EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios

Guoping Xu, Hua-Chieh Shao, You Zhang

Machine Learning: Health · 2026

DOI: 10.1088/3049-477x/ae291a ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Health, 2026. Verfasst von Guoping Xu und 2 weiteren Autor:innen. Beteiligte Einrichtung: The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Cent…. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIBIB NIH HHS, US National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Promptable video object segmentation and tracking (VOST) has seen significant advances with the emergence of foundation models like Segment Anything Model 2 (SAM2); however, their application in surgical video analysis remains challenging due to complex motion dynamics and the redundancy of memory that impedes effective learning. In this work, we propose TSMS-SAM2, a novel framework that enhances promptable VOST in surgical videos by addressing challenges of rapid object motion and memory redundancy in SAM2. TSMS-SAM2 introduces two key strategies: multi-temporal-scale video sampling augmentation to improve robustness against motion variability, and a memory splitting and pruning mechanism that organizes and filters past frame features for more efficient and accurate segmentation. Evaluated on EndoVis2017 and EndoVis2018 datasets, TSMS-SAM2 achieved the highest mean (± s.d.) Dice scores of 95.24±0.96% and 86.73±15.46%, respectively, outperforming prior SAM-based and task-specific methods. Extensive ablation studies confirm the effectiveness of multiscale temporal augmentation and memory splitting, highlighting the framework's potential for robust, efficient segmentation in complex surgical scenarios. Our source code will be made available at https://github.com/apple1986/TSMS-SAM2.

Schlagwörter

Stichwörter der Autor:innen

AugmentationDeep LearningMemorySegment Anything 2Video Object Tracking and Segmentation

Autor:innen und Institutionen

  • The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.

Förderung

  • NCI NIH HHS
  • NIBIB NIH HHS
  • US National Institutes of Health

Zitieren

APA

Xu, G., Shao, H. C., & Zhang, Y. (2026). TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios. Machine Learning: Health. https://doi.org/10.1088/3049-477x/ae291a

Vancouver

Xu G, Shao HC, Zhang Y. TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios. Machine Learning: Health. 2026. doi:10.1088/3049-477x/ae291a

BibTeX
@article{Xu2026,
  author = {Xu, Guoping and Shao, Hua-Chieh and Zhang, You},
  title = {TSMS-SAM2: multi-scale temporal sampling augmentation and memory-splitting pruning for promptable video object segmentation and tracking in surgical scenarios},
  journal = {Machine Learning: Health},
  year = {2026},
  doi = {10.1088/3049-477x/ae291a}
}
Kostenlos starten →