Alibaba's AI model detects esophageal cancer early using plain ct scans

Alibaba DAMO Academy, in partnership with Sichuan Cancer Hospital and Sun Yat-sen University Cancer Center, has launched DAMO EAGLE, an AI model for esophageal cancer screening. The model identifies cancer and precancerous lesions from plain CT scans without endoscopy or contrast agents. Validated on 80,000 cases across three countries, the model was published in Nature Medicine on September 22, 2026. Esophageal cancer, prevalent in western China, has high mortality rates due to late diagnosis. Early detection through minimally invasive surgery offers a 95% five-year survival rate. DAMO EAGLE achieves 90% sensitivity for cancer and 52.5% for precancerous signals, with 99.2% specificity in real-world scenarios. Yao Jiawen, an algorithm expert, explained the model's ability to match endoscopic reports with CT images. Wang Qifeng, a chief physician at Sichuan Cancer Hospital, emphasized that AI complements endoscopy by identifying high-risk patients, improving detection rates. DAMO Academy's 'plain CT + AI' approach has published five Nature Medicine papers, potentially detecting the top seven deadliest cancers in China through a single scan.