Tumor targeting for lung cancer radiotherapy using machine learning techniques

Tong Lin, Laura Cervino, Xiaoli Tang, Nuno Vaseoncelos, Steve B. Jiang

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

1 Citation (Scopus)

Abstract

Accurate lung tumor targeting in real time plays a fundamental role in image-guide radiotherapy of lung cancers. Precise tumor targeting is required for both respiratory gating and tracking. Gating is considered as the current state of the art for precise lung cancer radiotherapy, which irradiates the tumor when it moves into a predefined gating window. Tracking seems to he a next-generation technique, and it operates in a more aggressive fashion by following the tumor position with radiation beam in real time. Existing methods for gating and tracking often rely on observed motion patterns of external surrogates or implanted fiducial markers. However, external surrogates suffer from certain degrees of inaccuracy, and implanted fiducial markers are in limited uses due to the risk of pneumothorax. Therefore, direct tumor targeting techniques without implanting fiducial markers are desired. Previous studies in fluoroscopic markerless targeting are mainly based on template matching methods, which may fail when tumor boundary is unclear in fluoroscopic images. In this paper, we propose a novel framework of markerless gating and tracking based on machine learning algorithms. Specifically, gating is treated as a two-class classification problem, which is solved by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Further, we formulate the tracking problem as a regression task, which employs the correlation between the tumor position and nearby surrogate anatomic features in the image. Four regression methods were tested in this study: 1-degree and 2-degree linear regression, artificial neural network (ANN), and support vector machine (SVM). Finally, we demonstrate the superb performance of the proposed markerless gating and tracking algorithms on 10 fluoroscopic image sequences of 9 patients. For gating, the target coverage (the precision) ranges from 90% to 99%, with mean of 96.5%. For tracking, the mean localization error is about 2.1 pixels and the maximum error at 95% confidence level is about 4.6 pixels (pixel size is about 0.5 mm).

Original languageEnglish (US)
Title of host publicationProceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
Pages533-538
Number of pages6
DOIs
StatePublished - 2008
Event7th International Conference on Machine Learning and Applications, ICMLA 2008 - San Diego, CA, United States
Duration: Dec 11 2008Dec 13 2008

Other

Other7th International Conference on Machine Learning and Applications, ICMLA 2008
CountryUnited States
CitySan Diego, CA
Period12/11/0812/13/08

Fingerprint

Radiotherapy
Learning systems
Tumors
Pixels
Neural networks
Template matching
Linear regression
Principal component analysis
Learning algorithms
Support vector machines
Radiation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software

Cite this

Lin, T., Cervino, L., Tang, X., Vaseoncelos, N., & Jiang, S. B. (2008). Tumor targeting for lung cancer radiotherapy using machine learning techniques. In Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008 (pp. 533-538). [4725025] https://doi.org/10.1109/ICMLA.2008.143

Tumor targeting for lung cancer radiotherapy using machine learning techniques. / Lin, Tong; Cervino, Laura; Tang, Xiaoli; Vaseoncelos, Nuno; Jiang, Steve B.

Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008. p. 533-538 4725025.

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

Lin, T, Cervino, L, Tang, X, Vaseoncelos, N & Jiang, SB 2008, Tumor targeting for lung cancer radiotherapy using machine learning techniques. in Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008., 4725025, pp. 533-538, 7th International Conference on Machine Learning and Applications, ICMLA 2008, San Diego, CA, United States, 12/11/08. https://doi.org/10.1109/ICMLA.2008.143
Lin T, Cervino L, Tang X, Vaseoncelos N, Jiang SB. Tumor targeting for lung cancer radiotherapy using machine learning techniques. In Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008. p. 533-538. 4725025 https://doi.org/10.1109/ICMLA.2008.143
Lin, Tong ; Cervino, Laura ; Tang, Xiaoli ; Vaseoncelos, Nuno ; Jiang, Steve B. / Tumor targeting for lung cancer radiotherapy using machine learning techniques. Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008. pp. 533-538
@inproceedings{5ec292723b4b441c9861457deaa070fe,
title = "Tumor targeting for lung cancer radiotherapy using machine learning techniques",
abstract = "Accurate lung tumor targeting in real time plays a fundamental role in image-guide radiotherapy of lung cancers. Precise tumor targeting is required for both respiratory gating and tracking. Gating is considered as the current state of the art for precise lung cancer radiotherapy, which irradiates the tumor when it moves into a predefined gating window. Tracking seems to he a next-generation technique, and it operates in a more aggressive fashion by following the tumor position with radiation beam in real time. Existing methods for gating and tracking often rely on observed motion patterns of external surrogates or implanted fiducial markers. However, external surrogates suffer from certain degrees of inaccuracy, and implanted fiducial markers are in limited uses due to the risk of pneumothorax. Therefore, direct tumor targeting techniques without implanting fiducial markers are desired. Previous studies in fluoroscopic markerless targeting are mainly based on template matching methods, which may fail when tumor boundary is unclear in fluoroscopic images. In this paper, we propose a novel framework of markerless gating and tracking based on machine learning algorithms. Specifically, gating is treated as a two-class classification problem, which is solved by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Further, we formulate the tracking problem as a regression task, which employs the correlation between the tumor position and nearby surrogate anatomic features in the image. Four regression methods were tested in this study: 1-degree and 2-degree linear regression, artificial neural network (ANN), and support vector machine (SVM). Finally, we demonstrate the superb performance of the proposed markerless gating and tracking algorithms on 10 fluoroscopic image sequences of 9 patients. For gating, the target coverage (the precision) ranges from 90{\%} to 99{\%}, with mean of 96.5{\%}. For tracking, the mean localization error is about 2.1 pixels and the maximum error at 95{\%} confidence level is about 4.6 pixels (pixel size is about 0.5 mm).",
author = "Tong Lin and Laura Cervino and Xiaoli Tang and Nuno Vaseoncelos and Jiang, {Steve B.}",
year = "2008",
doi = "10.1109/ICMLA.2008.143",
language = "English (US)",
isbn = "9780769534954",
pages = "533--538",
booktitle = "Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008",

