What We Offer

Analysis comes to the data — and every result can be verified.

The capabilities below are built and running on the platform today. Not a roadmap — the working system.

How a result is produced

Four stages, end to end. Your data never leaves the institution that holds it — only governed, verifiable outputs do.

STAGE 1 Archived imaging Dormant · activated STAGE 2 Inside the walls Model in · data stays STAGE 3 Safe output Noise · suppression STAGE 4 Verifiable cert Signed · public data never crosses this line anyone can verify — offline

Live on the platform

Five capabilities, enforced in software

Access control, disclosure control, and audit are mechanisms the platform runs — not promises in a policy document.

Discover & access

A governed catalogue of reactivated ophthalmic and neuro cohorts — each with provenance, access terms, and institution-scoped isolation, with every request logged.

Analyse without moving data

Federated learning runs the model inside each institution over a signed, outbound-only node. Only model updates leave — never the images. Fine-tune modern foundation models on cohorts that were previously unreachable.

Privacy-safe outputs

Differentially private queries with an enforced per-dataset budget, synthetic datasets, and automatic small-cell suppression — the numbers you take away can't be traced back to a person.

Prove it — to anyone

Every result gets a signed Verifiable Research Certificate binding it to its lineage, disclosure settings, and a tamper-evident audit trail. Verifies offline against a public key — no account, no contacting us.

Interoperate & evidence

OMOP CDM v5.4 with the imaging extension, FHIR R4 ingestion, and one-click evidence packs that support your institution's compliance assessments under the UK (Five Safes · DSPT), EU (GDPR · EHDS), and US (HIPAA · Common Rule) frameworks.


Proven, not experimental

A method with a clinical track record.

Federated analysis isn't a bet. Models trained this way have reached roughly 99% of centralised performance in multi-institutional brain-imaging studies (Sheller et al., Scientific Reports, 2020), and a single clinical model has been trained across 20 institutions worldwide without any data leaving a hospital (Dayan et al., Nature Medicine, 2021).

For a data custodian, participation never creates a new copy of the dataset anywhere — which shortens governance review, keeps the institution in control, and aligns with UK GDPR Article 89 research safeguards and the FAIR principles UK funders now expect.


Enforced in software

Governance you don't take on faith

Consent & ethics review before activation Disclosure control on all outputs Tamper-evident audit trail Multi-factor authentication Enforced privacy budgets Institution-scoped isolation UK-resident by default Security & governance detail →
Get Involved

Have archived imaging, or a question these capabilities could answer?

We're onboarding data custodians and research partners now. Tell us what you're holding or what you're trying to find out.

Get Involved Why Data Reuse