阿里达摩院开源医学影像模型 Damo Radar，可识别近 150 种腹部病变
Alibaba open-sources AI model that can detect cancer and nearly 150 conditions
阿里巴巴达摩院开源视觉语言模型 Damo Radar，可分析增强 CT 扫描，覆盖 18 个腹部器官并识别包括癌症在内的近 150 种腹部病变。在近 4 万例真实检查中，模型在 146 项临床发现的平均 AUC 为 0.913；与 26 名放射科医生的对比中，其平均准确率超过其中 23 人，医生借助该模型漏诊预防能力提升 10%，耗时减少逾 30%。研究已发表于《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. 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. The model was trained using CT scans paired with clinical reports. In nearly 40,000 real-world examinations, it achieved an average area under the curve (AUC) of 0.913 across 146 clinical findings. An AUC of 1.0 represents perfect diagnostic 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”. In a comparative study involving 26 human radiologists from multiple hospitals, the model’s average accuracy exceeded that of 23 participants, according to the study. With the model’s help, the radiologists also managed to improve their ability to prevent missed diagnoses by 10 per cent while reducing the time required by more than 30 per cent, Damo said. The research was published on Thursday in the journal Science. Several institutions took part in the study alongside Alibaba, including a hospital affiliated with Zhejiang University. The model’s release builds on a string of recent medical AI advances by Alibaba as Chinese technology giants increasingly explore the use of cutting-edge technology in healthcare settings. Alibaba owns the South China Morning Post. In recent years, Damo Academy has focused on developing AI screening tools to help doctors identify conditions including pancreatic, stomach and colorectal cancers, as well as aortic dissections. In April, the division released the Coca AI model, which it said was more sensitive than radiologists in spotting early-stage colorectal cancer from CT scans. The model was co-developed with Chinese institutions including the Guangdong General Hospital.
来源：Hacker News：AI 热帖 · scmp.com