Alibaba Open-Sources Medical AI That Outperforms Human Radiologists

Alibaba’s Damo Academy just open-sourced Damo Radar, a vision-language AI model designed to analyze contrast-enhanced CT scans across 18 abdominal organs for nearly 150 conditions, including malignant tumors. In testing against nearly 40,000 real-world examinations, the model achieved an average area under the curve (AUC) of 0.913 across 146 clinical findings. A peer-reviewed study published in the journal Science revealed the AI's average accuracy exceeded that of 23 out of 26 human radiologists from multiple hospitals. When human radiologists used the AI tool, they reduced their required diagnostic time by more than 30% and improved their ability to prevent missed diagnoses by 10%. "The world’s first expert-level generalist medical imaging model." — Damo Academy research team