Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI

Ruey-Feng Chang, Hong-Hao Chen, Yeun-Chung Chang, Chiun-Sheng Huang, Jeon-Hor Chen, Chung Ming Lo

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Purpose: Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods: A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The proposed region-based features achieved the accuracy of 73.53%, 82.35%, and 77.45% for ER, HER2, and TNBC classifications. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. Conclusion: The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.

Original languageEnglish
Pages (from-to)809-819
Number of pages11
JournalMagnetic Resonance Imaging
Volume34
Issue number6
DOIs
Publication statusPublished - Jul 1 2016

Fingerprint

Triple Negative Breast Neoplasms
Magnetic resonance
Estrogen Receptors
Tumors
Magnetic Resonance Imaging
Breast Neoplasms
Imaging techniques
Pharmacokinetics
ROC Curve
Textures
Breast
Biopsy
Neoplasms
Logistics
Cell Surface Receptors
Feature extraction
Logistic Models
human ERBB2 protein
Estrogens
Epidermal Growth Factor

Keywords

  • Breast Cancer
  • Computer-aided diagnosis
  • DCE-MRI
  • Molecular marker

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging
  • Biomedical Engineering

Cite this

Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI. / Chang, Ruey-Feng; Chen, Hong-Hao; Chang, Yeun-Chung; Huang, Chiun-Sheng; Chen, Jeon-Hor; Lo, Chung Ming.

In: Magnetic Resonance Imaging, Vol. 34, No. 6, 01.07.2016, p. 809-819.

Research output: Contribution to journalArticle

Chang, Ruey-Feng ; Chen, Hong-Hao ; Chang, Yeun-Chung ; Huang, Chiun-Sheng ; Chen, Jeon-Hor ; Lo, Chung Ming. / Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI. In: Magnetic Resonance Imaging. 2016 ; Vol. 34, No. 6. pp. 809-819.
@article{618fd234f56142588b1f6f8783577c0e,
title = "Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI",
abstract = "Purpose: Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods: A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The proposed region-based features achieved the accuracy of 73.53{\%}, 82.35{\%}, and 77.45{\%} for ER, HER2, and TNBC classifications. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. Conclusion: The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.",
keywords = "Breast Cancer, Computer-aided diagnosis, DCE-MRI, Molecular marker",
author = "Ruey-Feng Chang and Hong-Hao Chen and Yeun-Chung Chang and Chiun-Sheng Huang and Jeon-Hor Chen and Lo, {Chung Ming}",
year = "2016",
month = "7",
day = "1",
doi = "10.1016/j.mri.2016.03.001",
language = "English",
volume = "34",
pages = "809--819",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",
number = "6",

}

TY - JOUR

T1 - Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI

AU - Chang, Ruey-Feng

AU - Chen, Hong-Hao

AU - Chang, Yeun-Chung

AU - Huang, Chiun-Sheng

AU - Chen, Jeon-Hor

AU - Lo, Chung Ming

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Purpose: Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods: A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The proposed region-based features achieved the accuracy of 73.53%, 82.35%, and 77.45% for ER, HER2, and TNBC classifications. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. Conclusion: The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.

AB - Purpose: Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Materials and methods: A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic (ROC) curve analysis. Results: The proposed region-based features achieved the accuracy of 73.53%, 82.35%, and 77.45% for ER, HER2, and TNBC classifications. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. Conclusion: The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.

KW - Breast Cancer

KW - Computer-aided diagnosis

KW - DCE-MRI

KW - Molecular marker

UR - http://www.scopus.com/inward/record.url?scp=84962920201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962920201&partnerID=8YFLogxK

U2 - 10.1016/j.mri.2016.03.001

DO - 10.1016/j.mri.2016.03.001

M3 - Article

C2 - 26968141

AN - SCOPUS:84962920201

VL - 34

SP - 809

EP - 819

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

IS - 6

ER -