A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer

Xuan Zhao, Edward K. Wong, Yao Wang, Stella Lymberis, Bixiu Wen, Silvia Formenti, Jenghwa Chang

Research output: Contribution to journalArticle

Abstract

Purpose: NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85% were better treated prone and 15% were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position. Methods: Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume ≤ 0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume >0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/ (true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/ (true-prone+false-supine) ]. The authors used K -fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance. Results: After the first stage, 49 of the 198 left-breast cancer patients were found to have >0.1 cc of in-field heart volume. The three geometric features of heart orientation,distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4% and 99.3%, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6%, as compared to 21/170 or 12.4% when the authors use only the first stage (thresholding) for classification. Conclusions: The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.

Original languageEnglish (US)
Pages (from-to)5341-5350
Number of pages10
JournalMedical Physics
Volume37
Issue number10
DOIs
StatePublished - Oct 2010

Fingerprint

Radiotherapy
Breast Neoplasms
Cardiac Volume
Prone Position
Breast
Therapeutics
Supine Position
Support Vector Machine
Organs at Risk
Lung
Heart Neoplasms
Patient Rights
Weights and Measures
Sensitivity and Specificity
Research
Neoplasms

Keywords

  • breast radiotherapy
  • feature selection
  • prone vs supine
  • support vector machine

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer. / Zhao, Xuan; Wong, Edward K.; Wang, Yao; Lymberis, Stella; Wen, Bixiu; Formenti, Silvia; Chang, Jenghwa.

In: Medical Physics, Vol. 37, No. 10, 10.2010, p. 5341-5350.

Research output: Contribution to journalArticle

Zhao, Xuan ; Wong, Edward K. ; Wang, Yao ; Lymberis, Stella ; Wen, Bixiu ; Formenti, Silvia ; Chang, Jenghwa. / A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer. In: Medical Physics. 2010 ; Vol. 37, No. 10. pp. 5341-5350.
@article{d5b82a83d7c542c0a3bfd9e439a2242e,
title = "A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer",
abstract = "Purpose: NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85{\%} were better treated prone and 15{\%} were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position. Methods: Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume ≤ 0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume >0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/ (true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/ (true-prone+false-supine) ]. The authors used K -fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance. Results: After the first stage, 49 of the 198 left-breast cancer patients were found to have >0.1 cc of in-field heart volume. The three geometric features of heart orientation,distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4{\%} and 99.3{\%}, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6{\%}, as compared to 21/170 or 12.4{\%} when the authors use only the first stage (thresholding) for classification. Conclusions: The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.",
keywords = "breast radiotherapy, feature selection, prone vs supine, support vector machine",
author = "Xuan Zhao and Wong, {Edward K.} and Yao Wang and Stella Lymberis and Bixiu Wen and Silvia Formenti and Jenghwa Chang",
year = "2010",
month = "10",
doi = "10.1118/1.3483264",
language = "English (US)",
volume = "37",
pages = "5341--5350",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "10",

}

TY - JOUR

T1 - A support vector machine (SVM) for predicting preferred treatment position in radiotherapy of patients with breast cancer

AU - Zhao, Xuan

AU - Wong, Edward K.

AU - Wang, Yao

AU - Lymberis, Stella

AU - Wen, Bixiu

AU - Formenti, Silvia

AU - Chang, Jenghwa

PY - 2010/10

Y1 - 2010/10

N2 - Purpose: NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85% were better treated prone and 15% were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position. Methods: Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume ≤ 0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume >0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/ (true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/ (true-prone+false-supine) ]. The authors used K -fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance. Results: After the first stage, 49 of the 198 left-breast cancer patients were found to have >0.1 cc of in-field heart volume. The three geometric features of heart orientation,distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4% and 99.3%, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6%, as compared to 21/170 or 12.4% when the authors use only the first stage (thresholding) for classification. Conclusions: The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.

AB - Purpose: NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85% were better treated prone and 15% were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position. Methods: Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume ≤ 0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume >0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/ (true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/ (true-prone+false-supine) ]. The authors used K -fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance. Results: After the first stage, 49 of the 198 left-breast cancer patients were found to have >0.1 cc of in-field heart volume. The three geometric features of heart orientation,distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4% and 99.3%, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6%, as compared to 21/170 or 12.4% when the authors use only the first stage (thresholding) for classification. Conclusions: The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.

KW - breast radiotherapy

KW - feature selection

KW - prone vs supine

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=77957722210&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957722210&partnerID=8YFLogxK

U2 - 10.1118/1.3483264

DO - 10.1118/1.3483264

M3 - Article

VL - 37

SP - 5341

EP - 5350

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 10

ER -