EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DyEndoVO: scene dynamics-aware pose estimation of endoscope in minimally invasive surgery

Jinjing Xu, Reuben Docea, Micha Pfeiffer, Martin Wagner, Marius Distler, Stefanie Speidel

International Journal of Computer Assisted Radiology and Surgery · 2025

DOI: 10.1007/s11548-025-03549-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Jinjing Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Center for Tumor Diseases (NCT/UCC), Dresden, Germany. jinjing.xu@nct-dresden.de. Hauptthemen laut MEDLINE: Minimally Invasive Surgical Procedures, Endoscopes, Surgery, Computer-Assisted, Endoscopy. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, HORIZON EUROPE Reforming and enhancing the European Research and Innovation system.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Estimating the 6 degrees of freedom (DoF) pose of an endoscope is crucial for various applications in minimally invasive computer-assisted surgery. Image-based approaches are some of the most practical solutions for pose estimation in surgical environments, due to a limited workspace and sensor constraints. However, these methods often struggle or fail in dynamic scenes, such as those involving tissue deformation, surgical tool movement, and tool-tissue interaction.

Methods

We propose DyEndoVO, an end-to-end visual odometry method in dynamic endoscopic scenes. Our method consists of a transformer-based motion detection network and a weighted pose-optimization module. The motion detection network infers scene dynamics and guides the pose estimation. Furthermore, we introduce a semi-synthetic dataset featuring tissue and tool movement categories. It serves as training data, improving pose estimation accuracy, and also includes motion masks to enable a fine-grained inspection and evaluation.

Results

DyEndoVO significantly outperforms state-of-the-art methods in pose estimation for dynamic surgical scenes. Despite being trained solely on a synthetic dataset, our method generalizes well to real-world data without fine-tuning. Further analysis attributes this success to the effective detection of scene dynamics and the adaptation in the learned weight toward pose estimation; moreover, the semi-synthetic dataset also plays a key role in bridging the sim-to-real gap.

Conclusions

In this work, we aim to improve the accuracy and robustness of pose estimation in challenging dynamic surgical scenes, by effectively handling scene dynamics. Our method, combined with the proposed synthetic dataset, demonstrates improved performance in pose estimation and generalizes well to real-world data, showing its potential in advancing related works such as SLAM and 3D reconstruction in complex surgical environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Minimally Invasive Surgical ProceduresEndoscopesSurgery, Computer-AssistedEndoscopyHumansAlgorithms

Stichwörter der Autor:innen

Endoscope localizationMotion detectionTissue deformationVisual odometry

Autor:innen und Institutionen

  • National Center for Tumor Diseases (NCT/UCC), Dresden, Germany. jinjing.xu@nct-dresden.de.
  • German Cancer Research Center (DKFZ), Heidelberg, Germany. jinjing.xu@nct-dresden.de.
  • National Center for Tumor Diseases (NCT/UCC), Dresden, Germany.
  • German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • The Centre for Tactile Internet with Human-in-the-Loop (CeTI), TU Dresden, Dresden, Germany.
  • University Hospital Carl Gustav Carus, Dresden, Germany.

Förderung

  • Deutsche Forschungsgemeinschaft
  • HORIZON EUROPE Reforming and enhancing the European Research and Innovation system

Zitieren

APA

Xu, J., Docea, R., Pfeiffer, M., Wagner, M., Distler, M., & Speidel, S. (2025). DyEndoVO: scene dynamics-aware pose estimation of endoscope in minimally invasive surgery. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03549-0

Vancouver

Xu J, Docea R, Pfeiffer M, Wagner M, Distler M, Speidel S. DyEndoVO: scene dynamics-aware pose estimation of endoscope in minimally invasive surgery. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03549-0

BibTeX
@article{Xu2025,
  author = {Xu, Jinjing and Docea, Reuben and Pfeiffer, Micha and Wagner, Martin and Distler, Marius and Speidel, Stefanie},
  title = {DyEndoVO: scene dynamics-aware pose estimation of endoscope in minimally invasive surgery},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2025},
  doi = {10.1007/s11548-025-03549-0}
}
Kostenlos starten →