Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images

TL;DR

This paper presents a deep learning model for early detection and grading of diabetic retinopathy from retinal images, achieving state-of-the-art accuracy and high sensitivity, aiding in timely diagnosis and treatment.

Contribution

A novel deep convolutional neural network designed for early-stage detection and grading of diabetic retinopathy, outperforming existing methods on a large public dataset.

Findings

Achieved 0.851 quadratic weighted kappa score and 0.844 AUC on severity grading.

Attained 98% sensitivity and over 94% specificity in early-stage detection.

Model is simple, efficient, and suitable for clinical application.

Abstract

Diabetic Retinopathy (DR) is a constantly deteriorating disease, being one of the leading causes of vision impairment and blindness. Subtle distinction among different grades and existence of many significant small features make the task of recognition very challenging. In addition, the present approach of retinopathy detection is a very laborious and time-intensive task, which heavily relies on the skill of a physician. Automated detection of diabetic retinopathy is essential to tackle these problems. Early-stage detection of diabetic retinopathy is also very important for diagnosis, which can prevent blindness with proper treatment. In this paper, we developed a novel deep convolutional neural network, which performs the early-stage detection by identifying all microaneurysms (MAs), the first signs of DR, along with correctly assigning labels to retinal fundus images which are graded into five categories. We have tested our network on the largest publicly available Kaggle diabetic retinopathy dataset, and achieved 0.851 quadratic weighted kappa score and 0.844 AUC score, which achieves the state-of-the-art performance on severity grading. In the early-stage detection, we have achieved a sensitivity of 98% and specificity of above 94%, which demonstrates the effectiveness of our proposed method. Our proposed architecture is at the same time very simple and efficient with respect to computational time and space are concerned.