Artificial intelligence in ophthalmology: the present and the future
https://doi.org/10.21516/2072-0076-2024-17-2-135-141
Abstract
The medical industry is undergoing an active digital transformation, including the creation of electronic databases, cloud security systems, mobile health monitoring devices, and telemedicine tools. Artificial intelligence (AI), one of the most important technological achievements of the last decade, is gradually gaining momentum in various areas of practical medicine. The cutting edge of AI, neural networks, offers promising approaches to the improvement of clinical examination quality. The review presents data of studies focusing on the use of AI tools in the diagnosis of the most common ophthalmic diseases: diabetic retinopathy, macular degeneration, retinopathy of prematurity, glaucoma, cataracts, and ophthalmic oncology. We discuss both the advantages of neural networks in the diagnosis and monitoring of eye diseases, and outline the difficulties of their implementation, including ethical and legal conflicts.
About the Authors
V. V. Neroev
Helmholtz National Medical Research Center of Eye Diseases;
A.I. Evdokimov Moscow State University of Medicine and Dentistry
Russian Federation
Russian Federation
Vladimir V. Neroev — Academician of RAS, Dr. of Med. Sci., professor, director; head of eye diseases chair of the faculty of additional professional education
14/19, Sadovaya-Chernogryazskaya St., Moscow, 105062;
20, Bldg.1, Delegatskaya St., Moscow, 127473
O. V. Zaytseva
Helmholtz National Medical Research Center of Eye Diseases;
A.I. Evdokimov Moscow State University of Medicine and Dentistry
Russian Federation
Russian Federation
Olga V. Zaytseva — Cand. of Med. Sci., deputy director, leading researcher of the department of retina and optic nerve pathology; assistant professor of eye diseases chair of the faculty of additional professional education
14/19, Sadovaya-Chernogryazskaya St., Moscow, 105062;
20, Bldg.1, Delegatskaya St., Moscow, 127473
S. Yu. Petrov
Helmholtz National Medical Research Center of Eye Diseases
Russian Federation
Russian Federation
Sergey Yu. Petrov — Dr. of Med. Sci., head of the glaucoma department
14/19, Sadovaya-Chernogryazskaya St., Moscow, 105062
A. A. Bragin
Helmholtz National Medical Research Center of Eye Diseases
Russian Federation
Russian Federation
Aleksey A. Bragin — Cand. of Sci. (Engineering), head of the information technology department
14/19, Sadovaya-Chernogryazskaya St., Moscow, 105062
References
1. Sidorova T.A. Digital transformation as a semantic switch in medicine. Praxeme Problems of visual semiotics. 2023; 35 (1): 113–29 (In Russ.). doi: 10.23951/2312-7899-2023-1-113-129
2. Larder B, Wang D, Revell A. Application of artificial neural networks for decision support in medicine. Methods Mol Biol. 2008; 458: 123–36. doi: 10.1007/978-1-60327-101-1_7
3. Yuan G, Lv B, Hao C. Application of artificial neural networks in reproductive medicine. Hum Fertil (Camb). 2023: 1–7. doi: 10.1080/14647273.2022.2156301
4. Lusted LB. Medical electronics. N Engl J Med. 1955; 252 (14): 580–5. doi: 10.1056/NEJM195504072521405
5. Gunn AA. The diagnosis of acute abdominal pain with computer analysis. J R Coll Surg Edinb. 1976 May; 21(3): 170–2. PMID: 781220
6. Stamey TA. Benign prostatic hyperplasia in humans. West J Med. 1984; 141 (4): 517–8.
7. Ashizawa K, Ishida T, MacMahon H, et al. Artificial neural networks in chest radiography: application to the differential diagnosis of interstitial lung disease. Acad Radiol. 1999; 6 (1): 2–9. doi: 10.1016/s1076-6332(99)80055-5
8. Brickley MR, Cowpe JG, Shepherd JP. Performance of a computer simulated neural network trained to categorise normal, premalignant and malignant oral smears. J Oral Pathol Med. 1996; 25 (8): 424–8. doi: 10.1111/j.1600-0714.1996.tb00291.x
9. Karakitsos P, Cochand-Priollet B, Guillausseau PJ, et al. Potential of the back propagation neural network in the morphologic examination of thyroid lesions. Anal Quant Cytol Histol. 1996; 18(6): 494–500.
