Acquiring submillimeter-accurate multi-task vision datasets for computer-assisted orthopedic surgery
International Journal of Computer Assisted Radiology and Surgery · 2025
DOI: 10.1007/s11548-025-03385-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Emma Most und 9 weiteren Autor:innen. Beteiligte Einrichtung: Research in Orthopedic Computer Science, University Hospital Balgrist, University of Zurich, Zurich, Switzerland. emmost@ethz.ch. Hauptthemen laut MEDLINE: Surgery, Computer-Assisted, Imaging, Three-Dimensional, Orthopedic Procedures, Scoliosis. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Innosuisse - Schweizerische Agentur für Innovationsförderung.
Abstract (Originalsprache)
Purpose
Advances in computer vision, particularly in optical image-based 3D reconstruction and feature matching, enable applications like marker-less surgical navigation and digitization of surgery. However, their development is hindered by a lack of suitable datasets with 3D ground truth. This work explores an approach to generating realistic and accurate ex vivo datasets tailored for 3D reconstruction and feature matching in open orthopedic surgery.
Methods
A set of posed images and an accurately registered ground truth surface mesh of the scene are required to develop vision-based 3D reconstruction and matching methods suitable for surgery. We propose a framework consisting of three core steps and compare different methods for each step: 3D scanning, calibration of viewpoints for a set of high-resolution RGB images, and an optical method for scene registration.
Results
We evaluate each step of this framework on an ex vivo scoliosis surgery using a pig spine, conducted under real operating room conditions. A mean 3D Euclidean error of 0.35 mm is achieved with respect to the 3D ground truth.
Conclusion
The proposed method results in submillimeter-accurate 3D ground truths and surgical images with a spatial resolution of 0.1 mm. This opens the door to acquiring future surgical datasets for high-precision applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research in Orthopedic Computer Science, University Hospital Balgrist, University of Zurich, Zurich, Switzerland. emmost@ethz.ch.
- Computer Vision and Geometry, ETH Zurich, Zurich, Switzerland. emmost@ethz.ch.
- Research in Orthopedic Computer Science, University Hospital Balgrist, University of Zurich, Zurich, Switzerland.
- Computer Vision and Geometry, ETH Zurich, Zurich, Switzerland.
- Institut de Recherche en Informatique de Toulouse, Toulouse, France.
Förderung
- Innosuisse - Schweizerische Agentur für Innovationsförderung
Zitieren
APA
Most, E., Hein, J., Giraud, F., Cavalcanti, N. A., Zingg, L., Brument, B., Louman, N., Carrillo, F., Fürnstahl, P., & Calvet, L. (2025). Acquiring submillimeter-accurate multi-task vision datasets for computer-assisted orthopedic surgery. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03385-2
Vancouver
Most E, Hein J, Giraud F, Cavalcanti NA, Zingg L, Brument B, et al. Acquiring submillimeter-accurate multi-task vision datasets for computer-assisted orthopedic surgery. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03385-2
BibTeX
@article{Most2025,
author = {Most, Emma and Hein, Jonas and Giraud, Frédéric and Cavalcanti, Nicola A and Zingg, Lukas and Brument, Baptiste and Louman, Nino and Carrillo, Fabio and Fürnstahl, Philipp and Calvet, Lilian},
title = {Acquiring submillimeter-accurate multi-task vision datasets for computer-assisted orthopedic surgery},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2025},
doi = {10.1007/s11548-025-03385-2}
}
EUVIMED