Alibaba DAMO Academy's DAMO RADAR hits Science: expert-level universal abdominal CT model, open-sourced
机器之心 · wechat · 2026-09-18
DAMO RADAR, a universal abdominal CT model from Alibaba DAMO Academy and Zhejiang University-affiliated hospitals, published in Science and open-sourced. It aligns CT volumes with radiology reports at the anatomical level using vision-language learning, reaching mean AUC 0.913 across 39,160 exams (18 structures, 146 findings), 0.895 across 8 external centers, and 0.883 on Stanford's Merlin set. In a 26-radiologist reader study, AI assistance lifted sensitivity by 10% and cut reading time 30.7%, narrowing the gap between junior and senior doctors. It marks DAMO's shift from single-disease models (DAMO PANDA) toward generalist medical imaging AI.
More from Models
- Free models aren't the real problem: studies show hallucinations persist in SOTA LLMs — AryHHAry · 2026-09-19
- Why do AI models lack personality? Safety training and attachment fears, explained — alexisgallagher · 2026-09-19
- New model JEV is free on OpenRouter, Vercel, Cloudflare and others, at ~$0.042/M input tokens — airesearch12 · 2026-09-19
- Users ask why Cursor still doesn't offer GLM 5.3, hinting at imminent arrival — ChrisUniverse · 2026-09-19
- Distilling DeepSeek V4 Flash to a 4B model on DGX Spark: 26 hours, 22ms per judgment — Dan_Jeffries1 · 2026-09-19
- JevBench v1 puts nine typed-decision models head-to-head across 242 decisions — airesearch12 · 2026-09-19