EAGLE Trial validates Olympus CADDIE cloud AI for colorectal lesion detection
Study shows improved identification of high-risk polyps without disrupting colonoscopy workflow.
www.olympus-global.com
Olympus Corporation has announced the publication of results from the EAGLE Trial, a multicenter randomized controlled study evaluating its CADDIE™ solution—the first cloud-based, real-time computer-aided detection (CADe) system for colonoscopy that is both FDA-cleared and CE-marked.
Published in npj Digital Medicine, the study demonstrates that cloud-deployed artificial intelligence can significantly improve detection of clinically relevant, hard-to-identify colorectal lesions without compromising safety or procedural efficiency.
Improved detection of lesions linked to cancer risk
The EAGLE (Evaluation of AI for detection of Gastrointestinal Lesions in Endoscopy) study was conducted across eight centers in four European countries, involving 841 patients and 22 endoscopists performing screening and surveillance colonoscopies. Patients were randomized to either standard colonoscopy or colonoscopy assisted by CADDIE™.
Key findings from the trial include:
- A 7.3% absolute increase in adenoma detection rate (ADR) with CADDIE™ assistance
- 93% increase in detection of large adenomas (>10 mm)
- 57% increase in non-polypoid adenomas
- 230% increase in detection of sessile serrated lesions (SSLs)
These lesion types are strongly associated with colorectal cancer risk and are among the most challenging to detect using conventional methods.
Cloud-based AI without workflow disruption
The study confirms that CADDIE™ delivers real-time performance via a secure cloud architecture, operating efficiently across different clinical environments without increasing unnecessary resections or procedure complexity. By reducing dependence on on-site hardware, the cloud model supports scalable deployment and subscription-based adoption, lowering barriers for hospitals seeking to integrate AI into endoscopy workflows.
Expert insight
Rawen Kader, Principal Investigator of the EAGLE Trial and GI researcher at University College London, noted that cloud deployment “has the potential to remove hardware barriers and improve detection of the lesions that matter most for reducing colorectal cancer risk.”
From Olympus, Miquel Àngel García, Executive Vice President and General Manager of the Gastrointestinal Business Unit, said the results support broader clinical adoption of CADDIE™ as a solution that enhances detection without compromising safety or efficiency.
Peter Mountney, CEO of Odin Vision and Vice President of Olympus’ AI Unit, added that the study shows how cloud-based AI can be translated into routine endoscopy at scale, enabling faster innovation and wider global access to evidence-based AI tools.
CADDIE is the first application launched under Olympus’ OLYSENSE™ Intelligent Endoscopy Ecosystem, reinforcing the company’s strategy to integrate AI into everyday clinical practice for improved cancer prevention outcomes.
www.olympus-global.com
