Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction

Ivan Buzurovic, Ke Huang, Tarun K. Podder, Yan Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The prediction of respiration-induced organ motion is crucial in some applications such as dynamic delivery of radiation dose. In this paper, we have proposed the novel approach to construct an acceleration-enhanced (AE) filter that is comprised of two independent adaptive channels. The filters use the adapted position and adapted acceleration, together with a weight factor to provide prediction for respiratory motion. The proposed AE approach is universal and can be applied to the different filters. The performances of the adaptive normalized least mean square (nLMS) filter, the artificial neural network (ANN) filter, and their AE counterparts were compared for respiratory motion prediction during normal and irregular respiration. The results revealed that the adaptive ANN and nLMS filters were successful to perform predictions for normal and irregular respiration, respectively. AE filters showed more accurate prediction than their conventional counterparts. Implementing the AE approach, it was observed that the AE-ANN filter had the best performance in the prediction of normal respiratory motion, whereas the AE-nLMS filter excelled in the prediction of irregular respiratory motion.

Original languageEnglish (US)
Title of host publication11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings
Pages181-184
Number of pages4
DOIs
StatePublished - Dec 1 2012
Event2012 9th International Conference on High Capacity Optical Networks and Enabling Technologies, HONET 2012 - Istanbul, Turkey
Duration: Dec 14 2012Dec 14 2012

Publication series

Name11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings

Other

Other2012 9th International Conference on High Capacity Optical Networks and Enabling Technologies, HONET 2012
CountryTurkey
CityIstanbul
Period12/14/1212/14/12

Fingerprint

Adaptive filters
neural network
Neural networks
Dosimetry
performance

Keywords

  • Adaptive filters
  • neural network filters
  • prediction algorithms

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Communication

Cite this

Buzurovic, I., Huang, K., Podder, T. K., & Yu, Y. (2012). Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction. In 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings (pp. 181-184). [6420003] (11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings). https://doi.org/10.1109/NEUREL.2012.6420003

Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction. / Buzurovic, Ivan; Huang, Ke; Podder, Tarun K.; Yu, Yan.

11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings. 2012. p. 181-184 6420003 (11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Buzurovic, I, Huang, K, Podder, TK & Yu, Y 2012, Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction. in 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings., 6420003, 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings, pp. 181-184, 2012 9th International Conference on High Capacity Optical Networks and Enabling Technologies, HONET 2012, Istanbul, Turkey, 12/14/12. https://doi.org/10.1109/NEUREL.2012.6420003
Buzurovic I, Huang K, Podder TK, Yu Y. Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction. In 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings. 2012. p. 181-184. 6420003. (11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings). https://doi.org/10.1109/NEUREL.2012.6420003
Buzurovic, Ivan ; Huang, Ke ; Podder, Tarun K. ; Yu, Yan. / Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction. 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings. 2012. pp. 181-184 (11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings).
@inproceedings{5d011cedb3ca4cca9e3ed3232ecb1da7,
title = "Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction",
abstract = "The prediction of respiration-induced organ motion is crucial in some applications such as dynamic delivery of radiation dose. In this paper, we have proposed the novel approach to construct an acceleration-enhanced (AE) filter that is comprised of two independent adaptive channels. The filters use the adapted position and adapted acceleration, together with a weight factor to provide prediction for respiratory motion. The proposed AE approach is universal and can be applied to the different filters. The performances of the adaptive normalized least mean square (nLMS) filter, the artificial neural network (ANN) filter, and their AE counterparts were compared for respiratory motion prediction during normal and irregular respiration. The results revealed that the adaptive ANN and nLMS filters were successful to perform predictions for normal and irregular respiration, respectively. AE filters showed more accurate prediction than their conventional counterparts. Implementing the AE approach, it was observed that the AE-ANN filter had the best performance in the prediction of normal respiratory motion, whereas the AE-nLMS filter excelled in the prediction of irregular respiratory motion.",
keywords = "Adaptive filters, neural network filters, prediction algorithms",
author = "Ivan Buzurovic and Ke Huang and Podder, {Tarun K.} and Yan Yu",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/NEUREL.2012.6420003",
language = "English (US)",
isbn = "9781467315722",
series = "11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings",
pages = "181--184",
booktitle = "11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings",

}

TY - GEN

T1 - Comparison between acceleration-enhanced adaptive filters and neural network filters for respiratory motion prediction

AU - Buzurovic, Ivan

AU - Huang, Ke

AU - Podder, Tarun K.

AU - Yu, Yan

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The prediction of respiration-induced organ motion is crucial in some applications such as dynamic delivery of radiation dose. In this paper, we have proposed the novel approach to construct an acceleration-enhanced (AE) filter that is comprised of two independent adaptive channels. The filters use the adapted position and adapted acceleration, together with a weight factor to provide prediction for respiratory motion. The proposed AE approach is universal and can be applied to the different filters. The performances of the adaptive normalized least mean square (nLMS) filter, the artificial neural network (ANN) filter, and their AE counterparts were compared for respiratory motion prediction during normal and irregular respiration. The results revealed that the adaptive ANN and nLMS filters were successful to perform predictions for normal and irregular respiration, respectively. AE filters showed more accurate prediction than their conventional counterparts. Implementing the AE approach, it was observed that the AE-ANN filter had the best performance in the prediction of normal respiratory motion, whereas the AE-nLMS filter excelled in the prediction of irregular respiratory motion.

AB - The prediction of respiration-induced organ motion is crucial in some applications such as dynamic delivery of radiation dose. In this paper, we have proposed the novel approach to construct an acceleration-enhanced (AE) filter that is comprised of two independent adaptive channels. The filters use the adapted position and adapted acceleration, together with a weight factor to provide prediction for respiratory motion. The proposed AE approach is universal and can be applied to the different filters. The performances of the adaptive normalized least mean square (nLMS) filter, the artificial neural network (ANN) filter, and their AE counterparts were compared for respiratory motion prediction during normal and irregular respiration. The results revealed that the adaptive ANN and nLMS filters were successful to perform predictions for normal and irregular respiration, respectively. AE filters showed more accurate prediction than their conventional counterparts. Implementing the AE approach, it was observed that the AE-ANN filter had the best performance in the prediction of normal respiratory motion, whereas the AE-nLMS filter excelled in the prediction of irregular respiratory motion.

KW - Adaptive filters

KW - neural network filters

KW - prediction algorithms

UR - http://www.scopus.com/inward/record.url?scp=84874362150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874362150&partnerID=8YFLogxK

U2 - 10.1109/NEUREL.2012.6420003

DO - 10.1109/NEUREL.2012.6420003

M3 - Conference contribution

AN - SCOPUS:84874362150

SN - 9781467315722

T3 - 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings

SP - 181

EP - 184

BT - 11th Symposium on Neural Network Applications in Electrical Engineering,NEUREL 2012 - Proceedings

ER -