Automatic Rotation of Spinal X-Ray Images

Type: MA thesis

Status: running

Date: April 4, 2022 - October 4, 2022

Supervisors: Maximilian Rohleder, Holger Kunze (Siemens Healthineers), Andreas Maier, Johannes Groh (Klinik für Unfallchirurgie und Orthopädie, UK Erlangen)

Guidance in orthopedic and trauma surgery is increasingly relying on intraoperative fluoroscopy with a mobile C-arm. Mobile fluoroscopy is also used to assess the success of fracture reduction, implant position, and overall outcome [1]. This reduces the number of necessary revision surgeries [2]. Accurate standardized image rotation is essential to improve reading performance and interpretation. While alignment of a patient with the imaging system is not always achievable, the images must be rotated manually by radiographers [3].

As the interaction of the user with the imaging system should be minimized, the goal of this thesis is to develop an automatic procedure that determines the orientation of the acquired images and rotates them to a standard position to be viewed by radiologists. In this work, the focus is on the regression of the image rotation of anterior-posterior (AP) and lateral radiographs of the spine since these are the most frequently acquired and most relevant for spine procedures.


[1] Lisa Kausch, Sarina Thomas, Holger Kunze, Maxim Privalov, Sven Vetter, Jochen Franke, Andreas H.
Mahnken, Lena Maier-Hein, and Klaus Maier-Hein. Toward automatic c-arm positioning for standard
projections in orthopedic surgery. Int. J. Comput. Assist. Radiol. Surg., 15(7):1095–1105, Jul 2020.

[2] Celia Mart´ın Vicario, Florian Kordon, Felix Denzinger, MarkusWeiten, Sarina Thomas, Lisa Kausch, Jochen
Franke, Holger Keil, Andreas Maier, and Holger Kunze. Automatic plane adjustment of orthopedic intraoperative
flat panel detector ct-volumes. In Proc. MICCAI, Part II, volume 12262, pages 486–495, 2020.

[3] Ivo M. Baltruschat, Axel Saalbach, Mattias P. Heinrich, Hannes Nickisch, and Sascha Jockel. Orientation
regression in hand radiographs: a transfer learning approach. In Proc. SPIE Medical Imaging, volume 10574,
pages 473 – 480, 2018.