Automated beam placement for breast radiotherapy using a support vector machine based algorithm

Xuan Zhao, Dewen Kong, Gabor Jozsef, Jenghwa Chang, Edward K. Wong, Silvia C. Formenti, Yao Wang

Research output: Contribution to journalArticle

Abstract

Purpose: To develop an automated beam placement technique for whole breast radiotherapy using tangential beams. We seek to find optimal parameters for tangential beams to cover the whole ipsilateral breast (WB) and minimize the dose to the organs at risk (OARs). Methods: A support vector machine (SVM) based method is proposed to determine the optimal posterior plane of the tangential beams. Relative significances of including/avoiding the volumes of interests are incorporated into the cost function of the SVM. After finding the optimal 3-D plane that separates the whole breast (WB) and the included clinical target volumes (CTVs) from the OARs, the gantry angle, collimator angle, and posterior jaw size of the tangential beams are derived from the separating plane equation. Dosimetric measures of the treatment plans determined by the automated method are compared with those obtained by applying manual beam placement by the physicians. The method can be further extended to use multileaf collimator (MLC) blocking by optimizing posterior MLC positions. Results: The plans for 36 patients (23 prone- and 13 supine-treated) with left breast cancer were analyzed. Our algorithm reduced the volume of the heart that receives >500 cGy dose (V5) from 2.7 to 1.7 cm3 (p = 0.058) on average and the volume of the ipsilateral lung that receives >1000 cGy dose (V10) from 55.2 to 40.7 cm3 (p = 0.0013). The dose coverage as measured by volume receiving >95 of the prescription dose (V95) of the WB without a 5 mm superficial layer decreases by only 0.74 (p = 0.0002) and the V95 for the tumor bed with 1.5 cm margin remains unchanged. Conclusions: This study has demonstrated the feasibility of using a SVM-based algorithm to determine optimal beam placement without a physician's intervention. The proposed method reduced the dose to OARs, especially for supine treated patients, without any relevant degradation of dose homogeneity and coverage in general.

Original languageEnglish (US)
Pages (from-to)2536-2543
Number of pages8
JournalMedical Physics
Volume39
Issue number5
DOIs
StatePublished - May 2012

Fingerprint

Organs at Risk
Breast
Radiotherapy
Physicians
Cardiac Volume
Jaw
Prescriptions
Support Vector Machine
Breast Neoplasms
Costs and Cost Analysis
Lung
Neoplasms
Therapeutics

Keywords

  • automated beam placement
  • breast radiotherapy
  • support vector machines

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Automated beam placement for breast radiotherapy using a support vector machine based algorithm. / Zhao, Xuan; Kong, Dewen; Jozsef, Gabor; Chang, Jenghwa; Wong, Edward K.; Formenti, Silvia C.; Wang, Yao.

In: Medical Physics, Vol. 39, No. 5, 05.2012, p. 2536-2543.

Research output: Contribution to journalArticle

Zhao, X, Kong, D, Jozsef, G, Chang, J, Wong, EK, Formenti, SC & Wang, Y 2012, 'Automated beam placement for breast radiotherapy using a support vector machine based algorithm', Medical Physics, vol. 39, no. 5, pp. 2536-2543. https://doi.org/10.1118/1.3700736
Zhao, Xuan ; Kong, Dewen ; Jozsef, Gabor ; Chang, Jenghwa ; Wong, Edward K. ; Formenti, Silvia C. ; Wang, Yao. / Automated beam placement for breast radiotherapy using a support vector machine based algorithm. In: Medical Physics. 2012 ; Vol. 39, No. 5. pp. 2536-2543.
@article{633000926d8e4788a21b43ba969e7acf,
title = "Automated beam placement for breast radiotherapy using a support vector machine based algorithm",
abstract = "Purpose: To develop an automated beam placement technique for whole breast radiotherapy using tangential beams. We seek to find optimal parameters for tangential beams to cover the whole ipsilateral breast (WB) and minimize the dose to the organs at risk (OARs). Methods: A support vector machine (SVM) based method is proposed to determine the optimal posterior plane of the tangential beams. Relative significances of including/avoiding the volumes of interests are incorporated into the cost function of the SVM. After finding the optimal 3-D plane that separates the whole breast (WB) and the included clinical target volumes (CTVs) from the OARs, the gantry angle, collimator angle, and posterior jaw size of the tangential beams are derived from the separating plane equation. Dosimetric measures of the treatment plans determined by the automated method are compared with those obtained by applying manual beam placement by the physicians. The method can be further extended to use multileaf collimator (MLC) blocking by optimizing posterior MLC positions. Results: The plans for 36 patients (23 prone- and 13 supine-treated) with left breast cancer were analyzed. Our algorithm reduced the volume of the heart that receives >500 cGy dose (V5) from 2.7 to 1.7 cm3 (p = 0.058) on average and the volume of the ipsilateral lung that receives >1000 cGy dose (V10) from 55.2 to 40.7 cm3 (p = 0.0013). The dose coverage as measured by volume receiving >95 of the prescription dose (V95) of the WB without a 5 mm superficial layer decreases by only 0.74 (p = 0.0002) and the V95 for the tumor bed with 1.5 cm margin remains unchanged. Conclusions: This study has demonstrated the feasibility of using a SVM-based algorithm to determine optimal beam placement without a physician's intervention. The proposed method reduced the dose to OARs, especially for supine treated patients, without any relevant degradation of dose homogeneity and coverage in general.",
keywords = "automated beam placement, breast radiotherapy, support vector machines",
author = "Xuan Zhao and Dewen Kong and Gabor Jozsef and Jenghwa Chang and Wong, {Edward K.} and Formenti, {Silvia C.} and Yao Wang",
year = "2012",
month = "5",
doi = "10.1118/1.3700736",
language = "English (US)",
volume = "39",
pages = "2536--2543",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "5",

