BoneMRI v1.6
MRIguidance B.V.BoneMRI v1.6 is an AI-powered software that enhances MRI images to improve visualization of bone structures in the pelvic and lumbar spine regions. It uses advanced algorithms, including convolutional neural networks, to generate 3D images with enhanced bone contrast. This allows clinicians such as radiologists and orthopedic surgeons to better assess bone morphology and tissue density without the need for CT scans, improving diagnostic capabilities in these regions.
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 enhanced contrast with respect to the surrounding soft tissue. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones and femoral heads; and the lumbar spine region, which includes the bony anatomy of the vertebrae from L3 to S1. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors. Warning: BoneMRI images are not intended to replace CT images.
Technology
BoneMRI v1.6 processes 3D gradient echo MRI scans using a convolutional neural network-based image enhancement algorithm. It constructs 3D tomographic radiodensity contrast images from MRI scans. The software runs on hospital or clinic servers, interfacing with DICOM archives (PACS). It provides enhanced bone images with Hounsfield Unit (HU) values estimated from MRI intensity and context. The AI model was trained on multicenter datasets, including multiple anatomies and scanners to ensure robust generalization.
Performance
Performance testing included software verification, validation, and clinical studies with retrospective data. Quantitative voxel-by-voxel comparisons of BoneMRI versus co-registered CT scans were done on pelvic and lumbar spine images from over 200 patients. Results demonstrated clinically acceptable accuracy in 3D bone morphology (mean absolute cortical delineation error below 1.0 mm), radiodensity (mean deviation below 25 HU on average), and radiodensity contrast reconstruction (mean HU correlation above 0.75), meeting pre-specified acceptance criteria (p<0.05).
Predicate Devices
No predicate devices specified
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.