FGR-Net:Interpretable fundus imagegradeability classification based on deepreconstruction learning

TL;DR

FGR-Net is a novel deep learning framework that automatically assesses and interprets fundus image quality, enhancing diagnostic accuracy by focusing on relevant retinal structures and providing visual explanations.

Contribution

The paper introduces FGR-Net, combining autoencoder and classifier networks for interpretable fundus image quality assessment, outperforming existing methods.

Findings

Achieved 89% accuracy and 87% F1-score in quality classification.

Autoencoder enhances focus on key retinal structures for interpretability.

Provides visual feedback to assist ophthalmologists in understanding model decisions.

Abstract

The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called FGR-Net to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of 89% and an F1-score of 87%.