- Department of Ophthalmology, Nanjing University of Traditional Chinese Medicine, Nanjing 210029, China;
Xu Xinrong,
Email: yfy133@njucm.edu.cn
Diabetic retinopathy (DR) is a major cause of visual impairment among working-age populations. In recent years, artificial intelligence (AI) has demonstrated significant application value in DR diagnosis, leveraging core advantages such as high efficiency and low error rates. Currently, the technical system of AI in DR image diagnosis mainly includes links like image preprocessing, feature extraction, diverse algorithmic models, and dataset construction. In practical applications, AI models can achieve automated screening and grading diagnosis of DR images, enhance diagnostic efficiency by integrating multimodal technologies, and have been successfully applied to mobile devices; meanwhile, the development of explainable AI has further boosted the credibility of AI models. Currently, this field still faces challenges, including insufficient data quality and scale, limited model interpretability, inadequate clinical validation, ethical and privacy risks, and a lack of unified technical standards. In the future, with continuous technological breakthroughs and the establishment of standardized evaluation systems, the reliability and accessibility of AI in DR diagnosis will be further enhanced.
Copyright ? the editorial department of Chinese Journal of Ocular Fundus Diseases of West China Medical Publisher. All rights reserved
| 1. | Zago GT, Andre?o RV, Dorizzi B, et al. Diabetic retinopathy detection using red lesion localization and convolutional neural networks[J/OL]. Comput Biol Med, 2020, 116: 103537[2019-11-11]. https://pubmed.ncbi.nlm.nih.gov/31747632/. DOI: 10.1016/j.compbiomed.2019.103537. |
| 2. | International Diabetes Federation. IDF Diabetes Atlas, 11th ed[EB/OL]. (2025-03-16)[2053-09-01]. https://diabetesatlas.org. |
| 3. | 中華醫學會眼科學分會眼底病學組, 中國醫師協會眼科醫師分會眼底病學組. 我國糖尿病視網膜病變臨床診療指南(2022年)—基于循證醫學修訂[J]. 中華眼底病雜志, 2023, 39(2): 99-124. DOI: 10.3760/cma.j.cn511434-20230110-00018.Retinal Disease Group of Ophthalmology Branch, Chinese Medical Association, Retinal Disease Group of Ophthalmology Physicians Branch, Chinese Medical Doctor Association. Evidence-based guidelines for diagnosis and treatment of diabetic retinopathy in China (2022)[J]. Chin J Ocul Fundus Dis, 2023, 39(2): 99-124. DOI: 10.3760/cma.j.cn511434-20230110-00018. |
| 4. | 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/OL]. BMC Ophthalmol, 2019, 19(1): 184[2019-08-14]. https://pubmed.ncbi.nlm.nih.gov/31412800/. DOI: 10.1186/s12886-019-1196-9. |
| 5. | Van Craenendonck T, Elen B, Gerrits N, et al. Systematic comparison of heatmapping techniques in deep learning in the context of diabetic retinopathy lesion detection[J/OL]. Transl Vis Sci Technol, 2020, 9(2): 64[2020-12-29]. https://pubmed.ncbi.nlm.nih.gov/33403156/. DOI: 10.1167/tvst.9.2.64. |
| 6. | 《人工智能在OCTA圖像分析和眼部疾病診斷中的應用指南2024》專家組, 國際轉化醫學會眼科專業委員會, 中國醫藥教育協會眼科影像與智能醫療分會, 等. 人工智能在OCTA圖像分析和眼部疾病診斷中的應用指南(2024)[J]. 眼科新進展, 2024, 44(5): 337-345. DOI: 10.13389/j.cnki.rao.2024.0066.The expert group of "Guidelines for the Application of Artificial Intelligence in OCTA Image Analysis and Ocular Disease Diagnosis 2024", the Ophthalmology Professional Committee of the International Translational Medicine Society, the Ophthalmology Imaging and Intelligent Healthcare Branch of the China Medical Education Association, et al. Guidelines for the application of artificial intelligence in optical coherence tomography angiography image analysis and ocular disease diagnosis(2024)[J]. Rec Adv Ophthalmol, 2024, 44(5): 337-345. DOI: 10.13389/j.cnki.rao.2024.0066. |
| 7. | 趙學功. 基于眼底圖像的糖尿病誘發視網膜病變輔助診斷關鍵技術研究[D]. 成都: 電子科技大學, 2021.Zhao XG. Research on key technologies for auxiliary diagnosis of diabetic retinopathy based on fundus images[D]. Chengdu: University of Electronic Science and Technology of China, 2021. |
| 8. | Nandhini T. Rectal fundus image recognition using deep learning ensemble CNN models[J/OL]. Rec Adv Ophthalmol, 2025, 10(26): 690-702. DOI: 10.52783/jisem.v10i26s.4276. |
| 9. | van Grinsven MJ, van Ginneken B, Hoyng CB, et al. Fast convolutional neural network training using selective data sampling: application to hemorrhage detection in color fundus images[J]. IEEE Trans Med Imaging, 2016, 35(5): 1273-1284. DOI: 10.1109/TMI.2016.2526689. |
