Classification of blood cells.

Classification of blood cells.

Source publication
Article
Full-text available
White blood cells (leukocytes) are a very important component of the blood that forms the immune system, which is responsible for fighting foreign elements. The five types of white blood cells include neutrophils, eosinophils, lymphocytes, monocytes, and basophils, where each type constitutes a different proportion and performs specific functions....

Similar publications

Article
Full-text available
The present research was carried out in an attempt to identify the problems associated with the morphofunctional analysis of vertebrate animal’s leukocyte blood cells. For this blood samples of four age groups chickens (Gallus gallus L.) were collected and analysis was carried out as per the recommendations of the International Council for Standard...
Article
Full-text available
Background: Unique features of elephant hematology are known challenges in analytical methodology like two types of monocytes typical for members of the Order Afrotheria and platelet counts of the comparatively small elephant platelet. Aim: To investigate WBC differential and platelet data generated by an impedance-based hematology analyzer without...
Article
Full-text available
Background Circulating white blood cell (WBC) counts have been related to lung function impairment, but causal relationship was not established. We aimed to evaluate independent effects and causal relationships of WBC subtypes with lung function.Methods The 19,159 participants from NHANES 2011–2012 (n = 3570), coke-oven workers (COW, n = 1762) and...
Article
Full-text available
Blood cell count is an important parameter in analysing a person’s health condition. White blood corpuscles (leukocytes) are responsible for deciding the immunity system of a person. White blood cells (WBC) are classified into: lymphocytes, monocytes and granulocytes. Granulocytes are sub-classified into: neutrophils, eosinophils, and basophils. Th...
Article
Full-text available
Background Peripheral hematological changes in severe COVID-19 patients may reflect the immune response during SARS-CoV-2 infection. Characteristics of peripheral white blood cells as early signals were needed to be investigated for clarifying its associations with the fatal outcomes in COVID-19 patients. Methods A retrospective cohort study was p...

Citations

... WBCs, also called leukocytes, are created in the bone marrow and lymphoid masses in the human immune system. These cells protect the human body from infections such as bacteria, viruses, and fungi [1][2][3]. Traditionally, WBCs are mainly divided into granulocytes and agranulocytes [4,5]. The granulocytes contain basophils (0-1%), eosinophils (1-5%), and neutrophils (50-70%), while the agranulocytes include monocytes (2-10%) and lymphocytes (20-45%) [4,6]. ...
Article
Full-text available
Background Via counting the different kinds of white blood cells (WBCs), a good quantitative description of a person’s health status is obtained, thus forming the critical aspects for the early treatment of several diseases. Thereby, correct classification of WBCs is crucial. Unfortunately, the manual microscopic evaluation is complicated, time-consuming, and subjective, so its statistical reliability becomes limited. Hence, the automatic and accurate identification of WBCs is of great benefit. However, the similarity between WBC samples and the imbalance and insufficiency of samples in the field of medical computer vision bring challenges to intelligent and accurate classification of WBCs. To tackle these challenges, this study proposes a deep learning framework by coupling the pre-trained ResNet and DenseNet with SCAM (spatial and channel attention module) for accurately classifying WBCs. Results In the proposed network, ResNet and DenseNet enables information reusage and new information exploration, respectively, which are both important and compatible for learning good representations. Meanwhile, the SCAM module sequentially infers attention maps from two separate dimensions of space and channel to emphasize important information or suppress unnecessary information, further enhancing the representation power of our model for WBCs to overcome the limitation of sample similarity. Moreover, the data augmentation and transfer learning techniques are used to handle the data of imbalance and insufficiency. In addition, the mixup approach is adopted for modeling the vicinity relation across training samples of different categories to increase the generalizability of the model. By comparing with five representative networks on our developed LDWBC dataset and the publicly available LISC, BCCD, and Raabin WBC datasets, our model achieves the best overall performance. We also implement the occlusion testing by the gradient-weighted class activation mapping (Grad-CAM) algorithm to improve the interpretability of our model. Conclusion The proposed method has great potential for application in intelligent and accurate classification of WBCs.
