Learning methods for lung tumor markerless gating in image-guided radiotherapy

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

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

2 Citations (Scopus)

Abstract

In an idealized gated radiotherapy treatment, radiation is delivered only when the tumor is at the right position. For gated lung cancer radiotherapy, it is difficult to generate accurate gating signals due to the large uncertainties when using external surrogates and the risk of pneumothorax when using implanted fiducial markers. In this paper, we investigate machine learning algorithms for markerless gated radiotherapy with fluoroscopic images. Previous approach utilizes template matching to localize the tumor position. Here, we investigate two ways to improve the precision of tumor target localization by applying: (1) an ensemble of templates where the representative templates are selected by Gaussian mixture clustering, and (2) a support vector machine (SVM) classifier with radial basis kernels. Template matching only considers images inside the gating window, but images outside the gating window might provide additional information. We take advantage of both states and re-cast the gating problem into a classification problem. Thus, we are able to use the SVM classifier for gated radiotherapy. To verify the effectiveness of the two proposed techniques, we apply them on five sequences of fluoroscopic images from five lung cancer patients against the gating signal of manually contoured tumors as ground truth. Our five-patient case study shows that both ensemble template matching and SVM are reasonable tools for image-guided markerless gated radiotherapy with an average of approximately 95% precision in terms of delivered target dose at approximately 35% duty cycle.

Original languageEnglish (US)
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Pages902-910
Number of pages9
DOIs
StatePublished - 2008
Event14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008 - Las Vegas, NV, United States
Duration: Aug 24 2008Aug 27 2008

Other

Other14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008
CountryUnited States
CityLas Vegas, NV
Period8/24/088/27/08

Fingerprint

Radiotherapy
Tumors
Template matching
Support vector machines
Classifiers
Learning algorithms
Learning systems
Radiation

Keywords

  • Applied machine learning
  • Classification
  • Clustering
  • Image-guided radiotherapy
  • Mixture model
  • Support vector machine

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Cui, Y., Dy, J. G., Sharp, G. C., Alexander, B. M., & Jiang, S. B. (2008). Learning methods for lung tumor markerless gating in image-guided radiotherapy. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 902-910) https://doi.org/10.1145/1401890.1401998

Learning methods for lung tumor markerless gating in image-guided radiotherapy. / Cui, Ying; Dy, Jennifer G.; Sharp, Gregory C.; Alexander, Brian M.; Jiang, Steve B.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2008. p. 902-910.

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

Cui, Y, Dy, JG, Sharp, GC, Alexander, BM & Jiang, SB 2008, Learning methods for lung tumor markerless gating in image-guided radiotherapy. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 902-910, 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008, Las Vegas, NV, United States, 8/24/08. https://doi.org/10.1145/1401890.1401998
Cui Y, Dy JG, Sharp GC, Alexander BM, Jiang SB. Learning methods for lung tumor markerless gating in image-guided radiotherapy. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2008. p. 902-910 https://doi.org/10.1145/1401890.1401998
Cui, Ying ; Dy, Jennifer G. ; Sharp, Gregory C. ; Alexander, Brian M. ; Jiang, Steve B. / Learning methods for lung tumor markerless gating in image-guided radiotherapy. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2008. pp. 902-910
@inproceedings{8f2d7b1058464056a5e5f1896507983b,
title = "Learning methods for lung tumor markerless gating in image-guided radiotherapy",
abstract = "In an idealized gated radiotherapy treatment, radiation is delivered only when the tumor is at the right position. For gated lung cancer radiotherapy, it is difficult to generate accurate gating signals due to the large uncertainties when using external surrogates and the risk of pneumothorax when using implanted fiducial markers. In this paper, we investigate machine learning algorithms for markerless gated radiotherapy with fluoroscopic images. Previous approach utilizes template matching to localize the tumor position. Here, we investigate two ways to improve the precision of tumor target localization by applying: (1) an ensemble of templates where the representative templates are selected by Gaussian mixture clustering, and (2) a support vector machine (SVM) classifier with radial basis kernels. Template matching only considers images inside the gating window, but images outside the gating window might provide additional information. We take advantage of both states and re-cast the gating problem into a classification problem. Thus, we are able to use the SVM classifier for gated radiotherapy. To verify the effectiveness of the two proposed techniques, we apply them on five sequences of fluoroscopic images from five lung cancer patients against the gating signal of manually contoured tumors as ground truth. Our five-patient case study shows that both ensemble template matching and SVM are reasonable tools for image-guided markerless gated radiotherapy with an average of approximately 95{\%} precision in terms of delivered target dose at approximately 35{\%} duty cycle.",
keywords = "Applied machine learning, Classification, Clustering, Image-guided radiotherapy, Mixture model, Support vector machine",
author = "Ying Cui and Dy, {Jennifer G.} and Sharp, {Gregory C.} and Alexander, {Brian M.} and Jiang, {Steve B.}",
year = "2008",
doi = "10.1145/1401890.1401998",
language = "English (US)",
isbn = "9781605581934",
pages = "902--910",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

