Color image analysis of the optic disc to assist diagnosis of glaucoma risk and evolution

Abstract

This work aims to build an algorithm to segment the optic cup inside the optic disc, and the optic disc from the rest of the eye fundus image. The algorithm is intended to give assistance in the cup to disc ratio estimation of glaucomatous eyes. Often the contours of both the optic cup and disc are faint and intersected by entangled veins that make it difficult to draw their silhouettes. The algorithm, which includes the spatial filtering proposed in the S-CIELAB extension, is based on the information of color, the color differences between neighbor pixels and the geometry of the areas involved.