... Here, Type I measures are "positive measures like Accuracy, Sensitivity, Specificity, Precision, Negative Predictive Value (NPV), F1-Score and Mathews correlation coefficient (MCC), and Type II measures are negative measures like False positive rate (FPR), False negative rate (FNR), and False Discovery Rate (FDR)". It was compared with some meta-heuristic-based algorithms like Particle Swarm Optimization (PSO) [30,41], GWO [31], WOA [32] and MFO [26] with BS-MFO-NLSTM and classifiers such as CNN [33], LSTM [34], NN [35,42], NLSTM [34,35] with BS-MFO-NLSTM. The parameter details for the AFCM is given by, number of clusters is considered as 4, Maximum iteration is taken as 10 and for LSTM, the number of epochs is 25 [4 + 10], respectively. ...
Article
The fundamental goal of this paper is to develop a novel blood cell classification using a hybrid learning model. The proposed model encompasses different processing steps like “(a) pre-processing, (b) cell segmentation, (c) Feature extraction, and (d) classification”. In the initial step, the blood smear images are pre-processed using Red Green Blue (RGB) scale to gray scale conversion and contrast enhancement. Then, the Adaptive Fuzzy C-Means (A-FCM) clustering with heuristic improvement is developed for blood cell classification. During testing, the feature extraction from the segmented cell image is performed by the Gray Level Co-occurrence Matrix1 (GLCM), Local Binary Pattern (LBP), geometric features, and color features. These features are subjected to the hybrid learning model with Neural Network (NN) and Long Short-Term Memory (LSTM) termed NLSTM. The modification of the A-FCM-based cell segmentation and hybrid learning-based cell classification is performed by a Best search-based Moth-Flame Optimization (BS-MFO) algorithm. The experimental analysis specifies that the suggested model has shown better efficiency on the identification of blood cell images, and attains high accuracy when compared over the competitive methods.
... By supplementing the given dataset with the generated data, different forms of GANs are designed for data augmentation in many domains, such as medical image analysis [29,41,75,76], brain-computer interface [42,77], agriculture [43,78,79], and civil engineering [30,80]. In particular, researchers increasingly utilize GANs for data augmentation in the field of emotion recognition, including speech emotion recognition [27,28,81], facial expression recognition [31,82,83], EEG emotion recognition [44,84], and so on. ...
Article
Full-text available
Audio–visual emotion recognition is the research of identifying human emotional states by combining the audio modality and the visual modality simultaneously, which plays an important role in intelligent human–machine interactions. With the help of deep learning, previous works have made great progress for audio–visual emotion recognition. However, these deep learning methods often require a large amount of data for training. In reality, data acquisition is difficult and expensive, especially for the multimodal data with different modalities. As a result, the training data may be in the low-data regime, which cannot be effectively used for deep learning. In addition, class imbalance may occur in the emotional data, which can further degrade the performance of audio–visual emotion recognition. To address these problems, we propose an efficient data augmentation framework by designing a multimodal conditional generative adversarial network (GAN) for audio–visual emotion recognition. Specifically, we design generators and discriminators for audio and visual modalities. The category information is used as their shared input to make sure our GAN can generate fake data of different categories. In addition, the high dependence between the audio modality and the visual modality in the generated multimodal data is modeled based on Hirschfeld–Gebelein–Re´nyi (HGR) maximal correlation. In this way, we relate different modalities in the generated data to approximate the real data. Then, the generated data are used to augment our data manifold. We further apply our approach to deal with the problem of class imbalance. To the best of our knowledge, this is the first work to propose a data augmentation strategy with a multimodal conditional GAN for audio–visual emotion recognition. We conduct a series of experiments on three public multimodal datasets, including eNTERFACE’05, RAVDESS, and CMEW. The results indicate that our multimodal conditional GAN has high effectiveness for data augmentation of audio–visual emotion recognition.
... Semisupervised learning-based approaches are widely used for such activity [1], [3], [8], [9], [10], [11], [8], [12], [13] as it helps in using available training samples as well. Deep learning based convolutional approaches are used in [6], [8], [14], [15]. Apart from Convolutional Neural Network (CNN), most of the studies used Generative Adversarial Network (GAN) models in order to deep with shortage of training samples in HSI classification approaches. ...
