Benchmarking Pathology Foundation Models for Spatial Domain Understanding

• URL: http://arxiv.org/abs/2605.25764v1
• Date: Mon, 25 May 2026 12:18:32 GMT
• Title: Benchmarking Pathology Foundation Models for Spatial Domain Understanding
• Abstract summary: We present SpaPath-Bench, a representation level benchmark designed to diagnose spatial representation capability in PFMs.<n>SpaPath-Bench formulates spatial domain identification on paired whole slide image and spatial transcriptomics (ST) data as a diagnostic task.<n>It curates 42 public WSI and ST slides, enables large scale evaluation across 19 encoders and seven SDI methods, and measures partition quality using three complementary criteria.
• Score: 12.450466280086184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• Semantic-Aware Subgraph State Space Model for WSI Classification in Histopathology [10.122580025041303]
  We propose the Semantic-Aware Subgraph State Space Model (SASG-SSM) for whole slide image (WSI) classification.<n>SASG-SSM approximates irregularly shaped semantic units by adaptively grouping spatially connected patches.<n>This module integrates local structural information within semantic units with global contextual information arising from their distribution and co-occurrence.
  arXiv  Detail & Related papers  (2026-09-03T11:26:43Z)
• P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing [0.9329978164030672]
  position-prompted PCA (P3CA) is an encoder-agnostic method for local probing of channel-rich spatial tensors.<n>We implement P3CA in EmbedVision, an interactive 3D Slicer-based workflow, and evaluate it across natural images, colorectal pathology foundation-model embeddings, and spatial transcriptomic tensors.
  arXiv  Detail & Related papers  (2026-08-10T18:42:38Z)
• Probing Geospatial SSL Representations with Environmental Signals [51.908606610432194]
  Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task.<n>We ask a different question: do SSL representations preserve statistical associations with environmental variables that co-vary with the imaging process?<n>To answer this question, we probe SSL representations using co-located ERA5 reanalysis variables, a global dataset of physically consistent environmental variables.
  arXiv  Detail & Related papers  (2026-07-06T15:24:25Z)
• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation [8.483387656208363]
  Whole-slide images (WSIs) digitize tissue specimens at gigapixel resolution.<n>Current methods implicitly embed patch representations in homogeneous Euclidean spaces.<n>We introduce a hybrid hyperbolic-Euclidean representation that embeds WSI features in dual geometric spaces.
  arXiv  Detail & Related papers  (2026-05-06T17:33:30Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• PathSegDiff: Pathology Segmentation using Diffusion model representations [63.20694440934692]
  We propose PathSegDiff, a novel approach for histopathology image segmentation that leverages Latent Diffusion Models (LDMs) as pre-trained featured extractors.<n>Our method utilizes a pathology-specific LDM, guided by a self-supervised encoder, to extract rich semantic information from H&E stained histopathology images.<n>Our experiments demonstrate significant improvements over traditional methods on the BCSS and GlaS datasets.
  arXiv  Detail & Related papers  (2025-04-09T14:58:21Z)
• A Graph-Based Framework for Interpretable Whole Slide Image Analysis [86.37618055724441]
  We develop a framework that transforms whole-slide images into biologically-informed graph representations.<n>Our approach builds graph nodes from tissue regions that respect natural structures, not arbitrary grids.<n>We demonstrate strong performance on challenging cancer staging and survival prediction tasks.
  arXiv  Detail & Related papers  (2025-03-14T20:15:04Z)
• PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model [77.00221501105788]
  Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification.<n>We present the first work that studies the generalizability of state space models (SSMs) in DG PCC.<n>We propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-08-24T12:53:48Z)
• WEEP: A method for spatial interpretation of weakly supervised CNN models in computational pathology [0.36096289461554343]
  We propose a novel method, Wsi rEgion sElection aPproach (WEEP), for model interpretation. We demonstrate WEEP on a binary classification task in the area of breast cancer computational pathology.
  arXiv  Detail & Related papers  (2024-03-22T14:32:02Z)
• EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models [52.3015009878545]
  We develop an image segmentor capable of generating fine-grained segmentation maps without any additional training. Our framework identifies semantic correspondences between image pixels and spatial locations of low-dimensional feature maps. In extensive experiments, the produced segmentation maps are demonstrated to be well delineated and capture detailed parts of the images.
  arXiv  Detail & Related papers  (2024-01-22T07:34:06Z)
• The Whole Pathological Slide Classification via Weakly Supervised Learning [7.313528558452559]
  We introduce two pathological priors: nuclear disease of cells and spatial correlation of pathological tiles. We propose a data augmentation method that utilizes stain separation during extractor training. We then describe the spatial relationships between the tiles using an adjacency matrix. By integrating these two views, we designed a multi-instance framework for analyzing H&E-stained tissue images.
  arXiv  Detail & Related papers  (2023-07-12T16:14:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.