Loading
companiesCompany
Owkin
French AI biotech using federated learning across hospitals; first CE-marked AI for MSI prediction from H&E.
Overview
Owkin, based in Paris and New York, is a French AI biotechnology company that uses federated learning across hospitals and produced the first CE-marked AI for predicting microsatellite instability from routine H&E slides. Its products include MSIntuit CRC, RlapsRisk BC for breast cancer relapse risk, the K1.0 agentic biology platform and the Phikon pathology foundation models, alongside federated research consortia. OnCo links it to digital pathology, federated learning and privacy-preserving AI, digital twins and spatial-omics-guided treatment, and to ideas on a federated learning consortium of cancer centres that jointly own the models. Data silos and AI that is built but not validated are the bottlenecks it addresses. Whether federated training can match centralised data on model quality is the open question.
Similar pages
- CompanyArtera
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI that is built but not validated or deployed.
- IdeaA registry of external validation datasets for cancer AI models, with mandatory reporting
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI that is built but not validated or deployed.
- CompanyPaige AI
Shares A pre-competitive consortium to train a shared multimodal cancer foundation model, AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow.
- TreatmentArteraAI Breast
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI that is built but not validated or deployed.
- CompanyPathAI
Shares A pre-competitive consortium to train a shared multimodal cancer foundation model, AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI that is built but not validated or deployed.
- IdeaWhole-patient digital twins validated in prospective randomised trials
Shares Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models, AI that is built but not validated or deployed, Digital pathology & AI.
- CompanyTempus AI
Shares A pre-competitive consortium to train a shared multimodal cancer foundation model, Digital twins and virtual control arms, Patient-level multimodal foundation models for treatment selection, Pathology & radiology foundation models.
- IdeaDigitise the nation's pathology slides and link them to outcomes
Shares Pathology & radiology foundation models, AI that is built but not validated or deployed, Digital pathology & AI, Data silos.
fronts
technologies
companies
roadmaps
ideas
A federated learning consortium of cancer centres that jointly own the modelsA pre-competitive consortium to train a shared multimodal cancer foundation modelAI-first reading for high-volume common cancer diagnoses, pathologist for the exceptionsFederated training of pathology and radiology models across hospitalsPatient-level multimodal foundation models for treatment selection
bottlenecks
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.
Owkin's self-supervised pathology foundation models trained on TCGA; the code is open and the weights on Hugging Face are under Owkin's non-commercial licence.
Software in use
The software of oncology →Commercial and regulated products that this organisation sells. Each card says what is behind it: a regulator's database, the literature, a public body's list, or only the company's own words. Listing is not endorsement, and a clearance is a regulatory fact, not a clinical one.
A pre-screening algorithm that reads a routine colorectal slide and rules out the cases unlikely to be microsatellite unstable, so fewer go for molecular testing.
OwkinPaper 2023