NaviCam ProScan
Ankon Technologies co., ltdNaviCam ProScan is an AI-assisted software tool designed to aid clinicians in reviewing small bowel capsule endoscopy images, helping to reduce the time needed for image review by detecting suspected lesions and identifying anatomical regions within the digestive tract. It supports clinicians in diagnosing small bowel bleeding by highlighting images with potential abnormalities without replacing the clinical decision-making process.
Intended Use
AI-assisted reading tool to aid small bowel capsule endoscopy reviewers in decreasing review time and identifying digestive tract location in adults with suspected small bowel bleeding; not intended to replace clinical decision making.
Technology
The device uses convolutional neural networks with deep learning models for two main algorithms: digestive tract site recognition (oral cavity, esophagus, stomach, small bowel) and small bowel lesion detection. It processes capsule endoscopy images and overlays graphical markers on the original video to identify potential lesions and anatomical locations, aiding clinicians in review without altering the source video.
Performance
Performance testing included training and validation on a large patient dataset from capsule endoscopy. Lesion detection showed high patient-level sensitivity (98%) but moderate specificity (37%); image-level sensitivity and specificity were higher (95.05% and 97.54%). Tract site recognition sensitivity and specificity were above 98% across all anatomical locations. A multicenter clinical study showed AI-assisted reading reduced mean reading time significantly while maintaining non-inferior diagnostic yield compared to standard reading.
Ready to Sharpen Your Edge?
Subscribe to join 11k+ 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.