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 10×10mm2 (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.
There are various kinds of birds in the Qinghai Lake National Nature Reserve. In recent years, avian influenza breaks out in this region for several times. The biologists need to identify the species of birds after the discovery of infected birds. They can classify the birds according to the appearance by experience; or they can identify the birds according to the gene collected from the birds. But these two methods all lack of precision. This paper comes up with a method that integrates these two methods.
This paper proposes a texture analysis technique applied on human breast Optical Coherence Microscopy (OCM) images to classify different types of breast tissues. Local binary pattern (LBP) image features are extracted. In order to improve classification precision, a new variant of LBP feature, average LBP (ALBP) is proposed. The new LBP is integrated with the original LBP feature to improve classification precision. Our experiments show that by integrating a selected set of LBP and ALBP features, very high classification accuracy is achieved using a AdaBoost meta classifier combined with neural network weak classifiers.Index Terms-Image analysis, texture analysis, Local binary pattern, Optical coherence microscopy (OCM), tissue classification 1. INTRODUCTION Breast cancer is a high incidence cancer in women worldwide. The survival rate of breast cancer improves with screening and early detection [1]. A biopsy is a frequently used medical test in which tissue samples are removed from a human subject and then examined by a pathologist under a microscope to determine the presence or extent of a disease. Traditionally, the tissue is processed to extremely thin slices and stained before being observed under a microscope. Optical coherence tomography (OCT) provides an alternative non-invasive optical imaging modality that can provide 3D, high-resolution images of biopsy sample tissues without staining [2]. Optical coherence microscopy (OCM) combines the advantages of OCT and confocal microscopy using high numerical aperture objectives to provide cellular resolution images [3]. Tissue classification based on OCM images can be used to help diagnose breast cancer [4]. To improve accuracy and efficiency, computer algorithms for automated classification of tissue areas in medical images have been proposed [5]; in these works, image processing and data mining techniques are applied on large number of medical images to distinguish different patterns of tissues.In this work, we propose a breast tissue classification and abnormality detection technique based on texture analysis of Ex vivo breast specimen imaged using an OCM system. Figure 1 shows example OCM images of human breast tissue. Our proposed classification process consists of two steps: training and testing. In the training process, a series of LBP features which represent image textures are extracted from OCM images. Variants of LBP have been proposed to improve the performance in certain applications. Guo et al. proposed a complete model of LBP which takes into consideration the magnitude of grayscale difference between the neighbors and the center pixel [6]; Tan et al. proposed an enhanced LBP feature which uses three states to describe the similarity of intensity values for the purpose of face recognition [7]; Wang et al. proposed to use integrated HOG and LBP features to handle partial occlusion in human detections [8].In this work, we propose a new variant of LBP, the average LBP (ALBP), for texture analysis in OCM images. In LBP, the grayscale values of a certa...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.