White Blood Cell Segmentation Research Articles

Color Space Transformation and Multi-Class Weighted Loss for Adhesive White Blood Cell Segmentation

White blood cells (WBCs) are the cells of immune system, protecting against infective diseases and invasion of viruses and bacteria. Their aberrant number, both abnormal increase and decrease, is a sign of an ongoing pathology, a precise evaluation of their number is of the utmost importance as the first step of assessing a potential disease. In blood cell microscopic images, since red blood cells and platelets are similar in color with WBCs, and WBCs are partially adhesive, WBC segmentation for counting is often not resulting in a good performance. Therefore, in this work, a color space transformation is proposed to filter out red blood cells and platelets, which is transforming the blood cell microscopic images of patients with acute lymphoblastic leukemia from RGB color space to HSV to detect and extract WBCs. For precisely segmenting adhesive WBCs in extraction results, we set cell border to the third class, in addition to foreground and background. A weighted cross-entropy loss function based on class weight and distance transformation weight enhanced U-Net to learn cell border features. Our results showed that the method proposed in this paper for WBC segmentation using the data set ALL_IDB1 could achieve an accuracy of 97.92%.

Unified Approach for White Blood Cell Segmentation, Feature Extraction, and Counting using Max-Tree Data Structure

Accurate identification and counting of White Blood Cells (WBCs) from microscopy blood cell images are vital for several blood-related disease diagnoses such as leukemia. The inevitability of automated cell image analysis in medical diagnosis results in a plethora of research for the last few decades. Microscopic blood cell image analysis involves three major steps: cell segmentation, classification, and counting. Several techniques have been employed separately to solve these three problems. In this paper, a simple unified model is proposed for White Blood Cell segmentation, feature extraction for classification, and counting with connected mathematical morphological operators implemented using the max-tree data structure. Max-tree creates a hierarchical representation of connected components of all possible gray levels present in an image in such a way that the root holds the connected components comprise of pixels with the lowest intensity value and the connected components comprise of pixels with the highest intensity value are in the leaves. Any associated attributes such as the size or shape of each connected component can be efficiently calculated on the fly and stored in this data structure. Utilizing this knowledge-rich data structure, we obtain a better segmentation of the cells that preserves the morphology of the cells and consequently obtain better accuracy in cell counting.

An optimised pixel-based classification approach for automatic white blood cells segmentation

The pixel-based classification is an automatic approach for classifying all pixels in the image but does not take into account the spatial information for the region of interest. On the other hand, region-growing methods take into account the neighbourhood pixels information. However, in region-growing methods, a pixel-group called 'points of interest' are needed to initialise the growing process. In this paper, we proposed an optimised pixel-based classification by the cooperation of region growing strategy. This original segmentation scheme is performed in two phases for the automatic recognition of white blood cells (WBC): the first is a learning step with colour characteristics of each pixel in the image. The second is a region growing application by classifying neighbouring pixels from pixels of interest extracted by the ultimate erosion technique. This process has proved that the cooperation allows obtaining a nucleus and cytoplasm segmentation as closer to what as expected in the reference images.

Automatic Detection and Classification of White Blood Cells in Blood Smear Images Using Convolutional Neural Network

