区域图最优传输路由用于专家混合的全滑片图像分类
Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification
AI总结：
本文提出ROAM方法，通过区域图最优传输实现平衡的专家利用，提升全滑片图像分类性能。
摘要：
多重实例学习（MIL）是计算病理学中用于千兆像素全滑片图像（WSI）分类的主导框架。然而，当前MIL聚合器将所有实例通过共享路径路由，限制了其在每张滑片固有病理异质性中专业化的能力。混合专家（MoE）方法提供了一种自然的解决方案，通过将实例分配到专门的专家子网络中；然而，无约束的softmax路由可能导致高度不平衡的利用，其中一个或几个专家吸收大部分路由质量，使混合回归到近单路径解决方案。为了解决这些限制，我们提出了ROAM（区域图最优传输混合专家），一种空间感知的MoE-MIL聚合器，通过容量受限的熵最优传输将区域标记路由到专家池器，通过构造促进平衡的专家利用。ROAM在空间区域标记上运行，这些标记通过压缩密集的片段袋为空间分组单元获得，使路由与局部组织邻域对齐，并引入两种关键机制：（i）区域到专家分配公式化为熵最优传输（Sinkhorn）并具有显式的每张滑片容量边际，强制平衡的专家利用而不需辅助负载平衡损失；（ii）图正则化的Sinkhorn迭代扩散路由分配在空间区域图上，鼓励相邻区域共同路由到相同的专家。在四个WSI基准测试上评估，ROAM在冻结基础模型片段嵌入下实现了与强MIL和MoE基线相竞争的性能，并在NSCLC泛化（TCGA-CPTAC）上达到外部AUC 0.845 ± 0.019。
英文摘要：
Multiple Instance Learning (MIL) is the dominant framework for gigapixel whole-slide image (WSI) classification in computational pathology. However, current MIL aggregators route all instances through a shared pathway, constraining their capacity to specialise across the pathological heterogeneity inherent in each slide. Mixture-of-Experts (MoE) methods offer a natural remedy by partitioning instances across specialised expert subnetworks; yet unconstrained softmax routing may yield highly imbalanced utilisation, where one or a few experts absorb most routing mass, collapsing the mixture back to a near-single-pathway solution. To address these limitations, we propose ROAM (Region-graph OptimAl-transport Mixture-of-experts), a spatially aware MoE-MIL aggregator that routes region tokens to expert poolers via capacity-constrained entropic optimal transport, promoting balanced expert utilisation by construction. ROAM operates on spatial region tokens, obtained by compressing dense patch bags into spatially binned units that align routing with local tissue neighbourhoods and introduces two key mechanisms: (i) region-to-expert assignment formulated as entropic optimal transport (Sinkhorn) with explicit per slide capacity marginals, enforcing balanced expert utilisation without auxiliary load-balancing losses; and (ii) graph-regularised Sinkhorn iterations that diffuse routing assignments over the spatial region graph, encouraging neighbouring regions to coherently route to the same experts. Evaluated on four WSI benchmarks with frozen foundation-model patch embeddings, ROAM achieves performance competitive against strong MIL and MoE baselines, and on NSCLC generalisation (TCGA-CPTAC) reaches external AUC 0.845 +- 0.019.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
