MuscleView
Springbok, Inc.MuscleView is an AI-powered software that automatically segments muscles and bones in MRI scans of the lower limbs. It calculates useful metrics such as muscle and bone volume, fat infiltration, and asymmetry to assist physicians in analyzing musculoskeletal health. The segmentations need to be reviewed and edited by trained clinicians. This tool helps improve the efficiency and accuracy of muscle and bone analysis from MRI images but is not intended for diagnostic use of diseases.
Intended Use
MuscleView is used in adults and pediatrics aged 18 and older to automatically segment muscle and bone structures of the lower extremities from magnetic resonance imaging using a machine learning-based approach and provide derived metrics including muscle volume, bone volume, intramuscular fat percentage, and left/right asymmetry.
Technology
MuscleView is a software-only product using pretrained convolutional neural networks (CNNs) to automatically segment 80 different muscles and bones of the lower extremity from preprocessed 3D MRI volumes. It operates locally on a workstation with GPU acceleration, providing segmentation, 3D visualization, and derived metrics such as volume and fat infiltration via a web-based interface.
Performance
Performance was validated by comparing AI segmentations against expert manual segmentations using dice similarity coefficients and volume difference metrics on an independent dataset of 148 validation scans, including healthy and patient subgroups. Results showed that MuscleView met or exceeded acceptance criteria for accuracy and demonstrated generalizability across multiple MRI manufacturers and patient demographics.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/10/2024
4 months - 2
FDA Approval
10/1/2024
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.