AI-Enabled Assessment of Cardiac Systolic and Diastolic Function from Echocardiography

Left ventricular (LV) function is an important factor in terms of patient management, outcome, and long-term survival patients with heart disease. The most recently published clinical guidelines for failure recognise that over reliance on only one measure cardiac (LV ejection fraction) as a diagnostic treatment stratification biomarker suboptimal. Recent advances AI-based echocardiography analysis have shown excellent results automated estimation LV volumes fraction. However, from time-varying 2-D acquisition, richer description can be obtained by estimating functional biomarkers the complete cycle. In this work we propose first time AI approach deriving advanced systolic diastolic based segmentations full These will allow clinicians to obtain much picture health model ’nn-Unet’ framework was trained tested using four different databases. Results show agreement between manual showcase potential stratification. Finally, subset 50 cases, perform correlation derived magnetic resonance very strong relationship two modalities.