Low Complexity Point Tracking of the Myocardium in 2D Echocardiography

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chernyshov, Artem, Nyberg, John, Holmstrøm, Vegard, Azad, Md Abulkalam, Grenne, Bjørnar, Dalen, Håvard, Aase, Svein Arne, Lovstakken, Lasse, Østvik, Andreas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909536724451328
author Chernyshov, Artem
Nyberg, John
Holmstrøm, Vegard
Azad, Md Abulkalam
Grenne, Bjørnar
Dalen, Håvard
Aase, Svein Arne
Lovstakken, Lasse
Østvik, Andreas
author_facet Chernyshov, Artem
Nyberg, John
Holmstrøm, Vegard
Azad, Md Abulkalam
Grenne, Bjørnar
Dalen, Håvard
Aase, Svein Arne
Lovstakken, Lasse
Østvik, Andreas
contents Deep learning methods for point tracking are applicable in 2D echocardiography, but do not yet take advantage of domain specifics that enable extremely fast and efficient configurations. We developed MyoTracker, a low-complexity architecture (0.3M parameters) for point tracking in echocardiography. It builds on the CoTracker2 architecture by simplifying its components and extending the temporal context to provide point predictions for the entire sequence in a single step. We applied MyoTracker to the right ventricular (RV) myocardium in RV-focused recordings and compared the results with those of CoTracker2 and EchoTracker, another specialized point tracking architecture for echocardiography. MyoTracker achieved the lowest average point trajectory error at 2.00 $\pm$ 0.53 mm. Calculating RV Free Wall Strain (RV FWS) using MyoTracker's point predictions resulted in a -0.3$\%$ bias with 95$\%$ limits of agreement from -6.1$\%$ to 5.4$\%$ compared to reference values from commercial software. This range falls within the interobserver variability reported in previous studies. The limits of agreement were wider for both CoTracker2 and EchoTracker, worse than the interobserver variability. At inference, MyoTracker used 67$\%$ less GPU memory than CoTracker2 and 84$\%$ less than EchoTracker on large sequences (100 frames). MyoTracker was 74 times faster during inference than CoTracker2 and 11 times faster than EchoTracker with our setup. Maintaining the entire sequence in the temporal context was the greatest contributor to MyoTracker's accuracy. Slight additional gains can be made by re-enabling iterative refinement, at the cost of longer processing time.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10431
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
Chernyshov, Artem
Nyberg, John
Holmstrøm, Vegard
Azad, Md Abulkalam
Grenne, Bjørnar
Dalen, Håvard
Aase, Svein Arne
Lovstakken, Lasse
Østvik, Andreas
Image and Video Processing
Computer Vision and Pattern Recognition
Deep learning methods for point tracking are applicable in 2D echocardiography, but do not yet take advantage of domain specifics that enable extremely fast and efficient configurations. We developed MyoTracker, a low-complexity architecture (0.3M parameters) for point tracking in echocardiography. It builds on the CoTracker2 architecture by simplifying its components and extending the temporal context to provide point predictions for the entire sequence in a single step. We applied MyoTracker to the right ventricular (RV) myocardium in RV-focused recordings and compared the results with those of CoTracker2 and EchoTracker, another specialized point tracking architecture for echocardiography. MyoTracker achieved the lowest average point trajectory error at 2.00 $\pm$ 0.53 mm. Calculating RV Free Wall Strain (RV FWS) using MyoTracker's point predictions resulted in a -0.3$\%$ bias with 95$\%$ limits of agreement from -6.1$\%$ to 5.4$\%$ compared to reference values from commercial software. This range falls within the interobserver variability reported in previous studies. The limits of agreement were wider for both CoTracker2 and EchoTracker, worse than the interobserver variability. At inference, MyoTracker used 67$\%$ less GPU memory than CoTracker2 and 84$\%$ less than EchoTracker on large sequences (100 frames). MyoTracker was 74 times faster during inference than CoTracker2 and 11 times faster than EchoTracker with our setup. Maintaining the entire sequence in the temporal context was the greatest contributor to MyoTracker's accuracy. Slight additional gains can be made by re-enabling iterative refinement, at the cost of longer processing time.
title Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.10431