10. Karakitsos P, Stergiou EB, Pouliakis A, et al. Potential of the back propagation neural network in the discrimination of benign from malignant gastric cells. Anal Quant Cytol Histol. 1996 Jun; 18 (3): 245–50. PMID: 8790840
11. Lucht R, Delorme S, Brix G. Neural network-based segmentation of dynamic MR mammographic images. Magn Reson Imaging. 2002; 20 (2): 147–54. doi:10.1016/s0730-725x(02)00464-2
12. Matsuki Y, Nakamura K, Watanabe H, et al. Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on highresolution CT: evaluation with receiver operating characteristic analysis. AJR Am J Roentgenol. 2002; 178 (3): 657–63. doi: 10.2214/ajr.178.3.1780657
13. Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017; 318 (22): 2199–210. doi: 10.1001/jama.2017.14585
14. Defigueiredo RJ, Shankle WR, Maccato A, et al. Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain. Proc Natl Acad Sci USA. 1995; 92 (12): 5530–4. doi:10.1073/pnas.92.12.5530
15. Rozanova O.I., Mikhalevich I.M. Neural network analysis of the functional transformation of the visual system in normal aging. Ophthalmosurgery. 2022; S4: 470–1 (In Russ.).
16. Katalevskaya E.A., Katalevsky D.Yu., Tyurikov M.I., et al. Prospects for the use of artificial intelligence in the diagnosis and treatment of retinal diseases. RMJ Clinical ophthalmology. 2022; 22 (1): 36–43 (In Russ.). doi: 10.32364/2311-7729-2022-22-1-36-43
17. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016; 316 (22): 2402–10. doi: 10.1001/jama.2016.17216
18. Ting DSW, Cheung CY., Lim G., et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017; 318 (22): 2211–23. doi: 10.1001/jama.2017.18152
19. Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. ophthalmology. 2017; 124 (7): 962–9. doi: 10.1016/j.ophtha.2017.02.008
20. Gardner GG, Keating D, Williamson TH, et al. Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. Br J Ophthalmol. 1996; 80 (11): 940–4. doi: 10.1136/bjo.80.11.940
21. Garcia M, Sanchez CI, Lopez MI, et al. Neural network based detection of hard exudates in retinal images. Comput Methods Programs Biomed. 2009; 93 (1): 9–19. doi: 10.1016/j.cmpb.2008.07.006
22. Bernardes R. Optical coherence tomography: Health information embedded on OCT signal statistics. Annu Int Conf IEEE Eng Med Biol Soc. 2011; 6131–3. doi: 10.1109/IEMBS.2011.6091514
23. Srinivasan PP, Kim LA, Mettu PS, et al. Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. Biomed Opt Express. 2014; 5 (10): 3568–77. doi: 10.1364/BOE.5.003568
24. Wu H, Zhao S, Zhang X, et al. Back-propagation artificial neural network for early diabetic retinopathy detection based on a priori knowledge. J Phys Conf Ser. 2020; 1: 1437. doi: 10.1088/1742-6596/1437/1/012019
25. Krause J, Gulshan V, Rahimy E, et al. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology. 2018; 125 (8): 1264–72. doi: 10.1016/j.ophtha.2018.01.034
26. Anton N, Dragoi EN, Tarcoveanu F, et al. Assessing changes in diabetic retinopathy caused by diabetes mellitus and glaucoma using support vector machines in combination with differential evolution algorithm. Appl Sci. 2021; 11: 3944. doi: 10.3390/app11093944
27. Neroev V.V., Bragin A.A., Zaitseva O.V. Development of a prototype service for the diagnosis of diabetic retinopathy based on fundus images using artificial intelligence methods. National Health. 2021; 2 (2): 65–72 (In Russ.). doi:10.47093/2713-069X.2021.2.2.64-72
28. Lois N, Cook JA, Wang A, et al. Evaluation of a new model of care for people with complications of diabetic retinopathy: The EMERALD study. Ophthalmology. 2021; 128 (4): 561–73. doi: 10.1016/j.ophtha.2020.10.030
29. Pieczynski J, Kuklo P, Grzybowski A. The role of telemedicine, in-home testing and artificial intelligence to alleviate an increasingly burdened healthcare system: Diabetic retinopathy. Ophthalmol Ther. 2021; 10 (3): 445–64. doi: 10.1007/s40123-021-00353-2