}

TY - JOUR

T1 - Automated beam placement for breast radiotherapy using a support vector machine based algorithm

AU - Zhao, Xuan

AU - Kong, Dewen

AU - Jozsef, Gabor

AU - Chang, Jenghwa

AU - Wong, Edward K.

AU - Formenti, Silvia C.

AU - Wang, Yao

PY - 2012/5

Y1 - 2012/5

N2 - Purpose: To develop an automated beam placement technique for whole breast radiotherapy using tangential beams. We seek to find optimal parameters for tangential beams to cover the whole ipsilateral breast (WB) and minimize the dose to the organs at risk (OARs). Methods: A support vector machine (SVM) based method is proposed to determine the optimal posterior plane of the tangential beams. Relative significances of including/avoiding the volumes of interests are incorporated into the cost function of the SVM. After finding the optimal 3-D plane that separates the whole breast (WB) and the included clinical target volumes (CTVs) from the OARs, the gantry angle, collimator angle, and posterior jaw size of the tangential beams are derived from the separating plane equation. Dosimetric measures of the treatment plans determined by the automated method are compared with those obtained by applying manual beam placement by the physicians. The method can be further extended to use multileaf collimator (MLC) blocking by optimizing posterior MLC positions. Results: The plans for 36 patients (23 prone- and 13 supine-treated) with left breast cancer were analyzed. Our algorithm reduced the volume of the heart that receives >500 cGy dose (V5) from 2.7 to 1.7 cm3 (p = 0.058) on average and the volume of the ipsilateral lung that receives >1000 cGy dose (V10) from 55.2 to 40.7 cm3 (p = 0.0013). The dose coverage as measured by volume receiving >95 of the prescription dose (V95) of the WB without a 5 mm superficial layer decreases by only 0.74 (p = 0.0002) and the V95 for the tumor bed with 1.5 cm margin remains unchanged. Conclusions: This study has demonstrated the feasibility of using a SVM-based algorithm to determine optimal beam placement without a physician's intervention. The proposed method reduced the dose to OARs, especially for supine treated patients, without any relevant degradation of dose homogeneity and coverage in general.

AB - Purpose: To develop an automated beam placement technique for whole breast radiotherapy using tangential beams. We seek to find optimal parameters for tangential beams to cover the whole ipsilateral breast (WB) and minimize the dose to the organs at risk (OARs). Methods: A support vector machine (SVM) based method is proposed to determine the optimal posterior plane of the tangential beams. Relative significances of including/avoiding the volumes of interests are incorporated into the cost function of the SVM. After finding the optimal 3-D plane that separates the whole breast (WB) and the included clinical target volumes (CTVs) from the OARs, the gantry angle, collimator angle, and posterior jaw size of the tangential beams are derived from the separating plane equation. Dosimetric measures of the treatment plans determined by the automated method are compared with those obtained by applying manual beam placement by the physicians. The method can be further extended to use multileaf collimator (MLC) blocking by optimizing posterior MLC positions. Results: The plans for 36 patients (23 prone- and 13 supine-treated) with left breast cancer were analyzed. Our algorithm reduced the volume of the heart that receives >500 cGy dose (V5) from 2.7 to 1.7 cm3 (p = 0.058) on average and the volume of the ipsilateral lung that receives >1000 cGy dose (V10) from 55.2 to 40.7 cm3 (p = 0.0013). The dose coverage as measured by volume receiving >95 of the prescription dose (V95) of the WB without a 5 mm superficial layer decreases by only 0.74 (p = 0.0002) and the V95 for the tumor bed with 1.5 cm margin remains unchanged. Conclusions: This study has demonstrated the feasibility of using a SVM-based algorithm to determine optimal beam placement without a physician's intervention. The proposed method reduced the dose to OARs, especially for supine treated patients, without any relevant degradation of dose homogeneity and coverage in general.

KW - automated beam placement

KW - breast radiotherapy

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84861581018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861581018&partnerID=8YFLogxK

U2 - 10.1118/1.3700736

DO - 10.1118/1.3700736

M3 - Article

VL - 39

SP - 2536

EP - 2543

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 5

ER -