Diabetic Retinopathy Detection By Means Of Deep Learning

Abstract

Diabetic Retinopathy (DR) is an eye abnormality caused due to diabetes. As the sickness progresses it results in distortion and blurred vision. The diagnosing of the DR image needs sure-handed clinicians to spot the presence of vital options that makes this a tough and time-intensive task. The proposed methodology relies on R-CNN (Regional Convolutional Neural Network) approach to diagnose DR from digital anatomical structure pictures. In the proposed approach the total image is segmental and the regions of interest are taken for further processing. The proposed method uses four layers of convolution neural network to train a hundred and thirty anatomical structures and tested on one hundred images. All the images are classified into two classes, images having DR and images not having DR. This R-CNN (Regional CNN) approach was found to be economical in terms of speed and accuracy.