Development of a prototype service for the diagnosis of diabetic retinopathy based on fundus photos using artificial intelligence methods

Justification and purpose of the study. The high social significance of diabetic retinopathy (DR), the complexity of early diagnosis and monitoring of the disease determine the urgency of developing a system for diagnosing diabetic changes in the fundus using artificial intelligence (AI) methods. The aim of the work is to build a demo prototype of a WEB service for recognizing signs of DR from fundus images using machine learning methods using the Python language and the Django framework.

Materials and methods. The study used the Messidor dataset (1200 eyes), which is publicly available on the Internet and includes photos of healthy fundus (546 eyes) and fundus with pathology (654 eyes). With the help of the augmentation method, this set for the study is increased several times. The fundus image recognition system is based on the trained neural network ResNet50. The web service with a connected neural network model was developed on the Django framework.

Results. The main result of the research is the development of a test prototype of a service for the diagnosis of diabetic fundus changes based on photos using machine learning tools, demonstrating the great potential of using AI to improve the effectiveness of decisions. The sensitivity of the neural network model during the diagnosis of DR, even on a small test sample and limited training time, was 85 %.

Conclusion. The high efficiency and potential of AI methods in the construction of a system for automatic detection of fundus pathology in the framework of the developed in the Helmholtz National Medical Research Center of Eye Diseases automated medical decision-making system. In the future, this service can be used to improve the effectiveness of early diagnosis and monitoring of diabetic changes in the fundus in conditions of reduced availability of primary ophthalmological care in parts of the Russian Federation, including at the pre-medical stage.

1. Clinical recommendations (treatment protocols) “Diabetes mellitus: diabetic retinopathy, diabetic macular edema (CR115)”. All-Russian public organization “Association of Ophthalmologists”, Public Organization “Russian Association of Endocrinologists” (In Russian). URL: http://avo-portal.ru/doc/fkr (accessed 23.06.2021).

2. Klein R., Klein B., Moss S., et al. The Wisconsin Epidemiologic Study of Diabetic Retinopathy: II. Prevalence and risk of diabetic retinopathy when age at diagnosis is less than 30 years. Arch Ophthalmol. 1984; 102: 520–526. https://doi.org/10.1001/archopht.1984.01040030398010. PMID: 6367724

3. Global report on diabetes. Geneva: World Health Organization. 2018; 88 p. URL: https://apps.who.int/iris/bitstream/handle/10665/204871/9789241565257_eng.pdf

4. Eye health and diabetes. A guide for healthcare professionals. IDF and the Fred Hollows Foundation. Brussels, Belgium. 2017; 40 p (in Russian). URL: https://www.idf.org/component/attachments/attachments.html?id=875&task=download (accessed 23.06.2021).

5. Lipatov D.V., Vikulova O.K., Zheleznyakova A.V., et al. Trends in the epidemiology of diabetic retinopathy in Russian Federation according to the Federal Diabetes Register (2013–2016). Diabetes Mellitus. 2018; 21(4): 230–240 (In Russian). https://doi.org/10.14341/DM9797

6. Neroev V.V., Zaytseva O.V., Mikhailova L.A. Incidence of diabetic retinopathy in the Russian Federation according to Federal statistics. Russian Ophthalmological Journal. 2018; 11(2): 5–9 (In Russian). https://doi.org/10.21516/2072-0076-2018-11-2-5-9

7. Porta M., Kohner E. Screening for diabetic retinopathy in Europe. Diabetic Medicine. 1991; 8: 197–198. https://doi.org/10.1111/j.1464-5491.1991.tb01571.x. PMID: 1828731

8. Early Treatment Diabetic Retinopathy Study Research Group. Photocoagulation for diabetic macular edema. Early Treatment Diabetic Retinopathy Study (ETDRS) report No 1. Arch Ophthalmol. 1985; 103: 1796–1806. https://doi.org/10.1001/archopht.1985.01050120030015. PMID: 2866759

9. He K., Zhang X., Ren S., et al. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016; 770–778. https://doi.org/10.1109/cvpr.2016.90

10. Decencière E., Zhang X., Cazuguel G., et al. Feedback on a publicly distributed database: the Messidor database. Image Analysis & Stereology. 2014; 33(3): 231–234. https://doi.org/10.5566/ias.1155. ISSN 1854-5165

11. Julli A., Pal S. Deep learning with Keras. Moscow: DMK Press, 2017. 294 p (In Russian). ISBN 978-5-97060-573-8

12. Tufail A., Rudisill C., Egan C., et al. Automated Diabetic Retinopathy Image Assessment Software: Diagnostic Accuracy and Cost-Effectiveness Compared with Human Graders. Ophthalmology. 2017; 124(3): 343–351. https://doi.org/10.1016/j.ophtha.2016.11.014. PMID: 28024825