Respiratory Motion Compensation with Relevance Vector Machines

Robert Dürichen; Tobias Wissel; Floris Ernst; Achim Schweikard

doi:10.1007/978-3-642-40763-5_14

Respiratory Motion Compensation with Relevance Vector Machines

Robert Dürichen, Tobias Wissel, Floris Ernst, Achim Schweikard

Institute of Robotics and Cognitive Systems

Abstract

In modern robotic radiation therapy, tumor movements due to respiration can be compensated. The accuracy of these methods can be increased by time series prediction of external optical surrogates. An algorithm based on relevance vector machines (RVM) is introduced. We evaluate RVM with linear and nonlinear basis functions on a real patient data set containing 304 motion traces and compare it with a wavelet based least mean square algorithm (wLMS), the best algorithm for this data set so far. Linear RVM outperforms wLMS significantly and increases the prediction accuracy for 80.3 % of the data. We show that real time prediction is possible in case of linear RVM and discuss how the predicted variance can be used to construct promising hybrid algorithms, which further reduce the prediction error.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013
Editors	Kensaku Mori, Ichiro Sakuma, Yoshinobu Sato, Christian Barillot, Nassir Navab
Number of pages	8
Volume	8150
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.09.2013
Pages	108-115
ISBN (Print)	978-3-642-40762-8
ISBN (Electronic)	978-3-642-40763-5
DOIs	https://doi.org/10.1007/978-3-642-40763-5_14
Publication status	Published - 01.09.2013
Event	Workshop on Breast Image Analysis - In conjunction with the 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013) - Toyoda Auditrium, Nagoya University, Nagoya, Japan Duration: 22.09.2013 → 26.09.2013 http://www.miccai2013.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-40763-5_14

Cite this

Dürichen, R., Wissel, T., Ernst, F., & Schweikard, A. (2013). Respiratory Motion Compensation with Relevance Vector Machines. In K. Mori, I. Sakuma, Y. Sato, C. Barillot, & N. Navab (Eds.), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013 (Vol. 8150, pp. 108-115). ( Lecture Notes in Computer Science; Vol. 8150). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-40763-5_14

Dürichen, Robert ; Wissel, Tobias ; Ernst, Floris et al. / Respiratory Motion Compensation with Relevance Vector Machines. Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013. editor / Kensaku Mori ; Ichiro Sakuma ; Yoshinobu Sato ; Christian Barillot ; Nassir Navab. Vol. 8150 Berlin, Heidelberg : Springer Berlin Heidelberg, 2013. pp. 108-115 ( Lecture Notes in Computer Science).

@inproceedings{4f78c03a8fbe402c9057993a2ab45ec2,

title = "Respiratory Motion Compensation with Relevance Vector Machines",

abstract = "In modern robotic radiation therapy, tumor movements due to respiration can be compensated. The accuracy of these methods can be increased by time series prediction of external optical surrogates. An algorithm based on relevance vector machines (RVM) is introduced. We evaluate RVM with linear and nonlinear basis functions on a real patient data set containing 304 motion traces and compare it with a wavelet based least mean square algorithm (wLMS), the best algorithm for this data set so far. Linear RVM outperforms wLMS significantly and increases the prediction accuracy for 80.3 % of the data. We show that real time prediction is possible in case of linear RVM and discuss how the predicted variance can be used to construct promising hybrid algorithms, which further reduce the prediction error.",

author = "Robert D{\"u}richen and Tobias Wissel and Floris Ernst and Achim Schweikard",

year = "2013",

month = sep,

day = "1",

doi = "10.1007/978-3-642-40763-5_14",

language = "English",

isbn = "978-3-642-40762-8",

volume = "8150",

series = " Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "108--115",

editor = "Kensaku Mori and Ichiro Sakuma and Yoshinobu Sato and Christian Barillot and Nassir Navab",

