Multiple template-based fluoroscopic tracking of lung tumor mass without implanted fiducial markers

Ying Cui, Jennifer G. Dy, Gregory C. Sharp, Brian Alexander, Steve B. Jiang

Research output: Contribution to journalArticle

79 Citations (Scopus)

Abstract

Precise lung tumor localization in real time is particularly important for some motion management techniques, such as respiratory gating or beam tracking with a dynamic multi-leaf collimator, due to the reduced clinical tumor volume (CTV) to planning target volume (PTV) margin and/or the escalated dose. There might be large uncertainties in deriving tumor position from external respiratory surrogates. While tracking implanted fiducial markers has sufficient accuracy, this procedure may not be widely accepted due to the risk of pneumothorax. Previously, we have developed a technique to generate gating signals from fluoroscopic images without implanted fiducial markers using a template matching method (Berbeco et al 2005 Phys. Med. Biol. 50 4481-90, Cui et al 2007 Phys. Med. Biol. 52 741-55). In this paper, we present an extension of this method to multiple-template matching for directly tracking the lung tumor mass in fluoroscopy video. The basic idea is as follows: (i) during the patient setup session, a pair of orthogonal fluoroscopic image sequences are taken and processed off-line to generate a set of reference templates that correspond to different breathing phases and tumor positions; (ii) during treatment delivery, fluoroscopic images are continuously acquired and processed; (iii) the similarity between each reference template and the processed incoming image is calculated; (iv) the tumor position in the incoming image is then estimated by combining the tumor centroid coordinates in reference templates with proper weights based on the measured similarities. With different handling of image processing and similarity calculation, two such multiple-template tracking techniques have been developed: one based on motion-enhanced templates and Pearson's correlation score while the other based on eigen templates and mean-squared error. The developed techniques have been tested on six sequences of fluoroscopic images from six lung cancer patients against the reference tumor positions manually determined by a radiation oncologist. The tumor centroid coordinates automatically detected using both methods agree well with the manually marked reference locations. The eigenspace tracking method performs slightly better than the motion-enhanced method, with average localization errors less than 2 pixels (1 mm) and the error at a 95% confidence level of about 2-4 pixels (1-2 mm). This work demonstrates the feasibility of direct tracking of a lung tumor mass in fluoroscopic images without implanted fiducial markers using multiple reference templates.

Original languageEnglish (US)
Pages (from-to)6229-6242
Number of pages14
JournalPhysics in Medicine and Biology
Volume52
Issue number20
DOIs
StatePublished - Oct 21 2007

Fingerprint

Fiducial Markers
markers
lungs
Tumors
templates
tumors
Lung
Neoplasms
Template matching
centroids
pneumothorax
Particle beam tracking
Pixels
pixels
fluoroscopy
Fluoroscopy
Pneumothorax
Tumor Burden
breathing
collimators

ASJC Scopus subject areas

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

Cite this

Multiple template-based fluoroscopic tracking of lung tumor mass without implanted fiducial markers. / Cui, Ying; Dy, Jennifer G.; Sharp, Gregory C.; Alexander, Brian; Jiang, Steve B.

In: Physics in Medicine and Biology, Vol. 52, No. 20, 21.10.2007, p. 6229-6242.

Research output: Contribution to journalArticle

Cui, Ying ; Dy, Jennifer G. ; Sharp, Gregory C. ; Alexander, Brian ; Jiang, Steve B. / Multiple template-based fluoroscopic tracking of lung tumor mass without implanted fiducial markers. In: Physics in Medicine and Biology. 2007 ; Vol. 52, No. 20. pp. 6229-6242.
@article{7dbd6b983005469c971beccb33bda52b,
title = "Multiple template-based fluoroscopic tracking of lung tumor mass without implanted fiducial markers",
abstract = "Precise lung tumor localization in real time is particularly important for some motion management techniques, such as respiratory gating or beam tracking with a dynamic multi-leaf collimator, due to the reduced clinical tumor volume (CTV) to planning target volume (PTV) margin and/or the escalated dose. There might be large uncertainties in deriving tumor position from external respiratory surrogates. While tracking implanted fiducial markers has sufficient accuracy, this procedure may not be widely accepted due to the risk of pneumothorax. Previously, we have developed a technique to generate gating signals from fluoroscopic images without implanted fiducial markers using a template matching method (Berbeco et al 2005 Phys. Med. Biol. 50 4481-90, Cui et al 2007 Phys. Med. Biol. 52 741-55). In this paper, we present an extension of this method to multiple-template matching for directly tracking the lung tumor mass in fluoroscopy video. The basic idea is as follows: (i) during the patient setup session, a pair of orthogonal fluoroscopic image sequences are taken and processed off-line to generate a set of reference templates that correspond to different breathing phases and tumor positions; (ii) during treatment delivery, fluoroscopic images are continuously acquired and processed; (iii) the similarity between each reference template and the processed incoming image is calculated; (iv) the tumor position in the incoming image is then estimated by combining the tumor centroid coordinates in reference templates with proper weights based on the measured similarities. With different handling of image processing and similarity calculation, two such multiple-template tracking techniques have been developed: one based on motion-enhanced templates and Pearson's correlation score while the other based on eigen templates and mean-squared error. The developed techniques have been tested on six sequences of fluoroscopic images from six lung cancer patients against the reference tumor positions manually determined by a radiation oncologist. The tumor centroid coordinates automatically detected using both methods agree well with the manually marked reference locations. The eigenspace tracking method performs slightly better than the motion-enhanced method, with average localization errors less than 2 pixels (1 mm) and the error at a 95{\%} confidence level of about 2-4 pixels (1-2 mm). This work demonstrates the feasibility of direct tracking of a lung tumor mass in fluoroscopic images without implanted fiducial markers using multiple reference templates.",
author = "Ying Cui and Dy, {Jennifer G.} and Sharp, {Gregory C.} and Brian Alexander and Jiang, {Steve B.}",
year = "2007",
month = "10",
day = "21",
doi = "10.1088/0031-9155/52/20/010",
language = "English (US)",
volume = "52",
pages = "6229--6242",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "20",

