Pathology & radiology foundation models
Very large AI models trained on millions of slides or scans that can be adapted to almost any diagnostic question.
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).
How it works
Self-supervised pretraining (DINOv2, contrastive) on unlabelled images; frozen encoder plus small task heads.
- Data-efficient adaptation
- Discover morphology-genotype links
- Validation across sites
- Regulatory treatment of general-purpose models
An FDA-cleared AI test (May 2026) that reads breast cancer slides to estimate recurrence risk in early hormone-positive disease.
The first AI tool cleared by the FDA to predict both prognosis and treatment benefit from a routine biopsy slide, in prostate cancer.
Latest papers
topQuery for this technology: (TITLE:"foundation model" OR ABSTRACT:"foundation model") AND (TITLE:"pathology" OR ABSTRACT:"pathology" OR TITLE:"histopathology" OR ABSTRACT:"histopathology" OR TITLE:"radiology" OR ABSTRACT:"radiology") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about Pathology & radiology foundation models, not a curated reading list.
Pages like this
not linked directly; found by shared links- TechnologyAI-driven drug & target discovery
Shares AI compute and model platforms for oncology, AI that is built but not validated or deployed and the tag frontier.
- TechnologyFLASH radiotherapy
Shares NCT/UCC Dresden – University Hospital Carl Gustav Carus and the tag frontier.
- CompanyPathAI
Shares PLUTO (PathAI), AI second reads to stop borderline lesions being upgraded to cancer, Version control and locked reference sets for AI algorithms used as companion diagnostics, A pre-competitive consortium to train a shared multimodal cancer foundation model.
- CompanyLunit
Shares AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Turn the map of immune cells inside a tumour into a standardised test, AI in radiology, Digital pathology & AI.
- CompanyMicrosoft (Research and Health AI)
Shares Prov-GigaPath (Microsoft, Providence), Virchow / Virchow2 (Paige, MSK), Paige AI.
- IdeaPublic gold-standard datasets for validating every cancer biomarker test
Shares A registry of external validation datasets for cancer AI models, with mandatory reporting, Version control and locked reference sets for AI algorithms used as companion diagnostics, Digital pathology & AI, AI that is built but not validated or deployed.
- IdeaAI quantification of HER2-low and HER2-ultralow
Shares Version control and locked reference sets for AI algorithms used as companion diagnostics, AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Digital pathology & AI, AI that is built but not validated or deployed.
- IdeaAI clears the normal lung screening scans so radiologists read only the suspicious ones
Shares Aidoc, AI in radiology, Not enough oncologists, nurses, pathologists, physicists, AI that is built but not validated or deployed.