Article
Full-text available
Hyperspectral image classification is very complex and challenging process. However, with deep neural networks like Convolutional Neural Networks (CNN) with explicit dimensionality reduction, the capability of classifier is greatly increased. However, there is still problem with sufficient training samples. In this paper, we overcome this problem by proposing an Artificial Intelligence (AI) based framework named Deep Adversarial Learning Framework (DALF) that exploits deep autoencoder for dimensionality reduction, Generative Adversarial Network (GAN) for generating new Hyperspectral Imaging (HSI) samples that are to be verified by a discriminator in a non-cooperative game setting besides using a classifier. Convolutional Neural Network (CNN) is used for both generator and discriminator while classifier role is played by Support Vector Machine (SVM) and Neural Network (NN). An algorithm named Generative Model based Hybrid Approach for HSI Classification (GMHA-HSIC) which drives the functionality of the proposed framework is proposed. The success of DALF in accurate classification is largely dependent on the synthesis and labelling of spectra on regular basis. The synthetic samples made with an iterative process and being verified by discriminator result in useful spectra. By training GAN with associated deep learning models, the framework leverages classification performance. Our experimental results revealed that the proposed framework has potential to improve the state of the art besides having an effective data augmentation strategy. © 2021 Institute of Advanced Engineering and Science. All rights reserved.
... Normal range of the RBC count for healthy men varies from 4.7 -6.1 million cells per microliter and in women from 4.2 -5.4 million cells [38]. WBCs are responsible for the immune system of the body and consists of five sub-types which are neutrophils (40-60%), lymphocytes (0.5-1%), monocytes (2-8%), eosinophils (1-4%) and basophils (20-40%) [39]. Platelets are comparatively less in number and are responsible of minimizing complications due to heavy blood losses by forming blood clots to stop bleeding. ...
Article
Full-text available
With advancements in related sub-fields, research on photomicrography in life science is emerging and this is a review on its application towards human full blood count testing which is a primary test in medical practices. For a prolonged period of time, analysis of blood samples is the basis for bio medical observations of living creatures. Cell size, shape, constituents, count, ratios are few of the features identified using DIP based analysis and these features provide an overview of the state of human body which is important in identifying present medical conditions and indicating possible future complications. In addition, functionality of the immune system is observed using results of blood tests. In FBC tests, identification of different blood cell types and counting the number of cells of each type is required to obtain results. Literature discuss various techniques and methods and this article presents an insightful review on human blood cell morphology, photomicrography, digital image processing of photomicrographs, feature extraction and classification, and recent advances. Integration of emerging technologies such as microfluidics, micro-electromechanical systems, and artificial intelligence based image processing algorithms and classifiers with cell sensing have enabled exploration of novel research directions in blood testing applications.
... The model that turned out to be the most accurate one is Random Forest Classifier, with an accuracy of 98.7%. The research by Khaled Almezhghwi and Sertan Serte [7] looks into operations of image processing and generative adversarial networks (GAN) for data augmentation, as well as the pre-trained CNN based architectures such as VGG-16, ResNet, and DenseNet for classifying WBC into five types. DenseNet-169, the top-performing DNN model, has performed with a validation accuracy of 98.8%. ...
Article
Modern-day computation has become indispensable in the healthcare industry. From medical image processing to cost reduction, Artificial Intelligence has proved its significance in solving complex healthcare problems. One of the primary areas in which it can be of greater use in hematology. Categorization of white-blood cells is imperative to pre-identify abnormalities. Through this paper, we collected image samples for 4 major White Blood cell groups, which are Neutrophils, Lymphocytes, Monocytes, and Eosinophils. The aim of this research is to put forward an intelligent system that efficiently alleviates the stringent requirement of a cytological study. The proposed system classifies 4 white-blood-cell types based on their morphological variation. With the experimental modulations that we chose to integrate, the presented model attained an accuracy of 97%.
... It also achieved a sensitivity and specificity of 91% and 97%. In the paper [8], the authors used a data augmentation method based on generative adversarial networks (GAN), then used VGG-16, ResNet, and DenseNet for the recognition of leukocytes. The proposed method improves the classification performances of WBCs. ...
