Classification of Diabetic Retinopathy using Pre-Trained Deep Learning Models

TL;DR

This study develops a computer-aided diagnosis system using pre-trained deep learning models to classify diabetic retinopathy stages from retinal images, demonstrating varying levels of accuracy across different CNN architectures.

Contribution

It introduces a novel application of fine-tuned pre-trained CNNs for multi-class diabetic retinopathy classification using fundus images.

Findings

MobileNet achieved an AUC of 0.70

InceptionResNetV2 achieved an AUC of 0.69

Models showed potential for automated DR diagnosis

Abstract

Diabetic Retinopathy (DR) stands as the leading cause of blindness globally, particularly affecting individuals between the ages of 20 and 70. This paper presents a Computer-Aided Diagnosis (CAD) system designed for the automatic classification of retinal images into five distinct classes: Normal, Mild, Moderate, Severe, and Proliferative Diabetic Retinopathy (PDR). The proposed system leverages Convolutional Neural Networks (CNNs) employing pre-trained deep learning models. Through the application of fine-tuning techniques, our model is trained on fundus images of diabetic retinopathy with resolutions of 350x350x3 and 224x224x3. Experimental results obtained on the Kaggle platform, utilizing resources comprising 4 CPUs, 17 GB RAM, and 1 GB Disk, demonstrate the efficacy of our approach. The achieved Area Under the Curve (AUC) values for CNN, MobileNet, VGG-16, InceptionV3, and InceptionResNetV2 models are 0.50, 0.70, 0.53, 0.63, and 0.69, respectively.