# Pathology & radiology foundation models

Source: https://onco.cc/technologies/pathology-foundation-model/  
OnCo record `pathology-foundation-model` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Pathology and radiology foundation models are AI networks pretrained without labels on over a million slides or scans (Virchow used 1.5 million), then adapted with small task heads to predict mutations, prognosis or treatment response from routine images. They power the FDA-cleared ArteraAI tools, but validation across hospitals and how regulators treat general-purpose models remain unsettled.

## Summary

Virchow (Paige/MSK, 1.5M slides), UNI and CONCH (Harvard), Prov-GigaPath (Microsoft/Providence), PLUTO, and radiology models (Merlin, RadFM). They predict molecular alterations, prognosis, and treatment response from routine H&E and CT, and power the FDA-cleared ArteraAI tools. Multimodal patient-level models integrating genomics, imaging, and notes are in development (e.g., CanSim-style efforts, Tempus, Owkin).

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-04
- Tags: frontier
- Principle: Self-supervised pretraining (DINOv2, contrastive) on unlabelled images; frozen encoder plus small task heads.
- Strengths: Data-efficient adaptation; Discover morphology-genotype links
- Limitations: Validation across sites; Regulatory treatment of general-purpose models

## Sources

- Chen et al., Towards a general-purpose foundation model for computational pathology (Nature Medicine 2024): https://doi.org/10.1038/s41591-024-02857-3
- Vorontsov et al., A foundation model for clinical-grade computational pathology (Nature Medicine 2024): https://doi.org/10.1038/s41591-024-03141-0

