Histopathological Tissue Images Research Articles

Proposal of SVM Utility Kernel for Breast Cancer Survival Estimation.

The advancement of medical research in the field of cancer prognosis and diagnosis using various modalities has put oncologists under tremendous stress. The complexity and heterogeneity involved in multiple modalities and their significantly varied clinical outcomes make it difficult to analyze the disease and provide the correct treatment. Breast cancer is the major concern among all cancers worldwide, specifically for females. To help oncologists and cancer patients, research for breast cancer survival estimation has been proposed. It ranges from complex deep neural networks to simple and interpretable architectures. We propose a utility kernel for a support vector machine (SVM) in this article. It is a simple yet powerful function, which performs better than other popular machine learning algorithms and deep neural networks in the task of breast cancer survival prediction using the TCGA-BRCA dataset. This study validates the proposed utility kernel using four different modalities (gene expression, copy number variation, clinical, and histopathological tissue images) and their multi-modal combinations. The SVM based on our utility kernel empirically proves its efficacy by achieving the highest value on various performance measures, whereas advanced deep neural networks fail to train on small and highly imbalanced breast cancer data.

FAST INTERACTIVE REGIONAL PATTERN MERGING FOR GENERIC TISSUE SEGMENTATION IN HISTOPATHOLOGY IMAGES

The image segmentation of histopathological tissue images has always been a challenge due to the overlapping of tissue color distributions, the complexity of extracellular texture and the large image size. In this paper, we introduce a new region-merging algorithm, namely, the Regional Pattern Merging (RPM) for interactive color image segmentation and annotation, by efficiently retrieving and applying the user’s prior knowledge of stroke-based interaction. Low-level color/texture features of each region are used to compose a regional pattern adapted to differentiating a foreground object from the background scene. This iterative region-merging is based on a modified Region Adjacency Graph (RAG) model built from initial segmented results of the mean shift to speed up the merging process. The foreground region of interest (ROI) is segmented by the reduction of the background region and discrimination of uncertain regions. We then compare our method against state-of-the-art interactive image segmentation algorithms in both natural images and histological images. Taking into account the homogeneity of both color and texture, the resulting semi-supervised classification and interactive segmentation capture histological structures more completely than other intensity or color-based methods. Experimental results show that the merging of the RAG model runs in a linear time according to the number of graph edges, which is essentially faster than both traditional graph-based and region-based methods.

A Novel Probabilistic Nuclei Segmentation Algorithm for H&E Stained Histopathological Tissue Images

In this study, we propose a novel, fast and accurate segmentation algorithm to segment nuclei in H&E stained histopathological tissue images. The proposed algorithm doesn’t require pre-processing, post-processing, and any manual parameter or threshold. The algorithm utilizes probabilistic and statistical properties of the pixels’ color value in the images with RGB color, and determines whether pixels are a part of any nuclei or not by using an automatically calculated threshold value. The algorithm provides time efficiency and reduced overall cost in the segmentation. The other contributions of the study are false positive removal algorithm and automatically determination of nuclei cluster for K-means. In order to compare and evaluate the performance of the proposed algorithm in terms of time and cost efficiency, K-Means is preferred because of its common usage. Expert evaluation is declared as ground truth for determining the accuracy of the results. The experiments are performed on 60 healthy and 60 damaged kidney, and 60 healthy and 60 damaged liver tissue images. The evaluations are revealed that the proposed algorithm can effectively segment nuclei. The comparison results also demonstrate that the deviation between proposed algorithm and the expert is 2%, while the deviation between K-Means and Expert is 5%.

An Optimum Feature Selection Technique using Jaya Algorithm for Histopathology Tissue Image Classification

As a consequence of presence of complicated environment and composite architecture, analysis of histopathological tissue images is a challenging task. Relevant features are selected in the classification stage. Irrelevant and redundant features in results in elevated computational cost and poor performance. To achieve the salient set of features against the features that are extracted, in this paper, an advanced optimum method for selection of the features for classification of histopathology tissue image using Jaya algorithm has been exhibited. To do likewise, a previously instructed AlexNet has been utilized because of the differentiating performance in image classification. Additionally, execution of four distinct classifier have been tested for the features selected in reference of segregating the histopathological tissue images within four classifications especially; connective tissue, nervous tissue, muscular tissue and epithelium tissue. Exploratory outcomes approve that the proposed optimum feature selection method for classification of histopathology tissue image by applying jaya algorithm accomplishes better optimal values on CEC2015 functions along with accomplishing high classification performance when contrasted with the other feature selection methods.

Histopathological image classification using enhanced bag-of-feature with spiral biogeography-based optimization

An exponential growth of histopathological digital images over the Internet requires an efficient method for organizing them properly for better retrieval and analysis process. For the same, an automatic histopathological image classification system can be useful. Moreover, such classification system may also be used to identify the inflamed and healthy tissues from tissue image datasets. However, complex background structures and heterogeneity among histopathological tissue images make it a complicated process. Therefore, this paper introduces an innovative method for categorization of histopathological images using an enhanced bag-of-feature framework. To obtain the optimal visual words in bag-of-features, a new spiral biogeography-based optimization algorithm has been proposed which introduces a spiral search and random search in the mutation operator to generate the suitability index variables. The efficacy of the spiral biogeography-based optimization algorithm has been tested on CEC 2017 benchmarks problems. Moreover, the applicability of the proposed classification method has been observed on two histopathological image datasets, Blue Histology image dataset and ADL Histopathological image dataset. The efficacy of the spiral biogeography-based optimization algorithm based bag-of-features method has been analyzed and compared with other state-of-the-art methods with respect to average accuracy, recall, precision, and F1-measure parameters.