| 10. | Monemian M, Rabbani H. Detecting red-lesions from retinal fundus images using unique morphological features[J/OL]. Sci Rep, 2023, 13(1): 3487[2023-03-01]. https://pubmed.ncbi.nlm.nih.gov/36859429/. DOI: 10.1038/s41598-023-30459-5. |
| 11. | Chang MH, Chen CY, Yu CH, et al. Vessel segmentation and dirt/reflection detection for retinal fundus photographs. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France. New York: IEEE Press, 2022. |
| 12. | Sandhu HS, Elmogy M, Taher Sharafeldeen A, et al. Automated diagnosis of diabetic retinopathy using clinical biomarkers, optical coherence tomography, and optical coherence tomography angiography[J]. Am J Ophthalmol, 2020, 216: 201-206. DOI: 10.1016/j.ajo.2020.01.016. |
| 13. | Khojasteh P, Aliahmad B, Kumar DK. Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms[J/OL]. BMC Ophthalmol, 2018, 18(1): 288[2018-11-06]. https://pubmed.ncbi.nlm.nih.gov/30400869/. DOI: 10.1186/s12886-018-0954-4. |
| 14. | Saleh I, El-Den NN, Elsharkawy M, et al. AI-based methods for diagnosing and grading diabetic retinopathy: a comprehensive review[J/OL]. Artif Intell Med, 2025, 168: 103221[2025-07-19]. https://pubmed.ncbi.nlm.nih.gov/40706108/. DOI: 10.1016/j.artmed.2025.103221. |
| 15. | Vijayan M, Venkatakrishnan S. A regression-based approach to diabetic retinopathy diagnosis using efficientnet[J/OL]. Diagnostics (Basel), 2023, 13(4): 774[2023-02-17]. https://pubmed.ncbi.nlm.nih.gov/36832262/. DOI: 10.3390/diagnostics13040774. |
| 16. | Liu Z, Gao A, Sheng H, et al. Identification of diabetic retinopathy lesions in fundus images by integrating CNN and vision mamba models[J/OL]. PLoS One, 2025, 20(1): e0318264[2025-01-28]. https://pubmed.ncbi.nlm.nih.gov/39874303/. DOI: 10.1371/journal.pone.0318264. |
| 17. | Liu C, Wang W, Lian J, et al. Lesion classification and diabetic retinopathy grading by integrating softmax and pooling operators into vision transformer[J/OL]. Front Public Health, 2025, 12: 1442114[2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/39835306/. DOI: 10.3389/fpubh.2024.1442114. |
| 18. | Yang Y, Cai Z, Qiu S, et al. Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image[J/OL]. PLoS One, 2024, 19(3): e0299265[2024-03-06]. https://pubmed.ncbi.nlm.nih.gov/38446810/. DOI: 10.1371/journal.pone.0299265. |
| 19. | Li J, Guan Z, Wang J, et al. Integrated image-based deep learning and language models for primary diabetes care[J]. Nat Med, 2024, 30(10): 2886-2896. DOI: 10.1038/s41591-024-03139-8. |
| 20. | Porwal P, Pachade S, Kamble R, et al. Indian Diabetic Retinopathy Image Dataset (IDRiD): a database for diabetic retinopathy screening research[J/OL]. Data, 2018, 3(3): 25[2018-06-05]. https://doi.org/10.3390/data3030025. |
| 21. | Wu C, Restrepo D, Nakayama LF, et al. A portable retina fundus photos dataset for clinical, demographic, and diabetic retinopathy prediction[J/OL]. Sci Data, 2025, 12(1): 323[2025-02-22]. https://pubmed.ncbi.nlm.nih.gov/39987104/. DOI: 10.1038/s41597-025-04627-3. |
| 22. | Panchal S, Naik A, Kokare M, et al. Retinal fundus multi-disease image dataset (RFMiD) 2.0: a dataset of frequently and rarely identified diseases[J/OL]. ResearchGate, 2025, 8(2): 9[2025-10-02]. https://doi.org/10.3390/data8020029. DOI:10.3390/data8020029. |
| 23. | Pachade S, Porwal P, Kokare M, et al. RFMiD: retinal image analysis for multi-disease detection challenge[J/OL]. Med Image Anal, 2025, 99: 103365[2024-10-09]. https://pubmed.ncbi.nlm.nih.gov/39395210/. DOI: 10.1016/j.media.2024.103365. |
| 24. | Zhou Y, Wang B, Huang L, et al. A benchmark for studying diabetic retinopathy: segmentation, grading, and transferability[J]. IEEE Trans Med Imaging, 2021, 40(3): 818-828. DOI: 10.1109/tmi.2020.3037771. |
| 25. | Decencière E, Zhang X, Cazuguel G, et al. Feedback on a publicly distributed image database: the messidor database[J]. Image Anal Stereol, 2014, 33(3): 231-234. DOI: 10.5566/ias.1155. |
| 26. | Kauppi T, Pietil? J, Kalesnykiene V, et al. The DIARETDB1 diabetic retinopathy database and evaluation protocol[C/OL]//Proceedings of the British Machine Vision Conference. Warwick, UK: British Machine Vision Association, 2007: 15.1-15.10[2025-10-02]. http://www.bmva.org/bmvc/2007/papers/paper-60.html. DOI: 10.5244/C.21.15.2007. |
