Deep learning based retinal disease classification using an autoencoder and generative adversarial network

Abstract

Human eyesight relies heavily on retinal tissue, vision loss include infections of the retina and either a delay in treatment or the disease remaining untreated. Identifying retinopathy from retinal fundus image is a vital and diagnostic system performance depends on image quality and quantity. Furthermore, the diagnosis is prone to errors when a large imbalanced database is used. Hence, a fully automated retina disease prediction system is indispensable to minimize human intervention, increase the performance of the disease diagnostic system, and support ophthalmologists in conducting speedy and accurate investigations. Advancements in deep learning have remarkable results in identifying retinopathy from retinal fundus images. However, conventional deep-learning approaches struggle to learn enough in-depth features to identify aspects of mild retinal disease. To address this, integrates a deep autoencoder-based diagnostic system with a ResNet-based generative adversarial network (RGAN) to find retinal disease. This integrated model exploits a ResNet-50 structure to generate synthetic images to handle higher FAR and class imbalance-related problems and a deep autoencoder to categorize the retinal fundus pictures into benign and malicious. The proposed RGAN engenders synthetic images to train the diagnostic and real systems. The experimental outcomes have been implemented, and the recommended RGAN model increases the accuracy ratio of 95.6%, sensitivity ratio of 96.4%, specificity ratio of 97.3%, and F1-score ratio of 93.4% compared to other popular techniques.