30. Raman R, Dasgupta D, Ramasamy K, et al. Using artificial intelligence for diabetic retinopathy screening: policy implications. Indian J Ophthalmol. 2021; 69 (11): 2993–8. doi: 10.4103/ijo.IJO_1420_21
31. Takahashi H, Tampo H, Arai Y, et al. Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy. PLoS One. 2017; 12 (6): e0179790. doi: 10.1371/journal.pone.0179790
32. Pitkanen M, Kaikkonen O, Koskelainen A. A novel method for mouse retinal temperature determination based on ERG photoresponses. Ann Biomed Eng. 2017; 45 (10): 2360–72. doi: 10.1007/s10439-017-1872-y
33. Kulikov A.N., Malakhova E. u., Maltsev D.S. Artificial intelligence and machine learning for optical coherence tomography-based diagnosis in central serous chorioretinopathy. Ophthalmology journal. 2019; 12 (1): 13–20 (In Russ.). doi:10.17816/OV2019113-20
34. Lee CS, Baughman DM, Lee AY. Deep learning is effective for the classification of OCT images of normal versus age-related macular degeneration. Ophthalmol Retina. 2017; 1 (4): 322–7. doi: 10.1016/j.oret.2016.12.009
35. Treder M, Lauermann JL, Eter N. Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning. Graefes Arch Clin Exp Ophthalmol. 2018; 256 (2): 259–65. doi: 10.1007/s00417-017-3850-3
36. Prahs P, Marker D, Mayer C, et al. Deep learning to support therapy decisions for intravitreal injections. Ophthalmology. 2018; 115 (9): 722–7. doi: 10.1007/s00347-018-0708-y
37. Schlegl T, Waldstein SM, Bogunovic H, et al. Fully automated detection and quantification of macular fluid in OCT using deep learning. Ophthalmology. 2018; 125 (4): 549–58. doi: 10.1016/j.ophtha.2017.10.031
38. Keenan TDL, Goldstein M, Goldenberg D, et al. Prospective, longitudinal pilot study: Daily self-imaging with patient-operated home OCT in neovascular age-related macular degeneration. Ophthalmol Sci. 2021; 1 (2): 100034. doi: 10.1016/j.xops.2021.100034
39. Liu Y, Holekamp NM, Heier JS. Prospective, longitudinal study: Daily selfimaging with home OCT for neovascular age-related macular degeneration. Ophthalmol Retina. 2022; 6 (7): 575–85. doi: 10.1016/j.oret.2022.02.011
40. Dong L, Yang Q, Zhang RH, et al. Artificial intelligence for the detection of age-related macular degeneration in color fundus photographs: A systematic review and meta-analysis. EClinicalMedicine. 2021 May 8; 35: 100875. doi: 10.1016/j.eclinm.2021.100875
41. Brown JM, Campbell JP, Beers A, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol. 2018; 136 (7): 803–10. doi: 10.1001/jamaophthalmol.2018.1934
42. Anton A, Jordano J, Maquet JD. Sistema experto de diagn stico de glaucoma “Glaucom easy”. Arch Soc Esp Oftalmol. 1995; 69 (1): 23–8. https://dialnet.unirioja.es/servlet/articulo?codigo=6767973
43. Bowd C, Chan K, Zangwill LM, et al. Comparing neural networks and linear discriminant functions for glaucoma detection using confocal scanning laser ophthalmoscopy of the optic disc. Invest Ophthalmol Vis Sci. 2002 Nov; 43 (11): 3444–54. PMID: 12407155
44. Grewal DS, Jain R, Grewal SP, et al. Artificial neural network-based glaucoma diagnosis using retinal nerve fiber layer analysis. Eur J Ophthalmol. 2008; 18 (6): 915–21. doi: 10.1177/112067210801800610
45. Hern ndez GE, Santos-Garc a G, In s FB. Identification of glaucoma stages with artificial neural networks using retinal nerve fibre layer. Analysis and visual field parameters. Innov Hybrid Intell Syst. 2007; 44: 418–24. https://link.springer.com/chapter/10.1007/978-3-540-74972-1_54
46. Sim n MA, Alonso L, Ant n A. A hybrid visual field classifier to support early glaucoma diagnosis. Inteligencia Artificial Revista Iberoamericana de Inteligencia Artificial. 2005; 9 (26): 9–17.
