HeartFocus (V.1.1.1) is an AI-powered software accessory designed to help healthcare professionals acquire high-quality 2D cardiac ultrasound images. It guides users in real-time to position the ultrasound probe correctly and detects when images meet diagnostic quality. This assists both experienced sonographers and less trained medical professionals in capturing standardized heart views, improving the quality and consistency of cardiac ultrasound exams.
HeartFocus software is intended to assist and guide medical professionals in the acquisition of cardiac ultrasound images on compatible general-purpose diagnostic ultrasound systems. It guides acquisition of ten standard 2D transthoracic echocardiographic views in adult patients.
HeartFocus uses AI and machine learning models to emulate sonographer expertise by providing real-time probe position guidance and diagnostic-quality image detection. It offers live guidance cues, automatic and retrospective recording of diagnostic clips, and operates offline on a tablet connected to an ultrasound device providing 2D streams.
Performance testing included training on over 1.4 million ultrasound images from 1,483 patients and testing on an independent set of 290 patients. The AI algorithms demonstrated substantial agreement with expert annotations for diagnostic-quality view detection, with Cohen's kappa scores above 0.6, and high positive predictive values (>0.8) for providing guidance cues and auto-recording diagnostic clips. Clinical validation showed nurses without prior echo training successfully acquiring 10-view echocardiography exams of diagnostic quality in 99+% of cases across multiple cardiac parameters, with average exam time about 24 minutes.
No predicate devices specified
Submission
9/17/2024
FDA Approval
4/4/2025
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.