用空间感知的最优传输路由，让专家模型均衡分工，提升病理切片分类效果。
Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification
- 基于区域图与熵正则最优传输，约束专家负载均衡
- 在4个数据集上性能媲美强基线，外推测试AUC达0.845±0.019
- 适合需要精细分工的病理图像分析场景
多实例学习（MIL）是计算病理学中处理千兆像素全切片图像（WSI）分类的主流框架。然而现有MIL聚合器将所有实例经由共享路径处理，限制了其对切片内病理异质性的专业化能力。混合专家（MoE）方法通过将实例分配给专业子网络提供自然解决方案，但未受控的Softmax路由可能导致严重不均衡，少数专家承担大部分任务，使混合结构退化为近似单路径方案。为此，我们提出ROAM（Region-graph OptimAl-transport Mixture-of-experts），一种空间感知的MoE-MIL聚合器，通过容量受限的熵正则最优传输路由区域标记至专家池，从构造上促进专家均衡使用。ROAM作用于空间区域标记，这些标记由密集块袋压缩生成，与局部组织邻域对齐；引入两个关键机制：(i) 区域到专家分配建模为带显式每切片容量边际的熵正则最优传输（Sinkhorn），无需辅助负载均衡损失即可强制均衡；(ii) 图正则化Sinkhorn迭代，将路由分配在空间区域图上扩散，促使相邻区域协同路由至相同专家。在四个WSI基准上评估，使用冻结的预训练模型特征，ROAM表现媲美强大基线，在NSCLC外推测试（TCGA-CPTAC）中达到外部AUC 0.845 ± 0.019。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。