| 27. | Rahim SS, Palade V, Shuttleworth J, et al. Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing[J]. Brain Informatics, 2016, 3(4): 249-267. DOI: 10.1007/s40708-016-0045-3. |
| 28. | Chaudhary PK, Pachori RB. Automatic diagnosis of different grades of diabetic retinopathy and diabetic macular edema using 2-D-FBSE-FAWT[J]. IEEE Trans Instrum Meas, 2022, 71: 1-9. DOI: 10.1109/TIM.2022.3140437. |
| 29. | Wang S, Wang X, Hu Y, et al. Diabetic retinopathy diagnosis using multichannel generative adversarial network with semisupervision[J]. IEEE Trans Autom Sci Eng, 2021, 18(2): 574-585. DOI: 10.1109/TASE.2020.2981637. |
| 30. | Bilal A, Zhu L, Deng A, et al. AI-based automatic detection and classification of diabetic retinopathy using U-Net and deep learning[J/OL]. Symmetry, 2022, 14: 1427[2022-06-14]. https://doi.org/10.3390/sym14071427. |
| 31. | Li F, Pan J, Yang D, et al. A multicenter clinical study of the automated fundus screening algorithm[J/OL]. Transl Vis Sci Technol, 2022, 11(7): 22[2022-07-08]. https://pubmed.ncbi.nlm.nih.gov/35881410/. DOI: 10.1167/tvst.11.7.22. |
| 32. | Yao L, Cao CY, Yu GX, et al. Screening and evaluation of diabetic retinopathy via a deep learning network model: a prospective study[J]. World J Diabetes, 2024, 15(12): 2302-2310. DOI: 10.4239/wjd.v15.i12.2302. |
| 33. | Parthasharathi GU, Kumar KV, Premnivas R, et al. Diabetic retinopathy detection using machine learning[J]. J Innov Image Process, 2022, 1: 173-178. DOI: 10.36548/jiip.2022.1.003. |
| 34. | Lian J, Liu T. Lesion identification in fundus images via convolutional neural network-vision transformer[J/OL]. Biomed Signal Process Control, 2024, 88: 105607[2024-02-01]. https://doi.org/10.1016/j.bspc.2023.105607. DOI: 10.1016/j.bspc.2023.105607. |
| 35. | Asia AO, Zhu CZ, Althubiti SA, et al. Detection of diabetic retinopathy in retinal fundus images using CNN classification models[J/OL]. Electronics, 2022, 11(17): 2740[2022-08-05]. https://doi.org/10.3390/electronics11172740. |
| 36. | Li, F, Wang Y, Xu T, et al. Deep learning-based automated detection for diabetic retinopathy and diabetic macular oedema in retinal fundus photographs[J]. Eye, 2022, 36: 1433-1441. DOI: 10.1038/s41433-021-01552-8. |
| 37. | Oh K, Kang HM, Leem D, et al. Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images[J/OL]. Sci Rep, 2021, 11(1): 1897[2021-01-21]. https://pubmed.ncbi.nlm.nih.gov/33479406/. DOI: 10.1038/s41598-021-81539-3. |
| 38. | Ryu G, Lee K, Park D, et al. A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography[J/OL]. Sci Rep, 2021, 11(1): 23024[2021-11-26]. https://pubmed.ncbi.nlm.nih.gov/34837030/. DOI: 10.1038/s41598-021-02479-6. |
| 39. | Mehedi M, Mohammed FA, Zhang Y. A convolutional neural network model using weighted loss function to detect diabetic retinopathy[J]. ACM Trans Multimedia Comput, 2022, 40: 1-16. |
| 40. | Karkera T, Adak C, Chattopadhyay S, et al. Detecting severity of diabetic retinopathy from fundus images: a transformer network-based review[J/OL]. Neurocomputing, 2024, 597: 127991[2024-09-07]. https://doi.org/10.1016/j.neucom.2024.127991. DOI: 10.1016/j.neucom.2024.127991. |
| 41. | Jabbar MK, Yan J, Xu H, et al. Transfer learning-based model for diabetic retinopathy diagnosis using retinal images[J/OL]. Brain Sciences, 2022, 12(5): 535[2022-04-22]. https://doi.org/10.3390/brainsci12050535. |
| 42. | Wu J, Hu R, Xiao Z, et al. Vision transformer-based recognition of diabetic retinopathy grade[J]. Med Phys, 2021, 48(12): 7850-7863. DOI: 10.1002/mp.15312. |
| 43. | Chilukoti SV, Maida AS, Hei XL. Diabetic retinopathy detection using transfer learning from pre-trained convolutional neural network models[J/OL]. IEEE J Biomed. Health Inform, 2022, 2022: 10[2025-10-02]. https://doi.org/10.36227/techrxiv.18515357.v1. DOI:10.36227/techrxiv.18515357.v1. |
| 44. | Muthusamy D, Palani P. Deep learning model using classification for diabetic retinopathy detection: an overview[J]. Artif Intell Rev, 2024, 57(7): 185-205. DOI: 10.1007/s10462-024-10806-2. |
| 45. | Karthikeyan S, Selva SS, Sreeja GG, et al. Multimodal approach for diabetic retinopathy detection using deep learning and clinical data fusion[C]. Proceedings of the 2024 9th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 2024. New York: IEEE Press, 2024. |
