人工智能与深度学习在眼科中的应用：现状与未来展望。
Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives.
作者信息
Jin Kai, Ye Juan
机构信息
Department of Ophthalmology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China.
出版信息
Adv Ophthalmol Pract Res. 2022 Aug 24;2(3):100078. doi: 10.1016/j.aopr.2022.100078. eCollection 2022 Nov-Dec.
Abstract
BACKGROUND
The ophthalmology field was among the first to adopt artificial intelligence (AI) in medicine. The availability of digitized ocular images and substantial data have made deep learning (DL) a popular topic.
MAIN TEXT
At the moment, AI in ophthalmology is mostly used to improve disease diagnosis and assist decision-making aiming at ophthalmic diseases like diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), cataract and other anterior segment diseases. However, most of the AI systems developed to date are still in the experimental stages, with only a few having achieved clinical applications. There are a number of reasons for this phenomenon, including security, privacy, poor pervasiveness, trust and explainability concerns.
CONCLUSIONS
This review summarizes AI applications in ophthalmology, highlighting significant clinical considerations for adopting AI techniques and discussing the potential challenges and future directions.
摘要
背景
眼科领域是医学中最早采用人工智能（AI）的领域之一。数字化眼部图像的可用性和大量数据使深度学习（DL）成为一个热门话题。
正文
目前，眼科中的人工智能主要用于改善疾病诊断并协助针对糖尿病性视网膜病变（DR）、青光眼、年龄相关性黄斑变性（AMD）、白内障和其他眼前段疾病等眼科疾病进行决策。然而，迄今为止开发的大多数人工智能系统仍处于实验阶段，只有少数已实现临床应用。出现这种现象有多种原因，包括安全性、隐私性、普及性差、信任和可解释性问题。
结论
本综述总结了人工智能在眼科中的应用，强调了采用人工智能技术的重要临床考虑因素，并讨论了潜在挑战和未来方向。
相似文献
1
Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives.人工智能与深度学习在眼科中的应用：现状与未来展望。
Adv Ophthalmol Pract Res. 2022 Aug 24;2(3):100078. doi: 10.1016/j.aopr.2022.100078. eCollection 2022 Nov-Dec.
2
Updates in deep learning research in ophthalmology.眼科深度学习研究的新进展。
Clin Sci (Lond). 2021 Oct 29;135(20):2357-2376. doi: 10.1042/CS20210207.
3
Promising Artificial Intelligence-Machine Learning-Deep Learning Algorithms in Ophthalmology.人工智能-机器学习-深度学习算法在眼科学中的应用前景。
Asia Pac J Ophthalmol (Phila). 2019 May-Jun;8(3):264-272. doi: 10.22608/APO.2018479. Epub 2019 May 31.
4
Insights into the growing popularity of artificial intelligence in ophthalmology.洞察人工智能在眼科学领域日益普及的原因。
Indian J Ophthalmol. 2020 Jul;68(7):1339-1346. doi: 10.4103/ijo.IJO_1754_19.
5
From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.从数据到部署：眼科成像人工智能相关的年龄相关性黄斑变性协作社区路线图。
Ophthalmology. 2022 May;129(5):e43-e59. doi: 10.1016/j.ophtha.2022.01.002. Epub 2022 Jan 10.
6
Artificial Intelligence (AI) Applications for Age-Related Macular Degeneration (AMD) and Other Retinal Dystrophies.人工智能（AI）在年龄相关性黄斑变性（AMD）和其他视网膜营养不良中的应用。
Semin Ophthalmol. 2021 May 19;36(4):304-309. doi: 10.1080/08820538.2021.1896756. Epub 2021 Mar 25.
7
Artificial intelligence in ophthalmology.人工智能在眼科学中的应用。
Rom J Ophthalmol. 2023 Jul-Sep;67(3):207-213. doi: 10.22336/rjo.2023.37.
8
An overview of artificial intelligence in diabetic retinopathy and other ocular diseases.人工智能在糖尿病视网膜病变和其他眼部疾病中的应用概述。
Front Public Health. 2022 Oct 28;10:971943. doi: 10.3389/fpubh.2022.971943. eCollection 2022.
9
The upcoming role of Artificial Intelligence (AI) for retinal and glaucomatous diseases.人工智能（AI）在视网膜和青光眼疾病中的未来作用。
J Optom. 2022;15 Suppl 1(Suppl 1):S50-S57. doi: 10.1016/j.optom.2022.08.001. Epub 2022 Oct 8.
10
Artificial Intelligence in Ophthalmology - Status Quo and Future Perspectives.眼科中的人工智能——现状与未来展望
Semin Ophthalmol. 2023 Apr;38(3):226-237. doi: 10.1080/08820538.2022.2139625. Epub 2022 Nov 10.
引用本文的文献
1
A Generalized and Interpretable Multi-Label Multi-Disease Screening System for Ocular Anterior Segment Disease Detection.一种用于眼前节疾病检测的广义可解释多标签多病种筛查系统。
Ophthalmol Sci. 2025 Jul 12;5(6):100883. doi: 10.1016/j.xops.2025.100883. eCollection 2025 Nov-Dec.
2
Advances in machine learning for ABCA4-related retinopathy: segmentation and phenotyping.用于ABCA4相关视网膜病变的机器学习进展：分割与表型分析。
Int Ophthalmol. 2025 Jul 23;45(1):314. doi: 10.1007/s10792-025-03690-4.
3
Artificial intelligence in ophthalmology: a bibliometric analysis of the 5-year trends in literature.眼科中的人工智能：文献五年趋势的文献计量分析
Front Med (Lausanne). 2025 Jul 1;12:1580583. doi: 10.3389/fmed.2025.1580583. eCollection 2025.