Background: Blood cell identification and counting are very important in the diagnosis and treatment of diseases. Of the blood cells, the identification of white blood cells (WBC) and their changes is of particular importance due to their role in the immune system. Manual cell counting is time-consuming and dependent on expert experience. Also, the accuracy of blood cell counting can be influenced by human limitations such as fatigue and mental problems. Automatic systems can be a convenient and cost-effective choice for routine clinical services and can be used for fast and accurate blood disease diagnosis. In the automated systems, blood samples are analyzed using microscopic images of stained blood cells. There are various studies on automatic blood cell segmentation based on blood smear images [1-4]. Also, some studies have focused on WBC image classification [5-6]. Objectives: In this paper, the main objective is to provide the implementation of a deep learning-based automatic system to identify five main groups of WBCs in human peripheral blood smear, including Eosinophils, Basophils, Monocytes, Lymphocytes, and Neutrophils. Method: The block diagram of the proposed method is shown in Figure 1. As can be seen, the proposed method consisted of three pre-processing, segmentation, and deep learning-based classification stages. In the pre-processing stage, color normalization was used to normalize the color appearance variability. The color appearance can significantly vary between different labs due to differences in slide digitization conditions and staining protocols. Automatic image analysis methods can be significantly affected by different smear color appearances. In the color normalization stage, images to be examined were normalized to match the color appearance of a target image with standard calibrated staining. The second task was the removal stage of the background and segmentation of the desired region of WBCs. In this stage, by subtracting the B color channel of RGB blood smear image from G color channel and then by using morphological erosion and morphological reconstruction, the WBC probability map was obtained. The value of the WBC probability map showed that the pixels how likely were related to WBCs. In WBC probability map image, the pixels belonging to the WBCs had larger values than the pixels of non-WBCs. Finally, WBCs were segmented by applying optimal Otsu’s thresholding [7] on the probability map image. Detected WBCs were cropped from entire image by considering a patch with size 131 × 131 around all detected cells. The patches for segmented WBCs were then passed through a convolutional neural network (CNN) called CellDiff-Net, which returned the class of WBCs. The structure of the CNN architecture is shown in Figure 2. Results: Our blood smear image database used to train the proposed method was composed of 216 images with size 1536 × 2048. They were collected and labeled by experts at Avicenna Infertility Clinic (ACECR), Tehran, Iran. Stepwise processing of a sample blood smear image for WBC segmentation is shown in Figure 3. By the approach shown in Figure 3, all WBC patches were extracted from training images. Image augmentation (flips, rotations, and shears) was used to increase the size of the training set and balance out the classes. We tested our model for a test set of 10 blood smear samples. Then, 100 images were captured from each blood sample and all images were analyzed by the proposed method. Visualizing feature space in convolution layers for a test WBC image pass through learned CellDiff-Net is shown in Figure 4. To evaluate cell differential counts, the performance of the proposed method was compared with the results of manual counting and Sysmex kx-21 analyzer. Figure 5 compares three automated, Sysmex, and manual differential cell count results for a test sample. For objective evaluation of the proposed system, three criteria of sensitivity, specificity, and accuracy were used. The manually labeled WBCs were considered as ground-truth. The ground truth for all the images was determined by an expert and used to validate the proposed method. Table 1 shows the performance of the automated proposed WBC detection and classification method. Conclusion: In this paper, a novel automated system was proposed for WBC detection and classification in blood smear images. The experimental results proved the performance of the proposed system in WBC detection and classification.

Evaluation and benchmarking of level set-based three forces via geometric active contours for segmentation of white blood cell nuclei shape

The segmentation of white blood cells and their nuclei is still difficult and challenging for many reasons, including the differences in their colour, shape, background and staining techniques, the overlapping of cells, and changing cell topologies. This paper shows how these challenges can be addressed by using level set forces via edge-based geometric active contours. In this work, three level set forces-based (curvature, normal direction, and vector field) are comprehensively studied in the context of the problem of segmenting white blood cell nuclei based on geometric flows. Cell images are first pre-processed, using contrast stretching and morphological opening and closing in order to standardise the image colour intensity, to create an initial estimate of the cell foreground and to remove the narrow links between lobes and cell bulges. Next, segmentation is conducted to prune out the white blood cell nucleus region from the cell wall and cytoplasm by combining the theory of curve evolution using curvature, normal direction, and vector field-based level set forces and edge-based geometric active contours. The overall performance of the proposed segmentation method is compared and benchmarked against existing techniques for nucleus shape detection, using the same databases. The three level set forces studied here (curvature, normal direction, and vector field) via edge-based geometric active contours achieve F-index values of 92.09%, 91.13%, and 90.76%, respectively, and the proposed segmentation method results in better performance than all other techniques for all indices, including Jaccard distance, boundary displacement error, and Rand index.

