Guardado en:
Detalles Bibliográficos
Autores principales: Zhao, Bokai, Zhang, Yiyang, Zhu, Yuanchi, Chao, Hanqing, Bai, Long, Ma, Tai, Xu, Minfeng, Song, Ming, Jiang, Tianzi
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.25764
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910255012642816
author Zhao, Bokai
Zhang, Yiyang
Zhu, Yuanchi
Chao, Hanqing
Bai, Long
Ma, Tai
Xu, Minfeng
Song, Ming
Jiang, Tianzi
author_facet Zhao, Bokai
Zhang, Yiyang
Zhu, Yuanchi
Chao, Hanqing
Bai, Long
Ma, Tai
Xu, Minfeng
Song, Ming
Jiang, Tianzi
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25764
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Benchmarking Pathology Foundation Models for Spatial Domain Understanding
Zhao, Bokai
Zhang, Yiyang
Zhu, Yuanchi
Chao, Hanqing
Bai, Long
Ma, Tai
Xu, Minfeng
Song, Ming
Jiang, Tianzi
Computer Vision and Pattern Recognition
Artificial Intelligence
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/.
title Benchmarking Pathology Foundation Models for Spatial Domain Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.25764