Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy

Sunhua Wan, Hsiang Chieh Lee, Sharon Xiaolei Huang, Ting Xu, Tao Xu, Xianxu Zeng, Zhan Zhang, Yuri Sheikine, James L. Connolly, James G. Fujimoto, Chao Zhou

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

This paper proposes a texture analysis technique that can effectively classify different types of human breast tissue imaged by Optical Coherence Microscopy (OCM). OCM is an emerging imaging modality for rapid tissue screening and has the potential to provide high resolution microscopic images that approach those of histology. OCM images, acquired without tissue staining, however, pose unique challenges to image analysis and pattern classification. We examined multiple types of texture features and found Local Binary Pattern (LBP) features to perform better in classifying tissues imaged by OCM. In order to improve classification accuracy, we propose novel variants of LBP features, namely average LBP (ALBP) and block based LBP (BLBP). Compared with the classic LBP feature, ALBP and BLBP features provide an enhanced encoding of the texture structure in a local neighborhood by looking at intensity differences among neighboring pixels and among certain blocks of pixels in the neighborhood. Fourty-six freshly excised human breast tissue samples, including 27 benign (e.g. fibroadenoma, fibrocystic disease and usual ductal hyperplasia) and 19 breast carcinoma (e.g. invasive ductal carcinoma, ductal carcinoma in situ and lobular carcinoma in situ) were imaged with large field OCM with an imaging area of 10 × 10 mm2 (10, 000 × 10, 000 pixels) for each sample. Corresponding H&E histology was obtained for each sample and used to provide ground truth diagnosis. 4310 small OCM image blocks (500 × 500 pixels) each paired with corresponding H&E histology was extracted from large-field OCM images and labeled with one of the five different classes: adipose tissue (n = 347), fibrous stroma (n = 2,065), breast lobules (n = 199), carcinomas (pooled from all sub-types, n = 1,127), and background (regions outside of the specimens, n = 572). Our experiments show that by integrating a selected set of LBP and the two new variant (ALBP and BLBP) features at multiple scales, the classification accuracy increased from 81.7% (using LBP features alone) to 93.8% using a neural network classifier. The integrated feature was also used to classify large-field OCM images for tumor detection. A receiver operating characteristic (ROC) curve was obtained with an area under the curve value of 0.959. A sensitivity level of 100% and specificity level of 85.2% was achieved to differentiate benign from malignant samples. Several other experiments also demonstrate the complementary nature of LBP and the two variants (ALBP and BLBP features) and the significance of integrating these texture features for classification. Using features from multiple scales and performing feature selection are also effective mechanisms to improve accuracy while maintaining computational efficiency.

Original languageEnglish (US)
Pages (from-to)104-116
Number of pages13
JournalMedical Image Analysis
Volume38
DOIs
StatePublished - May 1 2017

Fingerprint

Microscopy
Microscopic examination
Breast
Textures
Tissue
Histology
Pixels
Imaging techniques
Fibroadenoma
Ductal Carcinoma
Carcinoma, Intraductal, Noninfiltrating
Computational efficiency
ROC Curve
Image analysis
Pattern recognition
Area Under Curve
Hyperplasia
Adipose Tissue
Feature extraction
Tumors

