AI Platform 2.0 (AIP002)
Exo ImagingAI Platform 2.0 (AIP002) by Exo Imaging is an AI-powered software tool designed to assist healthcare professionals by analyzing ultrasound images of the heart and lungs. It helps detect lung structures and artifacts, and quantifies cardiac functions such as left ventricular ejection fraction and myocardium wall thickness. The tool also provides real-time quality feedback to improve ultrasound image acquisition, aiding clinicians in making better diagnostic assessments for adult patients.
Intended Use
Intended for noninvasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of patients with suspected disease. Provides Quality Score feedback for echocardiography and lung ultrasound scans in adult patients.
Technology
Software as a Medical Device (SaMD) implementing deep convolutional neural networks for segmentation, landmark detection, and classification on digital ultrasound images in DICOM format from specified ultrasound scanners. Provides real-time frame and clip quality scoring. Cardiac AI quantifies left ventricular ejection fraction, myocardium wall thickness, and inferior vena cava diameter. Lung AI detects A-line and B-line artifacts.
Performance
The clinical performance was validated on diverse test data sets from multiple clinical sites with demographic diversity. Key metrics include high interclass correlation (ICC) values (~0.93-0.94) for left ventricle wall thickness and IVC measurements compared to expert ground truth. Quality AI was validated on over 226 clips (29,732 frames) with high agreement to expert ratings (ICC ~0.94), and real-time use in 396 scans from 26 users showed high concordance with expert diagnosis quality scores.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
4/8/2024
3 months - 2
FDA Approval
8/5/2024
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.