Intended Use

Software to process previously acquired DICOM-compliant cardiac ultrasound images and provide automated estimation of several cardiac measurements to support healthcare practitioners for clinical decision-making in adult patients.

Technology

The software uses machine learning algorithms for echocardiographic view classification, image quality assessment, key frame selection, automated keypoint detection, and segmentation of cardiac structures to compute multiple cardiac parameters from ultrasound images. It integrates these into a browser interface for clinicians to review, accept, or edit the automated measurements.

Performance

The software underwent retrospective standalone performance validation on 200 echocardiography studies from two clinical US sites with diverse patients and ultrasound systems, comparing automated measurements against ground truth from experienced clinicians. Statistical analysis showed the software met predetermined accuracy thresholds for all cardiac measurements with no bias by demographics or equipment and exhibited good agreement with the ground truth annotations.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    5/21/2024

    4 months
  • 2

    FDA Approval

    10/10/2024

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.