Non-rigid registration guided by landmarks and learning
Eckl J, Daum V, Hornegger J, Pohl KM (2012)
Publication Type: Conference contribution, Conference Contribution
Publication year: 2012
Journal
Original Authors: Eckl J., Daum V., Hornegger J., Pohl K.
Book Volume: null
Pages Range: 704-707
Event location: Barcelona
Journal Issue: null
DOI: 10.1109/ISBI.2012.6235645
Abstract
Registration methods frequently rely on prior information in order to generate anatomical meaningful transformations between medical scans. In this paper, we propose a novel intensity based non-rigid registration framework, which is guided by landmarks and a regularizer based on Principle Component Analysis (PCA). Unlike existing methods in this domain, the computational complexity of our approach reduces with the number of landmarks. Furthermore, our PCA is invariant to translations. The additional regularizer is based on the outcome of this PCA. We register a skull CT scan to MR scans aquired by a MR/PET hybrid scanner. This aligned CT scan can then be used to gain an attenuation map for PET reconstruction. As a result we have a Dice coefficient for bone areas at 0.71 and a Dice coefficient for bone and soft issue areas at 0.97. © 2012 IEEE.
Authors with CRIS profile
Jutta Eckl
Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung)
Volker Daum
Graduiertenzentrum der FAU
Joachim Hornegger
Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung)
Involved external institutions
United States (USA) (US)How to cite
APA:
Eckl, J., Daum, V., Hornegger, J., & Pohl, K.M. (2012). Non-rigid registration guided by landmarks and learning. In Proceedings of the 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 (pp. 704-707). Barcelona.
MLA:
Eckl, Jutta, et al. "Non-rigid registration guided by landmarks and learning." Proceedings of the 2012 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012, Barcelona 2012. 704-707.
BibTeX: Download