Detection of Non-Proliferative Diabetic Retinopathy in fundus images of the human retina

Abstract

Diabetic macular edema (DME) is the largest cause of visual acuity loss in diabetes. It is non-proliferative stage of diabetic retinopathy which affects central vision. A feature extraction technique is introduced to capture the global characteristics of the fundus images and discriminate the normal from DME images. DME detection is carried out via supervised learning. Disease severity is assessed using a rotational asymmetry metric by examining the symmetry of macular region. The automatic disease detection system can significantly reduce the load of experts by limiting the referrals to those cases that require immediate attention. The reduction in time and effort will be significant where a majority of patients screened for diseases turn out to be normal. The ratio of normal patients to the ones showing disease symptoms can be as high as 9 to 1 in DR screening. Microaneurysms are small blood clots which occur due to capillary burst. It also leads to vision loss. Microaneurysm is identified using Circular Hough Transform. The detection performance has specificity between 74% and 90%. The severity classification accuracy is 81%.