Al-Rad Companion (Musculoskeletal) is AI-powered software designed to analyze CT images of the spine. It supports clinicians by automatically segmenting and labeling vertebrae, measuring vertebral heights, and calculating the mean Hounsfield unit values within vertebrae, aiding in musculoskeletal disease evaluation and assessment.
AI-Rad Companion (Musculoskeletal) is an image processing software that provides quantitative and qualitative analysis from previously acquired Computed Tomography DICOM images to support radiologists and physicians from emergency medicine, specialty care, urgent care, and general practice in the evaluation and assessment of musculoskeletal disease.
The product is a software-only application that uses a 3D deep image-to-image convolutional encoder-decoder network with 3D convolutional and bilinear upscaling layers for vertebra segmentation, labeling, and measurement of vertebral height and Hounsfield values in CT scans.
Non-clinical testing showed conformity with special controls for medical software and comparable output to predicate devices. Clinical performance was validated retrospectively on 140 chest CT scans from multiple sites, showing vertebra height measurements within radiologist variation limits at 95.1% for thin slices and vertebra density measurements at 98.8%, consistent across subgroups. Risk control measures were implemented to mitigate hazards and cybersecurity follows IEC 80001-1:2010 guidelines.
No predicate devices specified
Submission
11/26/2019
FDA Approval
3/16/2020
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.