Alibaba releases AI model for detecting cancer and 150 other conditions from CT scans

Sep 18, 2026

AI Summary

Alibaba's Damo Academy has open-sourced an AI model named Damo Radar that can identify nearly 150 abdominal conditions, including cancers, from CT scans. The model was tested on nearly 40,000 exams and demonstrated superior performance compared to most radiologists.

Damo Radar is an AI model developed by Alibaba's Damo Academy for analyzing contrast-enhanced CT scans of 18 abdominal organs.
The model can detect a wide range of diseases, including malignant tumors, and is part of Alibaba's expanding medical AI initiatives.
It was trained using CT scans and clinical reports, achieving an average area under the curve (AUC) of 0.913 across 146 clinical findings in real-world tests.
An AUC of 1.0 indicates perfect diagnostic accuracy.
The research team suggests that the training methodology could be applied to other medical imaging types, positioning the model as a pioneering generalist in medical imaging.

alibabaopen-sourcemedical-aicancer-detectionhealthcare

Alibaba releases AI model for detecting cancer and 150 other conditions from CT scans

Related Stories

SNL Parodies Anthropic CEO Dario Amodei's Views on AI Risks

Ricursive Intelligence Aims to Revolutionize Chip Design with AI Technology

AI-Powered Health Care Clinic Opens in Manhattan Offering Advanced Checkups

Meta removes critical video discussing its AI glasses following filming on site