Myocardial Strain Drift Correction in Deep Learning Based Ultrasound Tracking
A state-of-the-art echocardiographic tracking method is extended with persistent memory tokens that share information across sliding windows over full cardiac cycles, supporting more reliable myocardial strain estimation in clinical practice and improving test-retest reproducibility.
Thierry Judge, Nicolas Duchateau, A. Østvik et al.
· 0 citations