CADDIE is a cloud-based AI software that helps gastroenterologists detect suspected colorectal polyps during colonoscopy procedures by analyzing live video from endoscopy. It highlights potential lesions with visual markers to aid clinical decision-making, improving polyp detection without replacing the physician's judgment.
The CADDIE computer-assisted detection device is intended to assist the gastroenterologist in detecting suspected colorectal polyps only, used with standard white-light endoscopy imaging. It supports but does not replace clinical judgment or primary interpretation.
CADDIE is standalone cloud-based AI software accessed through a web browser that analyzes video feed from an endoscopic processor in real-time during colonoscopy. It highlights regions with visual characteristics consistent with polyps by superimposing green bounding boxes with audio markers to notify the endoscopist. It requires a network connection and does not rely on bespoke hardware.
Comprehensive bench and clinical performance testing demonstrated safety and effectiveness: high true positive detection rate (~98%), low false positive rate (~1.5%), and non-inferior safety compared to standard colonoscopy. Clinical trial with 841 patients showed increased adenoma detection rate and no increase in unnecessary biopsies, confirming the device's utility in real-world use.
No predicate devices specified
Subscribe to join 7,600+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.