发表机构
National College for Excellent Engineers; Beihang University; School of Biological Science and Medical Engineering; College of Engineering; Peking University（卓越工程师学院; 北京航空航天大学; 生物与医学工程学院; 工学院; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对WSI分类中传统方法碎片化语义单元、难建模空间关系的问题，提出SASG-SSM框架，通过SASGs保留空间组织、SG-SSM融合局部与全局信息，在多数据集及少样本场景下表现优异。
AI 中文摘要
组织病理学亚型分类依赖于对特征性组织学模式的识别，这些模式可由单个组织结构表达，或由多个结构的空间分布与共现表达，且常跨越不规则形状的组织区域，本研究中将其称为语义单元。然而，传统基于patch的表示可能会碎片化此类单元，且无法明确保留其内部空间组织，同时高效建模大量空间分离单元间的关系仍是一项挑战。为解决这些局限，我们提出了语义感知子图状态空间模型（Semantic-Aware Subgraph State Space Model, SASG-SSM），这是一种用于全切片图像（Whole Slide Image, WSI）分类的灵活高效框架。语义感知子图（Semantic-Aware Subgraphs, SASGs）通过在类别不可知的视觉语义先验引导下自适应分组空间相连的patch，近似不规则形状的语义单元；将patch表示为带有邻接边的图节点，SASGs保留了其内部空间组织，而非将其视为无序集合。子图状态空间模块（Subgraph State Space Module, SG-SSM）随后结合了用于子图内部拓扑编码的图神经网络编码器，以及用于大量子图间高效上下文建模的基于Mamba的状态空间编码器；该模块将语义单元内的局部结构信息，与WSI中其分布及共现产生的全局上下文信息相融合，同时高效建模大量空间分布的区域。在四个WSI亚型分类数据集上开展的大量实验表明，该模型相较于代表性的最先进方法具有一致优势；在小队列和少样本设置下的进一步评估，验证了其在有限训练数据下的鲁棒性与数据效率。代码将发布于该https://URL。
英文摘要
Histopathological subtyping relies on the recognition of characteristic histological patterns. These patterns may be expressed by individual tissue structures or by the spatial distribution and co-occurrence of multiple structures, and they often span irregularly shaped tissue regions, termed semantic units in this work. However, conventional patch-based representations may fragment such units and fail to explicitly preserve their internal spatial organization, while efficiently modeling relationships among numerous spatially separated units remains challenging. To address these limitations, we propose the Semantic-Aware Subgraph State Space Model (SASG-SSM), a flexible and efficient framework for whole slide image (WSI) classification. Semantic-Aware Subgraphs (SASGs) first approximate irregularly shaped semantic units by adaptively grouping spatially connected patches guided by class-agnostic visual-semantic priors. By representing patches as graph nodes with adjacency edges, SASGs preserve their internal spatial organization rather than treating them as an unordered set. A Subgraph State Space Module (SG-SSM) subsequently combines a graph neural network encoder for intra-subgraph topology encoding with a Mamba-based state space encoder for efficient contextualization across large numbers of subgraphs. This module integrates local structural information within semantic units with global contextual information arising from their distribution and co-occurrence across the WSI, while efficiently modeling a large number of spatially distributed regions. Extensive experiments across four WSI subtyping datasets demonstrate consistent advantages over representative state-of-the-art methods. Further evaluations under small-cohort and few-shot settings demonstrate robustness and data efficiency under limited training data. Code will be released at https://github.com/HLSvois/SASG-SSM.
