Detection of Diabetic Retinopathy and its Classification from the Fundus Images

Abstract

Diabetes Mellitus is a condition in which a human body is unable to produce enough insulin to regulate metabolism of sugar for storage in human cells. This results in high sugar levels in blood that may progressively damage the blood vessels in the retina and can result in vision impairment leading to Diabetic Retinopathy. Early detection of Diabetic Retinopathy is critical for timely treatment to prevent loss of vision. In many countries Asia and Africa, early detection of Diabetic Retinopathy is a major challenge as the health care infrastructure is to yet to percolate to many areas. Through this paper, we propose a solution to address the problem of timely detection of Diabetic Retinopathy using a model developed using Artificial Intelligence. This model uses machine learning to identify Diabetic Retinopathy in the retina fundus images and classify them into various stages of progress of disease as Normal, Moderate and Proliferative Diabetic Retinopathy (PDR), with main focus being the Binary Classification, which will help doctors in the treatment of patients. Classification of the images into the different stages of eye disease was done using Convoluutional Neural Networks with Transferred Learning. Accuracy assessment of the results obtained using the Binary Classification model has revealed that normal cases were classified with 85% accuracy while diabetic retinopathy cases were 84.12% accurate.