Loading
companiesCompany
Microsoft (Research and Health AI)
Microsoft co-developed Prov-GigaPath and BiomedCLIP and is the compute partner for Paige's Virchow2.
Overview
Microsoft Research and its Health AI group, based in Redmond and part of Microsoft, listed as MSFT, co-developed the Prov-GigaPath and BiomedCLIP models and supplied the Azure compute for Paige's Virchow series. Prov-GigaPath, published in Nature in 2024, was the largest open pathology foundation model of its time, BiomedCLIP is its biomedical vision-language model, and the BioEmu protein dynamics model is also linked. OnCo connects it to Prov-GigaPath, Virchow and Virchow2, BioEmu and Paige AI. Whether openly released foundation models or proprietary ones become the base for clinical pathology AI is the question its releases bear on. Prov-GigaPath has its own technology page.
Similar pages
- InstitutionProvidence Health & Services
Shares Prov-GigaPath (Microsoft, Providence) and the tag ai.
- CompanyXaira Therapeutics
Shares AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag ai.
- CompanyGoogle DeepMind (and Google Research)
Shares AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag ai.
- TechnologyChemistry42 and Pharma.AI (Insilico)
Shares AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag ai.
- CompanyNVIDIA
Shares AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag ai.
- TreatmentPaige Prostate Detect
Shares Paige AI, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow.
- RoadmapAI in the oncology clinic: from narrow cleared tools to multimodal decision support
Shares Prov-GigaPath (Microsoft, Providence), Virchow / Virchow2 (Paige, MSK), Paige AI, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow.
- IdeaAI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions
Shares Paige AI, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow.
Open-source projects
All open source in oncology →Open-source projects that this organisation maintains, from OnCo's own catalogue: licence and last activity as the repository reported them on the day of the fetch. Listing is not endorsement; check the licence before reuse and the validation before clinical use.
Microsoft's model that samples protein conformational ensembles.
Microsoft's foundation model that segments, detects and recognises objects across nine imaging modalities from a text prompt.
Microsoft and Providence's whole-slide foundation model trained on 1.3 billion tiles, with released weights.