... Automatic recognition of peripheral blood cells using classical machine-learning approaches has been widely treated in the literature [24,25]. With the emergence of the CNN architectures, many works have been proposed to perform the automatic segmentation and classification of the white blood cells [8][9][10]. The classification of the eight components of the peripheral blood cells was proposed in the paper [22]. ...
Article
Full-text available
INTRODUCTION: The diagnosis of hematological diseases is based on the morphological differentiation of the peripheral blood cell types. OBJECTIVES: In this work, a hybrid model based on CNN features extraction and machine learning classifiers were proposed to improve peripheral blood cell image classification. METHODS: At first, a CNN model composed of four convolution layers and three fully connected layers was proposed. Second, the features from the deeper layers of the CNN classifier were extracted. Third, several models were trained and tested on the data. Moreover, a combination of CNN with traditional machine learning classifiers was carried out. This includes CNN_KNN, CNN_SVM (Linear), CNN_SVM (RBF), and CNN_AdaboostM1. The proposed methods were validated on two datasets. We have used a public dataset containing 12444 images with four types of leukocytes to find the best optimizer function(eosinophil, lymphocyte, monocyte, and neutrophil images). The second dataset contains 17,092 images divided into eight groups: lymphocytes, neutrophils, monocytes). the second public dataset was used to find the best combination of CNN and the machine learning algorithms. the dataset containing 17,092 images: lymphocytes, neutrophils, monocytes, eosinophils, basophils, immature granulocytes, erythroblasts, and platelets. RESULTS: The results reveal that CNN combined with AdaBoost decision tree classifier provided the best performance in terms of cells recognition with an accuracy of 88.8%, demonstrating the performance of the proposed approach. CONCLUSION: The obtained results show that the proposed system can be used in clinical practice.
... Based on the presence of visible granules in the microscopic view, WBCs can be classified into two broad categories: granulocytes and agranulocytes (nongranulocytes). Neutrophils, eosinophils, and basophils belong to the granulocytes category, while lymphocytes and monocytes belong to the agranulocytes category (Almezhghwi and Serte, 2020;Acevedo et al., 2019). Various types of WBCs play a role in immune response (L., 2005) and act as a defense mechanism in the body against illness-causing agents. ...
... The application of morphological analysis, including but not limited to morphological operators for PBC segmentation and classification, is the research area that has been explored in great detail in (Kim et al., 2001;Di Ruberto et al., 2002;Piuri and Scotti, 2004;Scotti, 2005;Dorini et al., 2007;Theera-Umpon and Dhompongsa, 2007;Taherisadr et al., 2013;Lee and Chen, 2014;Rodellar et al., 2018) before the deep learning-based approach became popular. There has been a significant increase in the studies on the deep learning-based WBC classification approaches (Su et al., 2014;Othman et al., 2017;Jiang et al., 2018;Macawile et al., 2018;Throngnumchai et al., 2019;Sharma et al., 2019;Banik et al., 2019;Shahin et al., 2019;Almezhghwi and Serte, 2020;Baydilli and Atila, 2020;Sahlol et al., 2020) in the last decade, especially after the successful application of CNNs on other computer vision problems. The works (Saraswat and Arya, 2014;Rawat et al., 2015;Al-Dulaimi et al., 2018;Patodia et al., 2020), provide a review of the state-of-the-art methods of leukocyte segmentation, feature extraction, and classification published in the last two decades. ...
... The reason behind it may be the simplicity and the smaller size of the PBC dataset compared to the ImageNet which has 1000 classes with over 14 million images making it a much harder dataset wherein the changes in architecture produce notable performance differences. It is noteworthy that the standard CNN architectures we fine-tuned, outperform the specialized architectures and techniques designed (Almezhghwi and Serte, 2020;Long et al., 2021) for the peripheral blood cell classification. ...
