BoneMRI
Mriguidance B.V.BoneMRI is a software tool that uses artificial intelligence to enhance MRI images so that doctors can see bone structures with greater clarity and contrast. This helps clinicians better assess bones in the pelvis and spine without needing a CT scan, supporting both qualitative and quantitative evaluations.
Intended Use
BoneMRI is an image processing software that can be used for image enhancement in MRI images. It can be used to visualize the bone structures in MRI images with increased contrast with respect to the surrounding soft tissue in BoneMRI images and to visualize the T1w contrast in Synthetic T1w images. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones and femoral heads; and the spine, which includes the bony anatomy of the cervical, thoracic, lumbar, and S1 vertebrae. BoneMRI is indicated for use in patients 12 years and older. Synthetic T1w is indicated for use in patients 18 years and older. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors. BoneMRI images are not intended to replace CT images in general but can be used to visualize 3D bone morphology, tissue radiodensity and tissue radiodensity contrast.
Technology
BoneMRI is a server-based or managed cloud image processing software that receives 3D gradient echo MRI scans, processes them using AI-based algorithms to generate 3D tomographic radiodensity contrast images (BoneMRI images) and synthetic T1-weighted images, and returns the results to the clinic using DICOM-compatible workflows. The AI was trained on diverse images from multiple clinical sites, scanners, and anatomies for robust performance.
Performance
Performance was validated with quantitative voxel-by-voxel comparisons of reconstructed images versus CT and conventional MRI, demonstrating mean absolute cortical delineation error below 1.0 mm, mean HU deviation below 25 (and below 55 specifically for bone), and high correlation coefficients. Synthetic T1w images were validated for structural similarity, PSNR, and diagnostic interchangeability with conventional T1w images in a multicenter, multireader blinded study. Synthetic T1w images were found diagnostically interchangeable (difference above non-inferiority threshold) and of equal or better quality compared to conventional T1w images (mean Likert score 3.3, 93% 3 or better).
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.