A Comparative Evaluation of Transfer Learning Techniques for White Blood Cell Detection

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.

White blood cell (WBC) detection is pivotal in medical diagnostics, crucial for diagnosing infections, inflammations, and certain cancers. Traditional WBC detection methods are labor-intensive and time-consuming. Convolutional Neural Networks (CNNs) are widely used for cell detection due to their strong feature extraction capability. However, they struggle with global information and long-distance dependencies in WBC images. Transformers, on the other hand, excel at modeling long-range dependencies, which improves their performance in vision tasks. To tackle the large foreground-background differences in WBC images, this paper introduces a novel WBC detection method, named the Multi-Scale Cross-Deformation Attention Fusion Network (MCDAF-Net), which combines CNNs and Transformers. The Attention Multi-scale Sensing Module (AMSM) is designed to localize WBCs more accurately by fusing features at different scales and enhancing feature representation through a self-attention mechanism. The Cross-Deformation Convolution Module (CDCM) reduces feature correlation, aiding the model in capturing diverse aspects and patterns in images, thereby improving generalization. MCDAF-Net outperforms other models on public datasets (LISC, BCCD, and WBCDD), demonstrating its superiority in WBC detection. Our code and pretrained models: https://github.com/xqq777/MCDAF-Net.

One of the body's most crucial blood cell kinds is the white blood cell. White blood cells, called leukocytes, are crucial for the body's defence mechanism and against hazardous foreign substances, tumour cells, and infectious bacteria. This paper suggests a computer-based automated system for detecting white blood cells using the YOLOV8 transformer and white blood cell analysis in digital images of blood cells. The Generate process uses Yolov8. In Generate, this will produce image processing in the form of annotation results on each type of white blood cell and dataset with COCO format. The DETR Model training conducted in this study is to increase the accuracy value of the white output of the blood cell picture formation. Test results using recall, precision, f1 score and object detection values. In the lymphocyte and basophil datasets, the number of white blood cell images used is only 10 images. Following the results of training from yolov8 using Roboflow, the results were increased relatively high, with an average increase of 0.68 in all five images of white blood cells. This test also gets an average improvement in detection results from Yolo to DETR, getting a fairly significant result of 68%, which is because YOLO cannot handle undetected objects (which are not in the training dataset; furthermore, DETR can handle multiple objects in a single image. Typically, detecting traditional objects such as YOLO requires repeatedly multiple object detection with a fixed batch size

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.

Data scieQuerynce (DS) methods and artificial intelligence (AI) are critical in today's healthcare services operations. This study focuses on evaluating the effectiveness of AI and DS in biomedical diagnostics, including automatic detection and counting of white blood cells (WBCs) and types, which provide valuable information for diagnosing and treating blood diseases such as leukemia. Automating these tasks using AI and DS saves time and avoids or minimizes errors compared to manual processes, which can be complex and error prone. The study utilizes bibliographic data from SCOPUS to evaluate research on applying AI algorithms and DS methods for mapping and classifying WBC images for treatment of blood diseases, such as leukemia using literature survey and science mapping methodology. The results show the potency of different DS methods and AI algorithms, such as machine learning, deep learning, and classification algorithms that enable the automatic detection of WBC images. AI and DS algorithms offer critical benefits in effectively and efficiently analyzing microscopic images of blood cells. The automatic identification, localization, and classification of WBCs speed up the patient diagnosis process, allowing hematologists to focus on interpreting results. Automatic processes identify specific abnormalities and patterns, enhancing accuracy and timely diagnoses. Future work will examine the application of generative AI in blood cells diagnostics.

BackgroundComputer-aided methods for analyzing white blood cells (WBC) are popular due to the complexity of the manual alternatives. Recent works have shown highly accurate segmentation and detection of white blood cells from microscopic blood images. However, the classification of the observed cells is still a challenge, in part due to the distribution of the five types that affect the condition of the immune system.Methods(i) This work proposes W-Net, a CNN-based method for WBC classification. We evaluate W-Net on a real-world large-scale dataset that includes 6562 real images of the five WBC types. (ii) For further benefits, we generate synthetic WBC images using Generative Adversarial Network to be used for education and research purposes through sharing.Results(i) W-Net achieves an average accuracy of 97%. In comparison to state-of-the-art methods in the field of WBC classification, we show that W-Net outperforms other CNN- and RNN-based model architectures. Moreover, we show the benefits of using pre-trained W-Net in a transfer learning context when fine-tuned to specific task or accommodating another dataset. (ii) The synthetic WBC images are confirmed by experiments and a domain expert to have a high degree of similarity to the original images. The pre-trained W-Net and the generated WBC dataset are available for the community to facilitate reproducibility and follow up research work.ConclusionThis work proposed W-Net, a CNN-based architecture with a small number of layers, to accurately classify the five WBC types. We evaluated W-Net on a real-world large-scale dataset and addressed several challenges such as the transfer learning property and the class imbalance. W-Net achieved an average classification accuracy of 97%. We synthesized a dataset of new WBC image samples using DCGAN, which we released to the public for education and research purposes.

