AI 中文总结
本研究提出无需训练的审计框架，利用 TabPFN 探针评估病理学基础模型在 HEST-1k 数据上编码分子程序的生物学对齐及其跨组织、患者和扰动下的可靠性。
AI 中文摘要
组织学和转录组学提供了组织生物学的互补视图，分别捕捉空间形态和分子活性。病理学基础模型（PFMs）从 H&E 图像中学习丰富的形态学表征，然而仅凭强大的下游性能并不能确定这些表征是否编码了具有生物学意义且稳健的分子信息。我们提出了一种**无需训练的可信审计框架**，用于评估冻结的 PFMs 中的生物学对齐，该框架利用来自 HEST-1k 的空间配对组织学和转录组学数据，在**覆盖三个器官的 240 个样本**上进行评估。使用多个冻结的 PFMs 提取 H&E 表征，而基因表达被聚合为生物学可解释的通路级程序。我们使用 TabPFN 作为预训练探针，量化在无需任务特定梯度更新的情况下，这些分子程序可从冻结图像表征中解码的程度。除了预测性能外，我们的审计还检查了通路可解码性是否跨组织切片、患者组和组织类型泛化；表征是否表现出切片级或其他捷径依赖；以及预测在小图像扰动和上下文重采样下是否保持稳定。这种多组织评估区分了持续编码的分子程序与那些组织特异性、不稳定或对捷径敏感的程序。因此，我们的框架提供了一种系统方法，用于评估**病理学基础模型编码了哪些生物学信息，以及这些信息在临床相关变异源下以何种可靠性持续存在**。
英文摘要
Histology and transcriptomics provide complementary views of tissue biology, capturing spatial morphology and molecular activity, respectively. Pathology foundation models (PFMs) learn rich morphological representations from H&E images, yet strong downstream performance alone does not establish whether these representations encode biologically meaningful and robust molecular information. We present a **training-free framework for auditing biological alignment in frozen PFMs** using spatially paired histology and transcriptomics from HEST-1k, evaluated on **240 samples spanning three organs**. Multiple frozen PFMs are used to extract H&E representations, while gene expression is aggregated into biologically interpretable pathway-level programs. We use TabPFN as a pretrained probe to quantify the extent to which these molecular programs can be decoded from frozen image representations without task-specific gradient updates. Beyond predictive performance, our audit examines whether pathway decodability generalizes across tissue sections, patient groups, and tissue types; whether representations exhibit section-level or other shortcut dependencies; and whether predictions remain stable under small image perturbations and context resampling. This multi-tissue evaluation distinguishes molecular programs that are consistently encoded from those that are tissue-specific, unstable, or shortcut-sensitive. Our framework therefore provides a systematic approach for assessing not only **what biological information pathology foundation models encode, but also how reliably that information persists under clinically relevant sources of variation**.
