Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images

TL;DR

This study evaluates multiple deep learning models for retinal fundus image classification and segmentation, emphasizing explainability techniques to improve transparency and trust in automated diagnosis tools.

Contribution

It introduces a comprehensive comparison of CNN and transformer-based models for retinal image analysis, integrating explainable AI methods to enhance interpretability.

Findings

ResNet101 achieved 94.17% accuracy in classification.

Swin-Unet achieved 86.19% mean pixel accuracy in segmentation.

Explainability techniques like Grad-CAM improve model transparency.

Abstract

Our research focuses on the critical field of early diagnosis of disease by examining retinal blood vessels in fundus images. While automatic segmentation of retinal blood vessels holds promise for early detection, accurate analysis remains challenging due to the limitations of existing methods, which often lack discrimination power and are susceptible to influences from pathological regions. Our research in fundus image analysis advances deep learning-based classification using eight pre-trained CNN models. To enhance interpretability, we utilize Explainable AI techniques such as Grad-CAM, Grad-CAM++, Score-CAM, Faster Score-CAM, and Layer CAM. These techniques illuminate the decision-making processes of the models, fostering transparency and trust in their predictions. Expanding our exploration, we investigate ten models, including TransUNet with ResNet backbones, Attention U-Net with DenseNet and ResNet backbones, and Swin-UNET. Incorporating diverse architectures such as ResNet50V2, ResNet101V2, ResNet152V2, and DenseNet121 among others, this comprehensive study deepens our insights into attention mechanisms for enhanced fundus image analysis. Among the evaluated models for fundus image classification, ResNet101 emerged with the highest accuracy, achieving an impressive 94.17%. On the other end of the spectrum, EfficientNetB0 exhibited the lowest accuracy among the models, achieving a score of 88.33%. Furthermore, in the domain of fundus image segmentation, Swin-Unet demonstrated a Mean Pixel Accuracy of 86.19%, showcasing its effectiveness in accurately delineating regions of interest within fundus images. Conversely, Attention U-Net with DenseNet201 backbone exhibited the lowest Mean Pixel Accuracy among the evaluated models, achieving a score of 75.87%.