DiaRet: A browser-based application for the grading of Diabetic Retinopathy with Integrated Gradients

TL;DR

This paper develops deep learning models to grade diabetic retinopathy severity from degraded retinal images and creates a browser app that highlights key features using Integrated Gradients for aiding diagnosis.

Contribution

It introduces a browser-based tool that visualizes model predictions on retinal images, integrating gradient-based explanations for improved clinical interpretability.

Findings

Models achieved accurate grading of retinal images.

The application effectively highlights key diagnostic features.

Degradation simulations improved model robustness.

Abstract

Patients with long-standing diabetes often fall prey to Diabetic Retinopathy (DR) resulting in changes in the retina of the human eye, which may lead to loss of vision in extreme cases. The aim of this study is two-fold: (a) create deep learning models that were trained to grade degraded retinal fundus images and (b) to create a browser-based application that will aid in diagnostic procedures by highlighting the key features of the fundus image. In this research work, we have emulated the images plagued by distortions by degrading the images based on multiple different combinations of Light Transmission Disturbance, Image Blurring and insertion of Retinal Artifacts. InceptionV3, ResNet-50 and InceptionResNetV2 were trained and used to classify retinal fundus images based on their severity level and then further used in the creation of a browser-based application, which implements the Integration Gradient (IG) Attribution Mask on the input image and demonstrates the predictions made by the model and the probability associated with each class.