Improvement of the Hard Exudates Detection Method Used For Computer- Aided Diagnosis of Diabetic Retinopathy

Abstract

Diabetic retinopathy is a severe and widely spread eye disease. Early diagnosis and timely treatment of these clinical signs such as hard exudates could efficiently prevent blindness. The presence of exudates within the macular region is a main hallmark of diabetic macular edema and allows its detection with high sensitivity. In this paper, we combine the k-means clustering algorithm and mathematical morphology to detect hard exudates (HEs) in retinal images of several diabetic patients. This method is tested on a set of 50 ophthalmologic images with variable brightness, color, and forms of HEs. The algorithm obtained a sensitivity of 95.92%, predictive value of 92.28% and accuracy of 99.70% using a lesion-based criterion.