Retinal Microaneurysm Detection by CNN

Diabetic Retinopathy (DR) is a fast-growing retinal disease happens as result of exponential growth in sugar level blood which diminishes eyesight. The severity identification this eye disorder performed by ophthalmologists due to scarcity good software for finding DR. initial stage diabetic retinopathy identified the presence microaneurysm. This paper conducts phase detection using Convolutional Neural Network (CNN). For conducting experiment DIARETDB1 dataset used. images from database are resized preprocessing step then automatic feature extraction done simple CNN By performing training, network classifies with and without disease. Sensitivity, Specificity Accuracy obtained technique explained 97.62%, 100% 97.75%.