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

• Published in: Medical image analysis 2017-05, Vol.38, p.104-116
• Main Authors: Wan, Sunhua, Lee, Hsiang-Chieh, Huang, Xiaolei, Xu, Ting, Xu, Tao, Zeng, Xianxu, Zhang, Zhan, Sheikine, Yuri, Connolly, James L., Fujimoto, James G., Zhou, Chao
• Format: Article
• Language: English
• Subjects: Adipose tissue; Algorithms; Benign; Breast; Breast - diagnostic imaging; Breast cancer; Breast carcinoma; Breast Neoplasms - diagnostic imaging; Classification; Coherence; Computer applications; Computing time; Experiments; Female; Fibroadenoma; Ground truth; Histology; Humans; Hyperplasia; Image acquisition; Image analysis; Image classification; Image detection; Image processing; Image Processing, Computer-Assisted - methods; Image resolution; Invasiveness; Local binary patterns; Microscopy; Microscopy, Confocal - methods; Neural networks; Optical coherence microscopy; Pattern Recognition, Automated - methods; Pixels; Reproducibility of Results; ROC Curve; Sensitivity and Specificity; Stroma; Texture; Texture features; Tissue classification; Tissues; Tomography, Optical Coherence - methods
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2017.03.002

•Texture analysis is applied on OCM images for human breast tissue classification.•New variants of local binary pattern (LBP) are proposed to extract texture features.•Using multi-scale and integrated image features improves classification accuracy.•Achieved high sensitivity (100%) and specificity (85.2%) for cancer detection. [Display omitted] 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 l