BoneMRI v1.4 is an image processing software that analyzes 3D gradient echo MRI scans to enhance visualization of bone structures in the pelvic and lumbar spine regions. It uses a convolutional neural network algorithm to generate images with improved bone contrast compared to surrounding soft tissue, helping clinicians better assess bone morphology and density without the need for CT scans. It is intended for use by radiologists and orthopedic surgeons to aid in image interpretation, but not for tumor diagnosis.
BoneMRI is an image processing software used for image enhancement in MRI images to visualize bone structures in the pelvic and lumbar spine regions with enhanced contrast relative to soft tissue.
BoneMRI is a standalone software application that analyzes 3D gradient echo MRI scans using convolutional neural network algorithms to construct tomographic radiodensity contrast images. It outputs DICOM images for viewing on standard PACS workstations. The algorithm was trained on multi-site, multi-scanner data to ensure robustness for its approved indications.
Performance testing included software verification and validation, and retrospective clinical studies comparing BoneMRI generated images voxel-by-voxel to CT scans in 73 patients. Results showed clinically acceptable accuracy in reconstructing 3D bone morphology, radiodensity (mean deviation <25 HU), and radiodensity contrast (correlation coefficient >0.75).
No predicate devices specified
Submission
6/17/2022
FDA Approval
11/16/2022
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.