Overview / Usage

Diabetic Retinopathy is one of the leading causes of blindness. It is curable but should be identified at the right stage (early stage). The blindness being caused due to late or no detection of diabetic retinopathy causes the loss in vision.
So, aim is to study and recognise various automated, suitable and sophisticated approach using deep learning and deep neural networks so that DR can be detected at early levels easily and damage to retina can be minimized.

Methodology / Approach

Diabetic Retinopathy is one of the leading causes of blindness and eye disease in working age population of developed world. The research is an attempt towards studying various automated ways of detection using deep learning to detect this disease in its early phase. Various supervised learning methods, their outcomes and comparison to classify a given set of images into stages of Diabetic Retinopathy.
For the study, use of these methods on retinal fundus images is done. The various methodologies that can be implanted and enhanced using Deep Learning and deep neural networks.