Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks

Kenneth Hoyt, Jason M. Warram, Heidi Umphrey, Lin Belt, Mark E. Lockhart, Michelle L. Robbin, Kurt R. Zinn

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

Objective. The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model. Methods. An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-μL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60% learning and 40% testing) to predict the breast cancer response to therapy. Results. The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10%, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response. Conclusions. Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.

Original languageEnglish (US)
Pages (from-to)577-585
Number of pages9
JournalJournal of Ultrasound in Medicine
Volume29
Issue number4
DOIs
StatePublished - Apr 1 2010

Fingerprint

Breast Neoplasms
perflutren
Neoplasms
Nude Mice
Contrast Media
Perfusion
Therapeutics
Microbubbles
Euthanasia
Microspheres
Tail
Veins
Software
Bevacizumab
Learning
Injections

Keywords

  • Bevacizumab
  • Breast cancer
  • Contrast agent
  • Neural networks
  • Ultrasound

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks. / Hoyt, Kenneth; Warram, Jason M.; Umphrey, Heidi; Belt, Lin; Lockhart, Mark E.; Robbin, Michelle L.; Zinn, Kurt R.

In: Journal of Ultrasound in Medicine, Vol. 29, No. 4, 01.04.2010, p. 577-585.

Research output: Contribution to journalArticle

Hoyt, Kenneth ; Warram, Jason M. ; Umphrey, Heidi ; Belt, Lin ; Lockhart, Mark E. ; Robbin, Michelle L. ; Zinn, Kurt R. / Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks. In: Journal of Ultrasound in Medicine. 2010 ; Vol. 29, No. 4. pp. 577-585.
@article{b35f6698e1df442f8c952beca02d5407,
title = "Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks",
abstract = "Objective. The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model. Methods. An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-μL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60{\%} learning and 40{\%} testing) to predict the breast cancer response to therapy. Results. The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10{\%}, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response. Conclusions. Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.",
keywords = "Bevacizumab, Breast cancer, Contrast agent, Neural networks, Ultrasound",
author = "Kenneth Hoyt and Warram, {Jason M.} and Heidi Umphrey and Lin Belt and Lockhart, {Mark E.} and Robbin, {Michelle L.} and Zinn, {Kurt R.}",
year = "2010",
month = "4",
day = "1",
doi = "10.7863/jum.2010.29.4.577",
language = "English (US)",
volume = "29",
pages = "577--585",
journal = "Journal of Ultrasound in Medicine",
issn = "0278-4297",
publisher = "American Institute of Ultrasound in Medicine",
number = "4",

}

TY - JOUR

T1 - Determination of breast cancer response to bevacizumab therapy using contrast-enhanced ultrasound and artificial neural networks

AU - Hoyt, Kenneth

AU - Warram, Jason M.

AU - Umphrey, Heidi

AU - Belt, Lin

AU - Lockhart, Mark E.

AU - Robbin, Michelle L.

AU - Zinn, Kurt R.

PY - 2010/4/1

Y1 - 2010/4/1

N2 - Objective. The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model. Methods. An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-μL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60% learning and 40% testing) to predict the breast cancer response to therapy. Results. The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10%, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response. Conclusions. Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.

AB - Objective. The purpose of this study was to evaluate contrast-enhanced ultrasound and neural network data classification for determining the breast cancer response to bevacizumab therapy in a murine model. Methods. An ultrasound scanner operating in the harmonic mode was used to measure ultrasound contrast agent (UCA) time-intensity curves in vivo. Twenty-five nude athymic mice with orthotopic breast cancers received a 30-μL tail vein bolus of a perflutren microsphere UCA, and baseline tumor imaging was performed using microbubble destruction-replenishment techniques. Subsequently, 15 animals received a 0.2-mg injection of bevacizumab, whereas 10 control animals received an equivalent dose of saline. Animals were reimaged on days 1, 2, 3, and 6 before euthanasia. Histologic assessment of excised tumor sections was performed. Time-intensity curve analysis for a given region of interest was conducted using customized software. Tumor perfusion metrics on days 1, 2, 3, and 6 were modeled using neural network data classification schemes (60% learning and 40% testing) to predict the breast cancer response to therapy. Results. The breast cancer response to a single dose of bevacizumab in a murine model was immediate and transient. Permutations of input to the neural network data classification scheme revealed that tumor perfusion data within 3 days of bevacizumab dosing was sufficient to minimize the prediction error to 10%, whereas measurements of physical tumor size alone did not appear adequate to assess the therapeutic response. Conclusions. Contrast-enhanced ultrasound may be a useful tool for determining the response to bevacizumab therapy and monitoring the subsequent restoration of blood flow to breast cancer.

KW - Bevacizumab

KW - Breast cancer

KW - Contrast agent

KW - Neural networks

KW - Ultrasound

UR - http://www.scopus.com/inward/record.url?scp=77951462041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951462041&partnerID=8YFLogxK

U2 - 10.7863/jum.2010.29.4.577

DO - 10.7863/jum.2010.29.4.577

M3 - Article

VL - 29

SP - 577

EP - 585

JO - Journal of Ultrasound in Medicine

JF - Journal of Ultrasound in Medicine

SN - 0278-4297

IS - 4

ER -