Microaneurysm Candidate Extraction Methodology in Retinal Images for the Integration into Classification-Based Detection Systems

Abstract

Diabetic Retinopathy (DR) is one of the most common complications of long-term diabetes. It is a progressive disease that causes retina damage. DR is asymptomatic at the early stages and can lead to blindness if it is not treated in time. Thus, patients with diabetes should be routinely evaluated through systemic screening programs using retinal photography. Automated pre-screening systems, aimed at filtering cases of patients not affected by the disease using retinal images, can reduce the specialist’ workload. Since microaneurysms (MAs) appear as a first sign of DR in retina, early detection of this lesion is an essential step in automatic detection of DR. Most of MA detection systems are based on supervised classification and are designed in two stages: MA candidate extraction and further description and classification. This work proposes a method that addresses the first stage. Evaluation of the proposed method on a test dataset of 83 images shows that the method could operate at sensitivities of 74%, 82% and 87% with a number of 92, 140 and 194 false positives per image, respectively. These results show that the methodology detects low contrast MAs with the background and is suitable to be integrated in a complete classification-based MA detection system.