Intended Use

Analysis and reporting of vascular ultrasound images.

Technology

Standalone software runs on standard desktop/laptop or cloud platform, analyzing DICOM-compliant vascular ultrasound images using proprietary algorithms incorporating artificial intelligence and machine learning methods for segmentation, intima-media thickness measurement, Doppler velocity analysis, and annotation reading to generate vascular ultrasound reports.

Performance

Performance evaluated on retrospective multi-center datasets showed strong correlation with expert readers for carotid IMT measurement (correlation coefficient 0.89 vs experts' 0.86 and predicate 0.6), text recognition accuracy 92-96%, and high correlation for Doppler peak systolic and end diastolic velocities (0.98 and 0.97), with waveform classification accuracy of 93%. Risk analysis shows all risks mitigated and acceptable. Overall performance and safety comparable or superior to predicate device.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    5/22/2020

    3 months
  • 2

    FDA Approval

    9/16/2020

Other devices from See-Mode Technologies Pte. Ltd.

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.