Pay attention to the application of artificial intelligence in constructing a three-tier screening and diagnosis-treatment system for ocular fundus diseases

doi:10.3877/cma.j.issn.2095-2007.2025.03.001

Abstract

Abstract:

In the face of the high prevalence of fundus diseases and the insufficient grassroots diagnostic resources, artificial intelligence (AI) is bringing transformative changes to the three-tiered diagnostic screening system. AI-based fundus imaging screening leverages automated analysis techniques to enhance the efficiency and accuracy of grassroots screening. Remote image interpretation, powered by AI, breaks geographical barriers and facilitates the sharing of medical resources. Additionally, the AI-assisted referral mechanism optimizes patient triage through intelligent assessment. These three components synergistically construct an intelligent diagnostic and treatment loop, offering new pathways to improve the prevention and treatment of fundus diseases and promote the implementation of tiered medical care. However, it is important to note that AI technology still faces challenges in clinical validation and data security, which urgently need to explore solutions.

Key words: Fundus diseases, Three-tier diagnosis and treatment, Artificial intelligence, Telemedicine reading, Referral

Huan Chen, Menghan Li, Weihong Yu. Pay attention to the application of artificial intelligence in constructing a three-tier screening and diagnosis-treatment system for ocular fundus diseases[J]. Chinese Journal of Ophthalmologic Medicine(Electronic Edition), 2025, 15(03): 129-134.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhykyxzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-2007.2025.03.001