## Connected records

- technologies: [AI compute and model platforms for oncology](https://onco.cc/technologies/ai-compute-platforms/), [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [Atlas (Aignostics, Mayo Clinic, Charité)](https://onco.cc/technologies/atlas-aignostics/), [CHIEF (Harvard, Yu Lab)](https://onco.cc/technologies/chief/), [Digital pathology & AI](https://onco.cc/technologies/digital-pathology-ai/), [Digital twins and virtual control arms](https://onco.cc/technologies/digital-twins-trials/), [Federated learning and privacy-preserving AI](https://onco.cc/technologies/federated-learning-medical-ai/), [H-optimus (Bioptimus)](https://onco.cc/technologies/h-optimus/), [Hibou (HistAI)](https://onco.cc/technologies/hibou/), [Merlin (Stanford abdominal CT vision-language model)](https://onco.cc/technologies/merlin-ct/), [Midnight (kaiko.ai)](https://onco.cc/technologies/kaiko-midnight/), [MUSK (Stanford, vision-language pathology)](https://onco.cc/technologies/musk/), [Phikon / Phikon-v2 (Owkin)](https://onco.cc/technologies/phikon/), [PLUTO (PathAI)](https://onco.cc/technologies/pluto/), [Prov-GigaPath (Microsoft, Providence)](https://onco.cc/technologies/prov-gigapath/), [RadFM (generalist radiology foundation model)](https://onco.cc/technologies/radfm/), [Spatial-omics-guided treatment selection](https://onco.cc/technologies/spatial-omics-guided-therapy/), [TITAN (whole-slide multimodal model)](https://onco.cc/technologies/titan/), [UNI and CONCH (Harvard, Mahmood Lab)](https://onco.cc/technologies/uni-conch/), [Virchow / Virchow2 (Paige, MSK)](https://onco.cc/technologies/virchow/), [Whole-slide scanners and image management](https://onco.cc/technologies/whole-slide-scanners/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/)
- companies: [Aidoc](https://onco.cc/companies/aidoc/), [Artera](https://onco.cc/companies/artera/), [Ataraxis AI](https://onco.cc/companies/ataraxis-ai/), [Imagene AI](https://onco.cc/companies/imagene-ai/), [Microsoft (Health & Life Sciences)](https://onco.cc/companies/microsoft/), [Noetik](https://onco.cc/companies/noetik/), [Owkin](https://onco.cc/companies/owkin/), [Paige AI](https://onco.cc/companies/paige/), [Pathos AI](https://onco.cc/companies/pathos-ai/), [Strand AI](https://onco.cc/companies/strand-ai/), [Tempus AI](https://onco.cc/companies/tempus/)
- key papers: [A foundation model for clinical-grade computational pathology and rare cancers detection](https://onco.cc/key-papers/paper-vorontsov-nat-med/), [Towards a general-purpose foundation model for computational pathology](https://onco.cc/key-papers/paper-chen-nat-med/)
- drugs: [ArteraAI Breast](https://onco.cc/drugs/artera-ai-breast/), [ArteraAI Prostate](https://onco.cc/drugs/artera-ai-prostate/), [Paige Prostate Detect](https://onco.cc/drugs/paige-prostate/)
- ideas: [A federated learning consortium of cancer centres that jointly own the models](https://onco.cc/ideas/idea-fund-federated-learning-consortium/), [A pre-competitive consortium to train a shared multimodal cancer foundation model](https://onco.cc/ideas/idea-data-precompetitive-cancer-foundation-model/), [A registry of external validation datasets for cancer AI models, with mandatory reporting](https://onco.cc/ideas/idea-tr2-ai-external-validation-registry/), [A same-week expert second opinion for every rare cancer diagnosis](https://onco.cc/ideas/idea-bio2-rare-cancer-telepathology-network/), [AI second reads to stop borderline lesions being upgraded to cancer](https://onco.cc/ideas/idea-prev-pathology-ai-borderline-anchor/), [AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions](https://onco.cc/ideas/idea-acc-ai-first-pathology-common-cases/), [An open model of every cancer cell state, built from perturbation atlases](https://onco.cc/ideas/idea-moon-open-cancer-cell-state-model/), [An organotropism atlas that predicts where a cancer will spread](https://onco.cc/ideas/idea-bio2-organotropism-atlas/), [Continuous prospective validation for every oncology AI tool after deployment](https://onco.cc/ideas/idea-moon-continuous-ai-validation-registry/), [Digitise the nation's pathology slides and link them to outcomes](https://onco.cc/ideas/idea-data-national-slide-archive/), [Federated training of pathology and radiology models across hospitals](https://onco.cc/ideas/idea-data-federated-learning-imaging/), [Patient-level multimodal foundation models for treatment selection](https://onco.cc/ideas/idea-multimodal-foundation-model/), [Pool every immunotherapy trial's biomarker data into one commons](https://onco.cc/ideas/idea-bio2-io-biomarker-data-commons/), [Turn the map of immune cells inside a tumour into a standardised test](https://onco.cc/ideas/idea-bio2-spatial-signature-cdx/), [Version control and locked reference sets for AI algorithms used as companion diagnostics](https://onco.cc/ideas/idea-tr2-ai-cdx-change-control/), [Whole-patient digital twins validated in prospective randomised trials](https://onco.cc/ideas/idea-moon-validated-digital-twins/)
- people: [Faisal Mahmood](https://onco.cc/people/faisal-mahmood/), [Jakob Nikolas Kather](https://onco.cc/people/jakob-nikolas-kather/), [Thomas J. Fuchs](https://onco.cc/people/thomas-fuchs/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Data silos](https://onco.cc/bottlenecks/b-data-silos/), [No one can predict who responds to immunotherapy](https://onco.cc/bottlenecks/b-immunotherapy-response/), [Not enough oncologists, nurses, pathologists, physicists](https://onco.cc/bottlenecks/b-workforce/)
- terms: [Cancer AI vocabulary (CanSim terms map)](https://onco.cc/terms/cancer-ai-vocabulary/), [Foundation model](https://onco.cc/terms/foundation-model/), [Histology](https://onco.cc/terms/histology/), [Pathology foundation models: UNI, UNI2, Virchow2, CTransPath, CONCH, TITAN](https://onco.cc/terms/pathology-foundation-models/), [Tile and patch encoding of slides](https://onco.cc/terms/tile-patch-encoding/)
- institutions: [Chan Zuckerberg Biohub](https://onco.cc/institutions/cz-biohub/), [Indian Institute of Science](https://onco.cc/institutions/iisc/), [NCT/UCC Dresden, University Hospital Carl Gustav Carus](https://onco.cc/institutions/nct-dresden/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/), [AI in the oncology clinic: from narrow cleared tools to multimodal decision support](https://onco.cc/roadmaps/ai-oncology-clinic/), [Diagnostics roadmap: stains → gene panels → blood tests that decide treatment](https://onco.cc/roadmaps/diagnostics-roadmap/)

---
JSON: https://onco.cc/api/v1/entities/pathology-foundation-model.json