Low Complexity Point Tracking of the Myocardium in 2D Echocardiography

This work presents a low-complexity alternative to existing deep learning-based myocardial point tracking methods in 2D echocardiography. By redesigning the tracking pipeline for efficiency, the approach achieves competitive accuracy compared to state-of-the-art methods while drastically reducing computational requirements — making it more feasible for deployment in clinical settings.

Authors: A. Chernyshov, J. Nyberg, V. Holmstrøm, M. A. Azad, B. Grenne, H. Dalen, S. A. Aase, L. Lovstakken, A. Østvik

Venue: arXiv preprint (2025)

Access preprint

Recommended citation: Chernyshov, A., Nyberg, J., Holmstrøm, V., Azad, M.A., Grenne, B., Dalen, H., Aase, S.A., Lovstakken, L., and Østvik, A. (2025). "Low Complexity Point Tracking of the Myocardium in 2D Echocardiography." arXiv preprint arXiv:2503.10431. https://arxiv.org/abs/2503.10431