Intended Use

Assist in making measurements for total hip arthroplasty, total knee arthroplasty, and lumbar spine fusion surgery, by measuring lengths, angles, and position of implants relative to bone structures on x-ray images.

Technology

Software as a medical device (SaMD) using AI/ML models to perform semi-automated, interpretable landmark detection and measurement on preoperative radiographic images of the pelvis, knee, and spine. Provides digital annotations editable by the user, outputs measurements in an HTML format, and supports image input in JPEG, PNG, BMP, and DICOM formats. Can also receive intraoperative images from fluoroscopic c-arm devices via direct connection.

Performance

Performance was validated using a dataset of thousands of images from adult patients, with ground truth established by experienced orthopedic surgeons. The models achieved a Dice coefficient > 0.85 on all connected domains, and measurements showed no statistically significant difference compared to human measurements, with degree or millimeter differences within clinically acceptable limits. Testing included subgroup analyses across different x-ray machine types and anatomical regions, supporting accuracy and reliability of the AI system.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    6/12/2024

    6 months
  • 2

    FDA Approval

    1/2/2025

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.