EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Video-based multi-target multi-camera tracking for postoperative phase recognition

Franziska Jurosch, Janik Zeller, Lars Wagner, Ege Özsoy, Alissa Jell, Sven Kolb, Dirk Wilhelm

International Journal of Computer Assisted Radiology and Surgery · 12.04.2025 · 20 (6) · 1159-1166

DOI: 10.1007/s11548-025-03344-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 12.04.2025. Verfasst von Franziska Jurosch und 6 weiteren Autor:innen. Beteiligte Einrichtung: Technical University of Munich, School of Medicine and Health, TUM University Hospital, Research Group MITI, Munich, Germany. franziska.jurosch@tum.d…. Hauptthemen laut MEDLINE: Video Recording, Workflow, Deep Learning, Postoperative Care. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium für Bildung und Forschung, Bayerische Staatsministerium für Wirtschaft, Landesentwicklung und Energie.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Deep learning methods are commonly used to generate context understanding to support surgeons and medical professionals. By expanding the current focus beyond the operating room (OR) to postoperative workflows, new forms of assistance are possible. In this article, we propose a novel multi-target multi-camera tracking (MTMCT) architecture for postoperative phase recognition, location tracking, and automatic timestamp generation.

Methods

Three RGB cameras were used to create a multi-camera data set containing 19 reenacted postoperative patient flows. Patients and beds were annotated and used to train the custom MTMCT architecture. It includes bed and patient tracking for each camera and a postoperative patient state module to provide the postoperative phase, current location of the patient, and automatically generated timestamps.

Results

The architecture demonstrates robust performance for single- and multi-patient scenarios by embedding medical domain-specific knowledge. In multi-patient scenarios, the state machine representing the postoperative phases has a traversal accuracy of $$84.9 \pm 6.0\%$$ 84.9 ± 6.0 % , $$91.4 \pm 1.5\%$$ 91.4 ± 1.5 % of timestamps are generated correctly, and the patient tracking IDF1 reaches $$92.0 \pm 3.6\%$$ 92.0 ± 3.6 % . Comparative experiments show the effectiveness of using AFLink for matching partial trajectories in postoperative settings.

Conclusion

As our approach shows promising results, it lays the foundation for real-time surgeon support, enhancing clinical documentation and ultimately improving patient care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Video RecordingWorkflowDeep LearningPostoperative CareHumansPostoperative Period

Stichwörter der Autor:innen

Patient trackingSurgical data scienceSurgical workflow analysis

Autor:innen und Institutionen

  • Technical University of Munich, School of Medicine and Health, TUM University Hospital, Research Group MITI, Munich, Germany. franziska.jurosch@tum.de.
  • Technical University of Munich, School of Medicine and Health, TUM University Hospital, Research Group MITI, Munich, Germany.
  • Technical University of Munich, School of Computation, Information and Technology, Chair of Computer Aided Medical Procedures, Munich, Germany.
  • Technical University of Munich, School of Medicine and Health, TUM University Hospital, Department of Surgery, Munich, Germany.

Förderung

  • Bundesministerium für Bildung und Forschung
  • Bayerische Staatsministerium für Wirtschaft, Landesentwicklung und Energie

Zitieren

APA

Jurosch, F., Zeller, J., Wagner, L., Özsoy, E., Jell, A., Kolb, S., & Wilhelm, D. (2025). Video-based multi-target multi-camera tracking for postoperative phase recognition. International Journal of Computer Assisted Radiology and Surgery, 20(6), 1159-1166. https://doi.org/10.1007/s11548-025-03344-x

Vancouver

Jurosch F, Zeller J, Wagner L, Özsoy E, Jell A, Kolb S, et al. Video-based multi-target multi-camera tracking for postoperative phase recognition. International Journal of Computer Assisted Radiology and Surgery. 2025;20(6):1159-1166. doi:10.1007/s11548-025-03344-x

BibTeX
@article{Jurosch2025,
  author = {Jurosch, Franziska and Zeller, Janik and Wagner, Lars and Özsoy, Ege and Jell, Alissa and Kolb, Sven and Wilhelm, Dirk},
  title = {Video-based multi-target multi-camera tracking for postoperative phase recognition},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2025},
  volume = {20},
  number = {6},
  pages = {1159--1166},
  doi = {10.1007/s11548-025-03344-x}
}
Kostenlos starten →