Leukocyte Imaging Research Articles

Type 2 diabetes remodels collateral circulation and promotes leukocyte adhesion following ischemic stroke.

Blood flow and leukocyte imaging in awake mice by two-photon microscopy before and after stroke under physiological conditionsT2DM induces collateral remodeling prior to strokeT2DM reduces blood flow and impedes recovery in pial arteries and veins after ischemic strokePoor recovery of penetrating arterial flow and sustained deficit in microvascular flow after ischemic stroke in T2DM miceT2DM increases persistent leukocyte adhesion to endothelium of veins and elevates neutrophils infiltration into the brain parenchyma after ischemic stroke.

Weakly supervised semantic segmentation of leukocyte images based on class activation maps.

Leukocytes are an essential component of the human defense system, accurate segmentation of leukocyte images is a crucial step towards automating detection. Most existing methods for leukocyte images segmentation relied on fully supervised semantic segmentation (FSSS) with extensive pixel-level annotations, which are time-consuming and labor-intensive. To address this issue, this paper proposes a weakly supervised semantic segmentation (WSSS) approach for leukocyte images utilizing improved class activation maps (CAMs). Firstly, to alleviate ambiguous boundary problem between leukocytes and background, preprocessing technique is employed to enhance the image quality. Secondly, attention mechanism is added to refine the CAMs generated by improving the matching of local and global features. Random walks, dense conditional random fields and hole filling were leveraged to obtain final pseudo-segmentation labels. Finally, a fully supervised segmentation network is trained with pseudo-segmentation labels. The method is evaluated on BCCD and TMAMD datasets. Experimental results demonstrate that by employing the pseudo segmentation annotations generated through this method can be utilized to train UNet as close as possible to FSSS. This method effectively reduces manual annotation cost while achieving WSSS of leukocyte images.

Channel Fusion Filter and Invariant Scattering Network-Based Leukocyte Image Discrimination Framework

Channel Fusion Filter and Invariant Scattering Network-Based Leukocyte Image Discrimination Framework

Efficient leukocytes detection and classification in microscopic blood images using convolutional neural network coupled with a dual attention network

Leukocytes, also called White Blood Cells (WBCs) or leucocytes, are the cells that play a pivotal role in human health and are vital indicators of diseases such as malaria, leukemia, AIDS, and other viral infections. WBCs detection and classification in blood smears offers insights to pathologists, aiding diagnosis across medical conditions. Traditional techniques, including manual counting, detection, classification, and visual inspection of microscopic images by medical professionals, pose challenges due to their labor-intensive nature. However, traditional methods are time consuming and sometimes susceptible to errors. Here, we propose a high-performance convolutional neural network (CNN) coupled with a dual-attention network that efficiently detects and classifies WBCs in microscopic thick smear images. The main aim of this study was to enhance clinical hematology systems and expedite medical diagnostic processes. In the proposed technique, we utilized a deep convolutional generative adversarial network (DCGAN) to overcome the limitations imposed by limited training data and employed a dual attention mechanism to improve accuracy, efficiency, and generalization. The proposed technique achieved overall accuracy rates of 99.83%, 99.35%, and 99.60% for the peripheral blood cell (PBC), leukocyte images for segmentation and classification (LISC), and Raabin-WBC benchmark datasets, respectively. Our proposed approach outperforms state-of-the-art methods in terms of accuracy, highlighting the effectiveness of the strategies employed and their potential to enhance diagnostic capabilities and advance real-world healthcare practices and diagnostic systems.

Miniaturized microscope for non-invasive imaging of leukocyte-endothelial interaction in human microcirculation

We present a miniature oblique back-illumination microscope (mOBM) for imaging the microcirculation of human oral mucosa, enabling real-time, label-free phase contrast imaging of individual leukocytes circulating in the bloodstream, as well as their rolling and adhesion on vascular walls—the initial steps in leukocyte recruitment that is a hallmark of inflammation. Using the mOBM system, we studied the leukocyte-endothelial interactions in healthy and locally inflamed tissue and observed drastic changes in leukocyte movement (velocity and displacement profile). Our findings suggest that real-time imaging of leukocyte dynamics can provide new diagnostic insights (assessment of inflammation, temporal progression of disease, evaluation of therapeutic response, etc.) that are not available using conventional static parameters such as cell number and morphology.

