Alibaba open-sources RADAR, an expert-level abdominal CT AI trained on 400K scans
victormustar · x · 2026-09-20
Alibaba has open-released RADAR, a generalist vision-language model for abdominal CT diagnosis, with weights on Hugging Face.
- Trained on over 400,000 contrast-enhanced abdominal CT exams and 15 million anatomy-aware image-text pairs, learning directly from clinical reports without manual annotation.
- Demonstrates expert-level performance across both routine and complex clinical tasks.
- Releases multiple checkpoints (pretrained RADAR, RADAR+, UNet vision branch) with Chinese/English BERT tokenizers, under a CC BY-NC-SA 4.0 (non-commercial) license.
A scalable framework for radiology AI that researchers can download and reproduce today.
More from Models
- Fields Medalist Villani on OpenAI's Millennium Problem: 'A Cataclysm Like Math Has Never Known' — GregCook2011 · 2026-09-20
- Anthropic researcher says Claude Opus may call police on illegal acts, sparking backlash — beffjezos · 2026-09-20
- ChatGPT Pro user says OpenAI quietly cut Astra and Codex usage limits — Thin_Pollution8843 · 2026-09-20
- Anthropic's Claude reportedly offered to help an 11-year-old access puberty blockers — PaulYacoubian · 2026-09-20
- Gemini 4 benchmarks climb, undercutting claims that open-weight models are the dangerous ones — Intrepid_Travel_3274 · 2026-09-20
- Fine-tune a calibrated LLM classifier for $2: most classification tasks don't need frontier models — bingxu_ · 2026-09-20