基于显著性引导的稀疏专家路由的共现视网膜病理解缠
Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing
浏览论文内容
中文总结 AI 辅助
该研究针对视网膜眼底图像共现病理问题，提出显著性引导的稀疏专家路由架构，在五类别患者不相交基准上取得0.912±0.008宏AUC等性能，验证了方法的可解释性与多疾病筛查价值。
中文摘要 AI 辅助
视网膜眼底图像常表现出多种共现病理，但标准深度学习分类器对每张图像应用静态、相同的计算，不考虑潜在的疾病分布。我们提出一种新型架构，通过稀疏条件计算解决该问题，将显著性引导的上下文门控（Guided Context Gating, GCG）空间注意力前端与在特征令牌上运行的稀疏路由专家混合（Mixture-of-Experts, MoE）块配对。关键是，这种路由产生可解释的、数据驱动的分解：专家分配显著依赖疾病（p < 0.001），健康正常状态及形态不同的病理（如ERM、AMD）被隔离到专用专家。在五类别、患者不相交的5折交叉验证基准上，我们的模型达到0.912 ± 0.008的宏AUC和0.653 ± 0.014的宏F1。此外，Grad-CAM++和MoE后t-SNE可视化证实，专家路由与局部病变对齐，并在其组成簇之间几何映射共现病例，使稀疏MoE成为可解释的多疾病视网膜筛查方法。
英文摘要
Retinal 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.