}

TY - GEN

T1 - Tumor targeting for lung cancer radiotherapy using machine learning techniques

AU - Lin, Tong

AU - Cervino, Laura

AU - Tang, Xiaoli

AU - Vaseoncelos, Nuno

AU - Jiang, Steve B.

PY - 2008

Y1 - 2008

N2 - Accurate lung tumor targeting in real time plays a fundamental role in image-guide radiotherapy of lung cancers. Precise tumor targeting is required for both respiratory gating and tracking. Gating is considered as the current state of the art for precise lung cancer radiotherapy, which irradiates the tumor when it moves into a predefined gating window. Tracking seems to he a next-generation technique, and it operates in a more aggressive fashion by following the tumor position with radiation beam in real time. Existing methods for gating and tracking often rely on observed motion patterns of external surrogates or implanted fiducial markers. However, external surrogates suffer from certain degrees of inaccuracy, and implanted fiducial markers are in limited uses due to the risk of pneumothorax. Therefore, direct tumor targeting techniques without implanting fiducial markers are desired. Previous studies in fluoroscopic markerless targeting are mainly based on template matching methods, which may fail when tumor boundary is unclear in fluoroscopic images. In this paper, we propose a novel framework of markerless gating and tracking based on machine learning algorithms. Specifically, gating is treated as a two-class classification problem, which is solved by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Further, we formulate the tracking problem as a regression task, which employs the correlation between the tumor position and nearby surrogate anatomic features in the image. Four regression methods were tested in this study: 1-degree and 2-degree linear regression, artificial neural network (ANN), and support vector machine (SVM). Finally, we demonstrate the superb performance of the proposed markerless gating and tracking algorithms on 10 fluoroscopic image sequences of 9 patients. For gating, the target coverage (the precision) ranges from 90% to 99%, with mean of 96.5%. For tracking, the mean localization error is about 2.1 pixels and the maximum error at 95% confidence level is about 4.6 pixels (pixel size is about 0.5 mm).

AB - Accurate lung tumor targeting in real time plays a fundamental role in image-guide radiotherapy of lung cancers. Precise tumor targeting is required for both respiratory gating and tracking. Gating is considered as the current state of the art for precise lung cancer radiotherapy, which irradiates the tumor when it moves into a predefined gating window. Tracking seems to he a next-generation technique, and it operates in a more aggressive fashion by following the tumor position with radiation beam in real time. Existing methods for gating and tracking often rely on observed motion patterns of external surrogates or implanted fiducial markers. However, external surrogates suffer from certain degrees of inaccuracy, and implanted fiducial markers are in limited uses due to the risk of pneumothorax. Therefore, direct tumor targeting techniques without implanting fiducial markers are desired. Previous studies in fluoroscopic markerless targeting are mainly based on template matching methods, which may fail when tumor boundary is unclear in fluoroscopic images. In this paper, we propose a novel framework of markerless gating and tracking based on machine learning algorithms. Specifically, gating is treated as a two-class classification problem, which is solved by Principal Component Analysis (PCA) and Artificial Neural Network (ANN). Further, we formulate the tracking problem as a regression task, which employs the correlation between the tumor position and nearby surrogate anatomic features in the image. Four regression methods were tested in this study: 1-degree and 2-degree linear regression, artificial neural network (ANN), and support vector machine (SVM). Finally, we demonstrate the superb performance of the proposed markerless gating and tracking algorithms on 10 fluoroscopic image sequences of 9 patients. For gating, the target coverage (the precision) ranges from 90% to 99%, with mean of 96.5%. For tracking, the mean localization error is about 2.1 pixels and the maximum error at 95% confidence level is about 4.6 pixels (pixel size is about 0.5 mm).

UR - http://www.scopus.com/inward/record.url?scp=60649084379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60649084379&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2008.143

DO - 10.1109/ICMLA.2008.143

M3 - Conference contribution

AN - SCOPUS:60649084379

SN - 9780769534954

SP - 533

EP - 538

BT - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

ER -