The Evolution of Artificial Intelligence in Eye Health

Abstract

Artificial intelligence (AI) is rapidly evolving and leading revolutionary innovations in ophthalmology, a field dedicated to eye health. By utilizing various ocular data, particularly retinal images, AI enables analysis, prediction, and improvement of disease management and treatment processes. The evolutionary process starting from traditional machine learning algorithms towards advanced deep learning architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based models has enabled the systematic overcoming of technical limitations in the field of ophthalmic diagnostics. AI-powered systems, supported by advanced algorithms, analyze large datasets with high accuracy, facilitating personalized healthcare services. Beyond diagnostic applications, AI enables personalized treatment planning, real-time disease monitoring, and scalable tele-ophthalmology solutions that expand access to eye care in underserved areas. While AI applications in ophthalmology offer numerous advantages, they may also introduce challenges that need to be addressed. The clinical translation of these technologies faces multifaceted challenges, including data privacy concerns, algorithmic interpretability requirements, cross-population generalizability limitations, and regulatory compliance complexities. As AI continues to shape the future of healthcare services, it is expected to create both new opportunities and obstacles. Considering these factors, this review provides a comprehensive examination of the historical development, current applications, and future potential of AI technologies in ophthalmology.

Keywords

• Artificial intelligence
• Machine learning
• Ophthalmology
• Tele-ophthalmology

Göz Sağlığında Yapay Zekânın Gelişimi

Abstract

Günümüzde yapay zekâ, hızla gelişen bir teknoloji olarak göz sağlığı ile ilgilenen oftalmoloji alanında devrim niteliğinde yeniliklere öncülük etmektedir. Bu sayede retina görüntüleri başta olmak üzere, çeşitli göz verileri kullanılarak hastalıkların analiz edilmesi, tahminlenmesi ve tedavi süreçlerinin iyileştirilmesi mümkün hale gelmiştir. Zaman içerisinde makine öğrenmesi ve derin öğrenmenin ön plana çıkması, oftalmoloji kapsamındaki çalışmalara da hız kazandırmış, pek çok konuda teknik zorlukları ve sınırlamaları kaldırarak, yenilikçi çözüm yöntemlerinin önünü açmıştır. Gelişmiş algoritmalarla desteklenen sistemler, büyük veri kümeleri üzerinde yüksek doğrulukla analiz yaparak, kişiselleştirilmiş sağlık hizmeti gibi imkanlar da sunmaktadır. Bu gelişmeler günümüzde yaygınlaşmaya devam eden tele-oftalmoloji uygulamaları için kritik bir role sahip olup, gelecek çalışmalara ışık tutmaktadır. İlerleyen dönemlerde sağlayacağı birçok avantajın yanında çeşitli dezavantajları da beraberinde getirebilecek yapay zekâ uygulamalarının, sağlık hizmetlerinin geleceğinde kritik bir rol oynayarak, yeni fırsatlar ve zorluklar yaratması tahmin edilmektedir. Tüm bu süreç göz önünde bulundurularak, oftalmolojide yapay zekâ teknolojilerinin tarihsel gelişimi, mevcut uygulamaları ve geleceğe yönelik potansiyeli kapsamlı bir şekilde incelenmiştir.

