Development of a Model of Segmentation of the Capillaries of the Ocular Surface Based on Images from an Ophthalmological Slit Lamp Using Artificial Intelligence Tools

Abstract

Justification and purpose of the study. Changes in the vessels of the ocular surface are often associated with the presence of various systemic or ocular diseases. Segmentation of the vessels of the ocular surface using artificial intelligence (AI) tools is highly relevant in terms of improving the quality of early diagnosis of pathology. Purpose: to develop a model of segmentation of the capillaries of the ocular surface based on images from an ophthalmic slit lamp using AI tools using Python.Materials and methods. The study used a dataset (700 eyes), which is publicly available on the Internet and includes photos from an ophthalmological slit lamp, marked up manually. With the help of the augmentation method, this set for research has been increased several times. The system of segmentation of the capillaries of the eye in the images from the ophthalmological slit lamp is based on the trained neural network Unet.Results. The main result of the study is the development of an algorithm for automatic segmentation of eye capillaries in images from an ophthalmic slit lamp. The metric reached 85% during the training of the neural network model.Conclusion. The high efficiency and potential of all methods in the construction of an automatic segmentation system of the capillaries of the ocular surface in the images within the framework of the developed in the Helmholtz National Medical Research Center of Eye Diseases automated system of medical decision-making. In the future, this service can be used to improve the effectiveness of early diagnosis and monitoring of treatment of eye diseases in conditions of reduced availability of primary ophthalmological care in part of the territories of the Russian Federation, including at the pre-medical stage.