4
Generative artificial intelligence for fundus fluorescein angiography interpretation and human expert evaluation.用于眼底荧光血管造影解读和人类专家评估的生成式人工智能。
NPJ Digit Med. 2025 Jul 2;8(1):396. doi: 10.1038/s41746-025-01759-z.
5
Diabetic Retinopathy Assessment through Multitask Learning Approach on Heterogeneous Fundus Image Datasets.基于异构眼底图像数据集的多任务学习方法进行糖尿病视网膜病变评估
Ophthalmol Sci. 2025 Mar 11;5(5):100755. doi: 10.1016/j.xops.2025.100755. eCollection 2025 Sep-Oct.
6
MCOA: A Comprehensive Multimodal Dataset for Advancing Deep Learning in Corneal Opacity Assessment.MCOA：用于推进角膜混浊评估中深度学习的综合多模态数据集。
Sci Data. 2025 May 30;12(1):911. doi: 10.1038/s41597-025-05205-3.
7
The march to harmonized imaging standards for retinal imaging.迈向视网膜成像统一标准的征程。
Prog Retin Eye Res. 2025 Jul;107:101363. doi: 10.1016/j.preteyeres.2025.101363. Epub 2025 May 11.
8
Lights and Shadows on Artificial Intelligence in Glaucoma: Transforming Screening, Monitoring, and Prognosis.青光眼人工智能领域的机遇与挑战：变革筛查、监测与预后
J Clin Med. 2025 Mar 21;14(7):2139. doi: 10.3390/jcm14072139.
9
Advancing Diabetic Retinopathy Screening: A Systematic Review of Artificial Intelligence and Optical Coherence Tomography Angiography Innovations.糖尿病视网膜病变筛查进展：人工智能与光学相干断层扫描血管造影创新的系统评价
Diagnostics (Basel). 2025 Mar 15;15(6):737. doi: 10.3390/diagnostics15060737.
10
Radiomic Feature Extraction from OCT Angiography of Idiopathic Epiretinal Membranes and Correlation with Visual Acuity: A Pilot Study.特发性视网膜前膜光学相干断层扫描血管造影的影像组学特征提取及其与视力的相关性：一项初步研究
Ophthalmol Sci. 2025 Jan 21;5(3):100716. doi: 10.1016/j.xops.2025.100716. eCollection 2025 May-Jun.
本文引用的文献
1
Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI.人工智能驱动的决策支持系统早期临床评估报告指南：DECIDE-AI。
Nat Med. 2022 May;28(5):924-933. doi: 10.1038/s41591-022-01772-9. Epub 2022 May 18.
2
A Structure-Related Fine-Grained Deep Learning System With Diversity Data for Universal Glaucoma Visual Field Grading.一种具有多样化数据的结构相关细粒度深度学习系统用于通用青光眼视野分级
Front Med (Lausanne). 2022 Mar 17;9:832920. doi: 10.3389/fmed.2022.832920. eCollection 2022.
3
End-to-end diabetic retinopathy grading based on fundus fluorescein angiography images using deep learning.基于深度学习的眼底荧光血管造影图像的端到端糖尿病视网膜病变分级
Graefes Arch Clin Exp Ophthalmol. 2022 May;260(5):1663-1673. doi: 10.1007/s00417-021-05503-7. Epub 2022 Jan 23.
4
From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.从数据到部署：眼科成像人工智能相关的年龄相关性黄斑变性协作社区路线图。
Ophthalmology. 2022 May;129(5):e43-e59. doi: 10.1016/j.ophtha.2022.01.002. Epub 2022 Jan 10.
5
Detecting Anomalies in Retinal Diseases Using Generative, Discriminative, and Self-supervised Deep Learning.使用生成式、判别式和自监督深度学习技术检测视网膜疾病中的异常。
JAMA Ophthalmol. 2022 Feb 1;140(2):185-189. doi: 10.1001/jamaophthalmol.2021.5557.
6
Trustworthy AI: Closing the gap between development and integration of AI systems in ophthalmic practice.可信人工智能：弥合眼科实践中人工智能系统开发与集成之间的差距。
Prog Retin Eye Res. 2022 Sep;90:101034. doi: 10.1016/j.preteyeres.2021.101034. Epub 2021 Dec 10.
7
Automatic Screening and Identifying Myopic Maculopathy on Optical Coherence Tomography Images Using Deep Learning.利用深度学习技术对光学相干断层扫描图像进行自动筛查和识别近视性黄斑病变。
Transl Vis Sci Technol. 2021 Nov 1;10(13):10. doi: 10.1167/tvst.10.13.10.
8
Clinically relevant deep learning for detection and quantification of geographic atrophy from optical coherence tomography: a model development and external validation study.基于深度学习的光学相干断层扫描检测与定量分析脉络膜新生血管的临床研究：模型的建立和外部验证。
Lancet Digit Health. 2021 Oct;3(10):e665-e675. doi: 10.1016/S2589-7500(21)00134-5. Epub 2021 Sep 8.
9
Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age-related macular degeneration.用于识别年龄相关性黄斑变性中脉络膜新生血管活性的具有特征级融合的多模态深度学习
Acta Ophthalmol. 2022 Mar;100(2):e512-e520. doi: 10.1111/aos.14928. Epub 2021 Jun 23.
10
Preventing corneal blindness caused by keratitis using artificial intelligence.利用人工智能预防角膜炎导致的角膜盲。
Nat Commun. 2021 Jun 18;12(1):3738. doi: 10.1038/s41467-021-24116-6.
Zotero 插件