Prediction of Patient and Mobile C-arm Orientation in Orthopedic Trauma Procedures

Scheuplein J, Kreher BW, Maier A (2026)

Publication Type: Conference contribution

Publication year: 2026

Journal

Informatik aktuell Gesellschaft für Informatik (GI)

Series: Informatik aktuell

Pages Range: 210-216

Conference Proceedings Title: Bildverarbeitung für die Medizin 2026

Event location: Lübeck DE

ISBN: 9783658510992

DOI: 10.1007/978-3-658-51100-5_43

Abstract

Accurate knowledge of patient and mobile C-arm system orientation is essential for intraoperative 3D scan acquisition, yet this information is currently entered manually by operating room staff, making the process timeconsuming and error-prone.We propose a deep learning approach for the joint classification of patient and C-arm orientation using only a pair of anteriorposterior and lateral projection images. The method builds on frozen DAX foundation model embeddings, combined with a task-specific head network trained on 633 clinical 3D scans. The developed model achieved a weighted mean F1-score of 89.9% (±1.3%). It can be seamlessly incorporated into the clinical 3D workflow to automatically infer orientation from pre-existing scout views, thus reducing the need for manual intervention and enhancing intraoperative efficiency.

Authors with CRIS profile

Joshua Scheuplein Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

APA:

Scheuplein, J., Kreher, B.W., & Maier, A. (2026). Prediction of Patient and Mobile C-arm Orientation in Orthopedic Trauma Procedures. In Bildverarbeitung für die Medizin 2026 (pp. 210-216). Lübeck, DE.

MLA:

Scheuplein, Joshua, Bjoern W. Kreher, and Andreas Maier. "Prediction of Patient and Mobile C-arm Orientation in Orthopedic Trauma Procedures." Proceedings of the German Conference on Medical Image Computing, Lübeck 2026. 210-216.

BibTeX: Download