NeoNet: A Novel Deep Learning Model for Retinal Disease Diagnosis and Localization

TL;DR

This paper introduces NeoNet, a deep learning model that accurately detects and localizes retinal diseases with high accuracy and provides explainable predictions.

Contribution

The novel NeoNet architecture achieves 99.5% accuracy for retinal disease diagnosis and offers explainable AI for model decisions.

Findings

NeoNet achieves 99.5% accuracy in detecting retinal diseases like Age-Related Macular Degeneration and Diabetic Retinopathy.

The model highlights critical regions in retinal images to provide explainability for its predictions.

The approach supports earlier and more accurate diagnosis of retinal diseases.

Abstract

Retinal diseases are among the leading causes of vision impairment worldwide, and early detection is essential for enabling personalized treatments and preventing irreversible vision loss. In this paper, we propose a method aimed to identify and localize retinal conditions, i.e., Age-Related Macular Degeneration, Diabetic Retinopathy, and Choroidal Neovascularization, using explainable deep learning. For this purpose, we consider seven fine-tuned convolutional neural networks: MobileNet, LeNet, StandardCNN, CustomCNN, DenseNet, Inception, and EfficientNet. Moreover, we develop a novel architecture i.e., NeoNet, specifically designed for the detection of retinal diseases, achieving an accuracy of 99.5%. Furthermore, with the aim to provide explaianability behind the model decision, we highlight the most critical regions within retinal images influencing the predictions of the model. The obtained results show the ability of the model to detect pathological features, thereby supporting earlier and more accurate diagnosis of retinal diseases.

Figures