Keywords

• Yapay zekâ
• Makine öğrenmesi
• Oftalmoloji
• Tele-oftalmoloji

References

1. Abràmoff MD, Lou Y, Erginay A, Clarida W, Amelon R, Folk JC, Niemeijer M. 2016. Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest Ophthalmol Vis Sci, 57(13): 5200-5206.
2. Akkara JD, Kuriakose A. 2019. Role of artificial intelligence and machine learning in ophthalmology. Kerala J Ophthalmol, 31(2): 150-160.
3. Alhejaily AMG. 2024. Artificial intelligence in healthcare (Review). Biomed Rep, 22(1): 11.
4. Benet D, Pellicer-Valero OJ. 2021. Artificial intelligence: the unstoppable revolution in ophthalmology. Surv Ophthalmol,67(1): 252-270.
5. Bowd C, Hao J, Tavares IM, Goldbaum MH, Zangwill LM, Weinreb RN, Sample PA. 2008. Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes. Invest Ophthalmol Vis Sci, 49(3): 945-953.
6. Burgansky-Eliash Z, Wollstein G, Bilonick RA, Ishikawa H, Kagemann L, Schuman JS, Fudemberg SJ. 2005. Optical coherence tomography machine learning classifiers for glaucoma detection: A preliminary study. Invest Ophthalmol Vis Sci, 46(11): 4147-4152.
7. Can A, Shen H, Turner JN, Tanenbaum HL, Roysam B. 1999. Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms. IEEE Trans Inf Technol Biomed, 3(2): 125-138.
8. Chen X, Xu Y, Wong DWK, Wong TY, Liu J. 2015. Glaucoma detection based on deep convolutional neural network. In: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), August 25-29, Milan, Italy, pp: 745-748.