Computer aided system for lymphoblast classification to detect acute lymphoblastic leukemia

Acute lymphoblastic leukemia (ALL) is a disease that is detected by the presence of lymphoblast cell. Basically, lymphoblast cell is the abnormal cell of lymphocyte which is one of the White Blood Cell (WBC) types. Early prevention is suggested as this disease can be fatal and caused death. Traditionally, ALL is detected by using manual analysis which is challenging and time consuming. It can also yield inaccurate result as it is highly dependent on the pathologist’s skills. Industry has come out with hematology counter which is fast, accurate and automated. However, these machines are costly and cannot be afforded by some countries. For that reason, Computer Aided System (CAS) will be a great help to the pathologist for assisting purposes and it also can act as second opinion for the pathologist. This system contains six main steps which are color space correction, WBC segmentation, post processing, clumped area extraction, feature extraction and lymphoblast classification. Firstly, color space correction is apply by using l*a*b* color space to standardize the image’s intensity. Next, WBC segmentation is made to prune out WBC region using color space analysis with Otsu thresholding. However, segmented image contains noises that need to be eliminated and it is accomplished by applying morphological filter with Connected Component Labelling (CCL). There is an overlapping WBC which need to be separated by using Watershed method to extract the individual cells. Next, feature extraction is made to collect the cell’s data to be fed into the classifier. Classifier used in this system to classify lymphoblast is Support Vector Machine (SVM) and this system is able to achieve 96.69% of accuracy.

Influence of normalization and color features on super-pixel classification: application to cytological image segmentation

Super-pixel feature extraction is a key problem to get an acceptable performance in color super-pixel classification. Given a color feature extraction problem, it is necessary to know which is the best approach to solve this problem. In the current work, we're interested in the challenge of nucleus and cytoplasm automatic recognition in the cytological image. We propose an automatic process for white blood cells (WBC) segmentation using super-pixel classification. The process is divided into five steps. In first step, the color normalization is calculated. The super-pixels generation by Simple Linear Iterative Clustering algorithm is performed in the second step. In third step, the color property is used to achieve illumination invariance. In fourth step, color features are calculated on each super-pixel. Finally, supervised learning is realized to classify each super-pixel into nucleus and cytoplasm region. The present work rallied an exhaustive statistical evaluation of a very wide variety of the color super-pixel classification, with height normalization methods, four-color spaces and four feature extraction techniques. Normalization and color spaces slightly increase the average accuracy of super-pixel classification. Our experiments based to statistical comparison allow to conclude that comprehensive gray world normalized normalization is better than without normalization for super-pixel classification achieving the first positions in the Friedman ranking. RGB space is the best color spaces to be used in super-pixel feature extraction for nucleus and cytoplasm segmentation. For feature extraction, the learning methods work better on the first order statistics features for the automatic WBC segmentation.

White Blood Cell Segmentation via Sparsity and Geometry Constraints

Digital pathology and microscopic image analysis play an important role in cell morphology research. In particular, the effective segmentation of White Blood Cells (WBCs) remains a challenging problem due to the blurring boundaries of WBCs under rapid staining, as well as the adhesion between leukocytes and other cells. In this paper, we propose a novel WBC (including nuclei and cells) segmentation algorithm based on both sparsity and geometry constraints. Specifically, we first construct a sparse image representation via combining the HSL color space and the RGB color channels, followed by the use of a sparsity constraint to only preserve useful information from the nuclei features. In addition, we introduce a robust model fitting strategy (i.e., the geometry constraint) to detect cells. Our model fitting strategy is able to significantly improve the robustness of the proposed segmentation algorithm against outliers that could seriously contaminate WBCs. The experimental results show that the proposed algorithm presents clear advantages over the state-of-the-art WBC segmentation algorithms in terms of accuracy.