A Brief History of Nuclear Medicine Imaging of Infection.

For nearly 50 years, nuclear medicine has played an important role in the diagnosis of infection. Gallium citrate Ga 67 was one of the first, if not the first, radionuclide used for this purpose. Unfavorable imaging characteristics, a lack of specificity, and the long interval (2-3 days) between administration and imaging spurred the search for alternatives. At the present time, gallium 67 citrate is used primarily for differentiating acute tubular necrosis from interstitial nephritis and as an alternative for indications including sarcoid, spondylodiscitis, and fever of unknown origin, when 18F-fluorodeoxyglucose (18F-FDG) is not available. The approval, in the mid-1980s, of techniques for in vitro labeling of leukocytes with indium-111 and technetium-99m that subsequently migrate to foci of infection was a significant advance in nuclear medicine imaging of infection and labeled leukocyte imaging still plays an important role in imaging of infection. There are significant disadvantages to in vitro labeled leukocyte imaging. Unfortunately, efforts devoted to developing in vivo leukocyte labeling methods have met with only limited success. Over the past 20 years 18F-FDG has established itself as a valuable imaging agent for musculoskeletal and cardiovascular infections, as well as sarcoidosis and fever of unknown origin. As useful as these agents are, their uptake is based on the host response to infection, not infection itself. Previous attempts at developing infection-specific agents, including radiolabeled antibiotics and vitamins, were limited by poor results and/or lack of availability, so investigators continue to focus on developing infection-specific nuclear medicine imaging agents.

Fine-grained imbalanced leukocyte classification with global-local attention transformer

Leukemia is a fatal disease that requires the counting of White Blood Cells (WBCs) in bone marrow for diagnosis. However, bone marrow blood contains many types of leukocytes, some of which have subtle differences. To address this issue, we propose the WBC-GLAformer model, which comprises three parts: Low-level Feature Extractor (LFE), Global–Local Attention based Encoder (GLAE), and Discrimination Part Select (DPS). The LFE uses a convolutional neural network (CNN) to tokenize patches from the extracted low-level features. The GLAE combines the ability of the CNN to extract local features with the ability of the transformer to extract global features, thereby enriching the features of leukocyte images. The DPS improves the accuracy of leukocyte classification by selecting the discriminative regions. Our method achieves state-of-the-art results in the bone marrow leukocyte fine-grained classification dataset. Experimental results demonstrate that the model has good generalization on different datasets and is more robust to the optimizer. And visualization results show that the model can effectively focus on the discriminative parts of different cells. Code is available at https://github.com/ywj1/WBC-GLAformer

Leukocyte classification for acute lymphoblastic leukemia timely diagnosis by interpretable artificial neural network

Leukemia is a blood cancer characterized by leukocyte overproduction. Clinically, the reference for acute lymphoblastic leukemia diagnosis is a blood biopsy that allows obtain microscopic images of leukocytes, whose early-stage classification into leukemic (LEU) and healthy (HEA) may be disease predictor. Thus, the aim of this study is to propose an interpretable artificial neural network (ANN) for leukocyte classification to timely diagnose acute lymphoblastic leukemia. The “ALL_IDB2” dataset was used. It contains 260 microscopic images showing leukocytes acquired from 130 LEU and 130 HEA subjects. Each microscopic image shows a single leukocyte that was characterized by 8 morphological and 4 statistical features. An ANN was developed to distinguish microscopic images acquired from LEU and HEA subjects, considering 12 features as inputs and the local-interpretable model-agnostic explanatory (LIME) algorithm as an interpretable post-processing algorithm. The ANN was evaluated by the leave-one-out cross-validation procedure. The performance of our ANN is promising, presenting a testing area under the curve of the receiver operating characteristic equal to 87%. Being implemented using standard features and having LIME as a post-processing algorithm, it is clinically interpretable. Therefore, our ANN seems to be a reliable instrument for leukocyte classification to timely diagnose acute lymphoblastic leukemia, guaranteeing a high clinical interpretability level.