9. Cortes C, Vapnik V. 1995. Support-vector networks. Machine Learn, 20(3): 273-297.
10. Cover T, Hart P. 1967. Nearest neighbor pattern classification. IEEE Trans Inf Theory, 13(1): 21-27.
11. Das A, Rad P, Choo KKR, Nouhi B, Lish J, Martel J. 2019. Distributed machine learning cloud teleophthalmology IoT for predicting AMD disease progression. Future Gener Comput Syst, 93: 486-498.
12. De Fauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, et al. 2018. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med, 24(9): 1342-1350.
13. Decenciere A, Zhang X, Cazuguel G, Lay B, Cochener B, Massin C, et al. 2014. Feedback on a publicly distributed image database: The Messidor database. Image Anal Stereol, 33(3): 231-234.
14. Demir F, Taşcı E. 2021. An effective and robust approach based on R-CNN+LSTM model and NCAR feature selection for ophthalmological disease detection from fundus images. J Pers Med, 11(12): 1276.
15. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. 2009. ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 20-25, Miami, USA, pp: 248-255.
16. Duda RO, Hart PE. 1973. Pattern classification and scene analysis. Wiley-Interscience, New York, USA, pp: 1-7.
17. Elman JL. 1990. Finding structure in time. Cogn Sci, 14(2): 179-211.
18. Fan R, Liu H, Wang Y, Zhao X, Li J, Xu Y. 2023. Detecting glaucoma from fundus photographs using deep learning without convolutions: Transformer for improved generalization. Ophthalmol Sci, 3(1): 100233.
19. Gardner NM, Keating D, Williamson TH, Elliott AT. 1996. Automatic detection of diabetic retinopathy using an artificial neural network: A screening tool. Br J Ophthalmol, 80(11): 940-944.
20. Gheisari S, Shariflou S, Phu J, Kennedy PJ, Agar A, Kalloniatis M, et al. 2021. A combined convolutional and recurrent neural network for enhanced glaucoma detection. Sci Rep, 11: 1945.
21. Goldbaum M, Moezzi S, Taylor A, Chatterjee S, Boyd J, Hunter E, Jain R. 1996. Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), September 16-19, Lausanne, Switzerland.
22. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. 2014. Generative adversarial networks. arXiv preprint arXiv:1406.2661. URL: https://arxiv.org/abs/1406.2661 (accessed date: 02 April 2025).
23. Gulshan V, Peng L, Coram M, Webster DR. 2016. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22): 2402-2410.
24. He J, Wang J, Han Z, Ma J, Wang C, Qi M. 2023. An interpretable transformer network for the retinal disease classification using optical coherence tomography. Sci Rep, 13: 3637.
25. He K, Zhang X, Ren S, Sun J. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385. URL: https://arxiv.org/pdf/1512.03385v1 (accessed date: 02 April 2025).
26. Hemalakshmi GR, Murugappan M, Sikkandar MY, Begum SS, Prakash NB. 2024. Automated retinal disease classification using hybrid transformer model (SViT) using optical coherence tomography images. Neural Comput Appl, 36(16): 9171-9188.
27. Hochreiter S, Schmidhuber J. 1997. Long short-term memory. Neural Comput, 9(8): 1735-1780.
28. Holste G, Wang T, Lee J, Patel A, Nguyen T, Chen H. 2024. Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling. arXiv preprint arXiv:2405.08780. URL: https://arxiv.org/abs/2405.08780 (accessed date: 02 April 2025).
29. Huang ML, Chen HY. 2005. Development and comparison of automated classifiers for glaucoma diagnosis using Stratus optical coherence tomography. Invest Ophthalmol Vis Sci, 46(11): 4121-4129.
30. Iliuță ME, Moisescu MA, Pop E, Mitulescu TC. 2024. Personalized diagnosis and treatment using digital twins in ophthalmology. In: Proceedings of the 2024 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), June 17-19, Trondheim, Norway, pp: 1-8.
31. Jampol LM, Glassman AR, Sun J. 2020. Evaluation and care of patients with diabetic retinopathy. New England J Med, 382(17), 1629-1637.
32. Jiang J, Liu X, Liu L, Wang S, Long E, Yang H, et al. 2018. Predicting the progression of ophthalmic disease based on slit-lamp images using a deep temporal sequence network. PLoS One, 13(7): e0201142.
33. Kaggle. 2015. Diabetic retinopathy detection. URL: https://www.kaggle.com/c/diabetic-retinopathy-detection (accessed date: 02 April 2025).
34. Kaggle. 2019. APTOS 2019 blindness detection. URL: https://www.kaggle.com/c/aptos2019-blindness-detection (accessed date: 02 April 2025).
35. Kim SJ, Cho KJ, Oh S. 2017. Development of machine learning models for diagnosis of glaucoma. PLoS One, 12(5): e0177726.
36. Koleilat T, Asgariandehkordi H, Rivaz H, Xiao Y. 2025. MedCLIP-SAMv2: Towards universal text-driven medical image segmentation. Med Image Anal, 106: 103749.
37. Krizhevsky A, Sutskever I, Hinton GE. 2012. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th Conference on Neural Information Processing Systems (NeurIPS), December 3-6, Lake Tahoe, USA, pp: 1097-1105.
38. Kugelman J, Alonso-Caneiro D, Read SA, Vincent SJ, Collins MJ. 2018. Automatic segmentation of OCT retinal boundaries using recurrent neural networks and graph search. Biomed Opt Express, 9(11): 5759-5777.
39. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD. 1989. Backpropagation applied to handwritten zip code recognition. Neural Comput, 1(4): 541-551.
40. Li L, Xu M, Liu H, Li Y, Wang X, Jiang L, et al. 2020. A large-scale database and a CNN model for attention-based glaucoma detection. IEEE Trans Med Imaging, 39(2): 413-425.
