White Blood Cell Imaging Research Articles

Identifikasi Acute Lymphoblastic Leukemia pada Citra Mikroskopis Menggunakan Algoritma Naïve Bayes

Leukemia is a type of blood cancer that occurs when the body overproduces abnormal white blood cells. Acute Lymphoblastic Leukemia (ALL) is a type of acute leukemia. ALL occurs when the spinal cord is excessively producing young lymphocytes, known as lymphoblasts. Leukemia is difficult to detect because it has the same symptoms as other diseases. One way to detect leukemia is to use a complete blood count test. Blood count test is done by calculating the population of red blood cells, white blood cells and platelets. The health condition of the body is indicated by the number of each blood cell. The small number of erythrocyte and abnormal cell shape is indicative of leukemia. How to identify leukemia still using a microscope. In this study the researchers made a way of identifying acute lymphoblastic leukemia cells by image processing, include cropping, segmentation, feature extraction and identification. The method used in image identification is Naive Bayes Classifier (NBC). NBC is a classification method which applies simple probability calculations using B ayes theorem. The white blood cell image tested using this application will be evaluated with accurations. The greatest accuracy results from several test scenarios obtained 80% accuracy.

Toward the development of an optical technique for identifying and imaging white blood cells in whole blood

An optical-disk-based system was developed to obtain images of blood cells for healthcare applications. The blood cells on the disk are scanned using a laser, and the intensity data of reflected or transmitted light from the sample are collected and reconstructed to form an image. Images of red and white blood cells were successfully obtained and both types of blood cells were visually distinguishable in the transmitted-light image. Our method is promising for finding a specific cell, among many other types, since the optical-disk system can scan a large area at high speed.

Diagnosis of Leukemia Disease Based on Enhanced Virtual Neural Network

White Blood Cell (WBC) cancer or leukemia is one of the serious cancers that threaten the existence of human beings. In spite of its prevalence and serious consequences, it is mostly diagnosed through manual practices. The risks of inappropriate, sub-standard and wrong or biased diagnosis are high in manual methods. So, there is a need exists for automatic diagnosis and classification method that can replace the manual process. Leukemia is mainly classified into acute and chronic types. The current research work proposed a computer-based application to classify the disease. In the feature extraction stage, we use excellent physical properties to improve the diagnostic system's accuracy, based on Enhanced Color Co-Occurrence Matrix. The study is aimed at identification and classification of chronic lymphocytic leukemia using microscopic images of WBCs based on Enhanced Virtual Neural Network (EVNN) classification. The proposed method achieved optimum accuracy in detection and classification of leukemia from WBC images. Thus, the study results establish the superiority of the proposed method in automated diagnosis of leukemia. The values achieved by the proposed method in terms of sensitivity, specificity, accuracy, and error rate were 97.8%, 89.9%, 76.6%, and 2.2%, respectively. Furthermore, the system could predict the disease in prior through images, and the probabilities of disease detection are also highly optimistic.

Detection of Acute Myeloid Leukemia based on White Blood Cell Morphological Imaging using Naïve Bayesian Algorithm

The process of diagnosing AML is based on the complete blood-count analysis of the patients. As such, it involves high energy consumption, long completion times, and is rather expensive compared to conventional medical practices. One of the methods for identifying tumor cells involves the utilization of image-processing techniques based on the morphology of white blood cells (WBCs). The principal objective of this study involves the identification of AML cells—especially of the AML M1 and AML M2 types—through morphological imaging of WBCs using the Naïve Bayes' Classifier. The Image-processing methods used in this study include YCbCr color space classification, image thresholding, morphological operations, chain code representation, and the use of bounding boxes. Regardless of the processing technique used, all identification procedures, performed in this study, were based on the Naïve Bayes' Classifier. The test process was performed on 30 images of each of the AML M1 and M2 cell types. The use of the cell identification method proposed in this study demonstrated an accuracy of 73.33%. While the accuracy of cell type identification is 54.92%. Based on the results obtained in this study, it is inferred that the Naïve Bayes' Classifier method can be employed in the process of identifying dominant AML cell types amongst AML M1 and AML M2 (myeloblast, promyelocyte, myelocyte, and metamyelocyte) based on the morphology of WBCs.