}

TY - JOUR

T1 - Multiple template-based fluoroscopic tracking of lung tumor mass without implanted fiducial markers

AU - Cui, Ying

AU - Dy, Jennifer G.

AU - Sharp, Gregory C.

AU - Alexander, Brian

AU - Jiang, Steve B.

PY - 2007/10/21

Y1 - 2007/10/21

N2 - Precise lung tumor localization in real time is particularly important for some motion management techniques, such as respiratory gating or beam tracking with a dynamic multi-leaf collimator, due to the reduced clinical tumor volume (CTV) to planning target volume (PTV) margin and/or the escalated dose. There might be large uncertainties in deriving tumor position from external respiratory surrogates. While tracking implanted fiducial markers has sufficient accuracy, this procedure may not be widely accepted due to the risk of pneumothorax. Previously, we have developed a technique to generate gating signals from fluoroscopic images without implanted fiducial markers using a template matching method (Berbeco et al 2005 Phys. Med. Biol. 50 4481-90, Cui et al 2007 Phys. Med. Biol. 52 741-55). In this paper, we present an extension of this method to multiple-template matching for directly tracking the lung tumor mass in fluoroscopy video. The basic idea is as follows: (i) during the patient setup session, a pair of orthogonal fluoroscopic image sequences are taken and processed off-line to generate a set of reference templates that correspond to different breathing phases and tumor positions; (ii) during treatment delivery, fluoroscopic images are continuously acquired and processed; (iii) the similarity between each reference template and the processed incoming image is calculated; (iv) the tumor position in the incoming image is then estimated by combining the tumor centroid coordinates in reference templates with proper weights based on the measured similarities. With different handling of image processing and similarity calculation, two such multiple-template tracking techniques have been developed: one based on motion-enhanced templates and Pearson's correlation score while the other based on eigen templates and mean-squared error. The developed techniques have been tested on six sequences of fluoroscopic images from six lung cancer patients against the reference tumor positions manually determined by a radiation oncologist. The tumor centroid coordinates automatically detected using both methods agree well with the manually marked reference locations. The eigenspace tracking method performs slightly better than the motion-enhanced method, with average localization errors less than 2 pixels (1 mm) and the error at a 95% confidence level of about 2-4 pixels (1-2 mm). This work demonstrates the feasibility of direct tracking of a lung tumor mass in fluoroscopic images without implanted fiducial markers using multiple reference templates.

AB - Precise lung tumor localization in real time is particularly important for some motion management techniques, such as respiratory gating or beam tracking with a dynamic multi-leaf collimator, due to the reduced clinical tumor volume (CTV) to planning target volume (PTV) margin and/or the escalated dose. There might be large uncertainties in deriving tumor position from external respiratory surrogates. While tracking implanted fiducial markers has sufficient accuracy, this procedure may not be widely accepted due to the risk of pneumothorax. Previously, we have developed a technique to generate gating signals from fluoroscopic images without implanted fiducial markers using a template matching method (Berbeco et al 2005 Phys. Med. Biol. 50 4481-90, Cui et al 2007 Phys. Med. Biol. 52 741-55). In this paper, we present an extension of this method to multiple-template matching for directly tracking the lung tumor mass in fluoroscopy video. The basic idea is as follows: (i) during the patient setup session, a pair of orthogonal fluoroscopic image sequences are taken and processed off-line to generate a set of reference templates that correspond to different breathing phases and tumor positions; (ii) during treatment delivery, fluoroscopic images are continuously acquired and processed; (iii) the similarity between each reference template and the processed incoming image is calculated; (iv) the tumor position in the incoming image is then estimated by combining the tumor centroid coordinates in reference templates with proper weights based on the measured similarities. With different handling of image processing and similarity calculation, two such multiple-template tracking techniques have been developed: one based on motion-enhanced templates and Pearson's correlation score while the other based on eigen templates and mean-squared error. The developed techniques have been tested on six sequences of fluoroscopic images from six lung cancer patients against the reference tumor positions manually determined by a radiation oncologist. The tumor centroid coordinates automatically detected using both methods agree well with the manually marked reference locations. The eigenspace tracking method performs slightly better than the motion-enhanced method, with average localization errors less than 2 pixels (1 mm) and the error at a 95% confidence level of about 2-4 pixels (1-2 mm). This work demonstrates the feasibility of direct tracking of a lung tumor mass in fluoroscopic images without implanted fiducial markers using multiple reference templates.

UR - http://www.scopus.com/inward/record.url?scp=36048941490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36048941490&partnerID=8YFLogxK

U2 - 10.1088/0031-9155/52/20/010

DO - 10.1088/0031-9155/52/20/010

M3 - Article

C2 - 17921582

AN - SCOPUS:36048941490

VL - 52

SP - 6229

EP - 6242

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 20

ER -