评测病理模型对组织空间结构的理解能力，发现不同预训练方法各有侧重。
Benchmarking Pathology Foundation Models for Spatial Domain Understanding
- 用病理切片与空间转录组配对数据构建空间识别任务
- 在19个编码器上评估，发现预训练方式影响空间表征差异
- 适合想提升模型空间感知能力的研究者和临床算法开发者
病理基础模型（PFM）已成为从全切片图像（WSI）中学习可迁移表征的核心方法，通常通过下游临床任务进行评估。然而这类任务级评估难以揭示表征本身所包含的信息，尤其无法判断嵌入是否能区分有意义的组织区域及其空间关系。本文提出SpaPath-Bench，一个面向表征层面的空间理解能力评测基准。该基准将配对的全切片图像与空间转录组（ST）数据上的空间域识别（SDI）建模为诊断任务，收集了42个公开的配对数据集，支持19个编码器与7种SDI方法的大规模评估，并通过三种互补标准衡量分割质量：无监督空间一致性、转录组参考一致性、专家参考一致性。在83,000次运行中，结果显示不同预训练范式捕捉了组织空间结构的不同方面，为构建下一代具备空间感知能力的计算病理模型提供实用指导。代码与数据流程已开源。
原文摘要 · Abstract (English)
Pathology foundation models (PFMs) have emerged as a core approach for learning transferable representations from whole slide images (WSIs), and they are typically benchmarked through downstream clinical endpoints. While such task level evaluations are indispensable, they offer limited insight into what the representations themselves encode, particularly whether PFM embeddings can distinguish meaningful tissue regions and capture their spatial relationships. We present SpaPath-Bench, a representation level benchmark designed to diagnose spatial representation capability in PFMs. SpaPath-Bench formulates spatial domain identification (SDI) on paired whole slide image and spatial transcriptomics (ST) data as a diagnostic task. It curates 42 public paired WSI and ST slides, enables large scale evaluation across 19 encoders and seven SDI methods, and measures partition quality using three complementary criteria: unsupervised spatial coherence, transcriptomics referenced agreement, and expert referenced agreement. Across 83K runs, SpaPath-Bench reveals that different pretraining paradigms capture distinct aspects of tissue spatial architecture, and it provides practical guidance for building the next generation of spatially aware computational pathology models. Code and data pipelines are publicly available at https://bokai-zhao.github.io/SpaPath-benchboard/.
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。