Technology for detection and subtype classification of drusen using OCT data for diagnosing age-related macular degeneration

The purpose of the paper is to identify the subtypes of drusen on OCT images for the diagnosis of age-related macular degeneration. The relevance of the problem is determined not only by the large number of people around the world suffering from this disease, but also by the crucial importance of identifying the age-related macular degeneration in the early stages. We propose a two-stage technology: at the first stage, the drusen are identified on OCT images, and at the second stage, they are classified based on features of reflexivity. The study showed that the proposed technology makes it possible to achieve 98 % classification accuracy.