Automatic circle detection in digital images has been considered as an important and complex task for the computer vision community that has devoted important research efforts into optimal circle detectors. On the other hand, medical imaging is a relevant field of application of image processing algorithms. In particular, the analysis of white blood cell (WBC) images has engaged researchers from fields of medicine and computer vision alike. Since WBC’s can be approximated by a quasi-circular form, a circular detector algorithm may be successfully applied. This chapter presents an algorithm for the automatic detection of white blood cells embedded into complicated and cluttered smear images that considers the complete process as a circle detection problem. The approach is based on a nature-inspired technique called the Electromagnetism-Like Optimization (EMO) which is a heuristic method that follows electromagnetism principles for solving complex optimization problems. The EMO algorithm is based on the electromagnetic attraction and repulsion among charged particles whose charge represents the fitness solution for each particle (a given solution). The algorithm uses the encoding of three non-collinear edge points as candidate circles over an edge map. A new objective function has been derived to measure the resemblance of a candidate circle to an actual WBC based on the information from the edge map and segmentation results. Guided by the values of such objective function, the set of encoded candidate circles (charged particles) are evolved by using the EMO algorithm so that they can fit into the actual blood cells contained in the edge-only map of the image. Experimental results from blood cell images with a varying range of complexity are included to validate the efficiency of the presented technique regarding detection, robustness and stability.

Medical imaging is a relevant field of application of image processing algorithms. In particular, the analysis of white blood cell (WBC) images has engaged researchers from fields of medicine and computer vision alike. Since WBCs can be approximated by a quasicircular form, a circular detector algorithm may be successfully applied. This paper presents an algorithm for the automatic detection of white blood cells embedded into complicated and cluttered smear images that considers the complete process as a circle detection problem. The approach is based on a nature-inspired technique called the electromagnetism-like optimization (EMO) algorithm which is a heuristic method that follows electromagnetism principles for solving complex optimization problems. The proposed approach uses an objective function which measures the resemblance of a candidate circle to an actual WBC. Guided by the values of such objective function, the set of encoded candidate circles are evolved by using EMO, so that they can fit into the actual blood cells contained in the edge map of the image. Experimental results from blood cell images with a varying range of complexity are included to validate the efficiency of the proposed technique regarding detection, robustness, and stability.

The number of white blood cells in the leucorrhea microscopic image can indicate the severity of vaginal inflammation. At present, the detection of white blood cells in leucorrhea mainly relies on manual microscopy by medical experts, which is time-consuming, expensive and error-prone. In recent years, some studies have proposed to implement intelligent detection of leucorrhea white blood cells based on deep learning technology. However, such methods usually require manual labeling of a large number of samples as training sets, and the labeling cost is high. Therefore, this study proposes the use of deep active learning algorithms to achieve intelligent detection of white blood cells in leucorrhea microscopic images. In the active learning framework, a small number of labeled samples were firstly used as the basic training set, and a faster region convolutional neural network (Faster R-CNN) training detection model was performed. Then the most valuable samples were automatically selected for manual annotation, and the training set and the corresponding detection model were iteratively updated, which made the performance of the model continue to increase. The experimental results show that the deep active learning technology can obtain higher detection accuracy under less manual labeling samples, and the average precision of white blood cell detection could reach 90.6%, which meets the requirements of clinical routine examination.

In this paper, a unique method for the identification of white blood cells (WBCs) is proposed. The system is based on morphological analysis and makes use of the red, blue, and hue components of digital pictures. The purpose is to design a technology that is both accurate and efficient for the detection of white blood cells, which is essential for a variety of medical diagnosis. Preprocessing of the pictures, segmentation of white blood cells (WBCs), feature extraction based on morphological features, and classification using machine learning approaches are all components of the procedure. Method: Increasing contrast and removing noise are the first steps in the proposed technique, which starts with picture preparation. In order to separate white blood cells (WBCs) from the background, the next step is to conduct segmentation, which involves a mix of thresholding and morphological processes. After the white blood cells have been segmented, characteristics such as area, perimeter, circularity, and intensity are retrieved from them. These attributes are given into a machine learning classifier, trained on a dataset of labeled WBC pictures, to discriminate between WBCs and other cells or artifacts. Python as well as OpenCV libraries are used in the implementation of the technique. Result: In the process of identifying white blood cells (WBCs) from microscopic pictures, the suggested algorithm yields encouraging results. In the identification of white blood cells (WBC), the evaluation on a dataset consisting of a variety of blood samples reveals good accuracy, sensitivity, and specificity. With regard to both accuracy and computing efficiency, the algorithm's performance is superior to that of other approaches that are currently in use. Moreover, the system demonstrates a high level of stability when confronted with differences in picture quality and staining processes. Conclusion: In conclusion, the algorithm that was created offers a dependable and automated method for the detection of white blood cells (WBC) based on the identification of morphological characteristics in digital pictures. Through the use of the red, blue, and hue components, it does an excellent job of distinguishing white blood cells from other cellular components. The precision and efficiency of the approach make it acceptable for incorporation into clinical workflows, which will help in the identification of a variety of blood illnesses in a timely and accurate manner using the method. It is possible that further improvements and validation on bigger datasets might make its use in clinical settings easier, which would thus contribute to improvements in patient care and diagnosis.