A computer system for the leukocytes classification in medical images

The paper is about the development of a computer system for the white blood cells images classification. Solving the leukocytes classification task makes it possible to diagnose not only the blood diseases, but also a wide range of other diseases, as well as to evaluate the overall state of a person’s health. Modern leukocytes classification methods have a fairly large number of shortcomings, which make a problem of finding the most effective method as a tool to solve this task. In our computer system we use the method based on using a trained convolutional neural network as a binary classifier for the leukocytes classification. This study shows the advantages of using this architecture and a deep learning technology to solve the objects classification task in medical digital images. The developed system allows one, in most cases, correctly and with a high speed to determine whether the white blood cell belongs to one of the two classes, which indicates to the possibility of using this system as an auxiliary tool for the blood hematological analysis.

Multi-Task Multi-Domain Learning for Digital Staining and Classification of Leukocytes

This paper addresses digital staining and classification of the unstained white blood cell images obtained with a differential contrast microscope. We have data coming from multiple domains that are partially labeled and partially matching across the domains. Using unstained images removes time-consuming staining procedures and could facilitate and automatize comprehensive diagnostics. To this aim, we propose a method that translates unstained images to realistically looking stained images preserving the inter-cellular structures, crucial for the medical experts to perform classification. We achieve better structure preservation by adding auxiliary tasks of segmentation and direct reconstruction. Segmentation enforces that the network learns to generate correct nucleus and cytoplasm shape, while direct reconstruction enforces reliable translation between the matching images across domains. Besides, we build a robust domain agnostic latent space by injecting the target domain label directly to the generator, i.e., bypassing the encoder. It allows the encoder to extract features independently of the target domain and enables an automated domain invariant classification of the white blood cells. We validated our method on a large dataset composed of leukocytes of 24 patients, achieving state-of-the-art performance on both digital staining and classification tasks.

White Blood Cell Image Segmentation Based on Color Component Combination and Contour Fitting

Background: White Blood Cell (WBC) image segmentation plays a key role in cell morphology analysis. However, WBC segmentation is still a challenging task due to the diversity of WBCs under different staining conditions. Objective: In this paper, we propose a novel WBC segmentation method based on color component combination and contour fitting to segment WBC images accurately. Methods: Specifically, the proposed method first uses color component combination and image thresholding to achieve nucleus segmentation, then uses a color prior to remove image background, and extracts the initial WBC contour via Canny edge detection, and finally judges and closes the unclosed WBC contour by contour fitting. Accordingly, cytoplasm segmentation is achieved by subtracting the nucleus region from the WBC region. Results: Experimental results on 100 WBC images under rapid staining condition and 50 WBC images under standard staining condition showed that the proposed method improved segmentation accuracy of white blood cells under rapid and standard staining conditions. Conclusion: The proposed color component combination and contour fitting is effective in WBC segmentation task.

A kit formulation for the preparation of [89Zr]Zr(oxinate)4 for PET cell tracking: White blood cell labelling and comparison with [111In]In(oxinate)3