TY - GEN

T1 - Learning methods for lung tumor markerless gating in image-guided radiotherapy

AU - Cui, Ying

AU - Dy, Jennifer G.

AU - Sharp, Gregory C.

AU - Alexander, Brian M.

AU - Jiang, Steve B.

PY - 2008

Y1 - 2008

N2 - In an idealized gated radiotherapy treatment, radiation is delivered only when the tumor is at the right position. For gated lung cancer radiotherapy, it is difficult to generate accurate gating signals due to the large uncertainties when using external surrogates and the risk of pneumothorax when using implanted fiducial markers. In this paper, we investigate machine learning algorithms for markerless gated radiotherapy with fluoroscopic images. Previous approach utilizes template matching to localize the tumor position. Here, we investigate two ways to improve the precision of tumor target localization by applying: (1) an ensemble of templates where the representative templates are selected by Gaussian mixture clustering, and (2) a support vector machine (SVM) classifier with radial basis kernels. Template matching only considers images inside the gating window, but images outside the gating window might provide additional information. We take advantage of both states and re-cast the gating problem into a classification problem. Thus, we are able to use the SVM classifier for gated radiotherapy. To verify the effectiveness of the two proposed techniques, we apply them on five sequences of fluoroscopic images from five lung cancer patients against the gating signal of manually contoured tumors as ground truth. Our five-patient case study shows that both ensemble template matching and SVM are reasonable tools for image-guided markerless gated radiotherapy with an average of approximately 95% precision in terms of delivered target dose at approximately 35% duty cycle.

AB - In an idealized gated radiotherapy treatment, radiation is delivered only when the tumor is at the right position. For gated lung cancer radiotherapy, it is difficult to generate accurate gating signals due to the large uncertainties when using external surrogates and the risk of pneumothorax when using implanted fiducial markers. In this paper, we investigate machine learning algorithms for markerless gated radiotherapy with fluoroscopic images. Previous approach utilizes template matching to localize the tumor position. Here, we investigate two ways to improve the precision of tumor target localization by applying: (1) an ensemble of templates where the representative templates are selected by Gaussian mixture clustering, and (2) a support vector machine (SVM) classifier with radial basis kernels. Template matching only considers images inside the gating window, but images outside the gating window might provide additional information. We take advantage of both states and re-cast the gating problem into a classification problem. Thus, we are able to use the SVM classifier for gated radiotherapy. To verify the effectiveness of the two proposed techniques, we apply them on five sequences of fluoroscopic images from five lung cancer patients against the gating signal of manually contoured tumors as ground truth. Our five-patient case study shows that both ensemble template matching and SVM are reasonable tools for image-guided markerless gated radiotherapy with an average of approximately 95% precision in terms of delivered target dose at approximately 35% duty cycle.

KW - Applied machine learning

KW - Classification

KW - Clustering

KW - Image-guided radiotherapy

KW - Mixture model

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=65449131274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65449131274&partnerID=8YFLogxK

U2 - 10.1145/1401890.1401998

DO - 10.1145/1401890.1401998

M3 - Conference contribution

AN - SCOPUS:65449131274

SN - 9781605581934

SP - 902

EP - 910

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

ER -