What question did this study set out to answer?

To develop an explainable neural network for identifying and grading diabetic retinopathy severity in retinal images.

April 22, 2026Open Access

A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification

SCSimona CorreraUniversity of Molise VSValeria SorgenteUniversity of Molise MCMario CesarelliUniversity of Sannio

Key Points

To develop an explainable neural network for identifying and grading diabetic retinopathy severity in retinal images.
Developed multiple CNN architectures, including a novel FGNet, for image classification.
Trained models on retinal images for varying epochs (10 and 20) to assess performance.
Utilized Gradient-weighted Class Activation Mapping for model explainability.
Achieved an accuracy of 0.75 after 10 epochs and 0.71 after 20 epochs.
Provided visual insights into decision-making processes of the model.

Abstract

Diabetic retinopathy represents one of the leading causes of blindness worldwide, making early diagnosis essential for effective clinical intervention. We propose an explainable method aimed at automatically identifying the severity levels of diabetic retinopathy in retinal images using deep learning. The proposed method considers several convolutional neural network architectures, i.e., VGG16, StandardCNN, ResNet, CustomCNN, EfficientNet, MobileNet, and a novel architecture, i.e., FGNet, specifically designed and developed by the authors for diabetic retinopathy detection. The proposed network achieves an accuracy of 0.75 when trained for 10 epochs and 0.71 for 20 epochs. Explainability behind model prediction is further supported through Gradient-weighted Class Activation Mapping, providing visual insight into the learned decision-making process and potentially supporting early clinical assessment.

KI fragen

Bookmark

View Full Paper