А.Yu. Ionov1, N.Yu. Ilyasova2, N.S. Demin3, K.R. Dotsenko4, A.V. Zolotarev5

1–3 Samara National Research University (Samara, Russia)
2, 3 Image Processing Systems Institute, NRC «Kurchatov Institute» (Moscow, Russia)
4 Samara State Medical University (Samara, Russia)
5 Samara Regional Ophtalmic Hospital n.a. T.I. Eroshevsky (Samara, Russia)
1 artem.ionov.96@mail.ru, 2 ilyasova.nata@gmail.com, 3 volfgunus@gmail.com, 4 khikamila@gmail.com, 5 avz65@mail.ru

Age-related macular degeneration (AMD) is one of the leading causes of irreversible vision loss in the elderly population. Early diagnosis of the disease is critical to prevent its progression. However, visual evaluation of optical coherence tomography (OCT) images used to detect signs of AMD requires high skill and significant time expenditure on the part of an ophthalmologist. This creates a need for automated methods of OCT image analysis capable of detecting biomarkers of the disease.

The aim of this work is to develop an algorithm based on deep learning methods for automatic detection of indications for 2RT-laser treatment of age-related macular degeneration on OCT images using segmentation and classification of retinal structures.

A method based on the use of two deep learning architectures is proposed: U-Net for segmentation of retinal structures with 85% accuracy and VGG16 for classification of TMD pathological features with 92% accuracy. The obtained results demonstrate the high efficiency of the proposed approach in the task of automatic analysis of medical images.

Ionov А.Yu., Ilyasova N.Yu., Demin N.S., Dotsenko K.R., Zolotarev A.V. Automated determination of indications for 2RT-laser treatment from optical coherence tomography images. Biomedicine Radioengineering. 2025. V. 28. № 5. P. 137–140. DOI: https:// doi.org/10.18127/j15604136-202505-27 (In Russian)

1. Shadrichev F.E. Vozrastnaya makulyarnaya degeneraciya. Sovremennaya optometriya. 2008. № 6. S. 27–34 (In Russian).
2. Budzinskaya M.V. Vozrastnaya makulyarnaya degeneraciya. Vestnik oftal'mologii. 2014. T. 130. № 6. S. 56–61 (In Russian).
3. Avetisov S.E., Egorov E.A., Moshetova L.K., Neroev V.V., Tahchidi H.P. Oftal'mologiya: nac. rukovodstvo. M.: GEOTAR-Media. 2014. 736 s. (In Russian).
4. Ilyasova N., Demin N. Application of artificial intelligence in ophthalmology for coagulate map formation to carry out laser eye treatment. In: Proceedings of the International Conference on Pattern Recognition. 2022. P. 387–402. DOI: 10.1007/978-3-031-37742-6_29.
5. Demin N.S., Ilyasova N.Yu., Paringer R.A., Kirsh D.V. Application of artificial intelligence in ophthalmology by the example of solving the problem of semantic segmentation of the ocular fundus image. Computer Optics. 2023. V. 47. № 5. P. 387–402. DOI: 10.18287/2412-6179-CO-1283.