BackgroundAdvances in immunology and cell-based therapies are creating a need to track individual cell types, such as immune cells (neutrophils, eosinophils, chimeric antigen receptor (CAR) T cells, etc.) and stem cells. As the fate of administered cells remains largely unknown, nuclear imaging could determine the migration and survival of cells in patients. [89Zr]Zr(oxinate)4, or [89Zr]Zr-oxine, is a radiotracer for positron emission tomography (PET) that has been evaluated in preclinical models of cell tracking and could improve on [111In]In-oxine, the current gold standard radiotracer for cell tracking by scintigraphy and single-photon emission computed tomography (SPECT), because of the better sensitivity, spatial resolution and quantification of PET. However, a clinically usable formulation of [89Zr]Zr-oxine is lacking. This study demonstrates a 1-step procedure for preparing [89Zr]Zr-oxine and evaluates it against [111In]In-oxine in white blood cell (WBC) labelling. MethodsCommercial [89Zr]Zr-oxalate was added to a formulation containing oxine, a buffering agent, a base and a surfactant or organic solvent. WBC isolated from 10 human volunteers were radiolabelled with [89Zr]Zr-oxine following a clinical radiolabelling protocol. Labelling efficiency, cell viability, chemotaxis and DNA damage were evaluated in vitro, in an intra-individual comparison against [111In]In-oxine. ResultsAn optimised formulation of [89Zr]Zr-oxine containing oxine, polysorbate 80 and 4-(2-hydroxyethyl)-1-piperazineethanesulfonic acid (HEPES) was developed. This enabled 1-step radiolabelling of oxine with commercial [89Zr]Zr-oxalate (0.1–25 MBq) in 5 min and radiotracer stability for 1 week. WBC labelling efficiency was 48.7 ± 6.3%, compared to 89.1 ± 9.5% (P < 0.0001, n = 10) for [111In]In-oxine. Intracellular retention of 89Zr and cell viability after radiolabelling were comparable to 111In. There were no significant differences in leukocyte chemotaxis or DNA damage between [89Zr]Zr-oxine or [111In]In-oxine. Conclusions, advances in knowledge and implications for patient careOur results demonstrate that [89Zr]Zr-oxine is a suitable PET alternative to [111In]In-oxine for WBC imaging. Our formulation allows rapid, stable, high-yield, single-step preparation of [89Zr]Zr-oxine from commercially available 89Zr. This will facilitate the clinical translation of cell tracking using [89Zr]Zr-oxine.

White Blood Cells Image Classification Using Deep Learning with Canonical Correlation Analysis

White Blood Cells play an important role in observing the health condition of an individual. The opinion related to blood disease involves the identification and characterization of a patient's blood sample. Recent approaches employ Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and merging of CNN and RNN models to enrich the understanding of image content. From beginning to end, training of big data in medical image analysis has encouraged us to discover prominent features from sample images. A single cell patch extraction from blood sample techniques for blood cell classification has resulted in the good performance rate. However, these approaches are unable to address the issues of multiple cells overlap. To address this problem, the Canonical Correlation Analysis (CCA) method is used in this paper. CCA method views the effects of overlapping nuclei where multiple nuclei patches are extracted, learned and trained at a time. Due to overlapping of blood cell images, the classification time is reduced, the dimension of input images gets compressed and the network converges faster with more accurate weight parameters. Experimental results evaluated using publicly available database show that the proposed CNN and RNN merging model with canonical correlation analysis determines higher accuracy compared to other state-of-the-art blood cell classification techniques.

Target-Independent Domain Adaptation for WBC Classification Using Generative Latent Search.

Automating the classification of camera-obtained microscopic images of White Blood Cells (WBCs) and related cell subtypes has assumed importance since it aids the laborious manual process of review and diagnosis. Several State-Of-The-Art (SOTA) methods developed using Deep Convolutional Neural Networks suffer from the problem of domain shift - severe performance degradation when they are tested on data (target) obtained in a setting different from that of the training (source). The change in the target data might be caused by factors such as differences in camera/microscope types, lenses, lighting-conditions etc. This problem can potentially be solved using Unsupervised Domain Adaptation (UDA) techniques albeit standard algorithms presuppose the existence of a sufficient amount of unlabelled target data which is not always the case with medical images. In this paper, we propose a method for UDA that is devoid of the need for target data. Given a test image from the target data, we obtain its 'closest-clone' from the source data that is used as a proxy in the classifier. We prove the existence of such a clone given that infinite number of data points can be sampled from the source distribution. We propose a method in which a latent-variable generative model based on variational inference is used to simultaneously sample and find the 'closest-clone' from the source distribution through an optimization procedure in the latent space. We demonstrate the efficacy of the proposed method over several SOTA UDA methods for WBC classification on datasets captured using different imaging modalities under multiple settings.