Preprint
The application of machine learning techniques to the medical domain is especially challenging due to the required level of precision and the incurrence of huge risks of minute errors. Employing these techniques to a more complex subdomain of hematological diagnosis seems quite promising, with automatic identification of blood cell types, which can help in detection of hematologic disorders. In this paper, we benchmark 27 popular deep convolutional neural network architectures on the microscopic peripheral blood cell images dataset. The dataset is publicly available, with large number of normal peripheral blood cells acquired using the CellaVision DM96 analyzer and identified by expert pathologists into eight different cell types. We fine-tune the state-of-the-art image classification models pre-trained on the ImageNet dataset for blood cell classification. We exploit data augmentation techniques during training to avoid overfitting and achieve generalization. An ensemble of the top performing models obtains significant improvements over past published works, achieving the state-of-the-art results with a classification accuracy of 99.51%. Our work provides empirical baselines and benchmarks on standard deep-learning architectures for microscopic peripheral blood cell recognition task.
... However, due to the limitations of experts, time constraints, and the irreversible consequences of misdiagnosis [4], it is crucial to discover a different approach to get faster and more reliable outcomes. The technological advancements facilitate the process of diagnosing the diseases, in other words, the widespread use of AI [14] mainly its areas such as machine learning and deep learning, are extremely constructive and researchers have made significant use of AI and deep learning in various medical areas [15]- [19]. CNN architecture is one of the most prominent deep learning techniques in the medical imaging field, with outstanding results [20]. ...
Preprint
Full-text available
The new coronavirus (known as COVID-19) was first identified in Wuhan and quickly spread worldwide, wreaking havoc on the economy and people's everyday lives. Fever, cough, sore throat, headache, exhaustion, muscular aches, and difficulty breathing are all typical symptoms of COVID-19. A reliable detection technique is needed to identify affected individuals and care for them in the early stages of COVID-19 and reduce the virus's transmission. The most accessible method for COVID-19 identification is RT-PCR; however, due to its time commitment and false-negative results, alternative options must be sought. Indeed, compared to RT-PCR, chest CT scans and chest X-ray images provide superior results. Because of the scarcity and high cost of CT scan equipment, X-ray images are preferable for screening. In this paper, a pre-trained network, DenseNet169, was employed to extract features from X-ray images. Features were chosen by a feature selection method (ANOVA) to reduce computations and time complexity while overcoming the curse of dimensionality to improve predictive accuracy. Finally, selected features were classified by XGBoost. The ChestX-ray8 dataset, which was employed to train and evaluate the proposed method. This method reached 98.72% accuracy for two-class classification (COVID-19, healthy) and 92% accuracy for three-class classification (COVID-19, healthy, pneumonia). <br
... However, due to the limitations of experts, time constraints, and the irreversible consequences of misdiagnosis [4], it is crucial to discover a different approach to get faster and more reliable outcomes. The technological advancements facilitate the process of diagnosing the diseases, in other words, the widespread use of AI [14] mainly its areas such as machine learning and deep learning, are extremely constructive and researchers have made significant use of AI and deep learning in various medical areas [15]- [19]. CNN architecture is one of the most prominent deep learning techniques in the medical imaging field, with outstanding results [20]. ...
Preprint
Full-text available
The new coronavirus (known as COVID-19) was first identified in Wuhan and quickly spread worldwide, wreaking havoc on the economy and people's everyday lives. Fever, cough, sore throat, headache, exhaustion, muscular aches, and difficulty breathing are all typical symptoms of COVID-19. A reliable detection technique is needed to identify affected individuals and care for them in the early stages of COVID-19 and reduce the virus's transmission. The most accessible method for COVID-19 identification is RT-PCR; however, due to its time commitment and false-negative results, alternative options must be sought. Indeed, compared to RT-PCR, chest CT scans and chest X-ray images provide superior results. Because of the scarcity and high cost of CT scan equipment, X-ray images are preferable for screening. In this paper, a pre-trained network, DenseNet169, was employed to extract features from X-ray images. Features were chosen by a feature selection method (ANOVA) to reduce computations and time complexity while overcoming the curse of dimensionality to improve predictive accuracy. Finally, selected features were classified by XGBoost. The ChestX-ray8 dataset, which was employed to train and evaluate the proposed method. This method reached 98.72% accuracy for two-class classification (COVID-19, healthy) and 92% accuracy for three-class classification (COVID-19, healthy, pneumonia). <br