Leukocyte subtype classification with multi-model fusion.

Accurate classification of leukocytes is crucial for the diagnosis of hematologic malignancies, particularly leukemia. However, traditional leukocyte classification methods are time-consuming and subject to subjective interpretation by examiners. To address this issue, we aimed to develop a leukocyte classification system capable of accurately classifying 11 leukocyte classes, which would aid radiologists in diagnosing leukemia. Our proposed two-stage classification scheme involved a multi-model fusion based on ResNet for rough leukocyte classification, which focused on shape features, followed by fine-grained leukocyte classification using support vector machine for lymphocytes based on texture features. Our dataset consisted of 11,102 microscopic leukocyte images of 11 classes. Our proposed method achieved accurate leukocyte subtype classification with high levels of accuracy, sensitivity, specificity, and precision of 97.03 ± 0.05, 96.76 ± 0.05, 99.65 ± 0.05, and 96.54 ± 0.05, respectively, in the test set. The experimental results demonstrate that the leukocyte classification model based on multi-model fusion can effectively classify 11 leukocyte classes, providing valuable technical support for enhancing the performance of hematology analyzers.

Research on Leukocyte Recognition Method Based on Convolutional Neural Network

There are various types of leukocytes in blood cells, and various types of leukocytes play an important role in fighting fungal, bacterial, viral and other infections in the human body, so studying and classifying leukocyte types is an important task for medical researchers. Based on the low efficiency and accuracy of traditional methods for detecting leukocytes, an efficient processing of leukocyte images using convolutional neural networks is proposed, which can perform tasks such as classification and localization of leukocytes. The proposed method and previous detection networks were also compared in experiments, and the experimental results proved that the proposed Yolov5 convolutional neural network has the highest detection speed and accuracy, with mAP reaching 86.47%.

Ghost-ResNeXt: An Effective Deep Learning Based on Mature and Immature WBC Classification

White blood cells (WBCs) must be evaluated to determine how well the human immune system performs. Abnormal WBC counts may indicate malignancy, tuberculosis, severe anemia, cancer, and other serious diseases. To get an early diagnosis and to check if WBCs are abnormal or normal, one needs to examine the numbers and determine the shape of the WBCs. To address this problem, computer-aided procedures have been developed because hematologists perform this laborious, expensive, and time-consuming process manually. Resultantly, a powerful deep learning model was developed in the present study to categorize WBCs, including immature WBCs, from the images of peripheral blood smears. A network based on W-Net, a CNN-based method for WBC classification, was developed to execute the segmentation of leukocytes. Thereafter, significant feature maps were retrieved using a deep learning framework built on GhostNet. Then, they were categorized using a ResNeXt with a Wildebeest Herd Optimization (WHO)-based method. In addition, Deep Convolutional Generative Adversarial Network (DCGAN)-based data augmentation was implemented to handle the imbalanced data issue. To validate the model performance, the proposed technique was compared with the existing techniques and achieved 99.16%, 99.24%, and 98.61% accuracy levels for Leukocyte Images for Segmentation and Classification (LISC), Blood Cell Count and Detection (BCCD), and the single-cell morphological dataset, respectively. Thus, we can conclude that the proposed approach is valuable and adaptable for blood cell microscopic analysis in clinical settings.

Activatable near-infrared probes for the detection of specific populations of tumour-infiltrating leukocytes in vivo and in urine.

Tracking the immune microenvironment of tumours is essential for understanding the mechanisms behind the effectiveness of cancer immunotherapies. Molecular imaging of tumour-infiltrating leukocytes (TILs) can be used to non-invasively monitor the tumour immune microenvironment, but current imaging agents do not distinguish TILs from leukocytes resident in other tissues. Here we report a library of activatable molecular probes for the imaging, via near-infrared fluorescence, of specific TILs (including M1 macrophages, cytotoxic T lymphocytes and neutrophils) in vivo in real time and also via excreted urine, owing to the probes' renal clearance. The fluorescence of the probes is activated only in the presence of both tumour and leukocyte biomarkers, which allows for the imaging of populations of specific TILs in mouse models of cancers with sensitivities and specificities similar to those achieved via flow-cytometric analyses of biopsied tumour tissues. We also show that the probes enable the non-invasive evaluation of the immunogenicity of different tumours, the dynamic monitoring of responses to immunotherapies and the accurate prediction of tumour growth under various treatments.