Multi Features Based Approach for White Blood Cells Segmentation and Classification in Peripheral Blood and Bone Marrow Images

In this paper, we propose a complete automated framework for white blood cells differential count in peripheral blood and bone marrow images, in order to reduce the analysis time and increase the accuracy of several blood disorders diagnosis. A new colour transformation is first proposed to highlight the white blood cells regions. Then, a marker controlled watershed algorithm is used to segment the region of interest. The nucleus and cytoplasm are subsequently separated. In the identification step, a set of colour, texture and morphological features are extracted from both nucleus and cytoplasm regions. Next, the performances of a random forest classifier on a set of microscopic images are compared and evaluated. The obtained results reveal high recognition accuracies for both segmentation and classification stage.

Automatic Segmentation and Classification of White Blood Cells in Peripheral Blood Samples

Automatic Segmentation and Classification of White Blood Cells in Peripheral Blood Samples

Automatic Segmentation and Classification of White Blood Cells in Peripheral Blood Samples

Automatic Segmentation and Classification of White Blood Cells in Peripheral Blood Samples

Segmentation of White Blood Cells and Lymphoblast Cells Using Moving K-Means

One of the diagnosis procedures for acute lymphoblastic leukemia is screening for blood cells by expert operator using microscope. This process is relatively long and will slow healing process of this disease which need fast treatment. Another way to screen this disease is by using digital image processing technique in microscopic image of blood smears to detect lymphoblast cells and types of white blood cells. One of essential step in digital image processing is segmentation because this process influences the subsequent process of detecting and classifying Acute Lymphoblastic Leukemia disease. This research performed segmentation of white blood cells using moving k-means algorithm. Some process are done to remove noise such as red blood cells and reduce detection errors such as white blood cells and/or lymphoblastic cell that’s appear overlap. Postprocessing are performed to improve segmentation quality and to separate connected white blood cell. The dataset in this study has been validated with expert clinical pathologists from Sardjito Regional General Hospital, Yogyakarta, Indonesia. This research produces systems performance with results in sensitivity of 85.6%, precision 82.3%, Fscore of 83,9% and accuracy of 72.3%. Based on the results of the testing process with a much larger number of datasets on the side of the variations level of cell segmentation difficulties both in terms of illumination and overlapping cell, the method proposed in this study was able to detect or segment overlapping white blood cells better.

A novel chaotic optimal foraging algorithm for unconstrained and constrained problems and its application in white blood cell segmentation

Meta-heuristic is defined as an iterative generation process with some random characters, which aims to generate a sufficiently good solution(s) for the global optimization problems. The process of solving a global optimization problem with near-optimal solutions is based on combining in some intelligent way different methodologies for exploiting and exploring the search space and building a structure information through different learning strategies. Optimal foraging algorithm (OFA) is a robust meta-heuristic algorithm inspired by following the animal foraging behavior. Recently, chaos and meta-heuristics have been combined in different algorithms with the aim of overcoming the limitations of meta-heuristics. In this paper, a novel algorithm for combining chaos with OFA is presented. The presented chaotic optimal foraging algorithm (COFA) is introduced with a set of unconstrained and constrained optimization problems using different chaotic maps. The results show that the proposed COFA outperforms the standard OFA for these benchmarks regarding exploitation, exploration, the trajectory of foraging individuals, search history, fitness improvement of the population and convergence rate. The performance of COFA has also compared with other most recent and popular meta-heuristic algorithms proofing its superior. An application of white blood cell segmentation in microscopic images has been chosen, and the proposed chaotic optimal foraging algorithm has been applied to see its ability and accuracy to identify and segment the white blood cell for further diagnosis. According to the statistical analysis of objective values, COFA algorithm is more accurate and robust than original OFA algorithm. COFA proves its ability to converge to the optimal multiple thresholds level-based segmentation more accurate than OFA. The experimental results also show that the proposed COFA proves its high degree of stability compared with original OFA in finding optimal multiple threshold values.

