Olympus Corporation today announced the publication of the EAGLE Trial in npj Digital Medicine, a multicenter randomized controlled study evaluating the CADDIE device, the first FDA-cleared and CE-marked cloud-based computer-aided detection (CADe) application for real-time polyp detection during colonoscopy. The trial indicates that cloud-deployed AI can help endoscopists detect high-risk and hard-to-detect colorectal lesions, including large adenomas (>10 mm), flat adenomas, and sessile serrated lesions (SSLs), without disrupting safety or workflow.
Conducted across eight centers in four European countries, the EAGLE study randomized 841 patients to standard colonoscopy or CADDIE-assisted colonoscopy. Results showed a 7.3% absolute increase in adenoma detection rate (ADR) with CADDIE. Notably, relative increases in lesions detected per colonoscopy were 93% for large adenomas, 57% for non-polypoid adenomas, and 230% for SSLs. These findings are critical because SSLs and flat adenomas are often missed but carry high risk for progression to colorectal cancer.
The CADDIE application is trained on a dataset enriched with clinically relevant and hard-to-detect lesions, addressing concerns raised in recent guidelines about unnecessary resections. The study observed no increase in unnecessary resections, supporting clinical safety. The cloud-based architecture allows real-time AI performance across diverse environments, enabling subscription-based procurement that reduces hardware reliance and democratizes access to advanced AI tools.
"This study marks a pivotal shift in the clinical translation of AI-assisted endoscopy," said Rawen Kader, Principal Investigator of the EAGLE Trial and GI Researcher at University College London. "Cloud deployment can remove hardware barriers and give hospitals access to the latest AI innovations, potentially improving detection of the lesions that matter most for reducing colorectal cancer risk."
Miquel Àngel García, Executive Vice President and General Manager of the Gastrointestinal Business Unit at Olympus, added, "The publication of the EAGLE study in a high-impact journal supports clinical adoption of the CADDIE device as an AI solution that enhances detection of clinically relevant lesions without compromising safety or efficiency."
The CADDIE software is the first solution introduced as part of the OLYSENSE Intelligent Endoscopy Ecosystem. For complete access to the EAGLE Trial study, visit npj Digital Medicine. The system is intended for use with standard white-light endoscopy imaging only, and the gastroenterologist remains responsible for confirming polyp presence based on medical judgment.
