[论文] Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation

论文概要

研究领域: CV 作者: Enhui Chai, Sicheng Chen, Tianyi Zhang, Chad Wong, Kecheng Huang, Zeyu Liu, Fei Xia 发布时间: 2026-05-06 arXiv: 2605.05164

中文摘要

准确的组织病理学图像分析对疾病诊断和治疗规划至关重要。全切片图像（WSIs）以千兆像素分辨率数字化组织标本，是这一过程的基础，但需要聚合数千个patch进行切片级预测。多实例学习（MIL）通过两阶段范式应对这一挑战，解耦瓦片级嵌入和切片级预测。然而，大多数现有方法隐式地将patch表示嵌入到同质欧几里得空间中，忽视了病理组织的层次化组织和区域异质性。这限制了当前模型捕获全局组织架构和细粒度细胞形态的能力。为解决这一局限，我们引入了一种混合双曲-欧几里得表示，将WSI特征嵌入到双重几何空间中，实现对层次化组织结构和局部形态细节的互补建模。基于这一表述，我们开发了BatMIL，一个利用两种几何空间的WSI分类框架。为建模数千个patch之间的长程依赖，我们采用结构化状态空间序列模型（S4）主干，以线性计算复杂度编码patch序列。此外，为考虑区域异质性，我们引入了块级混合专家（MoE）模块，将patch分组为区域并动态路由到专门的子网络，在提高表示能力的同时减少冗余计算。在涵盖六种癌症类型的七个WSI数据集上的大量实验表明，BatMIL在切片级分类任务中持续超越SOTA MIL方法。这些结果表明，几何感知表示学习为下一代计算病理学提供了有前景的方向。

原文摘要

Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specimens at gigapixel resolution, are fundamental to this process but require aggregating thousands of patches for slide-level predictions. Multiple Instance Learning (MIL) tackles this challenge with a two-stage paradigm, decoupling tile-level embedding and slide-level prediction. However, most existing methods implicitly embed patch representations in homogeneous Euclidean spaces, overlooking the hierarchical organization and regional heterogeneity of pathological tissues. This limits current models' ability to capture global tissue architecture and fine-grained cellular morphology. To address this limitation, we introduce a hybrid hyperbolic-Euclidean representation that embeds WSI features in dual geometric spaces, enabling complementary modeling of hierarchical tissue structures and local morphological details. Building on this formulation, we develop BatMIL, a WSI classification framework that leverages both geometric spaces. To model long-range dependencies among thousands of patches, we employ a structured state space sequence model (S4) backbone that encodes patch sequences with linear computational complexity. Furthermore, to account for regional heter质性, we introduce a chunk-level mixture-of-experts (MoE) module that groups patches into regions and dynamically routes them to specialized subnetworks, improving representational capacity while reducing redundant computation. Extensive experiments on seven WSI datasets spanning six cancer types demonstrate that BatMIL consistently outperforms state-of-the-art MIL approaches in slide-level classification tasks. These results indicate that geometry-aware representation learning offers a promising direction for next-generation computational pathology.

自动采集于 2026-05-08

#论文 #arXiv #CV #小凯