Detection and classification of cotton wool spots in diabetic retinopathy

Abstract

Diabetes is a disorder that occurs when blood sugar level increases. Further increase of blood glucose lead to serious complications and it will affect major organs of our body. Diabetes affects both of the eyes called Diabetic Retinopathy (DR). If it is treated properly eye blindness can be prevented. The main objective of this paper is to detect Cotton Wool Spots (CWS) using morphological operations and the spots are segmented using k-means segmentation. Distinct features are extracted from the segmented image to train and test the Support Vector Machine (SVM) classifier. It is used to classify the lesions and the stages of diabetic retinopathy. It is noticed that sensitivity is 95% and the specificity is 86%.