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Wan, Sunhua ; Lee, Hsiang Chieh ; Huang, Sharon Xiaolei ; Xu, Ting ; Xu, Tao ; Zeng, Xianxu ; Zhang, Zhan ; Sheikine, Yuri ; Connolly, James L. ; Fujimoto, James G. ; Zhou, Chao. / Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy. In: Medical Image Analysis. 2017 ; Vol. 38. pp. 104-116.
@article{a91fd8ccbd044a31886ff9d0749741aa,
title = "Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy",
abstract = "This paper proposes a texture analysis technique that can effectively classify different types of human breast tissue imaged by Optical Coherence Microscopy (OCM). OCM is an emerging imaging modality for rapid tissue screening and has the potential to provide high resolution microscopic images that approach those of histology. OCM images, acquired without tissue staining, however, pose unique challenges to image analysis and pattern classification. We examined multiple types of texture features and found Local Binary Pattern (LBP) features to perform better in classifying tissues imaged by OCM. In order to improve classification accuracy, we propose novel variants of LBP features, namely average LBP (ALBP) and block based LBP (BLBP). Compared with the classic LBP feature, ALBP and BLBP features provide an enhanced encoding of the texture structure in a local neighborhood by looking at intensity differences among neighboring pixels and among certain blocks of pixels in the neighborhood. Fourty-six freshly excised human breast tissue samples, including 27 benign (e.g. fibroadenoma, fibrocystic disease and usual ductal hyperplasia) and 19 breast carcinoma (e.g. invasive ductal carcinoma, ductal carcinoma in situ and lobular carcinoma in situ) were imaged with large field OCM with an imaging area of 10 × 10 mm2 (10, 000 × 10, 000 pixels) for each sample. Corresponding H&E histology was obtained for each sample and used to provide ground truth diagnosis. 4310 small OCM image blocks (500 × 500 pixels) each paired with corresponding H&E histology was extracted from large-field OCM images and labeled with one of the five different classes: adipose tissue (n = 347), fibrous stroma (n = 2,065), breast lobules (n = 199), carcinomas (pooled from all sub-types, n = 1,127), and background (regions outside of the specimens, n = 572). Our experiments show that by integrating a selected set of LBP and the two new variant (ALBP and BLBP) features at multiple scales, the classification accuracy increased from 81.7{\%} (using LBP features alone) to 93.8{\%} using a neural network classifier. The integrated feature was also used to classify large-field OCM images for tumor detection. A receiver operating characteristic (ROC) curve was obtained with an area under the curve value of 0.959. A sensitivity level of 100{\%} and specificity level of 85.2{\%} was achieved to differentiate benign from malignant samples. Several other experiments also demonstrate the complementary nature of LBP and the two variants (ALBP and BLBP features) and the significance of integrating these texture features for classification. Using features from multiple scales and performing feature selection are also effective mechanisms to improve accuracy while maintaining computational efficiency.",
author = "Sunhua Wan and Lee, {Hsiang Chieh} and Huang, {Sharon Xiaolei} and Ting Xu and Tao Xu and Xianxu Zeng and Zhan Zhang and Yuri Sheikine and Connolly, {James L.} and Fujimoto, {James G.} and Chao Zhou",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.media.2017.03.002",
language = "English (US)",
volume = "38",
pages = "104--116",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

Wan, S, Lee, HC, Huang, SX, Xu, T, Xu, T, Zeng, X, Zhang, Z, Sheikine, Y, Connolly, JL, Fujimoto, JG & Zhou, C 2017, 'Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy', Medical Image Analysis, vol. 38, pp. 104-116. https://doi.org/10.1016/j.media.2017.03.002

Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy. / Wan, Sunhua; Lee, Hsiang Chieh; Huang, Sharon Xiaolei; Xu, Ting; Xu, Tao; Zeng, Xianxu; Zhang, Zhan; Sheikine, Yuri; Connolly, James L.; Fujimoto, James G.; Zhou, Chao.

In: Medical Image Analysis, Vol. 38, 01.05.2017, p. 104-116.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy

AU - Wan, Sunhua

AU - Lee, Hsiang Chieh

AU - Huang, Sharon Xiaolei

AU - Xu, Ting

AU - Xu, Tao

AU - Zeng, Xianxu

AU - Zhang, Zhan

AU - Sheikine, Yuri

AU - Connolly, James L.

AU - Fujimoto, James G.

