Comparative performance of linear and nonlinear neural networks to predict irregular breathing

Martin J. Murphy, Sonja Dieterich

Research output: Contribution to journalArticle

97 Citations (Scopus)

Abstract

Breathing adaptation during external-beam radiotherapy is a matter of great concern because uncompensated tumour motion requires extended treatment margins that endanger sensitive tissue. Compensation strategies include beam gating, collimator tracking and robotic beam re-alignment. All of these schemes have a system latency of up to several hundred milliseconds, which calls in turn for predictive control loops. Irregularities in breathing make prediction difficult. We have evaluated the performance of two classes of control loop algorithms - the linear adaptive filter and the adaptive nonlinear neural network - for highly irregular patient breathing behaviours. The neural network demonstrated robust adaptability to all of the observed breathing patterns while the linear filter failed in a significant percentage of cases. For those cases where the linear filter could function, it made less accurate predictions than the neural network. Because the neural network presents no additional computational burden in the control loop we conclude that it is the preferred choice among heuristic predictive algorithms.

Original languageEnglish (US)
Article number012
Pages (from-to)5903-5914
Number of pages12
JournalPhysics in Medicine and Biology
Volume51
Issue number22
DOIs
StatePublished - Nov 21 2006
Externally publishedYes

Fingerprint

breathing
Respiration
Neural networks
linear filters
adaptive filters
Radiotherapy
Adaptive filters
Robotics
collimators
predictions
robotics
irregularities
Tumors
radiation therapy
margins
tumors
alignment
Tissue
Neoplasms
Therapeutics

ASJC Scopus subject areas

  • Biomedical Engineering
  • Physics and Astronomy (miscellaneous)
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology

Cite this

Comparative performance of linear and nonlinear neural networks to predict irregular breathing. / Murphy, Martin J.; Dieterich, Sonja.

In: Physics in Medicine and Biology, Vol. 51, No. 22, 012, 21.11.2006, p. 5903-5914.

Research output: Contribution to journalArticle

@article{8728f8355af44726beabd086539c851b,
title = "Comparative performance of linear and nonlinear neural networks to predict irregular breathing",
abstract = "Breathing adaptation during external-beam radiotherapy is a matter of great concern because uncompensated tumour motion requires extended treatment margins that endanger sensitive tissue. Compensation strategies include beam gating, collimator tracking and robotic beam re-alignment. All of these schemes have a system latency of up to several hundred milliseconds, which calls in turn for predictive control loops. Irregularities in breathing make prediction difficult. We have evaluated the performance of two classes of control loop algorithms - the linear adaptive filter and the adaptive nonlinear neural network - for highly irregular patient breathing behaviours. The neural network demonstrated robust adaptability to all of the observed breathing patterns while the linear filter failed in a significant percentage of cases. For those cases where the linear filter could function, it made less accurate predictions than the neural network. Because the neural network presents no additional computational burden in the control loop we conclude that it is the preferred choice among heuristic predictive algorithms.",
author = "Murphy, {Martin J.} and Sonja Dieterich",
year = "2006",
month = "11",
day = "21",
doi = "10.1088/0031-9155/51/22/012",
language = "English (US)",
volume = "51",
pages = "5903--5914",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "22",

}

TY - JOUR

T1 - Comparative performance of linear and nonlinear neural networks to predict irregular breathing

AU - Murphy, Martin J.

AU - Dieterich, Sonja

PY - 2006/11/21

Y1 - 2006/11/21

N2 - Breathing adaptation during external-beam radiotherapy is a matter of great concern because uncompensated tumour motion requires extended treatment margins that endanger sensitive tissue. Compensation strategies include beam gating, collimator tracking and robotic beam re-alignment. All of these schemes have a system latency of up to several hundred milliseconds, which calls in turn for predictive control loops. Irregularities in breathing make prediction difficult. We have evaluated the performance of two classes of control loop algorithms - the linear adaptive filter and the adaptive nonlinear neural network - for highly irregular patient breathing behaviours. The neural network demonstrated robust adaptability to all of the observed breathing patterns while the linear filter failed in a significant percentage of cases. For those cases where the linear filter could function, it made less accurate predictions than the neural network. Because the neural network presents no additional computational burden in the control loop we conclude that it is the preferred choice among heuristic predictive algorithms.

AB - Breathing adaptation during external-beam radiotherapy is a matter of great concern because uncompensated tumour motion requires extended treatment margins that endanger sensitive tissue. Compensation strategies include beam gating, collimator tracking and robotic beam re-alignment. All of these schemes have a system latency of up to several hundred milliseconds, which calls in turn for predictive control loops. Irregularities in breathing make prediction difficult. We have evaluated the performance of two classes of control loop algorithms - the linear adaptive filter and the adaptive nonlinear neural network - for highly irregular patient breathing behaviours. The neural network demonstrated robust adaptability to all of the observed breathing patterns while the linear filter failed in a significant percentage of cases. For those cases where the linear filter could function, it made less accurate predictions than the neural network. Because the neural network presents no additional computational burden in the control loop we conclude that it is the preferred choice among heuristic predictive algorithms.

UR - http://www.scopus.com/inward/record.url?scp=33846853755&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846853755&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/51/22/012

DO - 10.1088/0031-9155/51/22/012

M3 - Article

VL - 51

SP - 5903

EP - 5914

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 22

M1 - 012

ER -