Automatic Leukemia Cell Counting using Iterative Distance Transform for Convex Sets

The calculation of white blood cells on the acute leukemia microscopic images is one of the stages in the diagnosis of Leukemia disease. The main constraint on calculating the number of white blood cells is the precision in the area of overlapping white blood cells. The research on the calculation of the number of white blood cells overlapping generally based on geometry. However, there was still a calculation error due to over segment or under segment. This paper proposed an Iterative Distance Transform for Convex Sets (IDTCS) method to determine the markers and calculate the number of overlapping white blood cells. Determination of marker was performed on every cell both in single and overlapping white blood cell area. In this study, there were tree stages: segmentation of white blood cells, marker detection and white blood cell count, and contour estimation of every white blood cell. The used data testing was microscopic acute leukemia image data of Acute Lymphoblastic Leukemia (ALL) and Acute Myeloblastic Leukemia (AML). Based on the test results, Iterative Distance Transform for Convex Sets IDTCS method performs better than Distance Transform (DT) and Ultimate Erosion for Convex Sets (UECS) method.

Effective segmentations in white blood cell images using $$\epsilon $$ ϵ -SVR-based detection method

White blood cell (WBC) image detection plays an important role in automatic morphological systems since it can simplify and facilitate WBC segmentation and classification procedures. However, existing WBC detection methods mainly rely on the location of the nucleus, which is found difficult to achieve accurate detection results. This paper proposes a novel WBC detection algorithm through sliding windows with varying sizes to traverse the image for candidates. Three cues are explored to measure the candidates, and a combined cue is used as a single output to distinguish positives from negatives. The $$\epsilon $$ -support vector regression is employed to determine the detection window from the candidates. In this paper, two applications of the proposed WBC detection approach are carried out, including an adaptive thresholding algorithm based on WBC detection for nucleus segmentation from images and target detection to lessen the users’ interaction for automatic cytoplasm segmentation.

Research of the Leukocytes Segmentation Method in the Blood Cells Recognition Systems

.

Fast and robust segmentation of white blood cell images by self-supervised learning

A fast and accurate white blood cell (WBC) segmentation remains a challenging task, as different WBCs vary significantly in color and shape due to cell type differences, staining technique variations and the adhesion between the WBC and red blood cells. In this paper, a self-supervised learning approach, consisting of unsupervised initial segmentation and supervised segmentation refinement, is presented. The first module extracts the overall foreground region from the cell image by K-means clustering, and then generates a coarse WBC region by touching-cell splitting based on concavity analysis. The second module further uses the coarse segmentation result of the first module as automatic labels to actively train a support vector machine (SVM) classifier. Then, the trained SVM classifier is further used to classify each pixel of the image and achieve a more accurate segmentation result. To improve its segmentation accuracy, median color features representing the topological structure and a new weak edge enhancement operator (WEEO) handling fuzzy boundary are introduced. To further reduce its time cost, an efficient cluster sampling strategy is also proposed. We tested the proposed approach with two blood cell image datasets obtained under various imaging and staining conditions. The experiment results show that our approach has a superior performance of accuracy and time cost on both datasets.

A novel white blood cells segmentation algorithm based on adaptive neutrosophic similarity score.

