Toward automatic C-arm positioning for standard projections in orthopedic surgery



Guidance and quality control in orthopedic surgery increasingly rely on intra-operative fluoroscopy using a mobile C-arm. The accurate acquisition of standardized and anatomy-specific projections is essential in this process. The corresponding iterative positioning of the C-arm is error prone and involves repeated manual acquisitions or even continuous fluoroscopy. To reduce time and radiation exposure for patients and clinical staff and to avoid errors in fracture reduction or implant placement, we aim at guiding—and in the long-run automating—this procedure.


In contrast to the state of the art, we tackle this inherently ill-posed problem without requiring patient-individual prior information like preoperative computed tomography (CT) scans, without the need of registration and without requiring additional technical equipment besides the projection images themselves. We propose learning the necessary anatomical hints for efficient C-arm positioning from in silico simulations, leveraging masses of 3D CTs. Specifically, we propose a convolutional neural network regression model that predicts 5 degrees of freedom pose updates directly from a first X-ray image. The method is generalizable to different anatomical regions and standard projections.


Quantitative and qualitative validation was performed for two clinical applications involving two highly dissimilar anatomies, namely the lumbar spine and the proximal femur. Starting from one initial projection, the mean absolute pose error to the desired standard pose is iteratively reduced across different anatomy-specific standard projections. Acquisitions of both hip joints on 4 cadavers allowed for an evaluation on clinical data, demonstrating that the approach generalizes without retraining.


Overall, the results suggest the feasibility of an efficient deep learning-based automated positioning procedure, which is trained on simulations. Our proposed 2-stage approach for C-arm positioning significantly improves accuracy on synthetic images. In addition, we demonstrated that learning based on simulations translates to acceptable performance on real X-rays.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. 1.

    Bahrs C, Stojicevic T, Blumenstock G, Brorson S, Badke A, Stöckle U, Rolauffs B, Freude T (2014) Trends in epidemiology and patho-anatomical pattern of proximal humeral fractures. Int Orthop 38(8):1697–1704

    Article  Google Scholar 

  2. 2.

    Bier B, Unberath M, Zaech J, Fotouhi J, Armand M, Osgood G, Navab N, Maier A (2018) X-ray-transform invariant anatomical landmark detection for pelvic trauma surgery. In: Medical image computing and computer-assisted intervention. Springer, pp 55–63 (2018)

  3. 3.

    Binder N, Bodensteiner C, Matthäus L, Burgkart R, Schweikard A (2006) Image guided positioning for an interactive C-arm fluoroscope. Int J Comput Assist Radiol Surg 1:5–7

    Google Scholar 

  4. 4.

    Bott O, Dresing K, Wagner M, Raab B, Teistler M (2011) Informatics in radiology: use of a C-arm fluoroscopy simulator to support training in intraoperative radiography. RadioGraphics 31(3):E65–E75

    Article  Google Scholar 

  5. 5.

    Bui M, Albarqouni S, Schrapp M, Navab N, Ilic S (2017) X-Ray PoseNet: 6 DoF pose estimation for mobile X-ray devices. In: IEEE winter conference on applications of computer vision. IEEE, pp 1036–1044 (2017)

  6. 6.

    De Silva T, Punnoose J, Uneri A, Goerres J, Jacobson M, Ketcha MD, Manbachi A, Vogt S, Kleinszig G, Khanna A, Wolinksy J, Osgood G, Siewerdsen J (2017) C-arm positioning using virtual fluoroscopy for image-guided surgery. In: Medical imaging: image-guided procedures, robotic interventions, and modeling, vol 10135. International Society for Optics and Photonics, p 101352K

  7. 7.

    Fallavollita P, Winkler A, Habert S, Wucherer P, Stefan P, Mansour R, Ghotbi R, Navab N (2014) Desired-view controlled positioning of angiographic C-arms. In: Medical image computing and computer-assisted intervention. Springer, pp 659–666

  8. 8.

    Gao C, Unberath M, Taylor R, Armand M (2019) Localizing dexterous surgical tools in x-ray for image-based navigation. arXiv preprint arXiv:1901.06672

  9. 9.

    Gong R, Jenkins B, Sze R, Yaniv Z () A cost effective and high fidelity fluoroscopy simulator using the image-guided surgery toolkit (IGSTK). In: Medical imaging: image-guided procedures, robotic interventions, and modeling, vol 9036. International Society for Optics and Photonics, p 903618

  10. 10.

