Automatic classification of diabetic macular edema in digital fundus images

Diabetic macular edema is a common complication of diabetic retinopathy due to the presence of exudates in proximity with the fovea. In this paper, an automated method to classify diabetic macular edema is presented. The fovea is localized and the regions of macula are marked based on the Early Treatment Diabetic Retinopathy Studies (ETDRS) grading scale. Extraction method using marker-controlled watershed transformation is adopted and modified from the previous research. The location of the extracted exudates on the marked macular regions is computed to classify diabetic macular edema into normal, stage 1 and stage 2 diabetic macular edema. The performance of the proposed method is evaluated using 88 images of publicly available MESSIDOR database. The overall sensitivity, specificity and accuracy of the proposed method are 80.9%, 90.2% and 85.2%, respectively.