Intended Use

Clarius AI is intended to semi-automatically place calipers for non-invasive measurements of musculoskeletal structures (e.g., Achilles’ tendon, plantar fascia, patellar tendon) on ultrasound data acquired by the Clarius Ultrasound Scanner. The user shall be a healthcare professional trained and qualified in musculoskeletal ultrasound.

Technology

Clarius AI utilizes an AI image segmentation algorithm based on non-adaptive machine learning (Exception U-Net architecture) to analyze ultrasound images in real-time for tendon segmentation and thickness measurement, placing adjustable calipers on the thickest region of tendons. It is incorporated into the Clarius App software and operates with Clarius Ultrasound Scanner transducers L7 and L15.

Performance

Performance testing included AI model training on a large dataset of annotated ultrasound images, achieving a high average Dice score of 96%. Verification studies demonstrated that AI measurements of tendon thickness were statistically non-inferior to manual measurements by experienced clinicians, with an equivalence margin of 20%. Validation testing confirmed clinical usability and fulfillment of user needs for semi-automatic caliper placement with manual adjustment.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    8/9/2022

    5 months
  • 2

    FDA Approval

    1/23/2023

Other devices from Clarius Mobile Health Corp.

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.