TopoSlide：拓扑信息引导的组织病理全切片图像表征学习
TopoSlide: Topologically-Informed Histopathology Whole Slide Image Representation Learning
把持续同调这类拓扑描述子当作图像块聚类空间排布的监督信号，用条件多任务目标训练ViT，为视觉表征学习提供了一种可复用的全局结构归纳偏置，也可用于检索时的拓扑条件控制。
原文依据 leverages persistent homology from topological data analysis to capture the global spatial organization of tissue architecture in WSIs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论组织病理全切片图像（WSI）是十亿像素级图像，在生成既能捕捉局部组织学特征、又能刻画其全局空间组织的有效表征方面存在显著挑战。当前的病理基础模型主要关注局部图像块级特征，而忽视了病理学家用于诊断与预后所依赖的复杂空间关系。我们提出 TopoSlide，一种新颖的自监督表征学习框架，利用拓扑数据分析中的持续同调来捕捉 WSI 中组织结构架构的全局空间组织。该方法借助图像块级嵌入将切片分解为具有组织学意义的簇，再通过拓扑描述子刻画其空间排布。我们训练一个视觉 Transformer，以条件多任务目标从切片级嵌入预测簇的拓扑，该目标将局部图像块特征与其拓扑属性相融合。在肺腺癌与乳腺癌队列上评估，TopoSlide 取得更优性能：多数投票宏 F1 分数下组织学模式检索最高提升 15%，生存预测与基因突变预测也具竞争力，而训练仅使用数百张切片，相比之下基础模型需数十万张。结果表明，拓扑感知学习为病理表征学习提供了强大的归纳偏置，既带来性能提升，也赋予临床应用新颖的基于拓扑的条件检索能力。我们的代码与模型已公开。
英文原文摘要 1648 字符
Histopathology whole slide images (WSIs) are gigapixel images that present significant challenges in generating effective representations that capture both local histological features and their global spatial organization. Current pathology foundation models focus primarily on local patch-level features while neglecting the complex spatial relationships that pathologists rely on for diagnosis and prognosis. We introduce TopoSlide, a novel self-supervised representation learning framework that leverages persistent homology from topological data analysis to capture the global spatial organization of tissue architecture in WSIs. Our method decomposes slides into histologically meaningful clusters using patch-level embeddings, then characterizes their spatial arrangement through topological descriptors. We train a vision transformer to predict cluster topology from slide-level embeddings using a conditional multi-task objective that integrates local patch features with their topological attributes. Evaluated across lung adenocarcinoma and breast cancer cohorts, TopoSlide achieves superior performance improving histologic pattern retrieval by up to 15% in majority voting macro F1 score, and competitive survival and gene mutation predictions, while training on only hundreds of slides compared to hundreds of thousands for foundation models. Our results demonstrate that topology-aware learning provides a powerful inductive bias for pathology representation learning, enabling both improved performance and novel topology-based conditional retrieval capabilities for clinical applications. Our code and models are publicly available.