| 46. | Wijesinghe I, Gamage C, Perera I, et al. A smart telemedicine system with deep learning to manage diabetic retinopathy and foot ulcers[C]. Proceedings of the 2019 Moratuwa Engineering Research Conference (MERCon), Moratuwa, Sri Lanka, 2019. New York: IEEE Press, 2019. |
| 47. | Ayoub S, Khan MA, Jadhav VP, et al. Minimized computations of deep learning technique for early diagnosis of diabetic retinopathy using IoT-based medical devices[J/OL]. Comput Intell Neurosci, 2022, 2022: 7040141[2022-09-14]. https://pubmed.ncbi.nlm.nih.gov/36156979/. DOI: 10.1155/2022/7040141. |
| 48. | Rajalakshmi R, Subashini R, Anjana RM, et al. Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence[J]. Eye (Lond), 2018, 32(6): 1138-1144. DOI: 10.1038/s41433-018-0064-9. |
| 49. | Niu Y, Gu L, Zhao Y, et al. Explainable diabetic retinopathy detection and retinal image generation[J]. IEEE J Biomed Health Inform, 2022, 26(1): 44-55. DOI: 10.1109/jbhi.2021.3110593. |
| 50. | Ali R, Khan FG, Rehman ZU, et al. Enhanced diabetic retinopathy detection: an explainable semi-supervised approach using contrastive learning[J]. IEEE J Biomed Health Inform, 2025, 2025: 1-14. DOI: 10.1109/jbhi.2025.3551696. |
| 51. | Shahzad T, Saleem M, Farooq MS, et al. Developing a transparent diagnosis model for diabetic retinopathy using explainable AI[J]. IEEE Access, 2024, 12: 149700-149709. DOI: 10.1109/ACCESS.2024.3475550. |
| 52. | Ortigossa ES, Gon?alves T, Nonato LG. EXplainable artificial intelligence (XAI)—from theory to methods and applications[J]. IEEE Access, 2024, 12: 80799-80846. DOI: 10.1109/ACCESS.2024.3409843. |
| 53. | Amparore E, Perotti A, Bajardi P. To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods[J/OL]. PeerJ Comput Sci, 2021, 7: e479[2021-04-16]. https://pubmed.ncbi.nlm.nih.gov/33977131/. DOI: 10.7717/peerj-cs.479. |
| 54. | Anderson M, Sadiq S, Nahaboo Solim M, et al. Biomedical data annotation: an OCT imaging case study[J/OL]. J Ophthalmol, 2023, 2023: 5747010[2023-08-22]. https://pubmed.ncbi.nlm.nih.gov/37650051/. DOI: 10.1155/2023/5747010. |
| 55. | Aswal S, Ahuja NJ, Mehra R. Handling imbalance and limited data in thyroid ultrasound and diabetic retinopathy datasets using discrete levy flights grey wolf optimizer based random forest for robust medical data classification[J/OL]. ACM Trans Asian Low-Resour Lang Inf Process, 2024, 2024: e1-e25[2024-01-31]. https://doi.org/10.1145/3648363. DOI: 10.1145/3648363. |
| 56. | Liu R, Hall LO, Bowyer KW, et al. Synthetic minority image over-sampling technique: how to improve AUC for glioblastoma patient survival prediction[C]. Proceedings of the 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, AB, Canada, 2017. New York: IEEE Press, 2017. |
| 57. | Zhao R, Chen X, Chen Z, et al. Diagnosing glaucoma on imbalanced data with self-ensemble dual-curriculum learning[J/OL]. Med Image Anal, 2022, 75: 102295[2021-10-29]. https://pubmed.ncbi.nlm.nih.gov/34753022/. DOI: 10.1016/j.media.2021.102295. |
| 58. | Xie Y, Wan Q, Xie H, et al. Fundus image-label pairs synthesis and retinopathy screening via GANs with class-imbalanced semi-supervised learning[J]. IEEE Trans Med Imaging, 2023, 42(9): 2714-2725. DOI: 10.1109/TMI.2023.3263216. |
| 59. | Lee D, Yoon SN. Application of artificial intelligence-based technologies in the healthcare industry: opportunities and challenges[J/OL]. Int J Environ Res Public Health, 2021, 18(1): 271[2021-10-29]. https://pubmed.ncbi.nlm.nih.gov/34753022/. DOI: 10.3390/ijerph18010271. |
| 60. | 張漢成. 健康醫療數據共享的現實困境與合規因應[J]. 醫學與哲學, 2024, 45(17): 52-57. DOI: 10.12014/j.issn.1002-0772.2024.17.11.Zhang HC. Practical dilemmas and compliance responses in healthcare data sharing[J]. Medicine & Philosophy, 2024, 45(17): 52-57. DOI: 10.12014/j.issn.1002-0772.2024.17.11. |
| 61. | Mudgal SK, Agarwal R, Chaturvedi J, et al. Real-world application, challenges and implication of artificial intelligence in healthcare: an essay[J/OL]. Pan Afr Med J, 2022, 43: 3[2022-09-02]. https://pubmed.ncbi.nlm.nih.gov/36284890/. DOI: 10.11604/pamj.2022.43.3.33384. |
- 1. Zago GT, Andre?o RV, Dorizzi B, et al. Diabetic retinopathy detection using red lesion localization and convolutional neural networks[J/OL]. Comput Biol Med, 2020, 116: 103537[2019-11-11]. https://pubmed.ncbi.nlm.nih.gov/31747632/. DOI: 10.1016/j.compbiomed.2019.103537.
