The evaluation of breast cancer grades in immunohistochemistry (IHC) slides takes into account various types of visual markers and morphological features of stained membrane regions. Digital pathology algorithms using...
详细信息
The evaluation of breast cancer grades in immunohistochemistry (IHC) slides takes into account various types of visual markers and morphological features of stained membrane regions. Digital pathology algorithms using whole slide images (WSIs) of histology slides have recently been finding several applications in such computer-assisted evaluations. Features that are directly related to biomarkers used by pathologists are generally preferred over the pixel values of entire images, even though the latter has more information content. This paper explores in detail various types of feature measurements that are suitable for the automated scoring of human epidermal growth factor receptor 2 (HER2) in histology slides. These are intensity features known as characteristic curves, texture features in the form of uniform local binary patterns (ULBPs), morphological features specifying connectivity of regions, and first-order statistical features of the overall intensity distribution. This paper considers important properties of the above features and outlines methods for reducing information redundancy, maximizing inter-class separability, and improving classification accuracy in the combined feature set. This paper also presents a detailed experimental analysis performed using the aforementioned features on a WSI dataset of IHC stained slides.
Whole slide images (WSI) of histology slides are increasingly being used for computer assisted evaluations, automated grading and classification. In this rapidly evolving research field, several classification algorit...
详细信息
ISBN:
(纸本)9783319959214;9783319959207
Whole slide images (WSI) of histology slides are increasingly being used for computer assisted evaluations, automated grading and classification. In this rapidly evolving research field, several classification algorithms and feature descriptors have been reported for histopathological analysis. While some algorithms use pixel values of entire images as features, other methods try to use specific biomarker related features. This paper analyses in detail feature descriptors that have been found to be efficient in classifying ImmunoHistoChemistry (IHC) stained slides. These features are directly related to the Human Epidermal Growth Factor Receptor 2 (HER2) biomarkers that are commonly used for grading such slides. Characteristic curves are intensity features that encode information about the variation of the percentage of stained membrane regions with saturation levels. The uniform local binary patterns (ULBP) are texture features extracted from stained regions. ULBP contains several components and generates a high dimensional feature vector that needs to be compressed. Fisher Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) are used to select feature components important in classification. The paper proposes a method to combine different types of features (e.g., intensity and texture) after dimensionality reduction, and to improve classification accuracy by maximizing inter-class separability. The paper also discusses methods to visualize class-wise distribution of the computed feature vectors. Experimental analysis performed using a WSI dataset of IHC stained slides and aforementioned features are also presented.
In this paper, we present a method to face recognition which considers local shape information, weight of interesting region and texture information by Gabor filter, high-pass filter and localbinarypatterns, respect...
详细信息
ISBN:
(纸本)9781467322478
In this paper, we present a method to face recognition which considers local shape information, weight of interesting region and texture information by Gabor filter, high-pass filter and localbinarypatterns, respectively. The face area can be largely divided into two dominant parts that one has high frequency domain and the other has low frequency domain. High frequency parts are interesting region which is edge of face shape, eye, nose, mouth and so on. Low frequency parts are forehead, cheek, and background beside face in the image. Then, the face image is divided into 6×5 small bins which represents a weight of the interesting region. Weight of interesting region is adopted for weighting of distance measure. Gabor filter can be easily extract shape features in face image. localbinarypatterns are robust to various illumination conditions while Gabor transform is not. Therefore, we combined two features for robust features on various illuminations. For evaluating the illumination robustness of our face recognition system, we used the publicly available database POSTECH face 2007. Finally, we got 91.15% recognition rate by sixteen orientation of Gabor parameter + LBP + average Gaussian high-pass filter.
暂无评论