An optimal feature selection method for histopathology tissue image classification using adaptive jaya algorithm

Due to the complex background and heterogeneous structure, classification of histopathological tissue images is a challenging problem. Further, the selection of appropriate features is an important phase of classification process as irrelevant and redundant features may result in high computation and degrade the performance. Therefore, a new adaptive jaya algorithm has been introduced in this paper which is used to obtain the prominent feature set from the extracted features. The proposed adaptive jaya algorithm modifies the updation equation using the best and the worst solutions. For the feature extraction, a pre-trained AlexNet has been used due to its distinguishing performance in the image classification. Moreover, the performance of five different classifiers have been analyzed over the selected features in context of classifying the histopathological tissue images into four categories, namely epithelium tissue, nervous tissue, connective tissue, and muscular tissue. Experimental results validate that the proposed adaptive jaya algorithm attains better optimal values on CEC2015 functions. The proposed method eliminates 91.3% features from the extracted features which is maximum among other considered methods and also achieves high classification accuracy.

Unsupervised Feature Extraction via Deep Learning for Histopathological Classification of Colon Tissue Images

Histopathological examination is today's gold standard for cancer diagnosis. However, this task is time consuming and prone to errors as it requires a detailed visual inspection and interpretation of a pathologist. Digital pathology aims at alleviating these problems by providing computerized methods that quantitatively analyze digitized histopathological tissue images. The performance of these methods mainly relies on the features that they use, and thus, their success strictly depends on the ability of these features by successfully quantifying the histopathology domain. With this motivation, this paper presents a new unsupervised feature extractor for effective representation and classification of histopathological tissue images. This feature extractor has three main contributions: First, it proposes to identify salient subregions in an image, based on domain-specific prior knowledge, and to quantify the image by employing only the characteristics of these subregions instead of considering the characteristics of all image locations. Second, it introduces a new deep learning-based technique that quantizes the salient subregions by extracting a set of features directly learned on image data and uses the distribution of these quantizations for image representation and classification. To this end, the proposed deep learning-based technique constructs a deep belief network of the restricted Boltzmann machines (RBMs), defines the activation values of the hidden unit nodes in the final RBM as the features, and learns the quantizations by clustering these features in an unsupervised way. Third, this extractor is the first example for successfully using the restricted Boltzmann machines in the domain of histopathological image analysis. Our experiments on microscopic colon tissue images reveal that the proposed feature extractor is effective to obtain more accurate classification results compared to its counterparts.

A Study on Nuclei Segmentation, Feature Extraction and Disease Stage Classification for Human Brain Histopathological Images

Computer aided diagnosis (CAD) systems are important in obtaining precision medicine and patient driven solutions for various diseases. One of the main brain tumor is the Glioblastoma multiforme (GBM) and histopathological tissue images can provide unique insights into identifying and grading disease stages. In this study, we consider nuclei segmentation method, feature extraction and disease stage classification for brain tumor histopathological images using automatic image analysis methods. In particular we utilized automatic nuclei segmentation and labeling for histopathology image data obtained from The Cancer Genome Atlas (TCGA) and check for significance of feature descriptors using K-S test and classification accuracy using support vector machine (SVM) and Random Forests (RF). Our results indicate that we obtain classification accuracy 98.6% and 99.8% in the case of Object-Level features and 82.1% and 86.1% in the case of Spatial Arrangement features, respectively.

Multilevel Segmentation of Histopathological Images Using Cooccurrence of Tissue Objects

This paper presents a new approach for unsupervised segmentation of histopathological tissue images. This approach has two main contributions. First, it introduces a new set of high-level texture features to represent the prior knowledge of spatial organization of the tissue components. These texture features are defined on the tissue components, which are approximately represented by tissue objects, and quantify the frequency of two component types being cooccurred in a particular spatial relationship. As they are defined on components, rather than on image pixels, these object cooccurrence features are expected to be less vulnerable to noise and variations that are typically observed at the pixel level of tissue images. Second, it proposes to obtain multiple segmentations by multilevel partitioning of a graph constructed on the tissue objects and combine them by an ensemble function. This multilevel graph partitioning algorithm introduces randomization in graph construction and refinements in its multilevel scheme to increase diversity of individual segmentations, and thus, improve the final result. The experiments on 200 colon tissue images reveal that the proposed approach--the object cooccurrence features together with the multilevel segmentation algorithm--is effective to obtain high-quality results. The experiments also show that it improves the segmentation results compared to the previous approaches.

Graph Run-Length Matrices for Histopathological Image Segmentation

The histopathological examination of tissue specimens is essential for cancer diagnosis and grading. However, this examination is subject to a considerable amount of observer variability as it mainly relies on visual interpretation of pathologists. To alleviate this problem, it is very important to develop computational quantitative tools, for which image segmentation constitutes the core step. In this paper, we introduce an effective and robust algorithm for the segmentation of histopathological tissue images. This algorithm incorporates the background knowledge of the tissue organization into segmentation. For this purpose, it quantifies spatial relations of cytological tissue components by constructing a graph and uses this graph to define new texture features for image segmentation. This new texture definition makes use of the idea of gray-level run-length matrices. However, it considers the runs of cytological components on a graph to form a matrix, instead of considering the runs of pixel intensities. Working with colon tissue images, our experiments demonstrate that the texture features extracted from "graph run-length matrices" lead to high segmentation accuracies, also providing a reasonable number of segmented regions. Compared with four other segmentation algorithms, the results show that the proposed algorithm is more effective in histopathological image segmentation.