- 2. International Diabetes Federation. IDF Diabetes Atlas, 11th ed[EB/OL]. (2025-03-16)[2053-09-01]. https://diabetesatlas.org.
- 3. 中華醫學會眼科學分會眼底病學組, 中國醫師協會眼科醫師分會眼底病學組. 我國糖尿病視網膜病變臨床診療指南(2022年)—基于循證醫學修訂[J]. 中華眼底病雜志, 2023, 39(2): 99-124. DOI: 10.3760/cma.j.cn511434-20230110-00018.Retinal Disease Group of Ophthalmology Branch, Chinese Medical Association, Retinal Disease Group of Ophthalmology Physicians Branch, Chinese Medical Doctor Association. Evidence-based guidelines for diagnosis and treatment of diabetic retinopathy in China (2022)[J]. Chin J Ocul Fundus Dis, 2023, 39(2): 99-124. DOI: 10.3760/cma.j.cn511434-20230110-00018.
- 4. 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/OL]. BMC Ophthalmol, 2019, 19(1): 184[2019-08-14]. https://pubmed.ncbi.nlm.nih.gov/31412800/. DOI: 10.1186/s12886-019-1196-9.
- 5. Van Craenendonck T, Elen B, Gerrits N, et al. Systematic comparison of heatmapping techniques in deep learning in the context of diabetic retinopathy lesion detection[J/OL]. Transl Vis Sci Technol, 2020, 9(2): 64[2020-12-29]. https://pubmed.ncbi.nlm.nih.gov/33403156/. DOI: 10.1167/tvst.9.2.64.
- 6. 《人工智能在OCTA圖像分析和眼部疾病診斷中的應用指南2024》專家組, 國際轉化醫學會眼科專業委員會, 中國醫藥教育協會眼科影像與智能醫療分會, 等. 人工智能在OCTA圖像分析和眼部疾病診斷中的應用指南(2024)[J]. 眼科新進展, 2024, 44(5): 337-345. DOI: 10.13389/j.cnki.rao.2024.0066.The expert group of "Guidelines for the Application of Artificial Intelligence in OCTA Image Analysis and Ocular Disease Diagnosis 2024", the Ophthalmology Professional Committee of the International Translational Medicine Society, the Ophthalmology Imaging and Intelligent Healthcare Branch of the China Medical Education Association, et al. Guidelines for the application of artificial intelligence in optical coherence tomography angiography image analysis and ocular disease diagnosis(2024)[J]. Rec Adv Ophthalmol, 2024, 44(5): 337-345. DOI: 10.13389/j.cnki.rao.2024.0066.
- 7. 趙學功. 基于眼底圖像的糖尿病誘發視網膜病變輔助診斷關鍵技術研究[D]. 成都: 電子科技大學, 2021.Zhao XG. Research on key technologies for auxiliary diagnosis of diabetic retinopathy based on fundus images[D]. Chengdu: University of Electronic Science and Technology of China, 2021.
- 8. Nandhini T. Rectal fundus image recognition using deep learning ensemble CNN models[J/OL]. Rec Adv Ophthalmol, 2025, 10(26): 690-702. DOI: 10.52783/jisem.v10i26s.4276.
- 9. van Grinsven MJ, van Ginneken B, Hoyng CB, et al. Fast convolutional neural network training using selective data sampling: application to hemorrhage detection in color fundus images[J]. IEEE Trans Med Imaging, 2016, 35(5): 1273-1284. DOI: 10.1109/TMI.2016.2526689.
- 10. Monemian M, Rabbani H. Detecting red-lesions from retinal fundus images using unique morphological features[J/OL]. Sci Rep, 2023, 13(1): 3487[2023-03-01]. https://pubmed.ncbi.nlm.nih.gov/36859429/. DOI: 10.1038/s41598-023-30459-5.
- 11. Chang MH, Chen CY, Yu CH, et al. Vessel segmentation and dirt/reflection detection for retinal fundus photographs. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France. New York: IEEE Press, 2022.
