Alibaba Group Holding’s research arm, Damo Academy, has open-sourced Damo Radar, an artificial intelligence model capable of identifying nearly 150 abdominal conditions from computed tomography (CT) scans. The institute said the model is designed to analyze contrast-enhanced CT scans covering 18 abdominal organs to detect malignancies and other abnormalities. A study published in Science reported that the model outperformed most radiologists in testing.
Model ReleasesAlibaba Group HoldingDamo AcademyDamo Radar
Alibaba's Damo Academy open-sources Damo Radar, a medical AI capable of detecting nearly 150 abdominal conditions
The vision-language model was trained using CT scans paired with clinical reports. In tests involving nearly 40,000 real-world examinations, the model achieved an average area under the curve (AUC) of 0.913 across 146 clinical findings. An AUC of 1.0 represents perfect diagnostic accuracy.
The research team said the training method could eventually be extended to other types of medical imaging, describing the model as the world’s first expert-level generalist medical imaging model.
Sources
- Alibaba open-sources AI model that can detect cancer and nearly 150 conditions （Hacker News Frontpage, 2026-09-18）