A Kernel Ridge Regression Model for Respiratory Motion Estimation in Radiotherapy

Geimer T, Birlutiu A, Unberath M, Taubmann O, Bert C, Maier A (2017)

Publication Language: German

Publication Type: Conference contribution

Publication year: 2017

Journal

Publisher: Springer

Edited Volumes: Informatik aktuell

City/Town: Heidelberg, Berlin

Pages Range: 155-160

Conference Proceedings Title: Bildverarbeitung für die Medizin 2017 - Algorithmen - Systeme - Anwendungen

Event location: Heidelberg

ISBN: 978-3-662-54344-3

URI: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Geimer17-AKR.pdf

DOI: 10.1007/978-3-662-54345-0_38

Abstract

This paper discusses a kernel ridge regression (KRR) model for motion estimation in radiotherapy. Using KRR, dense internal motion fields are estimated from high-dimensional surrogates without the need for prior dimensionality reduction. We compare the proposed model to a related approach with dimensionality reduction in the form of principal component analysis and principle component regression. Evaluation was performed in a simulation study based on nine 4D CT patient data sets achieving a mean estimation error of 0.84 ± 0.21 mm for our approach.

Authors with CRIS profile

Additional Organisation(s)

How to cite

APA:

Geimer, T., Birlutiu, A., Unberath, M., Taubmann, O., Bert, C., & Maier, A. (2017). A Kernel Ridge Regression Model for Respiratory Motion Estimation in Radiotherapy. In Maier-Hein K H, Deserno Th, Handels H, Tolxdorff Th (Hrg.), Bildverarbeitung für die Medizin 2017 - Algorithmen - Systeme - Anwendungen (S. 155-160). Heidelberg, DE: Heidelberg, Berlin: Springer.

MLA:

Geimer, Tobias, et al. "A Kernel Ridge Regression Model for Respiratory Motion Estimation in Radiotherapy." Tagungsband Bildverarbeitung für die Medizin 2017, Heidelberg Hrg. Maier-Hein K H, Deserno Th, Handels H, Tolxdorff Th, Heidelberg, Berlin: Springer, 2017. 155-160.

BibTeX: Download