital.基于人工智能的眼底照相和光相干断层扫描双模态分析在社区医院糖尿病视网膜病变筛查中的应用。
Biomed Eng Online. 2022 Jul 20;21(1):47. doi: 10.1186/s12938-022-01018-2.

引用本文的文献

1
Artificial intelligence-based apps for screening and diagnosing diabetic retinopathy and common ocular disorders.用于筛查和诊断糖尿病视网膜病变及常见眼部疾病的人工智能应用程序。
World J Methodol. 2025 Dec 20;15(4):107166. doi: 10.5662/wjm.v15.i4.107166.
2
Diagnostic utility of artificial intelligence software through non-mydriatic digital retinography in the screening of diabetic retinopathy: an overview of reviews.人工智能软件通过免散瞳数字视网膜成像技术在糖尿病视网膜病变筛查中的诊断效用:综述概述
Eye (Lond). 2025 Apr 29. doi: 10.1038/s41433-025-03809-y.

本文引用的文献

1
Application of deep learning image assessment software VeriSee™ for diabetic retinopathy screening.深度学习图像评估软件 VeriSee™ 在糖尿病视网膜病变筛查中的应用。
J Formos Med Assoc. 2021 Jan;120(1 Pt 1):165-171. doi: 10.1016/j.jfma.2020.03.024. Epub 2020 Apr 16.
2
Deep learning in ophthalmology: The technical and clinical considerations.深度学习在眼科学中的技术和临床考虑。
Prog Retin Eye Res. 2019 Sep;72:100759. doi: 10.1016/j.preteyeres.2019.04.003. Epub 2019 Apr 29.
3
Deep Learning-Based Algorithms in Screening of Diabetic Retinopathy: A Systematic Review of Diagnostic Performance.
基于深度学习的算法在糖尿病视网膜病变筛查中的应用:诊断性能的系统评价
Ophthalmol Retina. 2019 Apr;3(4):294-304. doi: 10.1016/j.oret.2018.10.014. Epub 2018 Nov 3.
4
Diagnostic Accuracy of a Device for the Automated Detection of Diabetic Retinopathy in a Primary Care Setting.用于在初级保健环境中自动检测糖尿病视网膜病变的设备的诊断准确性。
Diabetes Care. 2019 Apr;42(4):651-656. doi: 10.2337/dc18-0148. Epub 2019 Feb 14.
5
Artificial intelligence and deep learning in ophthalmology.人工智能和深度学习在眼科学中的应用。
Br J Ophthalmol. 2019 Feb;103(2):167-175. doi: 10.1136/bjophthalmol-2018-313173. Epub 2018 Oct 25.
6
Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes.使用来自多民族糖尿病患者群体的视网膜图像开发并验证用于糖尿病视网膜病变及相关眼病的深度学习系统
JAMA. 2017 Dec 12;318(22):2211-2223. doi: 10.1001/jama.2017.18152.
7
Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System.在霍伦糖尿病护理系统中使用IDx-DR设备对可转诊糖尿病视网膜病变进行自动筛查的验证。
Acta Ophthalmol. 2018 Feb;96(1):63-68. doi: 10.1111/aos.13613. Epub 2017 Nov 27.
8
Automated Identification of Diabetic Retinopathy Using Deep Learning.基于深度学习的糖尿病视网膜病变自动识别。
Ophthalmology. 2017 Jul;124(7):962-969. doi: 10.1016/j.ophtha.2017.02.008. Epub 2017 Mar 27.
9
Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders.自动化糖尿病视网膜病变图像评估软件:与人工分级相比的诊断准确性和成本效益。
Ophthalmology. 2017 Mar;124(3):343-351. doi: 10.1016/j.ophtha.2016.11.014. Epub 2016 Dec 23.
10
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.深度学习算法在视网膜眼底照片糖尿病视网膜病变检测中的开发与验证。
JAMA. 2016 Dec 13;316(22):2402-2410. doi: 10.1001/jama.2016.17216.