Schaffert R, Weiß M, Wang J, Borsdorf A, Maier A (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Springer
Pages Range: 222-228
Conference Proceedings Title: Informatik aktuell
Event location: Berlin, DEU
ISBN: 9783658292669
DOI: 10.1007/978-3-658-29267-6_50
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.
APA:
Schaffert, R., Weiß, M., Wang, J., Borsdorf, A., & Maier, A. (2020). Learning-based correspondence estimation for 2-D/3-D registration. In Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm (Eds.), Informatik aktuell (pp. 222-228). Berlin, DEU: Springer.
MLA:
Schaffert, Roman, et al. "Learning-based correspondence estimation for 2-D/3-D registration." Proceedings of the International workshop on Algorithmen - Systeme - Anwendungen, 2020, Berlin, DEU Ed. Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm, Springer, 2020. 222-228.
BibTeX: Download