Mitigating errors in external respiratory surrogate-based models of tumor position

Kathleen T. Malinowski, Thomas J. McAvoy, Rohini George, Sonja Dieterich, Warren D. D'Souza

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precision in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16% for partial-least-squares and 57% for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.

Original languageEnglish (US)
JournalInternational Journal of Radiation Oncology Biology Physics
Volume82
Issue number5
DOIs
StatePublished - Apr 1 2012
Externally publishedYes

Fingerprint

tumors
Least-Squares Analysis
Neoplasms
markers
Tumor Biomarkers
Noise
regression analysis
education
predictions
files
time measurement

Keywords

  • Intrafraction motion
  • Partial-least-squares regression
  • Tumor tracking
  • Tumor-surrogate predictive models
  • Tumor-surrogate relationship

ASJC Scopus subject areas

  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Radiation
  • Cancer Research

Cite this

Mitigating errors in external respiratory surrogate-based models of tumor position. / Malinowski, Kathleen T.; McAvoy, Thomas J.; George, Rohini; Dieterich, Sonja; D'Souza, Warren D.

In: International Journal of Radiation Oncology Biology Physics, Vol. 82, No. 5, 01.04.2012.

Research output: Contribution to journalArticle

Malinowski, Kathleen T. ; McAvoy, Thomas J. ; George, Rohini ; Dieterich, Sonja ; D'Souza, Warren D. / Mitigating errors in external respiratory surrogate-based models of tumor position. In: International Journal of Radiation Oncology Biology Physics. 2012 ; Vol. 82, No. 5.
@article{1ae5f342876d4958b1c097c11e5841a9,
title = "Mitigating errors in external respiratory surrogate-based models of tumor position",
abstract = "Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precision in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16{\%} for partial-least-squares and 57{\%} for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.",
keywords = "Intrafraction motion, Partial-least-squares regression, Tumor tracking, Tumor-surrogate predictive models, Tumor-surrogate relationship",
author = "Malinowski, {Kathleen T.} and McAvoy, {Thomas J.} and Rohini George and Sonja Dieterich and D'Souza, {Warren D.}",
year = "2012",
month = "4",
day = "1",
doi = "10.1016/j.ijrobp.2011.05.042",
language = "English (US)",
volume = "82",
journal = "International Journal of Radiation Oncology Biology Physics",
issn = "0360-3016",
publisher = "Elsevier Inc.",
number = "5",

}

TY - JOUR

T1 - Mitigating errors in external respiratory surrogate-based models of tumor position

AU - Malinowski, Kathleen T.

AU - McAvoy, Thomas J.

AU - George, Rohini

AU - Dieterich, Sonja

AU - D'Souza, Warren D.

PY - 2012/4/1

Y1 - 2012/4/1

N2 - Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precision in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16% for partial-least-squares and 57% for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.

AB - Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precision in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16% for partial-least-squares and 57% for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.

KW - Intrafraction motion

KW - Partial-least-squares regression

KW - Tumor tracking

KW - Tumor-surrogate predictive models

KW - Tumor-surrogate relationship

UR - http://www.scopus.com/inward/record.url?scp=84858661658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858661658&partnerID=8YFLogxK

U2 - 10.1016/j.ijrobp.2011.05.042

DO - 10.1016/j.ijrobp.2011.05.042

M3 - Article

C2 - 22429333

AN - SCOPUS:84858661658

VL - 82

JO - International Journal of Radiation Oncology Biology Physics

JF - International Journal of Radiation Oncology Biology Physics

SN - 0360-3016

IS - 5

ER -