Mukesh Saraswat

Automated microscopic image analysis for leukocytes identification: a survey.

Automatic quantification and classification of leukocytes in microscopic images are of paramount importance in the perspective of disease identification, its progress and drugs development. Extracting numerical values of leukocytes from microscopic images of blood or tissue sections represents a tricky challenge. Research efforts in quantification of these cells include normalization of images, segmentation of its nuclei and cytoplasm followed by their classification. However, there are several related problems viz., coarse background, overlapped nuclei, conversion of 3-D nuclei into 2-D nuclei etc. In this review, we have categorized, evaluated, and discussed recently developed methods for leukocyte identification. After reviewing these methods and finding their constraints, a future research perspective has been presented. Further, the challenges faced by the pathologists with respect to these problems are also discussed.

Leukocyte segmentation in tissue images using differential evolution algorithm

Abstract An automatic segmentation of leukocytes can assist pharmaceutical companies to take decisions in the discovery of drugs and encourages for development of automated leukocyte recognition system. Segmentation of leukocytes in tissue images is a complex process due to the presence of various noise effects, large variability in the images and shape of the nuclei. Surprisingly, rare efforts have been made to automate the segmentation of leukocytes in various disease models on hematoxylin and eosin (H&E) stained tissue images. The present work proposes a novel strategy based on differential evolution (DE) algorithm to segment the leukocytes from the images of mice skin sections stained with H&E staining and acquired at 40×magnification. The proposed strategy is a first inline report used in such type of image database. Further, the proposed strategy is compared with well-known segmentation algorithms. The results show that the proposed strategy outperforms the traditional image segmentation techniques.

Twitter sentiment analysis using hybrid cuckoo search method

A hybrid cuckoo search method (CSK) has been presented for Twitter sentiment analysis.CSK modifies the random initialization of population in cuckoo search (CS) by K-means to resolve the problem of random initialization.The proposed algorithm has outperformed five popular algorithms.The statistical analysis has been done to validate the performance of the proposed algorithm. Sentiment analysis is one of the prominent fields of data mining that deals with the identification and analysis of sentimental contents generally available at social media. Twitter is one of such social medias used by many users about some topics in the form of tweets. These tweets can be analyzed to find the viewpoints and sentiments of the users by using clustering-based methods. However, due to the subjective nature of the Twitter datasets, metaheuristic-based clustering methods outperforms the traditional methods for sentiment analysis. Therefore, this paper proposes a novel metaheuristic method (CSK) which is based on K-means and cuckoo search. The proposed method has been used to find the optimum cluster-heads from the sentimental contents of Twitter dataset. The efficacy of proposed method has been tested on different Twitter datasets and compared with particle swarm optimization, differential evolution, cuckoo search, improved cuckoo search, gauss-based cuckoo search, and two n-grams methods. Experimental results and statistical analysis validate that the proposed method outperforms the existing methods. The proposed method has theoretical implications for the future research to analyze the data generated through social networks/medias. This method has also very generalized practical implications for designing a system that can provide conclusive reviews on any social issues.

Supervised leukocyte segmentation in tissue images using multi-objective optimization technique

Abstract Automated leukocytes segmentation in skin section images can be utilized by various researchers in animal experimentation for testing anti-inflammatory drugs and estimating dermatotoxicity of various toxic agents. However, complex morphological structure of skin section degrades the performance of leukocytes segmentation due to the extraction of vast number of artifacts/noise along with leukocytes. Rare works have been done to reduce such artifacts. Therefore, in this paper, a supervised methodology for leukocytes segmentation from the images of inflamed mice skin sections is introduced. The method is based on threshold based binary classifier to reduce the artifacts. The optimum values of thresholds are calculated using multi-objective optimization technique, non-dominated sorting genetic algorithm-II (NSGA-II) and receiver operating characteristic (ROC) curve. The experimental results confirm that the proposed method is prompt and precise to segment the leukocytes in highly variable images.

