Real-time marker-less needle tracking for CT-guided interventions using multiple RGB cameras
International Journal of Computer Assisted Radiology and Surgery · 25.04.2026
DOI: 10.1007/s11548-026-03622-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 25.04.2026. Verfasst von Max Steiger und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Campus STIMULATE, University of Magdeburg, Otto-Hahn-Straße 2, 39106, Magdeburg, Saxony-Anhalt, Germany. max.steiger@ovgu.de. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Research, Technology, and Space, European Regional Development Fund, Otto-von-Guericke-Universität Magdeburg.
Abstract (Originalsprache)
Purpose
In CT-guided interventions, instrument tracking reduces patient risk while improving the overall outcome. Though useful, marker-based tracking systems suffer from occlusion, are complex to set up, and fail when needles deflect. A marker-less tracking system could overcome these challenges, enabling streamlined integration.
Methods
We developed and evaluated a proof-of-concept system combining standard RGB cameras with a U-Net-ConvNeXt architecture for needle detection and tracking. We compiled a fully annotated dataset of 35,000 frames, spanning multiple needle types and scenarios. We evaluated tracking accuracy against state-of-the-art marker-based systems, utilizing an IR-based and an image-based system on static positioning, dynamic movement, and needle-deflection scenarios. Moreover, our marker-less system was evaluated using both known and unknown needle types.
Results
Our proof-of-concept system demonstrated a 3D tracking error of $$2.70\,\pm \,1.07$$ 2.70 ± 1.07 mm at 25 FPS with 3 cameras, outperforming ArUco marker-based tracking ( $$5.29\,\pm \,1.85$$ 5.29 ± 1.85 mm). Tracking accuracy remained consistent for unknown needle types not included in the training data, suggesting strong generalization. The system maintained a 99.4 % needle-tip detection rate across all frames with robust performance during needle deflection, while marker-based systems failed under identical conditions. With only 2 cameras, the tracking error of our system increased modestly ( $$4.81\,\pm \,2.38$$ 4.81 ± 2.38 mm).
Conclusion
Our proof-of-concept demonstrates the feasibility of marker-less needle tracking, suggesting potential for clinically relevant accuracy, reliability, and reduced complexity while exhibiting robustness to needle deflection and varying needle appearances. These preliminary results indicate promising directions for future clinical development.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Campus STIMULATE, University of Magdeburg, Otto-Hahn-Straße 2, 39106, Magdeburg, Saxony-Anhalt, Germany. max.steiger@ovgu.de.
- Research Campus STIMULATE, University of Magdeburg, Otto-Hahn-Straße 2, 39106, Magdeburg, Saxony-Anhalt, Germany.
- Department of Radiology and Nuclear Medicine, University Hospital Magdeburg, Leipziger Straße 44, 39120, Magdeburg, Saxony-Anhalt, Germany.
Förderung
- German Federal Ministry of Research, Technology, and Space
- European Regional Development Fund
- Otto-von-Guericke-Universität Magdeburg
Zitieren
APA
Steiger, M., Mielke, T., Bashkanov, O., Grosser, O. S., Pech, M., Hansen, C., & Rak, M. (2026). Real-time marker-less needle tracking for CT-guided interventions using multiple RGB cameras. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-026-03622-2
Vancouver
Steiger M, Mielke T, Bashkanov O, Grosser OS, Pech M, Hansen C, et al. Real-time marker-less needle tracking for CT-guided interventions using multiple RGB cameras. International Journal of Computer Assisted Radiology and Surgery. 2026. doi:10.1007/s11548-026-03622-2
BibTeX
@article{Steiger2026,
author = {Steiger, Max and Mielke, Tonia and Bashkanov, Oleksii and Grosser, Oliver S and Pech, Maciej and Hansen, Christian and Rak, Marko},
title = {Real-time marker-less needle tracking for CT-guided interventions using multiple RGB cameras},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2026},
doi = {10.1007/s11548-026-03622-2}
}
EUVIMED