Guided Context Gating: Learning to leverage salient lesions in retinal fundus images

TL;DR

This paper introduces Guided Context Gating, a novel attention mechanism that enhances the detection of lesions in retinal images, significantly improving accuracy and explainability over existing methods, especially with limited data.

Contribution

The paper presents a new attention mechanism called Guided Context Gating that better captures localized lesion context in retinal images, outperforming existing attention models and Vision Transformers.

Findings

2.63% accuracy improvement over existing attention mechanisms

6.53% accuracy boost over Vision Transformer in retinopathy severity assessment

Enhanced explainability of lesion localization

Abstract

Effectively representing medical images, especially retinal images, presents a considerable challenge due to variations in appearance, size, and contextual information of pathological signs called lesions. Precise discrimination of these lesions is crucial for diagnosing vision-threatening issues such as diabetic retinopathy. While visual attention-based neural networks have been introduced to learn spatial context and channel correlations from retinal images, they often fall short in capturing localized lesion context. Addressing this limitation, we propose a novel attention mechanism called Guided Context Gating, an unique approach that integrates Context Formulation, Channel Correlation, and Guided Gating to learn global context, spatial correlations, and localized lesion context. Our qualitative evaluation against existing attention mechanisms emphasize the superiority of Guided Context Gating in terms of explainability. Notably, experiments on the Zenodo-DR-7 dataset reveal a substantial 2.63% accuracy boost over advanced attention mechanisms & an impressive 6.53% improvement over the state-of-the-art Vision Transformer for assessing the severity grade of retinopathy, even with imbalanced and limited training samples for each class.