Colour normalisation of histopathological images

Colour transfer is a prime area of research in image processing in recent years. In many real-life image applications, colour transfer of the image is required. A few methods have been developed to alter the colour appearance of the images as per the colour information of the reference image. Histopathological image analysis is one of the application areas where colour transfer method can be used to reduce the effect of varying staining and illuminance. This paper proposes a hybrid method of colour normalisation using modified non-negative matrix factorisation (NMF) and novel colour transfer method. The NMF method has been initialised using Lab colour space which provides fast and reliable results. Uncorrelated color space has been used to transfer the colour of target image to source image. The results show that the proposed method outperforms the considered existing methods and can successfully be applied for the colour normalisation of histopathological images.

Feature selection and classification of leukocytes using random forest.

In automatic segmentation of leukocytes from the complex morphological background of tissue section images, a vast number of artifacts/noise are also extracted causing large amount of multivariate data generation. This multivariate data degrades the performance of a classifier to discriminate between leukocytes and artifacts/noise. However, the selection of prominent features plays an important role in reducing the computational complexity and increasing the performance of the classifier as compared to a high-dimensional features space. Therefore, this paper introduces a novel Gini importance-based binary random forest feature selection method. Moreover, the random forest classifier is used to classify the extracted objects into artifacts, mononuclear cells, and polymorphonuclear cells. The experimental results establish that the proposed method effectively eliminates the irrelevant features, maintaining the high classification accuracy as compared to other feature reduction methods.

Discrete wavelet transform-based color image watermarking using uncorrelated color space and artificial bee colony

AbstractThe exponential growth in electronic data over internet have increased the demand of a robust and high quality watermarking method for authentication and copyright protection. In general, the existing digital image watermarking methods embed the binary or gray scale watermark into the host image although most multimedia images are available in color. Moreover, available digital image watermarking methods generally use the correlated color spaces which impose the limitations to researchers for using only one color component at a time for embedding the watermark. Therefore, in this paper, a novel discrete wavelet transform (DWT) based color image watermarking method has been proposed which embeds the color watermark into host image using uncorrelated color space (UCS) and artificial bee colony (ABC) method. The results show that proposed method outperforms other existing methods against the various signal processing attacks.

Artificial bee colony algorithm for automatic leukocytes segmentation in histopathological images

An automatic segmentation of leukocytes can assist pharmaceutical companies to take decisions in the discovery of drug and encourages for development of automated leukocytes recognition system. Segmentation of leukocytes in tissue images is a complex process due to the presence of various noise effects, large variability in the images, and shape of the nuclei. Surprisingly, rare efforts have been done to automate the segmentation of leukocytes in various disease models on Hematoxylin and Eosin stained tissue images. The present work proposes a novel method based on artificial bee colony algorithm to segment the leukocytes from the images of mice skin sections stained with Hematoxylin and Eosin staining and acquired at 40 x magnification. The results show that the proposed method outperforms when compared with the well known segmentation methods.

Leukocyte Classification in Skin Tissue Images

Automated leukocyte classification can assist histopathologist for quantifying inflammatory cells in microscopic images. Most of the work for classification of leukocytes have been done on blood smear or immunohistochemically (IHC) stained or immunofluroscence (IF) stained tissue section images. But rare work have been initiated till date to automate identification of inflammatory cells in the tissue section images stained with routinely used Hematoxylin and Eosin (H and E) staining. This is due to the coarse background and availability of different artifacts in the tissue section images. Therefore, in this paper, an automated method for classification of inflammatory cells into monomorphonuclear cells and polymorphonuclear cells for H and E stained skin tissue section images has been presented.

An optimum multi-level image thresholding segmentation using non-local means 2D histogram and exponential Kbest gravitational search algorithm

Abstract Multi-level image thresholding segmentation divides an image into multiple non-overlapping regions. This paper presents a novel two-dimensional (2D) histogram-based segmentation method to improve the efficiency of multi-level image thresholding segmentation. In the proposed method, a new non-local means 2D histogram and a novel variant of gravitational search algorithm (exponential Kbest gravitational search algorithm) have been used to find the optimal thresholds. Further, for the optimization, a 2D Renyi entropy has been redefined for multi-level thresholding. The proposed method has been tested on the Berkeley Segmentation Dataset and Benchmark (BSDS300) in terms of both subjective and objective assessments. The experimental results affirm that the proposed method outperforms the other 2D histogram-based image thresholding segmentation methods on majority of performance parameters.