Sonix Health is a software product designed to analyze echocardiography ultrasound images automatically. It helps clinicians by classifying ultrasound views and measuring cardiac parameters using AI, thereby improving efficiency and accuracy in heart assessment for adult patients.
Sonix Health is intended for quantifying and reporting echocardiography for use by or on the order of a licensed physician. It accepts DICOM-compliant ultrasound medical images acquired via B (2D), M, Pulsed-wave Doppler, and Continuous-wave Doppler modes and is indicated for use in adult populations.
Sonix Health is a DICOM-compliant software installed on customer PC hardware, using a two-step AI algorithm: initial single identification model for view classification followed by deep learning algorithms (B-mode, M-mode, Doppler) for anatomy segmentation and automatic measurement. It allows manual verification and adjustment of results.
Performance validation utilized images from 335 patients from US and Korean hospitals. It demonstrated high accuracy for view recognition (96.25%), strong correlation with expert manual measurements for Auto Measure (0.918) and Auto Strain (0.88 for LVGLS, 0.69 for RV free wall strain), and low error rates, all surpassing predefined thresholds, confirming safety and effectiveness.
No predicate devices specified
Submission
3/7/2024
FDA Approval
11/27/2024
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.