Leukocyte deep learning classification assessment using Shapley additive explanations algorithm.

A peripheral blood smear is a basic test for hematological disease diagnosis. This test is performed manually in many places worldwide, which requires both time and qualified staff. Large laboratories are equipped with digital morphology analyzers, some of which are based on deep learning methods. However, it is difficult to explain to scientists how they work. In this paper, we proposed to add an explanatory factor to enhance the interpretability of deep learning models in leukocyte classification. 10 297 single images of leukocytes obtained from peripheral blood smears were included in this study. Pre-trained and fully trained VGG16 and VGG19 models were used to classify the leukocytes, and Shapley Additive Explanations (SHAP) DeepExplainer was applied to visualize the area of cells that were significant for classification. The output images from the DeepExplainer were compared with cellular elements that are essential to laboratory practice. The accuracy of our fully trained models was 99.81% for VGG16 and 99.79% for VGG19. It achieved slightly better results than the partially trained model, which scored 98.67% for VGG16 and 98.33% for VGG19. Their SHAP explanations indicated the significance of cellular structures in microscopic examination. Explanations in the pre-trained models have proved the cell and nucleus contours to be relevant to classification, while explanations in the fully trained models pointed to the cytoplasm area. Despite different SHAP DeepExplainer explanations for fully and partially trained models, this method appears to be helpful for the verification of leukocyte classification in automated peripheral blood smear examination.

Accurate stratification between VEXAS syndrome and differential diagnoses by deep learning analysis of peripheral blood smears.

VEXAS syndrome is a newly described autoinflammatory disease associated with UBA1 somatic mutations and vacuolization of myeloid precursors. This disease possesses an increasingly broad spectrum, leading to an increase in the number of suspected cases. Its diagnosis via bone-marrow aspiration and UBA1-gene sequencing is time-consuming and expensive. This study aimed at analyzing peripheral leukocytes using deep learning approaches to predict VEXAS syndrome in comparison to differential diagnoses. We compared leukocyte images from blood smears of three groups: participants with VEXAS syndrome (identified UBA1 mutation) (VEXAS); participants with features strongly suggestive of VEXAS syndrome but without UBA1 mutation (UBA1-WT); participants with a myelodysplastic syndrome and without clinical suspicion of VEXAS syndrome (MDS). To compare images of circulating leukocytes, we applied a two-step procedure. First, we used self-supervised contrastive learning to train convolutional neural networks to translate leukocyte images into lower-dimensional encodings. Then, we employed support vector machine to predict patients' condition based on those leukocyte encodings. The VEXAS, UBA1-WT, and MDS groups included 3, 3, and 6 patients respectively. Analysis of 33,757 images of neutrophils and monocytes enabled us to distinguish VEXAS patients from both UBA1-WT and MDS patients, with mean ROC-AUCs ranging from 0.87 to 0.95. Image analysis of blood smears via deep learning accurately distinguished neutrophils and monocytes drawn from patients with VEXAS syndrome from those of patients with similar clinical and/or biological features but without UBA1 mutation. Our findings offer a promising pathway to better screening for this disease.

AQAFI: a bioanalytical method for automated KPIs quantification of fluorescent images of human leukocytes and micro-nano particles.

