发表机构
Nanjing University of Science and Technology; Agency for Science, Technology and Research (A*STAR); Southeast University; Jiangnan University; Westlake University（南京理工大学; 新加坡科技研究局; 东南大学; 江南大学; 西湖大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对生存预测中多模态特征对齐不足与空间异质性处理粗糙的问题，提出锚定驱动的多模态多尺度专家选择框架，通过语义锚点对齐和分层专家混合实现精准预测与可解释性。
AI 中文摘要
组织病理学全切片图像（WSIs）与转录组谱的整合分析在癌症生存预测方面具有显著前景。然而，现有方法通常将多模态特征直接投影到共享潜在空间，缺乏显式对齐，导致不匹配的形态学线索与分子信号纠缠。此外，当前的融合策略往往对WSIs的极端空间异质性进行统一处理，缺乏自适应地优先考虑个体患者临床相关组织尺度的机制。为解决这些局限性，我们提出了一种锚定驱动的多模态多尺度专家选择（AM$^2$ES）框架用于生存预测。具体而言，我们提出了一种锚定驱动的多模态融合（AMF）模块，该模块引入可学习的语义锚点作为跨模态中介，通过强制转录组特征与多尺度病理表示之间的结构正则化对齐来弥合语义鸿沟。在此对齐的语义空间基础上，我们进一步设计了一个分层专家混合（H-MoE）选择模块，以解耦分层预后选择过程。模拟病理学家的诊断工作流程，H-MoE执行（i）尺度内专家过滤，以区分性地识别每个放大倍数下的显著肿瘤区域，以及（ii）尺度间层级路由，以动态加权并选择最具信息量的分辨率级别。在多个TCGA癌症队列上的大量实验表明，我们的AM$^2$ES实现了最先进的性能，同时通过可视化特定分子通路如何驱动跨组织尺度的专家路由决策，提供了细粒度的可解释性。代码将在此https URL发布。
英文摘要
The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival prediction. However, existing methods typically project multi-modal features directly into a shared latent space without explicit alignment, leading to the entanglement of mismatched morphological cues and molecular signals. Furthermore, current fusion strategies often treat the extreme spatial heterogeneity of WSIs uniformly, lacking mechanisms to adaptively prioritize clinically relevant tissue scales for individual patients. To address these limitations, we propose an Anchor-driven Multi-modal Multi-scale Expert Selection (AM$^2$ES) framework for survival prediction. Specifically, we present an Anchor-driven Multi-modal Fusion (AMF) module, which introduces learnable semantic anchors as cross-modal mediators to bridge the semantic gap by enforcing a structurally regularized alignment between transcriptomic features and multi-scale pathology representations. Built upon this aligned semantic space, we further design a Hierarchical Mixture-of-Experts (H-MoE) selection module to decouple the hierarchical prognostic selection process. Mimicking the pathologist's diagnostic workflow, H-MoE performs (i) Intra-scale Expert Filtering to discriminatively identify salient tumor regions within each magnification, and (ii) Inter-scale Hierarchy Routing to dynamically weight and select the most informative resolution levels. Extensive experiments on multiple TCGA cancer cohorts demonstrate that our AM$^2$ES achieves state-of-the-art performance while offering fine-grained interpretability by visualizing how specific molecular pathways drive the expert routing decisions across tissue scales. The code will be released at https://github.com/taozh2017/AM2ES.
Comments15 pages, 6 figures, 7 tables
