The EAGLE Trial, a multicenter randomized controlled study published in npj Digital Medicine, has demonstrated that Olympus's CADDIE cloud-based Computer-Aided Detection application significantly improves the detection of high-risk and hard-to-detect colorectal lesions during colonoscopy. The study, conducted across eight centers in four European countries, involved 841 patients and 22 endoscopists performing screening and surveillance colonoscopies, with patients randomized to either standard colonoscopy or CADDIE-assisted procedures.
Key findings from the trial show a 7.3% absolute increase in adenoma detection rate when using the CADDIE application compared to standard colonoscopy. More significantly, the study observed substantial relative increases in the detection of clinically relevant lesion subtypes: 93% for large adenomas (>10 mm), 57% for non-polypoid adenomas, and 230% for sessile serrated lesions (SSLs). These lesion types are particularly important because SSLs and flat lesions are difficult to detect visually but represent high-risk lesions whose detection is critical to reducing the risk of post-colonoscopy colorectal cancer.
The CADDIE application represents the first cloud-based CADe solution for real-time polyp detection that has received both FDA clearance and CE marking. As part of the OLYSENSE Intelligent Endoscopy Ecosystem, the system is trained on a dataset specifically enriched with clinically relevant and hard-to-detect lesions, including flat sessile serrated lesions and large polyps. This design focus addresses growing concerns in gastroenterology about improving detection of these challenging lesion types, which are increasingly viewed as critical quality indicators in colonoscopy according to recent guidelines.
Cloud deployment represents a significant innovation in medical AI implementation. The system demonstrated real-time performance and operational efficiency across diverse testing environments while using industry standard security controls. This cloud-based approach offers hospitals greater flexibility by reducing hardware dependencies and enabling subscription-based procurement models, potentially democratizing access to advanced AI tools. For complete access to the EAGLE Trial study, visit https://doi.org/10.1038/s41746-025-02270-1.
Clinical experts involved in the trial emphasize the broader implications of these findings. Rawen Kader, Principal Investigator of the EAGLE Trial and GI Researcher at University College London, noted that cloud deployment can remove hardware barriers and give hospitals access to the latest AI innovations, potentially improving detection of lesions that matter most for reducing colorectal cancer risk. Peter Mountney, CEO of Odin Vision and Vice President of the AI Unit at Olympus Corporation, highlighted how cloud-based AI can be translated into routine endoscopy at scale, enabling hospitals worldwide to benefit from evidence-based technologies that support clinicians and enhance care quality.
The trial results address concerns raised in recent guidelines about balancing improved detection with clinical workflow efficiency and safety. The study demonstrated increased detection of clinically relevant lesions without increasing unnecessary resections, suggesting that AI assistance can enhance physician performance without disrupting established clinical practices. As healthcare systems worldwide seek to improve colorectal cancer screening outcomes, cloud-based AI solutions like CADDIE offer a scalable approach to addressing detection gaps for high-risk lesions while maintaining operational efficiency.
