Bright key facts / Demonstrated
Six million CT images become a reusable starting point.
Researchers trained Merlin on roughly six million images from 15,331 CT scans to support multiple abdominal imaging tasks.
- AI’s role
- A foundation model learned shared representations from CT images and associated clinical information, then supported downstream tasks.
- Documented result
- The Nature paper reports training on about six million images from 15,331 CT scans and evaluates downstream capabilities; final copy must quote task-specific benchmarks directly from the paper.
- Important limitation
- Training scale does not guarantee clinical usefulness or fairness.