A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Histopathology

2026-03-16

AI Summary

This study addresses the inadequate performance of existing general-purpose histopathology foundation models on non-neoplastic chronic kidney disease tasks. We present the first comprehensive evaluation framework tailored to renal pathology, integrating multiple stains, scales, and tasks, and systematically assess 11 publicly available foundation models across 11 kidney-specific downstream tasks. To ensure rigor, we employ repeated stratified group cross-validation and nested cross-validation, complemented by Friedman tests, Wilcoxon signed-rank tests, and Holm–Bonferroni correction. Our findings reveal that while models perform adequately on mesoscopic structural diagnosis, they exhibit significant limitations in microscopic structure recognition, complex phenotype interpretation, and prognostic inference, highlighting their constrained ability to capture subtle renal pathological signals. The reproducible evaluation toolkit, kidney-hfm-eval, is openly released.

Technology Category

• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning
• Machine Learning: Other Foundations of Machine Learning
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Histopathology foundation models (HFMs), pretrained on large-scale cancer datasets, have advanced computational pathology. However, their applicability to non-cancerous chronic kidney disease remains underexplored, despite coexistence of renal pathology with malignancies such as renal cell and urothelial carcinoma. We systematically evaluate 11 publicly available HFMs across 11 kidney-specific downstream tasks spanning multiple stains (PAS, H&E, PASM, and IHC), spatial scales (tile and slide-level), task types (classification, regression, and copy detection), and clinical objectives, including detection, diagnosis, and prognosis. Tile-level performance is assessed using repeated stratified group cross-validation, while slide-level tasks are evaluated using repeated nested stratified cross-validation. Statistical significance is examined using Friedman test followed by pairwise Wilcoxon signed-rank testing with Holm-Bonferroni correction and compact letter display visualization. To promote reproducibility, we release an open-source Python package, kidney-hfm-eval, available at https://pypi.org/project/kidney-hfm-eval/ , that reproduces the evaluation pipelines. Results show moderate to strong performance on tasks driven by coarse meso-scale renal morphology, including diagnostic classification and detection of prominent structural alterations. In contrast, performance consistently declines for tasks requiring fine-grained microstructural discrimination, complex biological phenotypes, or slide-level prognostic inference, largely independent of stain type. Overall, current HFMs appear to encode predominantly static meso-scale representations and may have limited capacity to capture subtle renal pathology or prognosis-related signals. Our results highlight the need for kidney-specific, multi-stain, and multimodal foundation models to support clinically reliable decision-making in nephrology.

Problem

• histopathology foundation models
• chronic kidney disease
• computational pathology
• renal pathology
• prognostic inference

Innovation

• Histopathology foundation models
• Chronic kidney disease
• Multi-stain benchmarking
• Computational pathology
• Reproducible evaluation