ScanDiags Ortho L-Spine MR-Q
ScanDiags AGScanDiags Ortho L-Spine MR-Q is an AI-powered software tool that processes previously acquired lumbar spine MRI images to provide quantitative measurements of spinal anatomical structures such as vertebral bodies, intervertebral discs, neuroforamina, and thecal sacs. It utilizes deep learning algorithms for semi-automatic segmentation and measurements, allowing radiologists to review and adjust results. This tool helps clinicians save time and improve the accuracy of lumbar spine assessment without replacing their expert interpretation.
Intended Use
ScanDiags Ortho L-Spine MR-Q software is an image-processing and measurement software tool that provides quantitative spine measurements from previously-acquired DICOM lumbar spine Magnetic Resonance (MR) images for users' review, analysis, and interpretation. It provides functionality to assist users in visualizing, and documenting area and distance measurements of relevant anatomical structures (vertebral body, intervertebral disc, neuroforamina, thecal sac) of the lumbar spine: feature segmentation, feature measurement, and export of measurement results to a PDF report for review, revise and approval. It does not produce or recommend any type of medical diagnosis or treatment; it is intended only for use by hospitals and medical institutions with DICOM lumbar spine MR images of patients aged 22 and above.
Technology
The software uses semi-automatic segmentation of anatomical structures in lumbar spine MRI DICOM images based on deep convolutional neural networks (DCNN) developed with supervised deep learning methods. It combines deep learning, image analysis, and regression-based machine learning methods. Users can review and modify segmentations and measurements before generating PDF reports. It does not interface directly with MRI acquisition equipment and is independent of equipment vendor. The software saves time by automating manual segmentation and measurement tasks.
Performance
The software was validated in two studies: one with 100 individual MRI studies annotated by three MSK radiologists, and one with 101 MRI studies collected across multiple U.S. sites and MRI system manufacturers. Performance evaluation showed high intraclass correlation coefficients (ICCs) for measurements, high Dice similarity coefficients for segmentation accuracy, and low mean absolute errors (MAE). Verification and validation testing demonstrated acceptable segmentation accuracy compared to radiologist consensus, meeting design requirements and showing substantial equivalence to a predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
9/3/2024
5 months - 2
FDA Approval
2/21/2025
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.