Learning-Based Correspondence Estimation for 2-D/3-D Registration

  • Roman SchaffertEmail author
  • Markus Weiß
  • Jian Wang
  • Anja Borsdorf
  • Andreas Maier
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


In many minimally invasive procedures, image guidance using a C-arm system is utilized. To enhance the guidance, information from pre-operative 3-D images can be overlaid on top of the 2-D fluoroscopy and 2-D/3-D image registration techniques are used to ensure an accurate overlay. Despite decades of research, achieving a highly reliable registration remains challenging. In this paper, we propose a learning-based correspondence estimation, which focuses on contour points and can be used in combination with the point-to-plane correspondence model-based registration. When combined with classical correspondence estimation in a refinement step, the method highly increases the robustness, leading to a capture range of 36mm and a success rate of 98.5%, compared to 14mm and 71.9% for the purely classical approach, while maintaining a high accuracy of 0.430.08mm of mean re-projection distance.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Markelj P, Tomaževič D, Likar B, et al. A review of 3D/2D registration methods for image-guided interventions. Med Image Anal. 2010;16(3):642–661.Google Scholar
  2. 2.
    Maier A, Syben C, Lasser T, et al. A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik. 2019;29(2):86–101.Google Scholar
  3. 3.
    Miao S, Piat S, Fischer P, et al. Dilated FCN for multi-agent 2D/3D medical image registration. In: AAAI; 2018. p. 4694–4701.Google Scholar
  4. 4.
    Liao H, Lin WA, Zhang J, et al. Multiview 2D/3D rigid registration via a pointof-interest network for tracking and triangulation (POINT2). arXiv:190303896v3;.
  5. 5.
    Wang J, Schaffert R, Borsdorf A, et al. Dynamic 2-D/3-D rigid registration framework using point-to-plane correspondence model. IEEE Trans Med Imaging. 2017;36(9):1939–1954.Google Scholar
  6. 6.
    Schaffert R, Wang J, Fischer P, et al. Metric-Driven learning of correspondence weighting for 2-D/3-D image registration. In: GCPR; 2018. p. 140–152.Google Scholar
  7. 7.
    Wang J. Robust 2-D/3D registration for real-time patient motion compensation. FAU Erlangen-Nürnberg; to appear 2020.Google Scholar
  8. 8.
    Dosovitskiy A, Fischer P, Ilg E, et al. Flownet: learning optical flow with convolutional networks. In: IEEE ICCV; 2015. p. 2758–2766.Google Scholar
  9. 9.
    van de Kraats EB, Penney GP, Tomaževič D, et al. Standardized evaluation methodology for 2-D-3-D registration. IEEE Trans Med Imaging. 2005;24(9).Google Scholar
  10. 10.
    Mitrovič U, Špiclin Ž, Likar B, et al. 3D-2D registration of cerebral angiograms: a method and evaluation on clinical images. IEEE Trans Med Imaging. 2013;32(8):1550–1563.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  • Roman Schaffert
    • 1
    Email author
  • Markus Weiß
    • 1
  • Jian Wang
    • 2
  • Anja Borsdorf
    • 2
  • Andreas Maier
    • 1
    • 3
  1. 1.Pattern Recognition LabFriedrich-Alexander UniversityErlangenDeutschland
  2. 2.Siemens Healthineers AGForchheimDeutschland
  3. 3.Erlangen Graduate School in Advanced Optical Technologies (SAOT)ErlangenDeutschland

Personalised recommendations