https://zhykyxzz.cma-cmc.com.cn/EN/Y2025/V15/I03/129

References 52

[1]	GBD 2019 Blindness and Vision Impairment Collaborators Vision Loss Expert Group of the Global Burden of Disease Study. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020[J]. Lancet Glob Health, 2021, 9(2): 144-160.
[2]	Zhou C, Li S, Ye L, et al. Visual impairment and blindness caused by retinal diseases: A nationwide register－based study[J]. J Glob Health, 2023, 13: 04126.
[3]	Hao Z, Xu R, Huang X, et al. Application and observation of artificial intelligence in clinical practice of fundus screening for diabetic retinopathy with non－mydriatic fundus photography[J]. Ther Adv Chronic Dis, 2022, 13: 20406223221097335.
[4]	卫新. 国家卫生健康委发布中国眼健康白皮书[J]. 中国卫生画报，2020,29(6) :52-53.
[5]	Redd TK, Campbell JP, Brown JM, et al. Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity[J]. Br J Ophthalmol, 2019, 103: 580-584
[6]	Cleveland SD, Baker MJ, Erdman AG, et al. Current and future directions for the use of handheld. fundus cameras in telehealth[J]. Expert review of medical devices, 2025, 30:1-9
[7]	Rajalakshmi R, Prathiba V, Arulmalar S, et al. Review of retinal cameras for global coverage of diabetic retinopathy screening[J]. Eye (London, England) 2021, 35(1): 162-172
[8]	Lin D, Xiong J, Liu C, et al. Application of Comprehensive Artificial intelligence Retinal Expert (CARE) system[J]. Lancet Digit Health 2021, 3(8): 486-495.
[9]	Zedan MJM, Zulkifley MA, Ibrahim AA, et al. Automated Glaucoma Screening and Diagnosis Based on Retinal Fundus Images Using Deep Learning Approaches: A Comprehensive Review[J]. Diagnostics (Basel), 2023, 13(13): 2180.
[10]	Madduri VK, Rao BS. Detection and diagnosis of diabetic eye diseases using two phase transfer learning approach[J]. Peer J Comput Sci, 2024, 10: 2135.
[11]	Dai L, Wu L, Li H, et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum[J]. Nature communications, 2021, 12(1): 3242.
[12]	Zou Y, Wang Y, Kong X, et al. Deep Learner System Based on Focal Color Retinal Fundus Images to Assist in Diagnosis[J]. Diagnostics (Basel), 2023, 13(18): 2985.
[13]	Xu Y, Wang Y, Liu B, et al. The diagnostic accuracy of an. intelligent and automated fundus disease image assessment system with lesion quantitative function (SmartEye) in diabetic patients[J]. BMC Ophthalmol, 2019, 19(1): 184.
[14]	Gegundez ME, Marin D, Ponte B, et al. A tool for automated diabetic retinopathy pre－screening based on retinal image computer analysis[J]. Comput Biol Med, 2017, 88: 100-109.
[15]	Al－Jarrah MA, Shatnawi H. Non－proliferative diabetic retinopathy symptoms detection and. classification using neural network[J]. J Med Eng Technol, 2017, 41(6): 498-505.
[16]	Cao S, Zhang R, Jiang A, et al. Application effect of an artificial intelligence－based fundus screening system[J]. Biomedical engineering online, 2023, 22(1): 38.
[17]	Midena E, Frizziero L, Torresin T, et al. Optical coherence tomography and color fundus photography in the screening of age－related macular degeneration[J]. PLoS One, 2020, 15(8): 0237352.
[18]	Midena E, Frizziero L, Midena G, et al. Intraocular fluid biomarkers (liquid biopsy) in human diabetic retinopathy[J]. Graefes Arch Clin Exp Ophthalmol, 2021, 259(12): 3549-3560.
[19]	Lv B, Li S, Liu Y, et al. Development and Validation of an Explainable Artificial Intelligence Framework for Macular Disease Diagnosis Based on Optical Coherence Tomography Images[J]. Retina, 2022, 42(3): 456-464.
[20]	Chen X, Xue Y, Wu X, et al. Deep Learning－Based System for Disease Screening and Pathologic Region Detection From Optical Coherence Tomography Images[J]. Transl Vis Sci Technol, 2023, 12(1): 29.
[21]	Liu R, Li Q, Xu F, et al. Application of artificial intelligence－based dual－modality analysis combining fundus photography and optical coherence tomography in diabetic retinopathy screening in a community hospital[J]. Biomedical engineering online, 2022, 21(1): 47.
[22]	Wang M, Zhang X, Li D, et al. The potential of artificial intelligence reading label system on the training of ophthalmologists in retinal diseases[J]. BMC Med Educ, 2025, 25(1): 503.
[23]	Reiter GS, Mai J, Riedl S, et al. AI in the clinical management of GA: A novel therapeutic universe requires novel tools[J]. Prog Retin Eye Res, 2024, 103: 101305.
[24]	Mantel I, Lasagni Vitar RM, De Zanet S. Modeling pegcetacoplan treatment effect for atrophic age－related macular degeneration with AI－based progression prediction[J]. Int J Retina Vitreous, 2025, 11(1): 14.
[25]	Enzendorfer ML, Schmidt－Erfurth U. Artificial intelligence for geographic atrophy: pearls and pitfalls[J]. Curr Opin Ophthalmol, 2024, 35(6): 455-462.
[26]	Vairetti C, Maldonado S, Cuitino L, et al. Interpretable multimodal classification for age－related macular degeneration diagnosis[J]. PLoS One, 2024, 19(11): 0311811.
