BrightHeart View Classifier
BrightHeartBrightHeart View Classifier is a cloud-based AI-powered software designed to analyze 2D fetal ultrasound images and video clips to automatically identify and classify standard fetal heart views. It assists trained healthcare professionals in acquiring and interpreting fetal heart ultrasound exams in the second and third trimesters by providing annotated outputs and validating whether scanning protocols are met, improving diagnostic workflow and consistency.
Intended Use
The BrightHeart View Classifier device is intended to analyze fetal 2D ultrasound images and video clips using machine learning techniques to automatically detect standard views during fetal heart scanning. It is intended as an adjunct to the acquisition and interpretation of fetal anatomic ultrasound examinations at the second or third trimester of pregnancy performed with transabdominal probes.
Technology
BrightHeart View Classifier is a cloud-based software-only device employing neural networks to classify 2D grayscale fetal ultrasound images and video clips into standard fetal heart views. Outputs include annotated DICOM files and a web interface, aiding healthcare professionals in fetal heart image acquisition and interpretation.
Performance
Performance testing involved validation on 2290 images and frames from 579 fetal ultrasound examinations across 8 centers, showing a mean sensitivity of 0.939 and specificity of 0.984 for standard view recognition. Validation was performed with images from GE, Philips, Samsung, and Siemens ultrasound devices, and across diverse patient demographics.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/12/2025
24 days - 2
FDA Approval
6/5/2025
Other devices from BrightHeart
- BrightHeart View Classifier2025 • 510K
- Fetal EchoScan (v1.1)2025 • 510K
- Fetal EchoScan2024 • 510K
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.