booktitle = "Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013",

note = "Workshop on Breast Image Analysis - In conjunction with the 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013)<br/> ; Conference date: 22-09-2013 Through 26-09-2013",

url = "http://www.miccai2013.org/",

}

Dürichen, R, Wissel, T, Ernst, F & Schweikard, A 2013, Respiratory Motion Compensation with Relevance Vector Machines. in K Mori, I Sakuma, Y Sato, C Barillot & N Navab (eds), Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013. vol. 8150, Lecture Notes in Computer Science, vol. 8150, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 108-115, Workshop on Breast Image Analysis - In conjunction with the 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013)
, Nagoya, Japan, 22.09.13. https://doi.org/10.1007/978-3-642-40763-5_14

Respiratory Motion Compensation with Relevance Vector Machines. / Dürichen, Robert; Wissel, Tobias; Ernst, Floris et al.
Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013. ed. / Kensaku Mori; Ichiro Sakuma; Yoshinobu Sato; Christian Barillot; Nassir Navab. Vol. 8150 Berlin, Heidelberg: Springer Berlin Heidelberg, 2013. p. 108-115 ( Lecture Notes in Computer Science; Vol. 8150).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Respiratory Motion Compensation with Relevance Vector Machines

AU - Dürichen, Robert

AU - Wissel, Tobias

AU - Ernst, Floris

AU - Schweikard, Achim

PY - 2013/9/1

Y1 - 2013/9/1

N2 - In modern robotic radiation therapy, tumor movements due to respiration can be compensated. The accuracy of these methods can be increased by time series prediction of external optical surrogates. An algorithm based on relevance vector machines (RVM) is introduced. We evaluate RVM with linear and nonlinear basis functions on a real patient data set containing 304 motion traces and compare it with a wavelet based least mean square algorithm (wLMS), the best algorithm for this data set so far. Linear RVM outperforms wLMS significantly and increases the prediction accuracy for 80.3 % of the data. We show that real time prediction is possible in case of linear RVM and discuss how the predicted variance can be used to construct promising hybrid algorithms, which further reduce the prediction error.

AB - In modern robotic radiation therapy, tumor movements due to respiration can be compensated. The accuracy of these methods can be increased by time series prediction of external optical surrogates. An algorithm based on relevance vector machines (RVM) is introduced. We evaluate RVM with linear and nonlinear basis functions on a real patient data set containing 304 motion traces and compare it with a wavelet based least mean square algorithm (wLMS), the best algorithm for this data set so far. Linear RVM outperforms wLMS significantly and increases the prediction accuracy for 80.3 % of the data. We show that real time prediction is possible in case of linear RVM and discuss how the predicted variance can be used to construct promising hybrid algorithms, which further reduce the prediction error.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-84885914893&origin=inward&txGid=2dcb6a443a33f44b3a8a8824cc842a38

U2 - 10.1007/978-3-642-40763-5_14

DO - 10.1007/978-3-642-40763-5_14

M3 - Conference contribution

SN - 978-3-642-40762-8

VL - 8150

T3 - Lecture Notes in Computer Science

SP - 108

EP - 115

BT - Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013

A2 - Mori, Kensaku

A2 - Sakuma, Ichiro

A2 - Sato, Yoshinobu

A2 - Barillot, Christian

A2 - Navab, Nassir

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - Workshop on Breast Image Analysis - In conjunction with the 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013)<br/>

Y2 - 22 September 2013 through 26 September 2013

ER -

Dürichen R, Wissel T, Ernst F , Schweikard A. Respiratory Motion Compensation with Relevance Vector Machines. In Mori K, Sakuma I, Sato Y, Barillot C, Navab N, editors, Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2013. Vol. 8150. Berlin, Heidelberg: Springer Berlin Heidelberg. 2013. p. 108-115. ( Lecture Notes in Computer Science). doi: 10.1007/978-3-642-40763-5_14

Respiratory Motion Compensation with Relevance Vector Machines

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this