Point tracking as a temporal Cue for robust myocardial segmentation in echocardiography videos
International Journal of Computer Assisted Radiology and Surgery · 11.05.2026 · 21 (6) · 1227-1234
DOI: 10.1007/s11548-026-03645-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 11.05.2026. Verfasst von Bahar Khodabakhshian und 8 weiteren Autor:innen. Beteiligte Einrichtung: University of British Columbia, University Blvd, Vancouver, BC, V6T 1Z4, British Columbia, Canada. baharkhd@ece.ubc.ca. Hauptthemen laut MEDLINE: Echocardiography, Deep Learning, Image Processing, Computer-Assisted, Heart. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben.
Abstract (Originalsprache)
Myocardium segmentation in echocardiography videos is a challenging task due to low contrast, noise, and anatomical variability. Traditional deep learning models either process frames independently, ignoring temporal information, or rely on memory-based feature propagation, which accumulates error over time. We propose PointSeg, a transformer-based segmentation framework that integrates point tracking as a temporal cue to ensure stable and consistent segmentation of myocardium across frames. Our method leverages a point-tracking module trained on a synthetic echocardiography dataset to track key anatomical landmarks across video sequences. These tracked trajectories provide an explicit motion-aware signal that guides segmentation, reducing drift and eliminating the need for memory-based feature accumulation. Additionally, we incorporate a temporal smoothing loss to further enhance temporal consistency across frames. We evaluate our approach on both public and private echocardiography datasets. Experimental results demonstrate that PointSeg has statistically similar accuracy in terms of Dice to state-of-the-art segmentation models in high-quality echo data, while it achieves better segmentation accuracy in lower-quality echo with improved temporal stability. Furthermore, PointSeg has the key advantage of pixel-level myocardium motion information as opposed to other segmentation methods. Such information is essential in the computation of other downstream tasks such as myocardial strain measurement and regional wall motion abnormality detection. PointSeg demonstrates that point tracking can serve as an effective temporal cue for consistent video segmentation, offering a reliable and generalizable approach for myocardium segmentation in echocardiography videos. The code is available at https://github.com/DeepRCL/PointSeg.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of British Columbia, University Blvd, Vancouver, BC, V6T 1Z4, British Columbia, Canada. baharkhd@ece.ubc.ca.
- University of British Columbia, University Blvd, Vancouver, BC, V6T 1Z4, British Columbia, Canada. nima.hashemi.edu@gmail.com.
- University of British Columbia, University Blvd, Vancouver, BC, V6T 1Z4, British Columbia, Canada.
- Vancouver General Hospital, West 12th Avenue, Vancouver, BC, V5Z 1M9, British Columbia, Canada.
Zitieren
APA
Khodabakhshian, B., Hashemi, N., Saadat, A., Gholami, Z., Hwang, I. C., Sojoudi, S., Luong, C., Abolmaesumi, P., & Tsang, T. (2026). Point tracking as a temporal Cue for robust myocardial segmentation in echocardiography videos. International Journal of Computer Assisted Radiology and Surgery, 21(6), 1227-1234. https://doi.org/10.1007/s11548-026-03645-9
Vancouver
Khodabakhshian B, Hashemi N, Saadat A, Gholami Z, Hwang IC, Sojoudi S, et al. Point tracking as a temporal Cue for robust myocardial segmentation in echocardiography videos. International Journal of Computer Assisted Radiology and Surgery. 2026;21(6):1227-1234. doi:10.1007/s11548-026-03645-9
BibTeX
@article{Khodabakhshian2026,
author = {Khodabakhshian, Bahar and Hashemi, Nima and Saadat, Armin and Gholami, Zahra and Hwang, In-Chang and Sojoudi, Samira and Luong, Christina and Abolmaesumi, Purang and Tsang, Teresa},
title = {Point tracking as a temporal Cue for robust myocardial segmentation in echocardiography videos},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2026},
volume = {21},
number = {6},
pages = {1227--1234},
doi = {10.1007/s11548-026-03645-9}
}
EUVIMED