Global and Adaptive Thresholding Technique for White Blood Cell Image Segmentation

Global and local thresholding are two thresholding approaches for white blood cell (WBC) image segmentation. Global thresholding determines the threshold value based on the histogram of the overall pixel intensity distribution of the image. In contrast, adaptive thresholding computes the threshold value for each fractional region of the image, so that each fractional region has a different threshold value. In this work, we are assessing both of these approaches for two threshold values. We extended the Otsu’s equation to calculate more than one threshold as it originally designed to find only a single threshold value. Adaptive thresholding first divides an image into fractional-image by considering an imaginary bounding box that surrounds the location of WBC, which involves the Gram-Schmidt orthogonalization method. For segmentation performance evaluation, we compare 35 blood smear test images which segmented by our proposed method, with their corresponding ground truth image to representing them in Zijdenbos Similarity Index (ZSI), precision, and recall measurement. Experimental results show that adaptive thresholding achieves average ZSI, precision and recall, 92.5%, 91.79%, 94.03%, while global thresholding achieves 30.72%, 23.38%, and 99.39% respectively.

Fully Automated Detection and Classification of White Blood Cells.

The measure of White Blood Cells (WBC) in the blood is an important indicator of pathological conditions. Computer vision based methods for differential counting of WBC are increasing due to their advantages over traditional methods. However, most of these methods are proposed for single WBC images which are pre-processed, and do not generalize for raw microscopic images with multiple WBC. Moreover, they do not have the capability to detect the absence of WBC in the images. This paper proposes an image processing algorithm based on K-Means clustering to detect the presence of WBC in raw microscopic images and to localize them, and a VGG-16 classifier to classify those cells with a classification accuracy of 95.89%.

Evaluation of Peptide-Based Probes toward In Vivo Diagnostic Imaging of Bacterial Biofilm-Associated Infections.

The clinical management of bacterial biofilm infections represents an enormous challenge in today's healthcare setting. The NIH estimates that 65% of bacterial infections are biofilm-related, and therapeutic outcomes are positively correlated with early intervention. Currently, there is no reliable imaging technique to detect biofilm infections in vivo, and current clinical protocols for accurate and direct biofilm identification are nonexistent. In orthopedic implant-associated biofilm infections, for example, current detection methods are based on nonspecific X-ray or radiolabeled white blood cell imaging, coupled with peri-prosthetic tissue or fluid samples taken invasively, and must be cultured. This approach is time-consuming and often fails to detect biofilm bacteria due to sampling errors and a lack of sensitivity. The ability to quantify bacterial biofilms by real-time noninvasive imaging is an urgent unmet clinical need that would revolutionize the management and treatment of these devastating types of infections. In the present study, we assembled a collection of fluorescently labeled peptide candidates to specifically explore their biofilm targeting properties. We evaluated these fluorescently labeled peptides using various in vitro assays for their ability to specifically and nondestructively target biofilms produced by model bacterial pathogen Pseudomonas aeruginosa. The lead candidate that emerged, 4Iphf-HN17, demonstrated rapid biofilm labeling kinetics, a lack of bactericidal activity, and biofilm targeting specificity in human cell infection models. In vivo fluorescently labeled 4Iphf-HN17 showed enhanced accumulation in biofilm-infected wounds, thus warranting further study.

Hybrid adversarial-discriminative network for leukocyte classification in leukemia.