41. Luo R, Sun L, Xia Y, Qin T, Zhang S, Poon H, Liu TY. 2022. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Brief Bioinform, 23(6): bbac409.
42. MacQueen J. 1967. Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, June 21-July 18, Berkeley, USA, pp: 281-297.
43. Martin KR, Mansouri K, Weinreb RN, Wasilewicz R, Gisler C, Hennebert J, et al. 2018. Use of machine learning on contact lens sensor-derived parameters for the diagnosis of primary open-angle glaucoma. Am J Ophthalmol, 194: 46-53.
44. Muramatsu C, Hayashi Y, Sawada A, Hatanaka Y, Hara T, Yamamoto T, Fujita H. 2010. Detection of retinal nerve fiber layer defects on retinal fundus images for early diagnosis of glaucoma. J Biomed Opt, 15(1): 016021.
45. Nagasato D, Tabuchi H, Ohsugi H, Masumoto H, Enno H, Ishitobi N, et al. 2018. Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy. J Ophthalmol, 2018: 1875431.
46. Nazih W, Aseeri AO, Atallah OY, El-Sappagh S. 2023. Vision transformer model for predicting the severity of diabetic retinopathy in fundus photography-based retina images. IEEE Access, 11: 1-1.
47. Park K, Kim J, Lee J. 2019. Visual field prediction using recurrent neural network. Sci Rep, 9: 8385.
48. Phridviraj MSB, Bhukya R, Madugula S, Manjula A, Vodithala S, Waseem MS. 2023. A bi-directional long short-term memory-based diabetic retinopathy detection model using retinal fundus images. Healthc Anal, 3: 100174.
49. Playout C, Duval R, Boucher MC, Cheriet F. 2022. Focused attention in transformers for interpretable classification of retinal images. Med Image Anal, 82: 102608.
50. Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. 2016. Convolutional neural networks for diabetic retinopathy. Procedia Comput Sci, 90: 200-205.
51. Quinlan JR. 1986. Induction of decision trees. Mach Learn, 1(1): 81-106.
52. Rodríguez MA, AlMarzouqi H, Liatsis P. 2022. Multi-label retinal disease classification using transformers. arXiv preprint arXiv:2207.02335. URL: https://arxiv.org/abs/2207.02335 (accessed date: 02 April 2025).
53. Rohm M, Tresp V, Müller M, Hufendiek K, Kern C, Manakov I, et al. 2018. Predicting visual acuity by using machine learning in patients treated for neovascular age-related macular degeneration. Ophthalmology, 125(7): 1028-1036.
54. Romo-Bucheli D, Schmidt-Erfurth U, Bogunović H. 2020. End-to-end deep learning model for predicting treatment requirements in neovascular AMD from longitudinal retinal OCT imaging. IEEE J Biomed Health Inform, 24(12): 3456-3465.
55. Rumelhart DE, Hinton GE, Williams RJ. 1986. Learning representations by back-propagating errors. Nature, 323(6088): 533-536.
56. Samuel AL. 1959. Some studies in machine learning using the game of checkers. IBM J Res Dev, 3(3): 210-229.
57. Schlosser T, Beuth F, Meyer T, Sampath Kumar A, Stolze G, Furashova O, et al. 2024. Visual acuity prediction on real-life patient data using a machine learning based multistage system. Sci Rep, 14(1): 5532.
58. Schuster M, Paliwal KK. 1997. Bidirectional recurrent neural networks. IEEE Trans Signal Process, 45(11): 2673-2681.
59. Simonyan K, Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. URL: https://arxiv.org/pdf/1409.1556v6 (accessed date: 02 April 2025).
60. Solanki K, Bhaskaranand M, Ramachandra C, Bhat S, Nittala MG, Sadda SR, Cuadros J. 2017. Validation of EyeArt automated diabetic retinopathy screening system on large cohort of mydriatic and non-mydriatic telescreening data from EyePACS. Invest Ophthalmol Vis Sci, 58(8): 3775.
61. Staal J, Abramoff MD, Niemeijer M, Viergever MA, van Ginneken B. 2004. Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging, 23(4): 501-509.
62. Stahl, A. 2020. The diagnosis and treatment of age-related macular degeneration. Deutsches Aerzteblatt Online, 117(29-30), 513-520.
63. Sucuoglu HS. 2025. Development of Real-Time Fire Detection Robotic System with Hybrid-Cascade Machine Learning Detection Structure. Processes, 13(6): 1712.
64. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. 2014. Going deeper with convolutions. arXiv preprint arXiv:1409.4842. URL: https://arxiv.org/pdf/1409.4842v1 (accessed date: 02 April 2025).
65. Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, et al. 2017. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA, 318(22): 2211-2223.
66. Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY. 2018. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol, 103(2): 167-175.
67. Turing AM. 1950. Computing machinery and intelligence. Mind, 59(236): 433-460.
68. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. 2017. Attention is all you need. In: Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS), December 4-9, Long Beach, USA, pp: 5998-6008.
69. World Health Organization. 2019. World report on vision. URL: https://www.who.int/publications-detail/world-report-on-vision (accessed date: 02 April 2025).
70. Wu J, Hu R, Xiao Z, Chen J, Liu J. 2021. Vision transformer‐based recognition of diabetic retinopathy grade. Med Phys, 48(12): 7850-7863.
71. Yildiz O. 2025. Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks. Electronics, 14(15): 3023.
72. Zhou L, Rzeszotarski MS, Singerman LJ, Chokreff JM. 1994. The detection and quantification of retinopathy using digital angiograms. IEEE Trans Med Imaging, 13(4): 619-626.