Automatic detection of microaneurysms from fundus images using morphological operations

Abstract

Diabetic retinopathy is an ocular disorder resulting in patients with long history of diabetes. It is a progressive disease characterized by numerous features like, microaneurysms (MA), hard exudates, soft exudates, veins bleeding, and hemorrhages. Presence of microaneurysms is the early signs of Diabetic retinopathy. In this paper, automatic detection of microaneurysms, that alternates the tedious and time-consuming manual process, is presented. Thresholding and morphological operations are used for microaneurysms detection from fundus images. In the first step, optic disk and blood vessels are eliminated to facilitate the detection of MA. Secondly, the candidate features are extracted based on their size. Experiments are performed on a set of 100 fundus images and have yielded encouraging results. © 2013 Springer.