# Aidoc CARE (clinical radiology foundation model)

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

## TL;DR

Aidoc CARE is one radiology foundation model, pretrained on CT scans without labels, whose task-specific heads have each been FDA-cleared to flag urgent findings in emergency scans so radiologists read those first. Its oncology relevance is indirect, catching incidental masses; the regulatory evidence covers triage, not diagnostic accuracy for tumours.

## Summary

Aidoc CARE is a clinical radiology foundation model built from self-supervised pretraining on CT, with task-specific heads that have each been cleared by the FDA. Released in 2025, it underpins Aidoc's triage products, which flag urgent findings on CT scans in emergency radiology so radiologists read them first. Its relevance to oncology is indirect: detecting incidental findings such as unexpected masses and prompting follow-up. The model is not cancer-specific and its evidence base comes from the regulatory pathway for narrow triage uses, which shows that a shared backbone can pass regulatory review one task at a time, but does not speak to diagnostic accuracy for tumours. For a newcomer: it is one AI model behind many approved alerts that tell radiologists which scans need urgent attention.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: foundation-model; radiology
- Principle: Self-supervised CT pretraining with task-specific cleared heads.
- Since: 2025
- Strengths: Regulatory pathway proven for narrow uses
- Limitations: Not cancer-specific

## Sources

- Aidoc: https://www.aidoc.com

## Connected records

- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Imaging](https://onco.cc/fronts/imaging/)
- technologies: [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/)

---
JSON: https://onco.cc/api/v1/entities/aidoc-care.json