Overjet Caries Assist is an AI-powered software that helps dentists detect and segment dental caries (tooth decay) on bitewing and periapical X-ray images. It provides computer-generated annotations highlighting potential caries to support dentists' diagnosis, improving sensitivity in caries detection. It operates by processing dental radiographs using machine learning models and presenting annotated images in a viewer interface for the dentist. This assists dentists but does not replace professional judgment.
Overjet Caries Assist (OCA) is a radiological, automated, concurrent-read, computer-assisted detection (CADe) software intended to aid in the detection and segmentation of caries on bitewing and periapical radiographs. The device provides additional information for the dentist to use in their diagnosis of a tooth surface suspected of being carious. The device is not intended as a replacement for a complete dentist’s review or their clinical judgment that takes into account other relevant information from the image, patient history, or actual in vivo clinical assessment.
Overjet Caries Assist uses a machine learning system composed of three layers: Network Layer (handles image transmission from clinic systems), Decision Layer (processes images, classifies them as bitewing or periapical, segments carious lesions using an ensemble of segmentation models, and assigns lesions to teeth), and Presentation Layer (provides a non-diagnostic viewer for dentists to view, filter, and edit annotations). It utilizes image preprocessing, tooth number assignment, caries segmentation modules, and post-processing for lesion-to-tooth association.
Performance was tested via standalone and clinical reader studies. Standalone testing showed overall sensitivity of 76.6% (bitewing) and 79.4% (periapical) with specificity over 99%. Clinical reader studies involving 28 dentists demonstrated statistically significant improvements in sensitivity (increase from about 65% to 79%) and Dice scores when using the software, with only minor specificity decreases. The device was tested on multiple sensor manufacturers and images greater than 500x500 resolution.
No predicate devices specified
Submission
9/12/2022
FDA Approval
3/27/2023
Join hundreds of your 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.