[27]	Gu C, Wang Y, Jiang Y, et al. Application of artificial intelligence system for screening multiple fundus diseases in Chinese primary healthcare settings[J]. Br J Ophthalmol, 2024, 108(3): 424-431.
[28]	Li B, Chen H, Zhang B, et al. Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography[J]. Br J Ophthalmol, 2022, 106(8): 1079-1086.
[29]	Cen LP, Ji J, Lin JW, et al. Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks[J]. Nature communications, 2021, 12(1): 4828.
[30]	Banerjee R, Mujib R, Sanyal P, et al. Pan－Ret: a semi－supervised framework for scalable detection of pan－retinal diseases[J]. Med Biol Eng Comput, 2025, 63(4): 959-974.
[31]	Lin PK, Chiu YH, Huang CJ, et al. PADAr: physician－oriented artificial intelligence－facilitating diagnosis aid for retinal diseases[J]. J Med Imaging (Bellingham), 2022, 9(4): 044501.
[32]	Almotiri J, Elleithy K, Elleithy A. A Multi－Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding[J]. IEEE J Transl Eng Health Med, 2018, 6: 3800123.
[33]	Shen Z, Fu H, Shen J, et al. Modeling and Enhancing Low－Quality Retinal Fundus Images[J]. IEEE Trans Med Imaging, 2021, 40(3): 996-1006.
[34]	Zhang W, Zhao X, Chen Y, et al. DeepUWF: An Automated Ultra－Wide－Field Fundus Screening System via Deep Learning[J]. IEEE J Biomed Health Inform, 2021, 25(8): 2988-2996.
[35]	Liu Y, Xie H, Zhao X, et al. Automated detection of nine infantile fundus diseases and conditions in retinal images using a deep learning system[J]. EPMA J, 2024, 15(1): 39-51.
[36]	Mvoulana A, Kachouri R, Akil M. Fully automated method for glaucoma screening using robust optic nerve head detection and unsupervised segmentation based cup－to－disc ratio computation in retinal fundus images[J]. Comput Med Imaging Graph, 2019, 77: 101643.
[37]	Maheshwari S, Kanhangad V, Pachori RB, et al. Automated glaucoma diagnosis using bit－plane slicing and local binary pattern techniques[J]. Comput Biol Med, 2019, 105: 72-80.
[38]	Muramatsu C. Diagnosis of Glaucoma on Retinal Fundus Images Using Deep Learning: Detection of Nerve Fiber Layer Defect and Optic Disc Analysis[J]. Adv Exp Med Biol, 2020, 1213: 121-132.
[39]	Son J, Shin JY, Kong ST, et al. An interpretable and interactive deep learning algorithm for a clinically applicable retinal fundus diagnosis system by modelling finding－disease relationship[J]. Sci Rep, 2023, 13(1): 5934.
[40]	Gao M, Jiang H, Zhu L, et al. Discriminative ensemble meta－learning with co－regularization for rare fundus diseases diagnosis[J]. Medical image analysis, 2023, 89: 102884.
[41]	Tun YZ, Aimmanee P. A Complete Review of Automatic Detection, Segmentation, and Quantification of Neovascularization in Optical Coherence Tomography Angiography Images[J]. Diagnostics (Basel), 2023, 13(22): 3407.
[42]	Ardiyanto I, Nugroho HA, Buana RLB. Deep learning－based Diabetic Retinopathy assessment on embedded system. Conference proceedings[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2017, 2017: 1760-1763.
[43]	Kui X, Hai Z, Zou B, et al. DFC－Net: a dual－path frequency－domain cross－attention fusion network for retinal image quality assessment[J]. Biomedical optics express, 2024, 15(11): 6399-6415.
[44]	Wangweera C, Zanini P. Comparison review of image classification techniques for early diagnosis of diabetic retinopathy[J]. Biomed Phys Eng Express, 2024, 10(6): 10.
[45]	Wu X, Wu Y, Tu Z, et al. Cost－effectiveness and cost－utility of a digital technology－driven hierarchical healthcare screening pattern in China[J]. Nat Commun, 2024, 15(1): 3650.
[46]	Betzler BK, Rim TH, Sabanayagam C, et al. Artificial Intelligence in Predicting Systemic Parameters and Diseases From Ophthalmic Imaging[J]. Front Digit Health, 2022, 4: 889445.
[47]	Jiang X, Xie M, Ma L, et al. International publication trends in the application of artificial intelligence in ophthalmology research: an updated bibliometric analysis[J]. Ann Transl Med, 2023, 11(5): 219.
[48]	Tan YY, Kang HG, Lee CJ, et al. Correction: Prognostic potentials of AI in ophthalmology: systemic disease forecasting via retinal imaging[J]. Eye Vis (Lond), 2024, 11(1): 33.
[49]	Wei Q, Chi L, Li M, et al. Practical Applications of Artificial Intelligence Diagnostic Systems in Fundus Retinal Disease Screening[J]. Int J Gen Med, 2025, 18: 1173-1180.
[50]	Muqri H, Shrivastava A, Muhtadi R, et al. The Cost－Effectiveness of a Telemedicine Screening Program for Diabetic Retinopathy in New York City[J]. Clin Ophthalmol, 2022, 16: 1505-1512.
[51]	Weinreb RN, Lee AY, Baxter SL, et al. Application of Artificial Intelligence to Deliver Healthcare From the Eye[J]. JAMA Ophthalmol, 2025, 143(6): 529-535.
[52]	Vought R, Vought V, Szirth B, et al. Future direction for the deployment of deep learning artificial intelligence[J]. Saudi J Ophthalmol, 2023, 37(3): 193-199.

Please choose a citation manager

Content to export