Diabetic Retinopathy Detection Using CNN with Residual Block with DCGAN

TL;DR

This paper presents an automated diabetic retinopathy detection system using CNNs with residual blocks, enhanced by DCGAN-based data augmentation to improve robustness and generalization for early diagnosis.

Contribution

It introduces a novel combination of residual CNN architecture with DCGAN-generated data augmentation for improved DR classification accuracy.

Findings

Enhanced model performance with increased accuracy.

Robustness to real-world retinal image variations.

Effective classification into five DR severity levels.

Abstract

Diabetic Retinopathy (DR) is a major cause of blindness worldwide, caused by damage to the blood vessels in the retina due to diabetes. Early detection and classification of DR are crucial for timely intervention and preventing vision loss. This work proposes an automated system for DR detection using Convolutional Neural Networks (CNNs) with a residual block architecture, which enhances feature extraction and model performance. To further improve the model's robustness, we incorporate advanced data augmentation techniques, specifically leveraging a Deep Convolutional Generative Adversarial Network (DCGAN) for generating diverse retinal images. This approach increases the variability of training data, making the model more generalizable and capable of handling real-world variations in retinal images. The system is designed to classify retinal images into five distinct categories, from No DR to Proliferative DR, providing an efficient and scalable solution for early diagnosis and monitoring of DR progression. The proposed model aims to support healthcare professionals in large-scale DR screening, especially in resource-constrained settings.