Micro-nanoparticle and leukocyte imaging find significant applications in the areas of infectious disease diagnostics, cellular therapeutics, and biomanufacturing. Portable fluorescence microscopes have been developed for these measurements, however, quantitative assessment of the quality of images (micro-nanoparticles, and leukocytes) captured using these devices remains a challenge. Here, we present a novel method for automated quality assessment of fluorescent images (AQAFI) captured using smartphone fluorescence microscopes (SFM). AQAFI utilizes novel feature extraction methods to identify and measure multiple features of interest in leukocyte and micro-nanoparticle images. For validation of AQAFI, fluorescent particles of different diameters (8.3, 2, 1, 0.8 μm) were imaged using custom-designed SFM at a range of excitation voltages (3.8-4.5 V). Particle intensity, particle vicinity intensity, and image background noise were chosen as analytical parameters of interest and measured by the AQAFI algorithm. A control method was developed by manual calculation of these parameters using ImageJ which was subsequently used to validate the performance of the AQAFI method. For micro-nanoparticle images, correlation coefficients with R2 > 0.95 were obtained for each parameter of interest while comparing AQAFI vs. control (ImageJ). Subsequently, key performance indicators (KPIs) i.e., signal difference to noise ratio (SDNR) and contrast to noise ratio (CNR) were defined and calculated for these micro-nano particle images using both AQAFI and control methods. Finally, we tested the performance of the AQAFI method on the fluorescent images of human peripheral blood leukocytes captured using our custom SFM. Correlation coefficients of R2 = 0.99 were obtained for each parameter of interest (leukocyte intensity, vicinity intensity, background noise) calculated using AQAFI and control (ImageJ). A high correlation was also found between the CNR and SDNR values calculated using both methods. The developed AQAFI method thus presents an automated and precise way to quantify and assess the quality of fluorescent images (micro-nano particles and leukocytes) captured using portable SFMs. Similarly, this study finds broader applicability and can also be employed with benchtop microscopes for the quantitative assessment of their imaging performance.

Novelty Detection of Leukocyte Image via Mean-Shifted Feature and Directly Optimized Subspace

Novelty detection of leukocyte images aims to learn effective data description from in-distribution leukocyte samples and detect out-of-distribution ones that deviate from the expected patterns. Recently, the methods of fine-tuning on the pre-trained model have demonstrated excellent performance in novelty detection. However, those methods are prone to collapse or feature deterioration due to the training data of limited categories and tiny differences of medical images such as leukocyte images. To alleviate the above issues, we propose an unsupervised feature adaptation method based on the Mean-Shifted feature and the directly optimized subspace for leukocyte novelty detection, named SubMSF. Specifically, we first use Mean-Shifted features to alleviate the catastrophic collapse when fine-tuning the pre-trained model via contrastive learning. Then, we combine the Mean-Shifted feature with the directly optimized subspace to recognize tiny differences between leukocytes. Compared with several state-of-the-art methods, the results on real-world leukocyte datasets demonstrate the effectiveness of the proposed SubMSF.

Classification of Leukocytes Using Meta-Learning and Color Constancy Methods

In the human healthcare area, leukocytes are very important blood cells for the diagnosis of different pathologies, like leukemia. Recent technology and image-processing methods have contributed to the image classification of leukocytes. Especially, machine learning paradigms have been used for the classification of leukocyte images. However, reported models do not leverage the knowledge produced by the classification of leukocytes to solve similar tasks. For example, the knowledge can be reused to classify images collected with different types of microscopes and image-processing techniques. Therefore, we propose a meta-learning methodology for the classification of leukocyte images using different color constancy methods involving previous knowledge. Our methodology is trained with a specific task at the meta-level, and the knowledge produced is used to solve a different task at the base-level. For the meta-level, we implemented meta-models based on Xception, and for the base-level, we used support vector machine classifiers. Besides, we analyzed the Shades of Gray color constancy method commonly used in skin lesion diagnosis and now implemented for leukocyte images. Our methodology, at the meta-level, achieved 89.28% for precision, 95.65% for sensitivity, 91.78% for F1-score, and 94.40% for accuracy. These scores are competitive regarding the reported state-of-the-art models, especially the sensitivity which is very important for imbalanced datasets, and our meta-model outperforms previous works by +2.25%. Additionally, for the basophil images that were acquired from a chronic myeloid leukemia-positive sample, our meta-model obtained 100% for sensitivity. Moreover, we present an algorithm that generates a new conditioned output at the base-level obtaining highly competitive scores of 91.56% for sensitivity and F1 scores, 95.61% for precision, and 96.47% for accuracy. The findings indicate that our proposed meta-learning methodology can be applied to other medical image classification tasks and achieve high performances by reusing knowledge and reducing the training time for new similar tasks.

Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan)

Background and objectives: Visual analysis of cell morphology has an important role in the diagnosis of hematological diseases. Morphological cell recognition is a challenge that requires experience and in-depth review by clinical pathologists. Within the new trend of introducing computer-aided diagnostic tools in laboratory medicine, models based on deep learning are being developed for the automatic identification of different types of cells in peripheral blood. In general, well-annotated large image sets are needed to train the models to reach a desired classification performance. This is especially relevant when it comes to discerning between cell images in which morphological differences are subtle and when it comes to low prevalent diseases with the consequent difficulty in collecting cell images. The objective of this work is to develop, train and validate SyntheticCellGAN (SCG), a new system for the automatic generation of artificial images of white blood cells, maintaining morphological characteristics very close to real cells found in practice in clinical laboratories. Methods: SCG is designed with two sequential generative adversarial networks. First, a Wasserstein structure is used to transform random noise vectors into low resolution images of basic mononuclear cells. Second, the concept of image-to-image translation is used to build specific models that transform the basic images into high-resolution final images with the realistic morphology of each cell type target: 1) the five groups of normal leukocytes (lymphocytes, monocytes, eosinophils, neutrophils and basophils); 2) atypical promyelocytes and hairy cells, which are two relevant cell types of complex morphology with low abundance in blood smears. Results: The images of the SCG system are evaluated with four experimental tests. In the first test we evaluated the generated images with quantitative metrics for GANs. In the second test, morphological verification of the artificial images is performed by expert clinical pathologists with 100% accuracy. In the third test, two classifiers based on convolutional neural networks (CNN) previously trained with images of real cells are used. Two sets of artificial images of the SCG system are classified with an accuracy of 95.36% and 94%, respectively. In the fourth test, three CNN classifiers are trained with artificial images of the SCG system. Real cells are identified with an accuracy ranging from 87.7% to 100%. Conclusions: The SCG system has proven effective in creating images of all normal leukocytes and two low-prevalence cell classes associated with diseases such as acute promyelocyte leukemia and hairy cell leukemia. Once trained, the system requires low computational cost and can help augment high-quality image datasets to improve automatic recognition model training for clinical laboratory practice.

Deep self-supervised transformation learning for leukocyte classification.

The scarcity of training annotation is one of the major challenges for the application of deep learning technology in medical image analysis. Recently, self-supervised learning provides a powerful solution to alleviate this challenge by extracting useful features from a large number of unlabeled training data. In this article, we propose a simple and effective self-supervised learning method for leukocyte classification by identifying the different transformations of leukocyte images, without requiring a large batch of negative sampling or specialized architectures. Specifically, a convolutional neural network backbone takes different transformations of leukocyte image as input for feature extraction. Then, a pretext task of self-supervised transformation recognition on the extracted feature is conducted by a classifier, which helps the backbone learn useful representations that generalize well across different leukocyte types and datasets. In the experiment, we systematically study the effect of different transformation compositions on useful leukocyte feature extraction. Compared with five typical baselines of self-supervised image classification, experimental results demonstrate that our method performs better in different evaluation protocols including linear evaluation, domain transfer, and finetuning, which proves the effectiveness of the proposed method.

This Month's Highlights.

Our aim was to evaluate the role of SPECT/CT for the diagnosis of diabetic foot infection by labeled leukocytes. <b>Methods:</b> Seventeen patients with 19 clinically suspected sites of infection were included. After leukocyte labeling and administration, planar scans were acquired at 30 min, 4 h, and 24 h for 18 consecutive patients. SPECT/CT was obtained at 6 h. The final diagnosis was established by clinical follow-up (24 mo) in all cases and by bone biopsy for 14 sites. <b>Results:</b> Leukocyte scanning was positive in 16 of 19 lesions and negative in 3. SPECT/CT changed the interpretation of the planar and SPECT images for 10 of 19 suspected sites (52.6%): it excluded osteomyelitis in 6 cases, revealed bone infection in 1 case, and revealed both bone and soft-tissue infection in 3 cases. The hybrid device did not significantly contribute to the evaluation of patients with negative scan results. <b>Conclusion:</b> SPECT/CT can be useful for a more accurate diagnosis of diabetic foot infection by labeled leukocyte imaging.