A computer that can pinpoint bowel cancer in less than a second could advance patient diagnosis, researchers claim.
During a trial, the artificial intelligence system identified potentially dangerous tumours from endoscopy images with clinical accuracy.
The results were presented at United European Gastroenterology Week in Barcelona, Spain.
For the study, the AI was tasked with assessing 306 colorectal polyps - growths in the bowel which may or may not be cancerous - in 250 men and women.
The system took less than a second to analyse each image and decide if it was malignant. The AI, which works by comparing trial images with more than 300,000 images of polyps used for machine learning, correctly spotted 94% of cancers.
"The most remarkable breakthrough with this system is that artificial intelligence enables real-time optical biopsy of colorectal polyps during colonoscopy, regardless of the endoscopists' skill,” said Dr Yuichi Mori from Showa University in Yokohama, Japan.
"This allows the complete resection of adenomatous (cancerous) polyps and prevents unnecessary polypectomy (removal) of non-neoplastic polyps.
"We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system," he added.