White blood cells (WBCs) play a crucial role in the diagnosis of many diseases according to their numbers or morphology. The recent digital pathology equipments investigate and analyze the blood smear images automatically. The previous automated segmentation algorithms worked on healthy and non-healthy WBCs separately. Also, such algorithms had employed certain color components which leak adaptively with different datasets. In this paper, a novel segmentation algorithm for WBCs in the blood smear images is proposed using multi-scale similarity measure based on the neutrosophic domain. We employ neutrosophic similarity score to measure the similarity between different color components of the blood smear image. Since we utilize different color components from different color spaces, we modify the neutrosphic score algorithm to be adaptive. Two different segmentation frameworks are proposed: one for the segmentation of nucleus, and the other for the cytoplasm of WBCs. Moreover, our proposed algorithm is applied to both healthy and non-healthy WBCs. in some cases, the single blood smear image gather between healthy and non-healthy WBCs which is considered in our proposed algorithm. Also, our segmentation algorithm is performed without any external morphological binary enhancement methods which may effect on the original shape of the WBC. Different public datasets with different resolutions were used in our experiments. We evaluate the system performance based on both qualitative and quantitative measurements. The quantitative results indicates high precision rates of the segmentation performance measurement A1=96.5% and A2=97.2% of the proposed method. The average segmentation performance results for different WBCs types reach to 97.6%. In this paper, a method based on adaptive neutrosphic sets similarity score is proposed in order to detect WBCs from a blood smear microscopic image and segment its components (nucleus and the cytoplasm). The proposed segmentation algorithm can be utilized for fully-automated classification systems, such systems can be either for the healthy WBCs or even for non-healthy WBCs specially the leukemia cells.

White blood cell (WBC) counting analysis in blood smear images using various color segmentation methods

White blood cells (WBCs) is closely related to human immunity system which is useful to fight viruses and bacteria. Cancer therapy effectiveness and some of the blood-related diseases can be determined from the count of cell region. Traditionally, WBC count is done manually which yields inaccurate results as the blood sample increases. Moreover, even though hematology counter device is fast and accurate, it is very costly. These problems has led to the invention of cost effective Computer Aided System (CAS) which analyzes the blood smeared images obtained from microscope. In CAS, the most important step is segmentation and any failure at this stage will cause inaccuracy in the subsequent stages. Realizing the importance of segmentation, this paper investigated various segmentation methods for the purpose of WBC counting based on color band thresholding procedure. Initially, color space correction based on L∗a∗b∗ color space was applied to standardize the image color intensity. Next, segmentation process was conducted to prune out the WBC region from the background by combining color analysis of RGB, CMYK and HSV with Otsu thresholding. Morphological filter was employed as the segmented image contained noises would affect the system performance. Henceforth, Connected Component Labelling (CCL) was done to distinguish the small particles that still existed in the image. Eventually, Circle Hough Transform (CHT) was applied to identify and count the WBC including the one in the clump region. Overall system performance was accessed and it was found that by using S color component of HSV, color space provided the highest WBC segmentation accuracy which was 96.92%. Meanwhile, for the combination of two color bands; S-C produced 96.56% of WBC counting accuracy. Another interesting finding was that the usage of nucleus based detection was superior compared to cytoplasm-based detection for WBC counting purpose.

Fractional gravitational search-radial basis neural network for bone marrow white blood cell classification

ABSTRACTAutomotive image segmentation systems are becoming an important tool in the medical field for disease diagnosis. The white blood cell (WBC) segmentation is crucial, because it plays an important role in the determination of the diseases and helps experts to diagnose the blood disease disorders. The precise segmentation of the WBCs is quite challenging because of the complex contents in the bone marrow smears. In this paper, a novel neural network (NN) classifier is proposed for the classification of the bone marrow WBCs. The proposed NN classifier integrates the fractional gravitation search (FGS) algorithm for updating the weight in the radial basis function mapping for the classification of the WBC based on the cell nucleus feature. The experimentation of the proposed FGS-RBNN classifier is carried on the images collected from the publically available dataset. The performance of the proposed methodology is evaluated over the existing classifier approaches using the measures accuracy, sensitivity, and specificity. The results show that the classification using the nucleus features alone can be utilized to achieve the classification with the better accuracy. Moreover, the classification performance of the proposed FGS-RBNN is better than the existing classifiers, and it is proved to be the efficacious classifier with a classification accuracy of 95%.