- 12. Sandhu HS, Elmogy M, Taher Sharafeldeen A, et al. Automated diagnosis of diabetic retinopathy using clinical biomarkers, optical coherence tomography, and optical coherence tomography angiography[J]. Am J Ophthalmol, 2020, 216: 201-206. DOI: 10.1016/j.ajo.2020.01.016.
- 13. Khojasteh P, Aliahmad B, Kumar DK. Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms[J/OL]. BMC Ophthalmol, 2018, 18(1): 288[2018-11-06]. https://pubmed.ncbi.nlm.nih.gov/30400869/. DOI: 10.1186/s12886-018-0954-4.
- 14. Saleh I, El-Den NN, Elsharkawy M, et al. AI-based methods for diagnosing and grading diabetic retinopathy: a comprehensive review[J/OL]. Artif Intell Med, 2025, 168: 103221[2025-07-19]. https://pubmed.ncbi.nlm.nih.gov/40706108/. DOI: 10.1016/j.artmed.2025.103221.
- 15. Vijayan M, Venkatakrishnan S. A regression-based approach to diabetic retinopathy diagnosis using efficientnet[J/OL]. Diagnostics (Basel), 2023, 13(4): 774[2023-02-17]. https://pubmed.ncbi.nlm.nih.gov/36832262/. DOI: 10.3390/diagnostics13040774.
- 16. Liu Z, Gao A, Sheng H, et al. Identification of diabetic retinopathy lesions in fundus images by integrating CNN and vision mamba models[J/OL]. PLoS One, 2025, 20(1): e0318264[2025-01-28]. https://pubmed.ncbi.nlm.nih.gov/39874303/. DOI: 10.1371/journal.pone.0318264.
- 17. Liu C, Wang W, Lian J, et al. Lesion classification and diabetic retinopathy grading by integrating softmax and pooling operators into vision transformer[J/OL]. Front Public Health, 2025, 12: 1442114[2025-01-06]. https://pubmed.ncbi.nlm.nih.gov/39835306/. DOI: 10.3389/fpubh.2024.1442114.
- 18. Yang Y, Cai Z, Qiu S, et al. Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image[J/OL]. PLoS One, 2024, 19(3): e0299265[2024-03-06]. https://pubmed.ncbi.nlm.nih.gov/38446810/. DOI: 10.1371/journal.pone.0299265.
- 19. Li J, Guan Z, Wang J, et al. Integrated image-based deep learning and language models for primary diabetes care[J]. Nat Med, 2024, 30(10): 2886-2896. DOI: 10.1038/s41591-024-03139-8.
- 20. Porwal P, Pachade S, Kamble R, et al. Indian Diabetic Retinopathy Image Dataset (IDRiD): a database for diabetic retinopathy screening research[J/OL]. Data, 2018, 3(3): 25[2018-06-05]. https://doi.org/10.3390/data3030025.
- 21. Wu C, Restrepo D, Nakayama LF, et al. A portable retina fundus photos dataset for clinical, demographic, and diabetic retinopathy prediction[J/OL]. Sci Data, 2025, 12(1): 323[2025-02-22]. https://pubmed.ncbi.nlm.nih.gov/39987104/. DOI: 10.1038/s41597-025-04627-3.
- 22. Panchal S, Naik A, Kokare M, et al. Retinal fundus multi-disease image dataset (RFMiD) 2.0: a dataset of frequently and rarely identified diseases[J/OL]. ResearchGate, 2025, 8(2): 9[2025-10-02]. https://doi.org/10.3390/data8020029. DOI:10.3390/data8020029.
- 23. Pachade S, Porwal P, Kokare M, et al. RFMiD: retinal image analysis for multi-disease detection challenge[J/OL]. Med Image Anal, 2025, 99: 103365[2024-10-09]. https://pubmed.ncbi.nlm.nih.gov/39395210/. DOI: 10.1016/j.media.2024.103365.
- 24. Zhou Y, Wang B, Huang L, et al. A benchmark for studying diabetic retinopathy: segmentation, grading, and transferability[J]. IEEE Trans Med Imaging, 2021, 40(3): 818-828. DOI: 10.1109/tmi.2020.3037771.
- 25. Decencière E, Zhang X, Cazuguel G, et al. Feedback on a publicly distributed image database: the messidor database[J]. Image Anal Stereol, 2014, 33(3): 231-234. DOI: 10.5566/ias.1155.
- 26. Kauppi T, Pietil? J, Kalesnykiene V, et al. The DIARETDB1 diabetic retinopathy database and evaluation protocol[C/OL]//Proceedings of the British Machine Vision Conference. Warwick, UK: British Machine Vision Association, 2007: 15.1-15.10[2025-10-02]. http://www.bmva.org/bmvc/2007/papers/paper-60.html. DOI: 10.5244/C.21.15.2007.
- 27. Rahim SS, Palade V, Shuttleworth J, et al. Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing[J]. Brain Informatics, 2016, 3(4): 249-267. DOI: 10.1007/s40708-016-0045-3.
