Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing
This paper proposes a novel architecture for retinal fundus image classification using sparse conditional computation with Guided Context Gating and Mixture-of-Experts.
Proposed a novel architecture for retinal fundus image classification using sparse conditional computation with interpretable, data-driven expert routing.
Keywords
Before reading this…
Applications
- →Retinal fundus image classification
To understand this paper, make sure you know these concepts first:
- Deep learningfind papers →
- Computer visionfind papers →
Abstract
More Like ThisRetinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution. We propose a novel architecture that resolves this via sparse conditional computation, pairing a Guided Context Gating (GCG) spatial attention front-end with a sparsely-routed Mixture-of-Experts (MoE) block operating over feature tokens. Crucially, this routing yields an interpretable, data-driven decomposition. Expert allocation is significantly disease-dependent (p < 0.001), with the healthy Normal state and morphologically distinct pathologies (e.g., ERM, AMD) isolating to dedicated experts. On a five-class, patient-disjoint 5-fold cross-validation benchmark, our model achieves 0.912 +/- 0.008 macro AUC and 0.653 +/- 0.014 macro F1. Furthermore, Grad-CAM++ and post-MoE t-SNE visualizations confirm that expert routing aligns with localized lesions and geometrically maps co-occurring cases between their constituent clusters, positioning sparse MoE as an interpretable approach to multi-disease retinal screening.