Intended Use

Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device indicated as an adjunct to fetal heart ultrasound examination in pregnant women aged 18 or older undergoing second-trimester anatomic ultrasound exams. It detects suspicious radiographic findings such as overriding artery, septal defect at the cardiac crux, abnormal relationship of the outflow tracts, enlarged cardiothoracic ratio, ventricular size discrepancies, valve annular size discrepancies, and cardiac axis deviation.

Technology

The device is a cloud-based software-only solution using neural networks trained on fetal ultrasound video clips (4-chamber, left and right ventricular outflow tracts views) to identify suspicious cardiac morphological features. The algorithm outputs presence, absence, or inconclusive results per frame, with summaries per video and exam. Outputs may be displayed as annotated DICOM files in PACS or on a web interface.

Performance

Software validation included bench testing with 877 fetal ultrasound exams from multiple centers. The AI showed high sensitivity (up to 98.7%) and specificity (up to 100%) depending on analysis conditions. A multiple-reader multiple-case clinical study with 14 readers and 200 exams demonstrated significant improvement in detection accuracy when using the device, with ROC AUC increasing from 0.825 unaided to 0.974 aided. Performance was consistent across subgroups and device models.

Predicate Devices

No predicate devices specified

Device Timeline

  • 1

    Submission

    4/7/2025

    25 days
  • 2

    FDA Approval

    5/2/2025

Other devices from BrightHeart

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.