- 28. Chaudhary PK, Pachori RB. Automatic diagnosis of different grades of diabetic retinopathy and diabetic macular edema using 2-D-FBSE-FAWT[J]. IEEE Trans Instrum Meas, 2022, 71: 1-9. DOI: 10.1109/TIM.2022.3140437.
- 29. Wang S, Wang X, Hu Y, et al. Diabetic retinopathy diagnosis using multichannel generative adversarial network with semisupervision[J]. IEEE Trans Autom Sci Eng, 2021, 18(2): 574-585. DOI: 10.1109/TASE.2020.2981637.
- 30. Bilal A, Zhu L, Deng A, et al. AI-based automatic detection and classification of diabetic retinopathy using U-Net and deep learning[J/OL]. Symmetry, 2022, 14: 1427[2022-06-14]. https://doi.org/10.3390/sym14071427.
- 31. Li F, Pan J, Yang D, et al. A multicenter clinical study of the automated fundus screening algorithm[J/OL]. Transl Vis Sci Technol, 2022, 11(7): 22[2022-07-08]. https://pubmed.ncbi.nlm.nih.gov/35881410/. DOI: 10.1167/tvst.11.7.22.
- 32. Yao L, Cao CY, Yu GX, et al. Screening and evaluation of diabetic retinopathy via a deep learning network model: a prospective study[J]. World J Diabetes, 2024, 15(12): 2302-2310. DOI: 10.4239/wjd.v15.i12.2302.
- 33. Parthasharathi GU, Kumar KV, Premnivas R, et al. Diabetic retinopathy detection using machine learning[J]. J Innov Image Process, 2022, 1: 173-178. DOI: 10.36548/jiip.2022.1.003.
- 34. Lian J, Liu T. Lesion identification in fundus images via convolutional neural network-vision transformer[J/OL]. Biomed Signal Process Control, 2024, 88: 105607[2024-02-01]. https://doi.org/10.1016/j.bspc.2023.105607. DOI: 10.1016/j.bspc.2023.105607.
- 35. Asia AO, Zhu CZ, Althubiti SA, et al. Detection of diabetic retinopathy in retinal fundus images using CNN classification models[J/OL]. Electronics, 2022, 11(17): 2740[2022-08-05]. https://doi.org/10.3390/electronics11172740.
- 36. Li, F, Wang Y, Xu T, et al. Deep learning-based automated detection for diabetic retinopathy and diabetic macular oedema in retinal fundus photographs[J]. Eye, 2022, 36: 1433-1441. DOI: 10.1038/s41433-021-01552-8.
- 37. Oh K, Kang HM, Leem D, et al. Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images[J/OL]. Sci Rep, 2021, 11(1): 1897[2021-01-21]. https://pubmed.ncbi.nlm.nih.gov/33479406/. DOI: 10.1038/s41598-021-81539-3.
- 38. Ryu G, Lee K, Park D, et al. A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography[J/OL]. Sci Rep, 2021, 11(1): 23024[2021-11-26]. https://pubmed.ncbi.nlm.nih.gov/34837030/. DOI: 10.1038/s41598-021-02479-6.
- 39. Mehedi M, Mohammed FA, Zhang Y. A convolutional neural network model using weighted loss function to detect diabetic retinopathy[J]. ACM Trans Multimedia Comput, 2022, 40: 1-16.
- 40. Karkera T, Adak C, Chattopadhyay S, et al. Detecting severity of diabetic retinopathy from fundus images: a transformer network-based review[J/OL]. Neurocomputing, 2024, 597: 127991[2024-09-07]. https://doi.org/10.1016/j.neucom.2024.127991. DOI: 10.1016/j.neucom.2024.127991.
- 41. Jabbar MK, Yan J, Xu H, et al. Transfer learning-based model for diabetic retinopathy diagnosis using retinal images[J/OL]. Brain Sciences, 2022, 12(5): 535[2022-04-22]. https://doi.org/10.3390/brainsci12050535.
- 42. Wu J, Hu R, Xiao Z, et al. Vision transformer-based recognition of diabetic retinopathy grade[J]. Med Phys, 2021, 48(12): 7850-7863. DOI: 10.1002/mp.15312.
- 43. Chilukoti SV, Maida AS, Hei XL. Diabetic retinopathy detection using transfer learning from pre-trained convolutional neural network models[J/OL]. IEEE J Biomed. Health Inform, 2022, 2022: 10[2025-10-02]. https://doi.org/10.36227/techrxiv.18515357.v1. DOI:10.36227/techrxiv.18515357.v1.
- 44. Muthusamy D, Palani P. Deep learning model using classification for diabetic retinopathy detection: an overview[J]. Artif Intell Rev, 2024, 57(7): 185-205. DOI: 10.1007/s10462-024-10806-2.
- 45. Karthikeyan S, Selva SS, Sreeja GG, et al. Multimodal approach for diabetic retinopathy detection using deep learning and clinical data fusion[C]. Proceedings of the 2024 9th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 2024. New York: IEEE Press, 2024.
