2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution

Monika Béresová, Andrés Larroza, Estanislao Arana, J. Varga, L. Balkay, David Moratal

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objective: To find structural differences between brain metastases of lung and breast cancer, computing their heterogeneity parameters by means of both 2D and 3D texture analysis (TA). Materials and methods: Patients with 58 brain metastases from breast (26) and lung cancer (32) were examined by MR imaging. Brain lesions were manually delineated by 2D ROIs on the slices of contrast-enhanced T1-weighted (CET1) images, and local binary patterns (LBP) maps were created from each region. Histogram-based (minimum, maximum, mean, standard deviation, and variance), and co-occurrence matrix-based (contrast, correlation, energy, entropy, and homogeneity) 2D, weighted average of the 2D slices, and true 3D TA were obtained on the CET1 images and LBP maps. Results: For LBP maps and 2D TA contrast, correlation, energy, and homogeneity were identified as statistically different heterogeneity parameters (SDHPs) between lung and breast metastasis. The weighted 3D TA identified entropy as an additional SDHP. Only two texture indexes (TI) were significantly different with true 3D TA: entropy and energy. All these TIs discriminated between the two tumor types significantly by ROC analysis. For the CET1 images there was no SDHP at all by 3D TA. Conclusion: Our results indicate that the used textural analysis methods may help with discriminating between brain metastases of different primary tumors.

Original languageEnglish
Pages (from-to)285-294
Number of pages10
JournalMagnetic Resonance Materials in Physics, Biology and Medicine
Volume31
Issue number2
DOIs
Publication statusPublished - Apr 1 2018

Fingerprint

Entropy
Neoplasm Metastasis
Brain
Lung Neoplasms
Breast Neoplasms
ROC Curve
Neoplasms
Breast
Lung

Keywords

  • Brain neoplasms
  • Breast cancer
  • Computer-assisted
  • Image processing
  • Lung cancer
  • Magnetic resonance imaging
  • Metastasis
  • Texture analysis

ASJC Scopus subject areas

  • Biophysics
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

2D and 3D texture analysis to differentiate brain metastases on MR images : proceed with caution. / Béresová, Monika; Larroza, Andrés; Arana, Estanislao; Varga, J.; Balkay, L.; Moratal, David.

In: Magnetic Resonance Materials in Physics, Biology and Medicine, Vol. 31, No. 2, 01.04.2018, p. 285-294.

Research output: Contribution to journalArticle

@article{1bc290b4d10f4ee9b00b55d6796d5b33,
title = "2D and 3D texture analysis to differentiate brain metastases on MR images: proceed with caution",
abstract = "Objective: To find structural differences between brain metastases of lung and breast cancer, computing their heterogeneity parameters by means of both 2D and 3D texture analysis (TA). Materials and methods: Patients with 58 brain metastases from breast (26) and lung cancer (32) were examined by MR imaging. Brain lesions were manually delineated by 2D ROIs on the slices of contrast-enhanced T1-weighted (CET1) images, and local binary patterns (LBP) maps were created from each region. Histogram-based (minimum, maximum, mean, standard deviation, and variance), and co-occurrence matrix-based (contrast, correlation, energy, entropy, and homogeneity) 2D, weighted average of the 2D slices, and true 3D TA were obtained on the CET1 images and LBP maps. Results: For LBP maps and 2D TA contrast, correlation, energy, and homogeneity were identified as statistically different heterogeneity parameters (SDHPs) between lung and breast metastasis. The weighted 3D TA identified entropy as an additional SDHP. Only two texture indexes (TI) were significantly different with true 3D TA: entropy and energy. All these TIs discriminated between the two tumor types significantly by ROC analysis. For the CET1 images there was no SDHP at all by 3D TA. Conclusion: Our results indicate that the used textural analysis methods may help with discriminating between brain metastases of different primary tumors.",
keywords = "Brain neoplasms, Breast cancer, Computer-assisted, Image processing, Lung cancer, Magnetic resonance imaging, Metastasis, Texture analysis",
author = "Monika B{\'e}resov{\'a} and Andr{\'e}s Larroza and Estanislao Arana and J. Varga and L. Balkay and David Moratal",
year = "2018",
month = "4",
day = "1",
doi = "10.1007/s10334-017-0653-9",
language = "English",
volume = "31",
pages = "285--294",
journal = "Magnetic Resonance Materials in Physics, Biology, and Medicine",
issn = "0968-5243",
publisher = "Springer Verlag",
number = "2",

