Rayvolve by AZmed SAS is an AI-powered software designed to assist radiologists and emergency physicians in detecting fractures from X-ray images of various musculoskeletal regions in adults and children aged 2 years and older. It enhances fracture diagnosis by automatically highlighting potential fractures on standard radiographic views, improving diagnostic accuracy and workflow efficiency.
Intended Use
Rayvolve is a computer-assisted detection and diagnosis software device to assist radiologists and emergency physicians in detecting fractures during the review of musculoskeletal radiographs. It is indicated for adult and pediatric populations (≥ 2 years) covering a wide range of standard radiographic views of extremities.
Technology
Rayvolve is a standalone AI deep learning software that processes DICOM format musculoskeletal X-rays. It integrates with clinical DICOM nodes like PACS, runs on-premise or cloud, and outputs fracture detection predictions as annotated images to assist doctors. It uses supervised deep learning models retrained on large datasets of osteoarticular X-rays including pediatric cases.
Performance
Performance testing included extensive software verification and validation in compliance with FDA guidelines, standalone bench testing on over 3000 pediatric X-rays and over 2600 adult X-rays showing high sensitivity (∼0.96 pediatric; ∼0.99 adult), specificity (∼0.86 pediatric; ∼0.89 adult), and AUC (∼0.94 pediatric; ∼0.99 adult). Additionally, a retrained AI algorithm was non-inferior to the predicate. A clinical multi-reader, multicase retrospective study with 24 radiologists showed statistically significant improved diagnostic accuracy (AUC increase from 0.85 to 0.89), sensitivity, and specificity with Rayvolve assistance.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
3/27/2024
3 months - 2
FDA Approval
7/17/2024
Other devices from AZmed SAS
- Rayvolve2022 • 510K
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.