
New
HealthMore in Health→
AI Assistant RADAR Learns From Radiology Reports to Read Abdominal CT Scans
Key Takeaways
- Researchers presented RADAR (Rapid Abdominal Diagnosis with AI and Radiology), a generalist AI assistant that interprets abdominal CT scans to help doctors reach diagnoses.
- The vision-language framework was trained directly on clinical reports covering 424,911 examinations, 1.5 million image-text pairs and more than 15 million anatomy-specific pairs, with no manual tagging required.
- RADAR reached an average diagnostic accuracy (AUC) of 0.913 in real-world hospital testing, outperforming existing medical vision-language AI models.
- Performance held across eight hospitals, emergency room cases and diverse patient populations.
DE
DT Editorial Team··via medicalxpress.com

