CellPath-Bench：面向病理学基础模型的全片细胞表示多维基准
CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models
浏览论文内容
中文总结 AI 辅助
CellPath-Bench是评估冻结病理学基础模型全片细胞表示能力的多维基准，通过对30款模型的测试揭示了细胞类型可解码性的模型差异，为相关审计提供标准化框架。
中文摘要 AI 辅助
病理学基础模型（PFMs）日益被用作通用骨干，但现有基准无法系统评估其全片细胞表示能力，包括细胞类型信息的可解码性，以及此类信息在组织切片、数据集和解剖器官间的可迁移性。我们推出CellPath-Bench，这是一款评估冻结PFMs的细胞分辨率基准。在对52个候选Xenium数据集进行质量控制后，我们构建了涵盖11个器官、包含7079283个细胞的25个空间对齐的H&E-Xenium组织切片面板，这些细胞被协调为细粒度和粗粒度分类体系。CellPath-Bench在配准的核坐标处采样冻结的WSI特征图，并使用标准化多类线性探针对其进行评估。细胞表示优势（CRA）衡量核锚定表示在切片内相对于patch级平均池化的优势，而细胞表示可迁移性（CRT）表征细胞类型可解码性在组织切片、数据集和器官间的泛化能力。我们通过空间读数、放大倍数、分类粒度和评估协议的304920次运行，对30个病理学专用和通用基础模型进行了基准测试。结果显示，细胞类型可解码性及其跨域泛化存在显著的模型依赖差异，产生了不同的多维能力轮廓。CellPath-Bench为审计冻结PFM表示中的细胞信息提供了标准化框架。
英文摘要
Pathology foundation models (PFMs) are increasingly used as general-purpose backbones, yet existing benchmarks cannot systematically diagnose their whole-slide cellular representation capabilities, including the decodability of cell-type information and the transferability of such information across tissue sections, datasets, and anatomical organs. We introduce CellPath-Bench, a cellular-resolution benchmark that evaluates frozen PFMs themselves. Following quality control of 52 candidate Xenium datasets, we construct a panel of 25 spatially aligned H\&E--Xenium tissue sections spanning 11 organs and 7,079,283 cells, harmonized into fine- and coarse-grained taxonomies. CellPath-Bench samples frozen WSI feature maps at registered nuclear coordinates and evaluates them using standardized multiclass linear probes. Cell Representation Advantage (CRA) measures the within-section advantage of nucleus-anchored representations over patch-level mean pooling, while Cell Representation Transferability (CRT) characterizes the generalization of cell-type decodability across tissue sections, datasets, and organs. We benchmark 30 pathology-specific and general-purpose foundation models through 304,920 runs across spatial readouts, magnifications, taxonomic granularities, and evaluation protocols. The results reveal substantial model-dependent differences in cell-type decodability and its cross-domain generalization, yielding distinct multidimensional capability profiles. CellPath-Bench provides a standardized framework for auditing cellular information in frozen PFM representations.
