Exudates and Colour Analysis for the Detection of Diabetic Macular Edema

Diabetic macular edema (DME) is a variation with diabetic retinopathy. Vision loss and blindness are the most common effects of DME. DME is defined as thickening of the retina in diabetic patients due to fluid leakage within macula because of elevated sugar levels over long period. DME is assessed by detecting bright lesions called exudates and swelling of retina in fundus images. In the present paper, an algorithm is developed to detect DME, by estimating the pixel count from macula to nearest hard exudate. The macula and hard exudates are localized using image processing techniques. Severity of estimated from exudates analysis and color analysis. The algorithm is tested with 65 DME images with severity index 0, 1 and 2 from MESSIDOR database.