47. An G, Omodaka K, Tsuda S, et al. Comparison of machine-learning classification models for glaucoma management. J Healthc Eng. 2018; 2018: 6874765. doi: 10.1155/2018/6874765
48. Butnariu C, Lisa C, Leon F, et al. Prediction of liquid-crystalline property using support vector machine classification. J Chemom. 2013; 27: 179–88. https://doi.org/10.1002/cem.2508
49. Park K, Kim J, Lee J. Visual field prediction using recurrent neural network. Sci Rep. 2019; 9 (1): 8385. doi: 10.1038/s41598-019-44852-6
50. Dorofeev D.A., Vizgalova L.O., Gorobets A.V., et al. The possibilities of artificial intelligence use in the assessment of Maklakov intraocular pressure prints. National journal Glaucoma. 2020; 19 (1): 20–7 (In Russ.). doi: 10.25700/NJG.2020.01.03
51. Komarovskikh E.N., Podtynnykh E.V. Using artificial neural networks for early diagnosis of glaucoma. Russian ophthalmological journal. 2023; 16 (2): 28–32 (In Russ.). doi: 10.21516/2072-0076-2023-16-2-28-32
52. Movsisyan A.B., Kuroyedov A.V., Gorodnichy V.V., et. al. Evaluation of the efficacy of neural network technology in the analysis of the condition of the optic nerve disc and peripapillary retina in healthy individuals examined for glaucoma. Pacific Medical Journal. 2020; 3: 43–7 (In Russ.). doi: 10.34215/1609-1175-2020-3-43-47
53. Oh E, Yoo TK, Hong S. Artificial neural network approach for differentiating open-angle glaucoma from glaucoma suspect without a visual field test. Invest Ophthalmol Vis Sci. 2015; 56 (6): 3957–66. doi: 10.1167/iovs.15-16805
54. Raghavendra U, Fujita H, Bhandary SV, et al. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci. 2018; 441: 41–9.
