ArticleNature biomedical engineering2026
Benchmarking foundation models as feature extractors for weakly supervised computational pathology.
Article in Nature biomedical engineering, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 53 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
53 citing papers in PubMed.
- PathScaleBench: A Multidimensional Benchmark of Cross-Scale Representation Behavior and Magnification-Shift Robustness in Pathology Foundation Models.Journal of imaging informatics in medicine · 2026Article
- ProtoSurv: prototype-guided adaptation of computed tomography foundation model for lung-cancer prognosis prediction.Visual computing for industry, biomedicine, and art · 2026Article
- Article
- Ensemble learning of pathology foundation models for precision oncology.Cancer cell · 2026Article
- A Boveri perspective on cancer biomarker testing using artificial intelligence.NPJ precision oncology · 2026Review
- Leakage-Controlled Classification of Dataset-Derived Ordinal p53-Signature Size Categories in Fallopian-Tube Immunohistochemistry.Diagnostics (Basel, Switzerland) · 2026Article
- Artificial intelligence-assisted histopathological diagnosis of endocervical gastric-type adenocarcinoma: a multicenter model development and validation study.The journal of pathology. Clinical research · 2026Article
- The Missing Millions: Building Cancer Pathology Artificial Intelligence for Safety Net Populations.Mayo Clinic proceedings. Digital health · 2026Review
- Histological aging signatures for monitoring tissue-specific aging and disease.Nature medicine · 2026Article
- A multimodal murmuration for immunotherapy.Nature medicine · 2026Article
- Review
- Deep Learning-Assisted Quality Control of Histology Teaching Slides: Detection and Localization of Tissue Fold Artifacts in H&E-Stained Images.Bioengineering (Basel, Switzerland) · 2026Article
- Domain Generalization of Histopathology Foundation Models in Multicenter, Multi-Scanner Cohorts: A Comparative Benchmark.Journal of imaging · 2026Article
- Genome-scale molecular profiling from routine histopathology with a multimodal pathology foundation model.Research square · 2026Article
- REMIL-IBD: Region-filtered multiple instance learning for interpretable slide-level grading of inflammatory bowel disease.Journal of pathology informatics · 2026Article
- AI-based digital pathology and spatial proteomics enable precision oncology: A case report of recurrent melanoma in a young patient.NPJ precision oncology · 2026Article
- A benchmark study of vision and pathology foundation models for computational pathology.Nature communications · 2026Article
- A deep learning framework for efficient pathology image analysis.Nature communications · 2026Article
- Towards robust foundation models for digital pathology.Nature communications · 2026Article
- Compositional and interpretable representation of histology using AI foundation models and sparse autoencoders.bioRxiv : the preprint server for biology · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
16 authors.
Funding
Abstract
Numerous pathology foundation models have been developed to extract clinically relevant information. There is currently limited literature independently evaluating these foundation models on external cohorts and clinically relevant tasks to uncover adjustments for future improvements. Here we benchmark 19 histopathology foundation models on 13 patient cohorts with 6,818 patients and 9,528 slides from lung, colorectal, gastric and breast cancers. The models were evaluated on weakly supervised tasks related to biomarkers, morphological properties and prognostic outcomes. We show that a vision-language foundation model, CONCH, yielded the highest overall performance when compared with vision-only foundation models, with Virchow2 as close second, although its superior performance was less pronounced in low-data scenarios and low-prevalence tasks. The experiments reveal that foundation models trained on distinct cohorts learn complementary features to predict the same label, and can be fused to outperform the current state of the art. An ensemble combining CONCH and Virchow2 predictions outperformed individual models in 55% of tasks, leveraging their complementary strengths in classification scenarios. Moreover, our findings suggest that data diversity outweighs data volume for foundation models.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.