Leukemia is a lethal disease that is harmful to bone marrow and overall blood health. The classification of white blood cell images is crucial for leukemia diagnosis. The purpose of this study is to classify white blood cells by extracting discriminative information from cell segmentation and combining it with the fine-grained features. We propose a hybrid adversarial residual network with support vector machine (SVM), which utilizes the extracted features to improve the classification accuracy for human peripheral white cells. Firstly, we segment the cell and nucleus by utilizing an adversarial residual network, which contains a segmentation network and a discriminator network. To extract features that can handle the inter-class consistency problem effectively, we introduce the adversarial residual network. Then, we utilize convolutional neural network (CNN) features and histogram of oriented gradient (HOG) features, which can extract discriminative features from images of segmented cell nuclei. To utilize the representative features fully, a discriminative network is introduced to deal with neighboring information at different scales. Finally, we combine the vectors of HOG features with those of CNN features and feed them into a linear SVM to classify white blood cells into six types. We used three methods to evaluate the effect of leukocyte classification based on 5000 leukocyte images acquired from a local hospital. The first approach is to use the CNN features as the input of SVM to classify leukocytes, which achieved 94.23% specificity, 95.10% sensitivity, and 94.41% accuracy. The use of the HOG features for SVM achieved 83.50% specificity, 87.50% sensitivity, and 85.00% accuracy. The use of combined CNN and HOG features achieved 94.57% specificity, 96.11% sensitivity, and 95.93% accuracy. We propose a novel hybrid adversarial-discriminative network for the classification of microscopic leukocyte images. It improves the accuracy of cell classification, reduces the difficulty and time pressure of doctors' work, and economizes the valuable time of doctors in daily clinical diagnosis.

Implementation of Genetic Algorithms and Momentum Backpropagation in Classification of Subtype Cells Acute Myeloid Leukimia

Acute Myeloid Leukimia (AML) is a type of cancer which attacks white blood cells from myeloid. AML subtypes M1, M2, and M3 are affected by the same type of cells called myeloblasts, so it needs more detailed analysis to classify.Momentum Backpropagation is used to classified. In its application, optimal selection of architecture, learning rate, and momentum is still done by random trial. This is one of the disadvantage of Momentum Backpropagation. This study uses a genetic algorithm (GA) as an optimization method to get the best architecture, learning rate, and momentum of artificial neural network. Genetic algorithms are one of the optimization techniques that emulate the process of biological evolution.The dataset used in this study is numerical feature data resulting from the segmentation of white blood cell images taken from previous studies which has been done by Nurcahya Pradana Taufik Prakisya. Based on these data, an evaluation of the Momentum Backpropagation process was conducted the selection parameter in a random trial with the genetic algorithm. Furthermore, the comparison of accuracy values was carried out as an alternative to the ANN learning method that was able to provide more accurate values with the data used in this study.The results showed that training and testing with genetic algorithm optimization of ANN parameters resulted in an average memorization accuracy of 83.38% and validation accuracy of 94.3%. Whereas in other ways, training and testing with momentum backpropagation random trial resulted in an average memorization accuracy of 76.09% and validation accuracy of 88.22%.

Combining DC-GAN with ResNet for blood cell image classification.

In medicine, white blood cells (WBCs) play an important role in the human immune system. The different types of WBC abnormalities are related to different diseases so that the total number and classification of WBCs are critical for clinical diagnosis and therapy. However, the traditional method of white blood cell classification is to segment the cells, extract features, and then classify them. Such method depends on the good segmentation, and the accuracy is not high. Moreover, the insufficient data or unbalanced samples can cause the low classification accuracy of model by using deep learning in medical diagnosis. To solve these problems, this paper proposes a new blood cell image classification framework which is based on a deep convolutional generative adversarial network (DC-GAN) and a residual neural network (ResNet). In particular, we introduce a new loss function which is improved the discriminative power of the deeply learned features. The experiments show that our model has a good performance on the classification of WBC images, and the accuracy reaches 91.7%. Graphical Abstract Overview of the proposed method, we use the deep convolution generative adversarial networks (DC-GAN) to generate new samples that are used as supplementary input to a ResNet, the transfer learning method is used to initialize the parameters of the network, the output of the DC-GAN and the parameters are applied the final classification network. In particular, we introduced a modified loss function for classification to increase inter-class variations and decrease intra-class differences.

Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features

White Blood Cell (WBC) Leukaemia is caused by excessive production of leukocytes in the bone marrow, and image-based detection of malignant WBCs is important for its detection. Convolutional Neural Networks (CNNs) present the current state-of-the-art for this type of image classification, but their computational cost for training and deployment can be high. We here present an improved hybrid approach for efficient classification of WBC Leukemia. We first extract features from WBC images using VGGNet, a powerful CNN architecture, pre-trained on ImageNet. The extracted features are then filtered using a statistically enhanced Salp Swarm Algorithm (SESSA). This bio-inspired optimization algorithm selects the most relevant features and removes highly correlated and noisy features. We applied the proposed approach to two public WBC Leukemia reference datasets and achieve both high accuracy and reduced computational complexity. The SESSA optimization selected only 1 K out of 25 K features extracted with VGGNet, while improving accuracy at the same time. The results are among the best achieved on these datasets and outperform several convolutional network models. We expect that the combination of CNN feature extraction and SESSA feature optimization could be useful for many other image classification tasks.

An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell

White blood cells (WBCs) play a remarkable role in the human immune system. To diagnose blood-related diseases, pathologists need to consider the characteristics of WBC. The characteristics of WBC can be defined based on the morphological properties of WBC nucleus. Therefore, nucleus segmentation plays a vital role to classify the WBC image and it is an important part of the medical diagnosis system. In this study, color space conversion and k-means algorithm based new WBC nucleus segmentation method is proposed. Then we localize the WBC based on the location of segmented nucleus to separate them from the entire blood smear image. To classify the localized WBC image, we propose a new convolutional neural network (CNN) model by combining the concept of fusing the features of first and last convolutional layers, and propagating the input image to the convolutional layer. We also use a dropout layer for preventing the model from overfitting problem. We show the effectiveness of our proposed nucleus segmentation method by evaluating with seven quality metrics and comparing with other methods on four public databases. We achieve average accuracy of 98.61% and more than 97% on each public database. We also evaluate our proposed CNN model by using nine classification metrics and achieve an overall accuracy of 96% on BCCD test database. To validate the generalization capability of our proposed CNN model, we show the training and testing accuracy and loss curves for random test set of BCCD database. Further, we compare the performance of our proposed CNN model with four state-of-the-art CNN models (biomedical image classifier) by measuring the value of evaluation metrics.

White Blood Cell Detection Depending on Binary Analysis Based on Red, Blue and Hue Components

The automatic detection of white blood cells remains an unresolved problem in medical imaging. white blood cell image analysis has included researchers from the fields of medicine and computer vision alike. In this paper, a new algorithm for white blood cell detection is proposed. This algorithm is based on the binary conversion of red and blue identity compounds and gradient after defining the values of specific areas while deleting unwanted small areas depending on the median filter. In the experimental results from white blood cell images, the proposed algorithm was compared with several other algorithms for detection. A quality scale was used that compares manual cell counts with the automatic detection of algorithms where the proposed algorithm obtained a high distinction accuracy reaching 98 percent, as compared to other methods.

White Blood Cells Detection using YOLOv3 with CNN Feature Extraction Models

There are several types of blood cancer. One of them is Leukaemia. This is due to leukocyte or white blood cell (WBCs) production problem in the bone marrow. Detection at earlier stage is important so that the patient is able to get a proper treatment. The conventional detection and blood count method is less efficient and it is done manually by pathologist. Thus, there will be a long line to wait for the results and also delay the treatment. A faster detection procedure and technique will have high impact on the real time diagnostic. Fortunately, these problems are able to overcome by making the blood test procedures automatic. One of the effort is the development of deep learning for WBCs detection and classification. In computer aided WBCs detection, the You Only Look Once (YOLO) based platform present a promising outcome. However, the investigation of optimal YOLO structure remains vague. This paper investigate the effect of the deep learning based WBCs detection using You Only Look Once version 3 (YOLOv3) with different pretrained Convolutional Neural Network (CNN) model. The models that been tested are the Alexnet, Visual Geometry Group 16 (VGG16), Darknet19 and the existing YOLOv3 feature extraction model, the Darknet53. The architecture consist of the bounding box for class prediction, feature extraction, and additional convolutional layers. It was trained with 242 WBCs images from Local Initiatives Support Corporation (LISC) dataset. The final outcome shows that the YOLOv3 architecture with Alexnet as its feature extractor produced the highest mean average precision of 98% and have better performance than the other models.