Velmeni for Dentists (V4D)
Velmeni Inc.Velmeni for Dentists (V4D) is a computer-assisted detection software that helps dentists identify dental caries, restorations, fixed prostheses, and implants in various types of dental radiographs such as bitewing, periapical, and panoramic images. It uses machine learning algorithms to analyze radiographs and highlight areas of interest, providing additional information to aid clinical decisions without replacing dentist judgment.
Intended Use
VELMENI for DENTISTS (V4D) is a concurrent-read, computer-assisted detection software intended to assist dentists in the clinical detection of dental caries, fillings/restorations, fixed prostheses, and implants in digital bitewing, periapical, and panoramic radiographs of permanent teeth in patients 15 years of age or older. The device provides additional information for dentists in examining radiographs of patients’ teeth and is not intended as a replacement for a complete examination or clinical judgment. Final diagnosis and treatment plans are the responsibility of the dentist.
Technology
The device is a software medical device with components including a web application interface, machine learning engine, backend API, queue system, AI worker, and database/file storage. It uses proprietary neural network-based algorithms to analyze digital dental radiographs in formats such as JPEG and PNG, providing segmentations or bounding boxes for detected dental features. The device supports cloud-hosted solutions and communicates with third-party management or imaging software via an interface called VELMENI BRIDGE. It employs concurrent-read machine learning technology to assist dentists with detection of dental caries, restorations, prostheses, and implants across multiple dental radiograph types.
Performance
Performance testing included standalone testing on 600 bitewings, 597 periapical, and 600 panoramic images, compared to consensus ground truth by licensed dentists, showing sensitivity up to approximately 72.8% for caries detection in bitewing views and higher sensitivities for prostheses and implants. Clinical reader studies with 12 dentists demonstrated improved sensitivity and area under ROC curve (wAFROC) with model assistance across all radiograph types. The device passed software verification and validation tests and met FDA recommended guidance for performance and safety.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
1/2/2024
8 months - 2
FDA Approval
8/30/2024
Ready to Sharpen Your Edge?
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.