EUVIMEDEUVIMED entdecken
Crossref

ERegPose: An explicit regression based 6D pose estimation for snake‐like wrist‐type surgical instruments

Jinhua Li, Zhengyang Ma iD, Xinan Sun iD, He Su

The International Journal of Medical Robotics and Computer Assisted Surgery · 2024

DOI: 10.1002/rcs.2640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, 2024. Verfasst von Jinhua Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Key Lab for Mechanism Theory and Equipment Design of Ministry of Education, School of Mechanical Engineering, Tianjin University, Tianjin, China. Hauptthemen laut MEDLINE: Wrist, Neural Networks, Computer, Surgical Instruments. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Tianjin University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurately estimating the 6D pose of snake‐like wrist‐type surgical instruments is challenging due to their complex kinematics and flexible design.

Methods

We propose ERegPose, a comprehensive strategy for precise 6D pose estimation. The strategy consists of two components: ERegPoseNet, an original deep neural network model designed for explicit regression of the instrument's 6D pose, and an annotated in‐house dataset of simulated surgical operations. To capture rotational features, we employ an Single Shot multibox Detector (SSD)‐like detector to generate bounding boxes of the instrument tip.

Results

ERegPoseNet achieves an error of 1.056 mm in 3D translation, 0.073 rad in 3D rotation, and an average distance (ADD) metric of 3.974 mm, indicating an overall spatial transformation error. The necessity of the SSD‐like detector and L1 loss is validated through experiments.

Conclusions

ERegPose outperforms existing approaches, providing accurate 6D pose estimation for snake‐like wrist‐type surgical instruments. Its practical applications in various surgical tasks hold great promise.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WristNeural Networks, ComputerSurgical InstrumentsHumansEquipment DesignBiomechanical PhenomenaAlgorithmsRobotic Surgical ProceduresImaging, Three-DimensionalRotationReproducibility of ResultsSurgery, Computer-AssistedRegression Analysis

Stichwörter der Autor:innen

6D pose estimationexplicit regressionsnake‐like wrist‐type surgical instrumentssurgical robotics

Autor:innen und Institutionen

  • Key Lab for Mechanism Theory and Equipment Design of Ministry of Education, School of Mechanical Engineering, Tianjin University, Tianjin, China.
  • School of Mechanical Engineering, Tianjin University, Tianjin, China.

ORCID-Profile: Zhengyang Ma, Xinan Sun

Förderung

  • National Natural Science Foundation of China
  • Tianjin University

Zitieren

APA

Li, J., Ma, Z., Sun, X., & Su, H. (2024). ERegPose: An explicit regression based 6D pose estimation for snake‐like wrist‐type surgical instruments. The International Journal of Medical Robotics and Computer Assisted Surgery. https://doi.org/10.1002/rcs.2640

Vancouver

Li J, Ma Z, Sun X, Su H. ERegPose: An explicit regression based 6D pose estimation for snake‐like wrist‐type surgical instruments. The International Journal of Medical Robotics and Computer Assisted Surgery. 2024. doi:10.1002/rcs.2640

BibTeX
@article{Li2024,
  author = {Li, Jinhua and Ma, Zhengyang and Sun, Xinan and Su, He},
  title = {ERegPose: An explicit regression based 6D pose estimation for snake‐like wrist‐type surgical instruments},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2024},
  doi = {10.1002/rcs.2640}
}
Kostenlos starten →