Objective To investigate the value of urine dry chemistry method, urinary sediment analyzer and microscope in the diagnosis of urologic neoplasms. Methods The clinical data of 80 inpatients with urologic neoplasms treated in Nantong tumor hospital from June 2015 to October 2017 were retrospectively analyzed, and all selected cases were confirmed by pathological examination. The urine specimens of all patients were examined by urine dry chemistry method, urinary sediment analyzer and microscope. The detection of white blood cell (WBC) and red blood cell (RBC) in urine of patients were analyzed. Results The positive detection rate of WBC by urine dry chemistry method, urinary sediment analyzer was higher than that by and microscope (P<0.05). The positive detection rate of RBC by urine dry chemistry method, urinary sediment analyzer was higher than that by and microscope (P<0.05). The microscope examination result was taken as the reference standard, the sensitivity and specificity of urine dry chemistry method in the detection of WBC were slightly lower than those of urinary sediment analyzer. The sensitivity and specificity of urine dry chemistry method in the detection of RBC were slightly higher than those of urinary sediment analyzer. The total cost of automatic urine dry chemistry analyzer was less than that of other two inspection instruments, and the utilization rate of instrument was higher. Conclusions The three urine examination methods in the detection of RBC and WBC have some limitations and advantages. When selecting the clinical detection method, the appropriate method should be selected according to the purpose of the test. If necessary, it can be used in combination to reduce the rate of missed detection and improve the accuracy of detection. Key words: Urologic Neoplasms; Urine; Urinalysis; Microscopy

White blood cells are warrior cells that protect the human body against external factors. Each of these warrior cells performs a distinct task, making every piece of information about them highly valuable in the medical field. In this article, a classification framework for the four known types of white blood cells is proposed. It is hoped that the classification of these types will contribute to the prediction of diseases such as AIDS, malaria, leukemia, and many others. In the proposed method, images of white blood cells from the Blood Cell Classification and Detection dataset were used as input to Convolutional Neural Networks. The feature vectors extracted using these Convolutional Neural Network architectures were combined into a single vector. A Minimum Redundancy Maximum Relevance algorithm was then employed to identify the most effective features within the feature vector. Experiments were conducted using these selected features, and the analysis of each experiment was reported in detail. The Support Vector Machines classifier achieved an accuracy of 98.63% in classifying white blood cell types by combining features from multiple deep learning architectures. The experimental results demonstrated that the features obtained from different layers of the Convolutional Neural Networks had varying impacts on the classification performance.

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.

Accurate label-free 3-part leukocyte recognition with single cell lens-free imaging flow cytometry

Background Leukemia, which is a blood cancer, is caused by the abnormal growth of white blood cells (WBCs), primarily found in the myeloid and fatty tissues of bone marrow. Microscopy is used by microbiologists and pathologists to examine the blood for the detection of leukemia. Blood cells are analyzed for morphological markers that aid in the detection and classification of leukemia. However, this method is time-consuming for malignancy prognosis and may be influenced by the clinical abilities and work experience of microbiologists. Aims and Objectives This research aimed to review and analyze various machine learning (ML) and deep learning (DL) approaches for the identification and categorization of different types of leukemia, particularly acute myeloid leukemia (AML) and chronic myeloid leukemia (CML), based on microscopic images of white blood cells (WBCs). It also aimed to evaluate the efficacy of various machine learning and deep learning classifiers for detecting acute and chronic myeloid leukemia and classifying different types of leukocytes. Methods In this study, a Support Vector Machine (SVM) classifier, representing traditional machine learning (ML) models, and a Convolutional Neural Network (CNN) classifier, based on deep learning (DL) algorithms, were employed to identify and classify myelogenous leukemia and different types of leukocytes. Results The algorithms utilizing the above-mentioned classifiers demonstrated significantly better performance metrics compared to other models. Conventional artificial intelligence (AI) approaches in medical image analysis have demonstrated effectiveness in accurately and reliably classifying biological images, such as microscopic blood cells, with greater precision and reliability. Conclusion CNNs achieved the highest accuracy, while SVMs excelled in precision among traditional methods. Combining both techniques also yielded great results. While accuracy is an important metric, it is not the only factor to consider. Overall, CNNs are more effective at detecting and classifying leukocytes and myelogenous leukaemia.