AU - Zhou, Chao

PY - 2017/5/1

Y1 - 2017/5/1

N2 - This paper proposes a texture analysis technique that can effectively classify different types of human breast tissue imaged by Optical Coherence Microscopy (OCM). OCM is an emerging imaging modality for rapid tissue screening and has the potential to provide high resolution microscopic images that approach those of histology. OCM images, acquired without tissue staining, however, pose unique challenges to image analysis and pattern classification. We examined multiple types of texture features and found Local Binary Pattern (LBP) features to perform better in classifying tissues imaged by OCM. In order to improve classification accuracy, we propose novel variants of LBP features, namely average LBP (ALBP) and block based LBP (BLBP). Compared with the classic LBP feature, ALBP and BLBP features provide an enhanced encoding of the texture structure in a local neighborhood by looking at intensity differences among neighboring pixels and among certain blocks of pixels in the neighborhood. Fourty-six freshly excised human breast tissue samples, including 27 benign (e.g. fibroadenoma, fibrocystic disease and usual ductal hyperplasia) and 19 breast carcinoma (e.g. invasive ductal carcinoma, ductal carcinoma in situ and lobular carcinoma in situ) were imaged with large field OCM with an imaging area of 10 × 10 mm2 (10, 000 × 10, 000 pixels) for each sample. Corresponding H&E histology was obtained for each sample and used to provide ground truth diagnosis. 4310 small OCM image blocks (500 × 500 pixels) each paired with corresponding H&E histology was extracted from large-field OCM images and labeled with one of the five different classes: adipose tissue (n = 347), fibrous stroma (n = 2,065), breast lobules (n = 199), carcinomas (pooled from all sub-types, n = 1,127), and background (regions outside of the specimens, n = 572). Our experiments show that by integrating a selected set of LBP and the two new variant (ALBP and BLBP) features at multiple scales, the classification accuracy increased from 81.7% (using LBP features alone) to 93.8% using a neural network classifier. The integrated feature was also used to classify large-field OCM images for tumor detection. A receiver operating characteristic (ROC) curve was obtained with an area under the curve value of 0.959. A sensitivity level of 100% and specificity level of 85.2% was achieved to differentiate benign from malignant samples. Several other experiments also demonstrate the complementary nature of LBP and the two variants (ALBP and BLBP features) and the significance of integrating these texture features for classification. Using features from multiple scales and performing feature selection are also effective mechanisms to improve accuracy while maintaining computational efficiency.

AB - This paper proposes a texture analysis technique that can effectively classify different types of human breast tissue imaged by Optical Coherence Microscopy (OCM). OCM is an emerging imaging modality for rapid tissue screening and has the potential to provide high resolution microscopic images that approach those of histology. OCM images, acquired without tissue staining, however, pose unique challenges to image analysis and pattern classification. We examined multiple types of texture features and found Local Binary Pattern (LBP) features to perform better in classifying tissues imaged by OCM. In order to improve classification accuracy, we propose novel variants of LBP features, namely average LBP (ALBP) and block based LBP (BLBP). Compared with the classic LBP feature, ALBP and BLBP features provide an enhanced encoding of the texture structure in a local neighborhood by looking at intensity differences among neighboring pixels and among certain blocks of pixels in the neighborhood. Fourty-six freshly excised human breast tissue samples, including 27 benign (e.g. fibroadenoma, fibrocystic disease and usual ductal hyperplasia) and 19 breast carcinoma (e.g. invasive ductal carcinoma, ductal carcinoma in situ and lobular carcinoma in situ) were imaged with large field OCM with an imaging area of 10 × 10 mm2 (10, 000 × 10, 000 pixels) for each sample. Corresponding H&E histology was obtained for each sample and used to provide ground truth diagnosis. 4310 small OCM image blocks (500 × 500 pixels) each paired with corresponding H&E histology was extracted from large-field OCM images and labeled with one of the five different classes: adipose tissue (n = 347), fibrous stroma (n = 2,065), breast lobules (n = 199), carcinomas (pooled from all sub-types, n = 1,127), and background (regions outside of the specimens, n = 572). Our experiments show that by integrating a selected set of LBP and the two new variant (ALBP and BLBP) features at multiple scales, the classification accuracy increased from 81.7% (using LBP features alone) to 93.8% using a neural network classifier. The integrated feature was also used to classify large-field OCM images for tumor detection. A receiver operating characteristic (ROC) curve was obtained with an area under the curve value of 0.959. A sensitivity level of 100% and specificity level of 85.2% was achieved to differentiate benign from malignant samples. Several other experiments also demonstrate the complementary nature of LBP and the two variants (ALBP and BLBP features) and the significance of integrating these texture features for classification. Using features from multiple scales and performing feature selection are also effective mechanisms to improve accuracy while maintaining computational efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85015608468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015608468&partnerID=8YFLogxK

U2 - 10.1016/j.media.2017.03.002

DO - 10.1016/j.media.2017.03.002

M3 - Article

C2 - 28327449

AN - SCOPUS:85015608468

VL - 38

SP - 104

EP - 116

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -