Photo via South China Morning Post

Alibaba open-sources medical AI model that can detect cancer and nearly 150 conditions

Read the original at South China Morning Post ↗
Cite

Cao, A. (2026, September 18). Alibaba open-sources medical AI model that can detect cancer and nearly 150 conditions. South China Morning Post. https://www.scmp.com/tech/big-tech/article/3368055/alibaba-open-sources-medical-ai-model-can-detect-cancer-and-nearly-150-conditions?utm_source=rss_feed

Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.

South China Morning Post · collected 2026-09-18 · by Ann Cao

Quick Summary

Alibaba's Damo Academy has released an open-source artificial intelligence model called Damo Radar that can detect nearly 150 abdominal conditions, including cancers, from CT scans. Tested on almost 40,000 real-world exams, the model achieved an average AUC of 0.913 across 146 clinical findings, outperforming most radiologists according to a study published in Science. The vision-language model was trained using CT scans and corresponding clinical reports and is described as the world's first expert-level generalist medical imaging model that could potentially be adapted for other types of medical images.
Written by AI on 2026-09-18, from this article's own text only (the story summary below draws on all the coverage).

AI analysis

Story summary

Alibaba Group Holding's research arm, Damo Academy, has open-sourced a new artificial intelligence model named Damo Radar. This AI can detect nearly 150 abdominal conditions from CT scans, including cancers and other abnormalities. Trained on over 40,000 real-world exams paired with clinical reports, the model outperformed most radiologists in identifying various diseases with an average area under the curve (AUC) of 0.913 across 146 findings. An AUC score of 1.0 represents perfect accuracy. The research team claims this is the world’s first expert-level generalist medical imaging model and suggests its training method could be applied to other types of medical images.

Written for “Alibaba Medical AI Model” on 2026-11-01, grounded in this article and the 0 other(s) covering the same event.

Story

📰 Alibaba Medical AI Model
Technology · 1 article(s) covering the same event.

Compared with similar articles

This article reads unscored and hedges 33% of its claims. Each row says how that neighbour differs.
Washington Examiner
⚖️ Leans left Hedges 3 of 34 claims Outlet record 70/100
“While both articles discuss advancements in medical AI, they do not describe the same specific event or incident.”
Fox News
Hedges 26 of 162 claims Outlet record 69/100
“The articles discuss different aspects of AI in cancer treatment and medicine. Article A is a general overview of how AI can transform cancer treatments, while Article B specifically mentions Alibaba's open-sourced medical AI model for detecting cancer and other conditions.”
How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted
6
sentences that state something as happening or true
Uncertain
33%
2 of 6 hedged ("reportedly", "may", "according to")
Leaning
not political
takes no side on a contested political question
Publisher signals
64/100
South China Morning Post's corrections and hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
1
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Analyzed 2026-09-18 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability
Source leaning vs. consistency

Publisher

South China Morning Post · 3517 article(s) · 6 correction(s) detected
Running correction rate · 6 correction(s)

Who wrote this

Ann Cao
16 article(s) here · 1 carrying a prediction
🔮 Apple Intelligence to roll out on iPhones in China in December with Alibaba backing Alibaba’s flagship AI model Qwen will be integrated into Apple Intelligence, after years of speculation and regulatory uncertainty
🔮 Alibaba Cloud founder says open-source, closed-source AI philosophies not at odds, calls for more Chinese cloud competition to strengthen industry Long before artificial intelligence became the next big thing in the tech industry, Wang Jian was crafting the foundational infrastructure that would eventually power it.
🔮 The deal will enable Tesla drivers to pay for parking from their in-car touchscreens, with more features to follow, Alipay says Tesla has agreed a deal to integrate Chinese fintech giant Ant Group’s Alipay digital payment software into its vehicles in China, as Elon Musk’s firm steps up efforts to offer localised smart features amid intense competition in the Chinese market. The agreement, signed on Tuesday, will see Tesla roll out an Alipay-powered smart parking service across its Chinese fleet, according to the fintech firm.
🔮 Following the transaction, Guosheng’s direct stake in Hua Hong Group would jump to 41.7 per cent from 15.3 per cent, while its indirect holding would rise to 10.2 per cent from 3.8 per cent.
🔮 When trading begins, CanSemi is expected to set a milestone for the Shenzhen exchange as the first pure-play wafer fabrication company to list on its Shenzhen’s tech-heavy ChiNext board.
🔮 Chinese AI chipmaker Hygon plots expansion from data centres to robotics New chip targets range of physical AI applications, where machines interact directly with their environments Chinese chipmaker Hygon Information Technology is set to release a new chip targeting physical-world applications including robotics, expanding from its current focus on data centres, according to Chinese media reports and company information. The new chip, an iteration of the company’s CPU1000 series, is designed to meet “low-power, embedded and edge computing requirements”, targeting a range of physical AI applications in sectors including robotics, machine vision and intelligent manufacturing, according to reports by business news outlet Jiemian News and state-backed newspaper China Securities Journal on Sunday.
🔮 The research team said the training method could eventually be extended to other types of medical imaging, calling the model “the world’s first expert-level generalist medical imaging model”.
🔮 Cloudy with a chance of Big Macs: McDonald’s and Meituan launch drone route in Shanghai Fast-food orders will soar through the Shanghai sky, quickly reaching designated kiosks along the West Bund, offering a new way to collect meals Shanghai’s bustling riverfront has become the latest testing ground for urban logistics technology, with McDonald’s and Chinese food-delivery giant Meituan joining forces to launch the country’s first catering brand-exclusive drone-delivery route.
🔮 These digital workers could then be put to work within any of China’s three major workplace communication platforms: Alibaba’s DingTalk, ByteDance’s Feishu and Tencent’s WeCom.
Also by Ann Cao
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 16 articles by Ann Cao →

Topics

Alibaba Damo Academy Damo Radar Science Alibaba Group Holding’s

Subjects

Alibaba ORG · 1× Damo Academy ORG · 1× Science Alibaba Group Holding’s ORG · 1×

Narrative

The vision-language model, called Damo Radar, was designed to analyse contrast-enhanced CT scans covering 18 abdominal organs and identify a broad range of diseases and other abnormalities, such as malignant tumours, the institute said on Friday.
framing: mixed · carried by 1 article(s) · first seen 2026-09-18
🔮 The research team said the training method could eventually be extended to other types of medical imaging, calling the model “the world’s first expert-level generalist medical imaging model”.
2026-09-18 · South China Morning Post
Alibaba open-sources medical AI model that can detect cancer and nearly 150 conditions · mixed framing

Claims (6 extracted, 2 hedged)

Alibaba open-sources medical AI model that can detect cancer and nearly 150 conditions Tested on nearly 40,000 real-world exams, the model outperformed most radiologists, according to a new study published in Science 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. uncertain
model → source → efforts
The vision-language model, called Damo Radar, was designed to analyse contrast-enhanced CT scans covering 18 abdominal organs and identify a broad range of diseases and other abnormalities, such as malignant tumours, the institute said on Friday. asserted
institute → call → Friday
The model was trained using CT scans paired with clinical reports. asserted
model → train → reports
In nearly 40,000 real-world examinations, it achieved an average area under the curve (AUC) of 0.913 across 146 clinical findings. asserted
it → achieve → findings
An AUC of 1.0 represents perfect diagnostic accuracy. asserted
AUC → represent → accuracy
The research team said the training method could eventually be extended to other types of medical imaging, calling the model “the world’s first expert-level generalist medical imaging model”. uncertain
method → say → model
💬Give feedback
🕘History 🎫Support