Intended Use

Image processing software providing quantitative and qualitative analysis from previously acquired Computed Tomography DICOM images to support radiologists and physicians in evaluation and assessment of musculoskeletal disease, including vertebra segmentation, labeling, vertebral height measurement, and mean Hounsfield value measurement within vertebrae in adult patients.

Technology

Software utilizes deep learning algorithms for vertebra segmentation and labeling on CT DICOM images. Provides quantitative measurements of vertebral height and mean Hounsfield value. Supports cloud and on-premise (edge) deployment. Generates enhanced human and machine-readable DICOM structured reports compliant with TID 1500 standard. Maintains adherence to FDA cybersecurity guidance and relevant FDA-recognized standards for software lifecycle, risk management, and usability.

Performance

Performance testing included software validation and bench testing on 140 clinically relevant chest CT datasets with thoracic vertebrae, evaluating segmentation accuracy, vertebral height measurements, and mean density (HU). Mislabeling failure rate was 8.6%, and height measurement differences met clinical limits of agreement in over 92-95% of cases depending on slice thickness. Testing showed performance equivalent or superior to predicate device. Cybersecurity controls were verified per FDA guidance.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    8/4/2022

    2 months
  • 2

    FDA Approval

    10/20/2022

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.