Skip to main content

Alibaba's AI Spots Esophageal Cancer on Routine CT Scans

Alibaba's AI Spots Esophageal Cancer on Routine CT Scans

Alibaba's DAMO Academy has done it again. This time, they've rolled out DAMO EAGLE—an AI model that screens for esophageal cancer using plain CT scans. No endoscopy. No contrast agents. Just a routine scan that can spot early-stage tumors and precancerous lesions.

Developed with Sichuan Cancer Hospital and Sun Yat-sen University Cancer Center, the model was validated on 80,000 cases across three countries. The findings appeared in Nature Medicine on September 22.

Image

Why This Matters

China bears nearly half the world's esophageal cancer cases and deaths. Most patients are diagnosed late, when curative treatment is no longer an option. Catch it early, though, and the five-year survival rate tops 95% with minimally invasive surgery.

The standard screening tool—upper endoscopy—is invasive, uncomfortable, and hard to scale. Plain chest CT, on the other hand, is cheap, well-accepted, and already covers the esophagus when screening for lung cancer. The catch? The esophagus is a long, collapsible tube, and early lesions hide in the mucosal lining. Plus, the heart's constant beating blurs the picture. Radiologists struggle to spot trouble.

How They Cracked It

DAMO's algorithm expert Yao Jiawen explained the trick: the team matched endoscopic reports with precise lesion locations on contrast-enhanced CT, then mapped those onto plain CT images. This taught the AI to see what human eyes miss.

The results? In opportunistic screening, DAMO EAGLE hits 90% sensitivity for esophageal cancer—meaning it rarely misses a case. For the faintest precancerous signals, sensitivity is 52.5%. Specificity, or avoiding false alarms, reaches 99.2%. And it performs just as well on low-dose CT, so it can slip right into existing lung cancer screening programs without extra burden.

From Endoscopy to AI: A New Screening Path

"AI isn't replacing endoscopy," said Dr. Wang Qifeng, chief physician at Sichuan Cancer Hospital's Radiotherapy Department. "It's identifying high-risk individuals who then get endoscopy. That makes the exam more targeted and boosts detection rates." More importantly, it pushes prevention earlier, giving more people a fighting chance.

With this launch, DAMO Academy has now published five papers in Nature Medicine, covering AI models for pancreatic cancer, gastric cancer, colorectal cancer, esophageal cancer, and aortic dissection. All follow the same original "plain CT + AI" route. The ultimate goal: a single plain CT scan that can flag China's top seven deadliest cancers.

Key Points

  • DAMO EAGLE detects esophageal cancer from plain CT scans—no endoscopy or contrast needed.
  • Validated on 80,000 cases; published in Nature Medicine.
  • Achieves 90% sensitivity and 99.2% specificity, even on low-dose CT.
  • Designed to integrate into lung cancer screening for early detection.
  • Part of DAMO's broader "plain CT + AI" platform, with five Nature Medicine papers to date.

As Alibaba's fourth cancer-screening AI, DAMO EAGLE isn't just a technical feat—it's a practical tool that could save countless lives by making early detection as routine as a chest scan.