}

TY - JOUR

T1 - 2D and 3D texture analysis to differentiate brain metastases on MR images

T2 - proceed with caution

AU - Béresová, Monika

AU - Larroza, Andrés

AU - Arana, Estanislao

AU - Varga, J.

AU - Balkay, L.

AU - Moratal, David

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Objective: To find structural differences between brain metastases of lung and breast cancer, computing their heterogeneity parameters by means of both 2D and 3D texture analysis (TA). Materials and methods: Patients with 58 brain metastases from breast (26) and lung cancer (32) were examined by MR imaging. Brain lesions were manually delineated by 2D ROIs on the slices of contrast-enhanced T1-weighted (CET1) images, and local binary patterns (LBP) maps were created from each region. Histogram-based (minimum, maximum, mean, standard deviation, and variance), and co-occurrence matrix-based (contrast, correlation, energy, entropy, and homogeneity) 2D, weighted average of the 2D slices, and true 3D TA were obtained on the CET1 images and LBP maps. Results: For LBP maps and 2D TA contrast, correlation, energy, and homogeneity were identified as statistically different heterogeneity parameters (SDHPs) between lung and breast metastasis. The weighted 3D TA identified entropy as an additional SDHP. Only two texture indexes (TI) were significantly different with true 3D TA: entropy and energy. All these TIs discriminated between the two tumor types significantly by ROC analysis. For the CET1 images there was no SDHP at all by 3D TA. Conclusion: Our results indicate that the used textural analysis methods may help with discriminating between brain metastases of different primary tumors.

AB - Objective: To find structural differences between brain metastases of lung and breast cancer, computing their heterogeneity parameters by means of both 2D and 3D texture analysis (TA). Materials and methods: Patients with 58 brain metastases from breast (26) and lung cancer (32) were examined by MR imaging. Brain lesions were manually delineated by 2D ROIs on the slices of contrast-enhanced T1-weighted (CET1) images, and local binary patterns (LBP) maps were created from each region. Histogram-based (minimum, maximum, mean, standard deviation, and variance), and co-occurrence matrix-based (contrast, correlation, energy, entropy, and homogeneity) 2D, weighted average of the 2D slices, and true 3D TA were obtained on the CET1 images and LBP maps. Results: For LBP maps and 2D TA contrast, correlation, energy, and homogeneity were identified as statistically different heterogeneity parameters (SDHPs) between lung and breast metastasis. The weighted 3D TA identified entropy as an additional SDHP. Only two texture indexes (TI) were significantly different with true 3D TA: entropy and energy. All these TIs discriminated between the two tumor types significantly by ROC analysis. For the CET1 images there was no SDHP at all by 3D TA. Conclusion: Our results indicate that the used textural analysis methods may help with discriminating between brain metastases of different primary tumors.

KW - Brain neoplasms

KW - Breast cancer

KW - Computer-assisted

KW - Image processing

KW - Lung cancer

KW - Magnetic resonance imaging

KW - Metastasis

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=85029748501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029748501&partnerID=8YFLogxK

U2 - 10.1007/s10334-017-0653-9

DO - 10.1007/s10334-017-0653-9

M3 - Article

C2 - 28939952

AN - SCOPUS:85029748501

VL - 31

SP - 285

EP - 294

JO - Magnetic Resonance Materials in Physics, Biology, and Medicine

JF - Magnetic Resonance Materials in Physics, Biology, and Medicine

SN - 0968-5243

IS - 2

ER -