Extracting a DME area based on graph-based image segmentation and collation of OCT retinal images*

Abstract

This paper proposes a technique for improving the localization of areas of diabetic macular edema. This study is relevant because the incidence of serious eye diseases due to diabetic macular edema is only increasing among the world's population. The proposed method is graph-based image segmentation. Comparison of optical coherence tomography (OCT) data and retinal images is based on the search and comparison of special points on the original analyzed image and OCT analysis based on these images. Segmentation accuracy is improved by using specially selected parameters. Of these, the optimal parameters obtained in the course of the study made it possible to achieve a segmentation error of 2%.