- 46. Wijesinghe I, Gamage C, Perera I, et al. A smart telemedicine system with deep learning to manage diabetic retinopathy and foot ulcers[C]. Proceedings of the 2019 Moratuwa Engineering Research Conference (MERCon), Moratuwa, Sri Lanka, 2019. New York: IEEE Press, 2019.
- 47. Ayoub S, Khan MA, Jadhav VP, et al. Minimized computations of deep learning technique for early diagnosis of diabetic retinopathy using IoT-based medical devices[J/OL]. Comput Intell Neurosci, 2022, 2022: 7040141[2022-09-14]. https://pubmed.ncbi.nlm.nih.gov/36156979/. DOI: 10.1155/2022/7040141.
- 48. Rajalakshmi R, Subashini R, Anjana RM, et al. Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence[J]. Eye (Lond), 2018, 32(6): 1138-1144. DOI: 10.1038/s41433-018-0064-9.
- 49. Niu Y, Gu L, Zhao Y, et al. Explainable diabetic retinopathy detection and retinal image generation[J]. IEEE J Biomed Health Inform, 2022, 26(1): 44-55. DOI: 10.1109/jbhi.2021.3110593.
- 50. Ali R, Khan FG, Rehman ZU, et al. Enhanced diabetic retinopathy detection: an explainable semi-supervised approach using contrastive learning[J]. IEEE J Biomed Health Inform, 2025, 2025: 1-14. DOI: 10.1109/jbhi.2025.3551696.
- 51. Shahzad T, Saleem M, Farooq MS, et al. Developing a transparent diagnosis model for diabetic retinopathy using explainable AI[J]. IEEE Access, 2024, 12: 149700-149709. DOI: 10.1109/ACCESS.2024.3475550.
- 52. Ortigossa ES, Gon?alves T, Nonato LG. EXplainable artificial intelligence (XAI)—from theory to methods and applications[J]. IEEE Access, 2024, 12: 80799-80846. DOI: 10.1109/ACCESS.2024.3409843.
- 53. Amparore E, Perotti A, Bajardi P. To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods[J/OL]. PeerJ Comput Sci, 2021, 7: e479[2021-04-16]. https://pubmed.ncbi.nlm.nih.gov/33977131/. DOI: 10.7717/peerj-cs.479.
- 54. Anderson M, Sadiq S, Nahaboo Solim M, et al. Biomedical data annotation: an OCT imaging case study[J/OL]. J Ophthalmol, 2023, 2023: 5747010[2023-08-22]. https://pubmed.ncbi.nlm.nih.gov/37650051/. DOI: 10.1155/2023/5747010.
- 55. Aswal S, Ahuja NJ, Mehra R. Handling imbalance and limited data in thyroid ultrasound and diabetic retinopathy datasets using discrete levy flights grey wolf optimizer based random forest for robust medical data classification[J/OL]. ACM Trans Asian Low-Resour Lang Inf Process, 2024, 2024: e1-e25[2024-01-31]. https://doi.org/10.1145/3648363. DOI: 10.1145/3648363.
- 56. Liu R, Hall LO, Bowyer KW, et al. Synthetic minority image over-sampling technique: how to improve AUC for glioblastoma patient survival prediction[C]. Proceedings of the 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, AB, Canada, 2017. New York: IEEE Press, 2017.
- 57. Zhao R, Chen X, Chen Z, et al. Diagnosing glaucoma on imbalanced data with self-ensemble dual-curriculum learning[J/OL]. Med Image Anal, 2022, 75: 102295[2021-10-29]. https://pubmed.ncbi.nlm.nih.gov/34753022/. DOI: 10.1016/j.media.2021.102295.
- 58. Xie Y, Wan Q, Xie H, et al. Fundus image-label pairs synthesis and retinopathy screening via GANs with class-imbalanced semi-supervised learning[J]. IEEE Trans Med Imaging, 2023, 42(9): 2714-2725. DOI: 10.1109/TMI.2023.3263216.
- 59. Lee D, Yoon SN. Application of artificial intelligence-based technologies in the healthcare industry: opportunities and challenges[J/OL]. Int J Environ Res Public Health, 2021, 18(1): 271[2021-10-29]. https://pubmed.ncbi.nlm.nih.gov/34753022/. DOI: 10.3390/ijerph18010271.
- 60. 張漢成. 健康醫療數據共享的現實困境與合規因應[J]. 醫學與哲學, 2024, 45(17): 52-57. DOI: 10.12014/j.issn.1002-0772.2024.17.11.Zhang HC. Practical dilemmas and compliance responses in healthcare data sharing[J]. Medicine & Philosophy, 2024, 45(17): 52-57. DOI: 10.12014/j.issn.1002-0772.2024.17.11.
- 61. Mudgal SK, Agarwal R, Chaturvedi J, et al. Real-world application, challenges and implication of artificial intelligence in healthcare: an essay[J/OL]. Pan Afr Med J, 2022, 43: 3[2022-09-02]. https://pubmed.ncbi.nlm.nih.gov/36284890/. DOI: 10.11604/pamj.2022.43.3.33384.