Mutua Elizabeth Ndunge, Kasamani Bernard Shibwabo, Reich Christoph
School of Computing & Engineering Sciences, Strathmore University, Nairobi 00100, Kenya.
Institute for Data Science, Cloud Computing and IT Security, Furtwangen University, Furtwangen 78120, Germany.
Int J Ophthalmol. 2025 Aug 18;18(8):1594-1602. doi: 10.18240/ijo.2025.08.23. eCollection 2025.
To review the existing deep learning applications for diagnosing diabetic retinopathy and retinopathy of prematurity diseases, the available public retinal databases for the diseases and apply the International Journal of Medical Informatics (IJMEDI) checklist were assessed the quality of included studies; an in-depth literature search in Scopus, Web of Science, IEEE and ACM databases targeting articles from inception up to 31 January 2023 was done by two independent reviewers. In the review, 26 out of 1476 articles with a total of 36 models were included. Data size and model validation were found to be challenges for most studies. Deep learning models are gaining focus in the development of medical diagnosis tools and applications. However, there seems to be a critical issue with most of the studies being published, with some not including information about data sources and data sizes which is important for their performance verification.
为了回顾现有的用于诊断糖尿病视网膜病变和早产儿视网膜病变的深度学习应用、这些疾病可用的公共视网膜数据库，并应用《国际医学信息学杂志》（IJMEDI）清单评估纳入研究的质量；两名独立评审员对Scopus、Web of Science、IEEE和ACM数据库进行了深入的文献检索，检索时间从数据库创建到2023年1月31日，以查找相关文章。在此次综述中，1476篇文章中的26篇被纳入，共涉及36个模型。数据规模和模型验证被发现是大多数研究面临的挑战。深度学习模型在医学诊断工具和应用的开发中越来越受到关注。然而，大多数已发表的研究似乎存在一个关键问题，一些研究没有包含有关数据源和数据规模的信息，而这些信息对于其性能验证很重要。