55. Ahn JM, Kim S, Ahn K.S., et al. A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS One. 2018; 13 (11): e0207982. doi: 10.1371/journal.pone.0207982
56. Jiang Y, Duan L, Cheng J, et al. JointRCNN: A Region-based convolutional neural network for optic disc and cup segmentation. IEEE Trans Biomed Eng. 2020; 67 (2): 335–43. doi: 10.1109/TBME.2019.2913211
57. Anton N, Tircoveanu F, Cantemir A, et al. Predictions of ocular changes caused by diabetes in glaucoma patients. Comput Methods Programs Biomed. 2018; 154: 183–90. doi: 10.1016/j.cmpb.2017.11.013
58. Chen HS, Chen GA, Syu JY, et al. Early glaucoma detection by using style transfer to predict retinal nerve fiber layer thickness distribution on the fundus photograph. Ophthalmol Sci. 2022; 2 (3): 100180. doi: 10.1016/j.xops.2022.100180
59. Schuman JS, De Los Angeles Ramos Cadena M, McGee R, et al. A case for the use of artificial intelligence in glaucoma assessment. Ophthalmol Glaucoma. 2022; 5 (3): e3–e13. doi: 10.1016/j.ogla.2021.12.003
60. Saini C, Shen LQ, Pasquale LR, et al. Assessing surface shapes of the optic nerve head and peripapillary retinal nerve fiber layer in glaucoma with artificial intelligence. Ophthalmol Sci. 2022; 2 (3): 100161. doi:10.1016/j.xops.2022.100161
61. Wang SY, Tseng B, Hernandez-Boussard T. Deep learning approaches for predicting glaucoma progression using electronic health records and natural language processing. Ophthalmol Sci. 2022; 2 (2): 100127. doi: 10.1016/j.xops.2022.100127
62. Tarcoveanu F, Leon F, Curteanu S, et al. Classification algorithms used in predicting glaucoma progression. Healthcare (Basel). 2022; 10 (10). doi: 10.3390/healthcare10101831
63. Anton N, Lisa C, Doroftei B, et al. Use of artificial neural networks to predict the progression of glaucoma in patients with sleep apnea. Appl. Sci. 2022; 12 (12): 6061. https://doi.org/10.3390/app12126061
64. Kuroyedov A.V., Ostapenko G.A., Mitroshina K.V. Modern diagnostics of glaucoma: neural networks and artificial intelligence. RMJ Clinical ophthalmology. 2019; 19 (4): 230–7 (In Russ.). doi: 10.32364/2311-7729-2019-19-4-230-237
65. Goh JHL, Lim ZW, Fang X, et al. Artificial intelligence for cataract detection and management. Asia Pac J Ophthalmol (Phila). 2020; 9 (2): 88–95. doi: 10.1097/01.APO.0000656988.16221.04
66. Son KY, Ko J, Kim E, et al. Deep learning-based cataract detection and grading from slit-lamp and retro-illumination photographs: Model development and validation study. Ophthalmol Sci. 2022; 2 (2): 100147. doi: 10.1016/j.xops.2022.100147
67. Tognetto D, Giglio R, Vinciguerra AL, et al. Artificial intelligence applications and cataract management: A systematic review. Surv Ophthalmol. 2022; 67 (3): 817–29. doi: 10.1016/j.survophthal.2021.09.004
68. Sakhnov S.N., Aksenov K.D., Aksenova L.E., et al. Development of a cataract screening model using an open dataset and deep machine learning algorithms. Fyodorov journal of ophthalmic surgery. 2022; 4S: 13–20 (In Russ.). https://doi.org/10.25276/0235-4160-2022-4S-13-20
69. Lindegger DJ, Wawrzynski J, Saleh GM. Evolution and applications of artificial intelligence to cataract surgery. Ophthalmol Sci. 2022; 2 (3): 100164. doi:10.1016/j.xops.2022.100164
70. Vinogradov A.R., Dzhashi B.G., Yuferov O.V., et al. Modern possibilities for optimizing the calculation of intraocular lens optical power using deep machine learning capabilities. Fyodorov journal of ophthalmic surgery. 2022; 4S: 138–45 (In Russ.). doi: 10.25276/0235-4160-2022-4S-138-145
