Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression

Floris Ernst; Alexander Schlaefer; Achim Schweikard

doi:10.1007/978-3-540-75759-7_81

Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression

Floris Ernst, Alexander Schlaefer, Achim Schweikard

Institute of Robotics and Cognitive Systems

48 Citations (Scopus)

Abstract

In robotic radiosurgery, a photon beam source, moved by a robot arm, is used to ablate tumors. The accuracy of the treatment can be improved by predicting respiratory motion to compensate for system delay. We consider a wavelet-based multiscale autoregressive prediction method. The algorithm is extended by introducing a new exponential averaging parameter and the use of the Moore-Penrose pseudo inverse to cope with long-term signal dependencies and system matrix irregularity, respectively. In test cases, this new algorithm outperforms normalized LMS predictors by as much as 50%. With real patient data, we achieve an improvement of around 5 to 10%.

Original language	English
Title of host publication	MICCAI 2007: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007
Number of pages	8
Volume	4792
Publisher	Springer Verlag
Publication date	01.12.2007
Pages	668-675
ISBN (Print)	978-3-540-75758-0
ISBN (Electronic)	978-3-540-75759-7
DOIs	https://doi.org/10.1007/978-3-540-75759-7_81
Publication status	Published - 01.12.2007
Event	10th International Conference on Medical Imaging and Computer-Assisted Intervention - Brisbane, Australia Duration: 29.10.2007 → 02.11.2007 Conference number: 71013

UN SDGs

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

Access to Document

10.1007/978-3-540-75759-7_81

Cite this

@inproceedings{f40e4e878964496d8dfb4f0be25347f1,

title = "Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression",

abstract = "In robotic radiosurgery, a photon beam source, moved by a robot arm, is used to ablate tumors. The accuracy of the treatment can be improved by predicting respiratory motion to compensate for system delay. We consider a wavelet-based multiscale autoregressive prediction method. The algorithm is extended by introducing a new exponential averaging parameter and the use of the Moore-Penrose pseudo inverse to cope with long-term signal dependencies and system matrix irregularity, respectively. In test cases, this new algorithm outperforms normalized LMS predictors by as much as 50\%. With real patient data, we achieve an improvement of around 5 to 10\%.",

author = "Floris Ernst and Alexander Schlaefer and Achim Schweikard",

year = "2007",

month = dec,

day = "1",

doi = "10.1007/978-3-540-75759-7\_81",

language = "English",

isbn = "978-3-540-75758-0",

volume = "4792",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "668--675",

booktitle = "MICCAI 2007: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007",

note = "10th International Conference on Medical Imaging and Computer-Assisted Intervention , MICCAI 2007 ; Conference date: 29-10-2007 Through 02-11-2007",

}

Ernst, F, Schlaefer, A & Schweikard, A 2007, Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression. in MICCAI 2007: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007. vol. 4792, Lecture Notes in Computer Science, vol. 4792, Springer Verlag, pp. 668-675, 10th International Conference on Medical Imaging and Computer-Assisted Intervention , Brisbane, Queensland, Australia, 29.10.07. https://doi.org/10.1007/978-3-540-75759-7_81

Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression. / Ernst, Floris; Schlaefer, Alexander; Schweikard, Achim.
MICCAI 2007: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007. Vol. 4792 Springer Verlag, 2007. p. 668-675 (Lecture Notes in Computer Science; Vol. 4792).

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

TY - GEN

T1 - Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression

AU - Ernst, Floris

AU - Schlaefer, Alexander

AU - Schweikard, Achim

N1 - Conference code: 71013

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In robotic radiosurgery, a photon beam source, moved by a robot arm, is used to ablate tumors. The accuracy of the treatment can be improved by predicting respiratory motion to compensate for system delay. We consider a wavelet-based multiscale autoregressive prediction method. The algorithm is extended by introducing a new exponential averaging parameter and the use of the Moore-Penrose pseudo inverse to cope with long-term signal dependencies and system matrix irregularity, respectively. In test cases, this new algorithm outperforms normalized LMS predictors by as much as 50%. With real patient data, we achieve an improvement of around 5 to 10%.

AB - In robotic radiosurgery, a photon beam source, moved by a robot arm, is used to ablate tumors. The accuracy of the treatment can be improved by predicting respiratory motion to compensate for system delay. We consider a wavelet-based multiscale autoregressive prediction method. The algorithm is extended by introducing a new exponential averaging parameter and the use of the Moore-Penrose pseudo inverse to cope with long-term signal dependencies and system matrix irregularity, respectively. In test cases, this new algorithm outperforms normalized LMS predictors by as much as 50%. With real patient data, we achieve an improvement of around 5 to 10%.

UR - https://www.scopus.com/pages/publications/79551681344

U2 - 10.1007/978-3-540-75759-7_81

DO - 10.1007/978-3-540-75759-7_81

M3 - Conference contribution

SN - 978-3-540-75758-0

VL - 4792

T3 - Lecture Notes in Computer Science

SP - 668

EP - 675

BT - MICCAI 2007: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007

PB - Springer Verlag

T2 - 10th International Conference on Medical Imaging and Computer-Assisted Intervention

Y2 - 29 October 2007 through 2 November 2007

ER -

Prediction of Respiratory Motion with Wavelet-based Multiscale Autoregression

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this