Alibaba open-sources AI model that can detect cancer and nearly 150 conditions
Alibaba's Damo Academy open-sourced Damo Radar, a vision-language model that reads CT scans to detect nearly 150 abdominal conditions including cancers.
Alibaba's Damo Academy released Damo Radar as an open-source vision-language model that analyzes contrast-enhanced CT scans covering 18 abdominal organs and identifies roughly 146 clinical findings, including malignant tumors. Trained on CT scans paired with clinical reports, it achieved an average AUC of 0.913 across 146 findings in nearly 40,000 real-world examinations. The team describes it as the world's first expert-level generalist medical imaging model and says the training method could extend to other imaging types.
- Open-source vision-language model for contrast-enhanced abdominal CT analysis
- Average AUC of 0.913 across 146 clinical findings in nearly 40,000 exams
- Covers 18 abdominal organs, detecting tumors and other abnormalities
- Training approach could be extended to other medical imaging modalities
- Tags
- alibabact-scandamo-academydamo-radarhealthcare-aimedical-imagingopen-sourcevision-language-model
- Vendors
- Alibaba
- Products
- Damo Radar
- Organizations
- Damo Academy
- AI models
- Damo Radar
From the original article
1 min read at scmp.com
Alibaba Group Holding’s research arm, Damo Academy, has open-sourced an artificial intelligence model capable of identifying nearly 150 abdominal conditions – including cancers – by reading computed tomography (CT) scans, marking the latest step in the firm’s growing medical AI efforts.
By yogthos · scmp.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.