AI Surpasses Radiologists in Pancreatic Cancer Detection, Lancet Study Reveals
December 6, 2025
The publication, titled Artificial intelligence and radiologists in pancreatic cancer detection using standard of care CT scans (PANORAMA), was released online on November 20, 2025, in The Lancet Oncology.
The research is a collaboration among Radboud University Medical Center, Karolinska Institutet, and the University of Bergen, with involvement from major international partners including the Cleveland Clinic, Mayo Clinic, and Johns Hopkins University.
Key collaborators also include the Radboud University Medical Center, Karolinska Institutet, and University of Bergen, alongside prominent partners such as Cleveland Clinic, Mayo Clinic, and Johns Hopkins University.
The study evaluated 3,440 patients with 68 radiologists from 40 institutions across 12 countries, incorporating input from over 430 AI developers; the top three algorithms were combined for a final system tested on 1,130 patients.
An international study published in The Lancet Oncology finds that artificial intelligence can detect pancreatic cancer on CT scans more accurately than experienced radiologists.
Dawid Rutkowski of CLINTEC stresses that AI can serve as a valuable support tool for radiologists in identifying pancreatic cancer on imaging.
The project, PANORAMA, is EU-funded and reported to be free of conflicts of interest, focusing on AI-assisted detection using standard-of-care CT scans.
Researchers intend to expand AI applications to monitor patients with pancreatic cysts or precursors to cancer and plan prospective studies to test AI in clinical practice with careful oversight.
Summary based on 2 sources
Get a daily email with more AI stories
Sources

Mirage News • Dec 6, 2025
AI Outperforms Radiologists in Pancreatic Cancer Detection
Karolinska Institutet • Dec 5, 2025
AI can detect pancreatic cancer better than radiologists