Integrated Local Binary Pattern Texture Features for Classificationof Breast Tissue Imaged by Optical Coherence Microscopy

摘要

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 areaof 10×10mm²(10, 000 × 10,000 pixels) for each sample. Corresponding H&E histology was obtained foreach sample and used to provide ground truth diagnosis. 4310 small OCM imageblocks (500 × 500 pixels) each paired withcorresponding H&E histology was extracted from large-field OCM images andlabeled 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 thatby integrating a selected set of LBP and the two new variant (ALBP and BLBP)features at multiple scales, the classification accuracy increased from81.7% (using LBP features alone) to 93.8% using a neural networkclassifier. The integrated feature was also used to classify large-field OCMimages for tumor detection. A receiver operating characteristic (ROC) curve wasobtained with an area under the curve value of 0.959. A sensitivity level of100% and specificity level of 85.2% was achieved todifferentiate benign from malignant samples. Several other experiments alsodemonstrate the complementary nature of LBP and the two variants (ALBP and BLBPfeatures) and the significance of integrating these texture features forclassification. Using features from multiple scales and performing featureselection are also effective mechanisms to improve accuracy while maintainingcomputational efficiency.