Intended Use

The software is used to process previously acquired transthoracic cardiac ultrasound images to provide automated estimation of left ventricular ejection fraction to assist clinicians in cardiac evaluation, indicated for adult patients.

Technology

The software applies machine learning algorithms (convolutional neural networks) to biplane apical echocardiographic images from ultrasound video clips to calculate left ventricular ejection fraction. It operates as a microservice that selects relevant image clips automatically and communicates with DICOM sources and PACS systems, providing the EF measurement as a percentage along with qualitative and quantitative image quality feedback.

Performance

Performance testing included non-clinical software verification at multiple levels, retrospective validation on over 300 patient cases across various ultrasound device manufacturers, and a secondary clinical study confirming safety and effectiveness similar to the predicate LVivo EF Software. The primary endpoint used root mean square deviation (RMSD) of ejection fraction measurements, achieving 8.29% RMSD, demonstrating accurate and generalizable performance.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    12/12/2017

    6 months
  • 2

    FDA Approval

    6/14/2018

Other devices from Bay Labs, Inc.

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.