    Haiderbhai M, Turrubiates J, Gutta V, Fallavollita P (2019) Automatic C-arm positioning using multi-functional user interface. CMBES Proc 42:1

    Article  Google Scholar 

  11. 11.

    Hou B, Alansary A, McDonagh S, Davidson A, Rutherford M, Hajnal J, Rueckert D, Glocker B, Kainz B (2017) Predicting slice-to-volume transformation in presence of arbitrary subject motion. In: Medical image computing and computer-assisted intervention. Springer, pp 296–304

  12. 12.

    Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980

  13. 13.

    Kordon F, Lasowski R, Swartman B, Franke J, Fischer P, Kunze H (2019) Improved x-ray bone segmentation by normalization and augmentation strategies. In: Bildverarbeitung für die Medizin. Springer, pp 104–109

  14. 14.

    Kordon F, Maier A, Swartman B, Kunze H (2020) Font augmentation: implant and surgical tool simulation for X-ray image processing. In Bildverarbeitung für die Medizin

  15. 15.

    Maier J, Aichert A, Mehringer W, Bier B, Eskofier B, Levenston M, Gold G, Fahrig R, Bonaretti S, Maier A (2018) Feasibility of motion compensation using inertial measurement in C-arm CT nuclear science symposium and medical imaging conference proceedings, pp 1–3

  16. 16.

    Matthäus L, Binder N, Bodensteiner C, Schweikard A (2007) Closed-form inverse kinematic solution for fluoroscopic C-arms. Adv Robot 21(8):869–886

    Article  Google Scholar 

  17. 17.

    Miao S, Piat S, Fischer P, Tuysuzoglu A, Mewes P, Mansi T, Liao R (2018) Dilated FCN for multi-agent 2d/3d medical image registration. In: 32nd AAAI conference on artificial intelligence (2018)

  18. 18.

    Nolden M, Zelzer S, Seitel A, Wald D, Müller M, Franz A, Maleike D, Fangerau M, Baumhauer M, Maier-Hein L, Maier-Hein K, Meinzer H, Wolf I (2013) The medical imaging interaction toolkit: challenges and advances. Int J Comput Assist Radiol Surg 8(4):607–620

    Article  Google Scholar 

  19. 19.

    Rikli D, Seibert F, Benninger E, Platz A, Tomazevic M, Goldhahn S, Joeris A, Cunningham M (2018) Optimizing intraoperative imaging during proximal femoral fracture fixation—a performance improvement program for surgeons. Injury 104:19–19

    Google Scholar 

  20. 20.

    Rodas N, Bert J, Visvikis D, de Mathelin M, Padoy N (2017) Pose optimization of a C-arm imaging device to reduce intraoperative radiation exposure of staff and patient during interventional procedures. In: International conference on robotics and automation. IEEE, pp 4200–4207

  21. 21.

    Unberath M, Zaech J, Lee S, Bier B, Fotouhi J, Armand M, Navab N (2018) Deepdrr—a catalyst for machine learning in fluoroscopy-guided procedures. In: Medical image computing and computer-assisted intervention. Springer, pp 98–106

  22. 22.

    Wang L, Fallavollita P, Zou R, Chen X, Weidert S, Navab N (2012) Closed-form inverse kinematics for interventional C-arm X-ray imaging with six degrees of freedom: modeling and application. Trans Med Imag 31(5):1086–1099

    Article  Google Scholar 

Download references


We thank Mathias Unberath and Cong Gao for their insights into DeepDRR. Moreover, we thank Rimasys for facilitating the validation on cadaver data. This work was partially funded by Siemens Healthcare GmbH, Erlangen, Germany.

Author information



Corresponding author

Correspondence to Lisa Kausch.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

The data were obtained retrospectively from anonymized databases and not generated intentionally for the study. For this type of study, formal consent is not required.

Informed consent

The acquisition of data from living patients had a medical indication, and informed consent was not required. The acquired datasets of cadavers were available retrospectively after they had been generated during surgical courses for physicians. The corresponding consent for body donation for these purposes has been obtained.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kausch, L., Thomas, S., Kunze, H. et al. Toward automatic C-arm positioning for standard projections in orthopedic surgery. Int J CARS 15, 1095–1105 (2020).

Download citation


  • Pose estimation
  • Fluoroscopic imaging
  • C-arm positioning
  • Standard projection