Search papers, labs, and topics across Lattice.
Deep learning-based myocardial motion tracking frequently suffers from cumulative temporal drift across cardiac cycles due to a lack of cyclical physical priors, leading to inaccurate and often divergent strain estimation. To resolve this, the authors augment TAS-Net with persistent memory tokens that carry context across sliding windows and apply a teacher-student fine-tuning objective that enforces closed-loop cyclic consistency on real echocardiography. The approach significantly reduces both global and regional strain drift while improving test-retest reproducibility and clinical metric alignment without degrading local tracking fidelity.
Neural motion trackers routinely accumulate drift over repetitive biological cycles; pairing persistent cross-window memory tokens with cyclic teacher-student supervision forces trajectories to close naturally without sacrificing frame-to-frame precision.
Myocardial strain from echocardiography is a key biomarker for cardiac function. Recent deep learning methods show strong performance for myocardial motion tracking but often lack physiological constraints, leading to temporal drift across the cardiac cycle. Consequently, tracked points may not return to their relative initial positions at the end of each cardiac cycle, producing inaccurate strain estimates and even divergence in some cases. We propose a deep learning framework that compensates for drift during myocardial tracking. We extend a state-of-the-art echocardiographic tracking method (TAS-Net) with persistent memory tokens that share information across sliding windows over full cardiac cycles. A teacher-student fine-tuning strategy on real echocardiographic data then enforces physiologically consistent cyclic motion while preserving tracking accuracy. Experiments show reduced global and regional strain drift, improved agreement with clinical references, and better test-retest reproducibility, supporting more reliable myocardial strain estimation in clinical practice.