71. Arzamastsev A.A., Fabrikantov O.L., Belikov S.V., Zenkova N.A. The esults of using machine learning technology for calculation of optical power of intraocular lenses. Fyodorov journal of ophthalmic surgery. 2022; 4S: 6–12 (In Russ.). doi: 10.25276/0235-4160-2022-4S-6-12
72. Rampat R, Deshmukh R, Chen X, et al. Artificial intelligence in cornea, refractive surgery, and cataract: Basic principles, clinical applications, and future directions. Asia Pac J Ophthalmol (Phila). 2021; 10 (3): 268–81. doi: 10.1097/APO.0000000000000394
73. Siddiqui AA, Ladas JG, Lee JK. Artificial intelligence in cornea, refractive, and cataract surgery. Curr Opin Ophthalmol. 2020; 31 (4): 253–60. doi: 10.1097/ICU.0000000000000673
74. Malyugin B.E., Sakhnov S.N., Aksenova L.E., еt al. Application of artificial intelligence in the diagnosis and surgery of keratoconus: a systematic review. Fyodorov Journal of Ophthalmic Surgery. 2022; (1): 77–96 (In Russ.). doi:10.25276/0235-4160-2022-1-77-96
75. Shukhaev S.V., Mordovtseva E.A., Pustozerov E.A., Kudlakhmedov S.S. The use of convolutional neural networks to determine Fuchs' endothelial dystrophy. Fyodorov Journal of Ophthalmic Surgery. 2022; (S4): 70–6 (In Russ.). doi: 10.25276/0235-4160-2022-4S-70-76
76. Souza MB, Medeiros FW, Souza DB, et al. Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations. Clinics (Sao Paulo). 2010; 65 (12): 1223–8. doi: 10.1590/s1807-59322010001200002
77. Arbelaez MC, Versaci F, Vestri G, et al. Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data. Ophthalmology. 2012; 119 (11): 2231–8. doi: 10.1016/j.ophtha.2012.06.005
78. Smadja D, Touboul D, Cohen A, et al. Detection of subclinical keratoconus using an automated decision tree classification. Am J Ophthalmol. 2013; 156 (2): 237–46 e1. doi: 10.1016/j.ajo.2013.03.034
79. Ruiz Hidalgo I, Rodriguez P, Rozema JJ, et al. Evaluation of a machine-learning classifier for keratoconus detection based on scheimpflug tomography. Cornea. 2016; 35 (6): 827–32. doi: 10.1097/ICO.0000000000000834
80. Kovacs I, Mihaltz K, Kranitz K, et al. Accuracy of machine learning classifiers using bilateral data from a Scheimpflug camera for identifying eyes with preclinical signs of keratoconus. J Cataract Refract Surg. 2016; 42 (2): 275–83. doi: 10.1016/j.jcrs.2015.09.020
81. Ambrosio RJr, Lopes BT, Faria-Correia F, et al. Integration of scheimpflugbased corneal tomography and biomechanical assessments for enhancing ectasia detection. J Refract Surg. 2017; 33 (7): 434–43. doi: 10.3928/1081597X20170426-02
82. Harry D.D., Saakyan S.V., Khoroshilova-Maslova I.P., et al. Machine learning methods in ophthalmology. Literature review. Ophthalmology in Russia. 2020; 17 (1): 20–31 (In Russ.). doi: 10.18008/1816-5095-2020-1-20-31
83. Damato B, Eleuteri A, Fisher AC, et al. Artificial neural networks estimating survival probability after treatment of choroidal melanoma. Ophthalmology. 2008; 115 (9): 1598–607. doi: 10.1016/j.ophtha.2008.01.032
84. Vaquero-Garcia J, Lalonde E, Ewens KG, et al. PRiMeUM: A model for predicting risk of metastasis in uveal melanoma. Invest Ophthalmol Vis Sci.2017; 58 (10): 4096–105. doi: 10.1167/iovs.17-22255
85. Zhang H, Liu Y, Zhang K, et al. Validation of the relationship between iris color and uveal melanoma using artificial intelligence with multiple paths in a large chinese population. Front Cell Dev Biol. 2021; 9: 713209. doi: 10.3389/fcell.2021.713209
Review
For citations:
Neroev V.V., Zaytseva O.V., Petrov S.Yu., Bragin A.A. Artificial intelligence in ophthalmology: the present and the future. Russian Ophthalmological Journal. 2024;17(2):135-141. (In Russ.) https://doi.org/10.21516/2072-0076-2024-17-2-135-141
Views:
2035
Email this article 