TH‐C‐BRA‐09: Robust 3D Lung Tumor Tracking Using Maximum Likelihood Estimation

X. Wang, V. Kearney, H. Yan, X. Jia, L. Cervino, S. Jiang

Research output: Contribution to journalArticle

Abstract

Purpose: To develop a robust 3D lung tumor tracking method based on a single x‐ray projection using maximum likelihood estimation. Methods: 4DCT images at different phases are registered to yield motion vector fields and a PCA based lung motion model is built. An acquired CBCT projection is compared with the simulated projections under different metrics to yield the correct PCA coefficients and hence the corresponding motion vector fields, which can be used to derive the 3D tumor location at this projection. The metrics we considered include normalized cross correlation and normalized mutual information between the gradient images of the acquired CBCT and that of the simulated 4DCT projection, and the position of diaphragm. A maximum likelihood estimation method is developed to combine the tracking results from all the metrics and integrate the constraints regarding tumor motion smoothness and wave form, leading to robust tumor locations. The method is tested on real patient data. Results: It is found that normalized cross correlation, normalized mutual information, and diaphragm location can be used to determine the PCA coefficients and the tumor position, although the efficacy of any single metric depends on the gantry angles and breathing phases. However, with the combination of different metrics, the tumor tracking accuracy is greatly improved. The resulting mean 3D error is found to be 1.3mm. Conclusions: A robust 3D tumor tracking method is developed based on maximum likelihood estimation to derive tumor location corresponding to an x‐ray projection for lung cancer patient. This work is supported by Varian Medical Systems through a Master Research Agreement.

Original languageEnglish (US)
Pages (from-to)4001
Number of pages1
JournalMedical Physics
Volume39
Issue number6
DOIs
StatePublished - 2012

Fingerprint

Lung
Passive Cutaneous Anaphylaxis
Neoplasms
Diaphragm
X-Rays
Lung Neoplasms
Respiration
Research

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

TH‐C‐BRA‐09 : Robust 3D Lung Tumor Tracking Using Maximum Likelihood Estimation. / Wang, X.; Kearney, V.; Yan, H.; Jia, X.; Cervino, L.; Jiang, S.

In: Medical Physics, Vol. 39, No. 6, 2012, p. 4001.

Research output: Contribution to journalArticle

Wang, X. ; Kearney, V. ; Yan, H. ; Jia, X. ; Cervino, L. ; Jiang, S. / TH‐C‐BRA‐09 : Robust 3D Lung Tumor Tracking Using Maximum Likelihood Estimation. In: Medical Physics. 2012 ; Vol. 39, No. 6. pp. 4001.
@article{281ac29b314c4f1b8aeb2a34d3a75b25,
title = "TH‐C‐BRA‐09: Robust 3D Lung Tumor Tracking Using Maximum Likelihood Estimation",
abstract = "Purpose: To develop a robust 3D lung tumor tracking method based on a single x‐ray projection using maximum likelihood estimation. Methods: 4DCT images at different phases are registered to yield motion vector fields and a PCA based lung motion model is built. An acquired CBCT projection is compared with the simulated projections under different metrics to yield the correct PCA coefficients and hence the corresponding motion vector fields, which can be used to derive the 3D tumor location at this projection. The metrics we considered include normalized cross correlation and normalized mutual information between the gradient images of the acquired CBCT and that of the simulated 4DCT projection, and the position of diaphragm. A maximum likelihood estimation method is developed to combine the tracking results from all the metrics and integrate the constraints regarding tumor motion smoothness and wave form, leading to robust tumor locations. The method is tested on real patient data. Results: It is found that normalized cross correlation, normalized mutual information, and diaphragm location can be used to determine the PCA coefficients and the tumor position, although the efficacy of any single metric depends on the gantry angles and breathing phases. However, with the combination of different metrics, the tumor tracking accuracy is greatly improved. The resulting mean 3D error is found to be 1.3mm. Conclusions: A robust 3D tumor tracking method is developed based on maximum likelihood estimation to derive tumor location corresponding to an x‐ray projection for lung cancer patient. This work is supported by Varian Medical Systems through a Master Research Agreement.",
author = "X. Wang and V. Kearney and H. Yan and X. Jia and L. Cervino and S. Jiang",
year = "2012",
doi = "10.1118/1.4736325",
language = "English (US)",
volume = "39",
pages = "4001",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "6",

}

TY - JOUR

T1 - TH‐C‐BRA‐09

T2 - Robust 3D Lung Tumor Tracking Using Maximum Likelihood Estimation

AU - Wang, X.

AU - Kearney, V.

AU - Yan, H.

AU - Jia, X.

AU - Cervino, L.

AU - Jiang, S.

PY - 2012

Y1 - 2012

N2 - Purpose: To develop a robust 3D lung tumor tracking method based on a single x‐ray projection using maximum likelihood estimation. Methods: 4DCT images at different phases are registered to yield motion vector fields and a PCA based lung motion model is built. An acquired CBCT projection is compared with the simulated projections under different metrics to yield the correct PCA coefficients and hence the corresponding motion vector fields, which can be used to derive the 3D tumor location at this projection. The metrics we considered include normalized cross correlation and normalized mutual information between the gradient images of the acquired CBCT and that of the simulated 4DCT projection, and the position of diaphragm. A maximum likelihood estimation method is developed to combine the tracking results from all the metrics and integrate the constraints regarding tumor motion smoothness and wave form, leading to robust tumor locations. The method is tested on real patient data. Results: It is found that normalized cross correlation, normalized mutual information, and diaphragm location can be used to determine the PCA coefficients and the tumor position, although the efficacy of any single metric depends on the gantry angles and breathing phases. However, with the combination of different metrics, the tumor tracking accuracy is greatly improved. The resulting mean 3D error is found to be 1.3mm. Conclusions: A robust 3D tumor tracking method is developed based on maximum likelihood estimation to derive tumor location corresponding to an x‐ray projection for lung cancer patient. This work is supported by Varian Medical Systems through a Master Research Agreement.

AB - Purpose: To develop a robust 3D lung tumor tracking method based on a single x‐ray projection using maximum likelihood estimation. Methods: 4DCT images at different phases are registered to yield motion vector fields and a PCA based lung motion model is built. An acquired CBCT projection is compared with the simulated projections under different metrics to yield the correct PCA coefficients and hence the corresponding motion vector fields, which can be used to derive the 3D tumor location at this projection. The metrics we considered include normalized cross correlation and normalized mutual information between the gradient images of the acquired CBCT and that of the simulated 4DCT projection, and the position of diaphragm. A maximum likelihood estimation method is developed to combine the tracking results from all the metrics and integrate the constraints regarding tumor motion smoothness and wave form, leading to robust tumor locations. The method is tested on real patient data. Results: It is found that normalized cross correlation, normalized mutual information, and diaphragm location can be used to determine the PCA coefficients and the tumor position, although the efficacy of any single metric depends on the gantry angles and breathing phases. However, with the combination of different metrics, the tumor tracking accuracy is greatly improved. The resulting mean 3D error is found to be 1.3mm. Conclusions: A robust 3D tumor tracking method is developed based on maximum likelihood estimation to derive tumor location corresponding to an x‐ray projection for lung cancer patient. This work is supported by Varian Medical Systems through a Master Research Agreement.

UR - http://www.scopus.com/inward/record.url?scp=85024799611&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024799611&partnerID=8YFLogxK

U2 - 10.1118/1.4736325

DO - 10.1118/1.4736325

M3 - Article

AN - SCOPUS:85024799611

VL - 39

SP - 4001

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 6

ER -