scholarly journals Deep Learning Model for the Automatic Classification of White Blood Cells

2022 ◽  
Vol 2022 ◽  
pp. 1-13
Author(s):  
Sarang Sharma ◽  
Sheifali Gupta ◽  
Deepali Gupta ◽  
Sapna Juneja ◽  
Punit Gupta ◽  
...  
Keyword(s):  
Deep Learning ◽  
Blood Cell ◽  
Cell Count ◽  
Blood Cells ◽  
White Blood Cells ◽  
Batch Size ◽  
Blood Cell Count ◽  
Sophisticated Equipment ◽  
Different Types ◽  
Batch Sizes

Blood cell count is highly useful in identifying the occurrence of a particular disease or ailment. To successfully measure the blood cell count, sophisticated equipment that makes use of invasive methods to acquire the blood cell slides or images is utilized. These blood cell images are subjected to various data analyzing techniques that count and classify the different types of blood cells. Nowadays, deep learning-based methods are in practice to analyze the data. These methods are less time-consuming and require less sophisticated equipment. This paper implements a deep learning (D.L) model that uses the DenseNet121 model to classify the different types of white blood cells (WBC). The DenseNet121 model is optimized with the preprocessing techniques of normalization and data augmentation. This model yielded an accuracy of 98.84%, a precision of 99.33%, a sensitivity of 98.85%, and a specificity of 99.61%. The proposed model is simulated with four batch sizes (BS) along with the Adam optimizer and 10 epochs. It is concluded from the results that the DenseNet121 model has outperformed with batch size 8 as compared to other batch sizes. The dataset has been taken from the Kaggle having 12,444 images with the images of 3120 eosinophils, 3103 lymphocytes, 3098 monocytes, and 3123 neutrophils. With such results, these models could be utilized for developing clinically useful solutions that are able to detect WBC in blood cell images.

scholarly journals Blood Cell Count Using Deep Learning Semantic Segmentation

2019 ◽  
Author(s):  
Thanh Tran ◽  
Lam Binh Minh ◽  
Suk-Hwan Lee ◽  
Ki-Ryong Kwon
Keyword(s):  
Deep Learning ◽  
Blood Cell ◽  
Cell Count ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Semantic Segmentation ◽  
Peripheral Blood Smear ◽  
Cell Counting ◽  
Blood Cell Count

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

scholarly journals White Blood Cells and Severe COVID-19: A Mendelian Randomization Study

2021 ◽  
Vol 11 (3) ◽  
pp. 195
Author(s):  
Yitang Sun ◽  
Jingqi Zhou ◽  
Kaixiong Ye
Keyword(s):  
Blood Cell ◽  
Cell Count ◽  
White Blood Cell Count ◽  
White Blood Cell ◽  
Blood Cells ◽  
Mendelian Randomization ◽  
Association Studies ◽  
White Blood Cells ◽  
Genome Wide Association Studies ◽  
Blood Cell Count

Increasing evidence shows that white blood cells are associated with the risk of coronavirus disease 2019 (COVID-19), but the direction and causality of this association are not clear. To evaluate the causal associations between various white blood cell traits and the COVID-19 susceptibility and severity, we conducted two-sample bidirectional Mendelian Randomization (MR) analyses with summary statistics from the largest and most recent genome-wide association studies. Our MR results indicated causal protective effects of higher basophil count, basophil percentage of white blood cells, and myeloid white blood cell count on severe COVID-19, with odds ratios (OR) per standard deviation increment of 0.75 (95% CI: 0.60–0.95), 0.70 (95% CI: 0.54–0.92), and 0.85 (95% CI: 0.73–0.98), respectively. Neither COVID-19 severity nor susceptibility was associated with white blood cell traits in our reverse MR results. Genetically predicted high basophil count, basophil percentage of white blood cells, and myeloid white blood cell count are associated with a lower risk of developing severe COVID-19. Individuals with a lower genetic capacity for basophils are likely at risk, while enhancing the production of basophils may be an effective therapeutic strategy.

scholarly journals White blood cells and severe COVID-19: a Mendelian randomization study

2020 ◽  
Author(s):  
Yitang Sun ◽  
Jingqi Zhou ◽  
Kaixiong Ye
Keyword(s):  
Blood Cell ◽  
Cell Count ◽  
White Blood Cell Count ◽  
White Blood Cell ◽  
Blood Cells ◽  
Mendelian Randomization ◽  
White Blood Cells ◽  
Causal Effects ◽  
Blood Cell Count ◽  
Granulocyte Count

AbstractBackgroundThe pandemic of coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has rapidly emerged to seriously threaten public health. We aimed to investigate whether white blood cell traits have potential causal effects on severe COVID-19 using Mendelian randomization (MR).MethodsTo evaluate the causal associations between various white blood cell traits and severe COVID-19, we conducted a two-sample MR analysis with summary statistics from recent large genome-wide association studies.ResultsOur MR results indicated potential causal associations of white blood cell count, myeloid white blood cell count, and granulocyte count with severe COVID-19, with odds ratios (OR) of 0.84 (95% CI: 0.72-0.98), 0.81 (95% CI: 0.70-0.94), and 0.84 (95% CI: 0.71-0.99), respectively. Increasing eosinophil percentage of white blood cells was associated with a higher risk of severe COVID-19 (OR: 1.22, 95% CI: 1.03-1.45).ConclusionsOur results suggest the potential causal effects of lower white blood cell count, lower myeloid white blood cell count, lower granulocyte count, and higher eosinophil percentage of white blood cells on an increased risk of severe COVID-19.

scholarly journals PSIV-27 Peripheral complete blood cell count results in pigs are impacted by gender, sow parity, and farrowing season

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 291-292
Author(s):  
Elle Rottman ◽  
Alisun N Watson ◽  
Catherine Buck ◽  
Tsungcheng Tsai ◽  
Jeffery J Chewning ◽  
...  
Keyword(s):  
Blood Cell ◽  
Cell Count ◽  
Whole Blood ◽  
Blood Cells ◽  
White Blood Cells ◽  
Mean Corpuscular Hemoglobin ◽  
Complete Blood Cell Count ◽  
Blood Cell Count ◽  
Corpuscular Hemoglobin ◽  
Cell Counts

Abstract Complete blood cell counts have been used as a diagnostic tool across many animal species including swine. To investigate the factors that cause variation in complete blood cell count results, a total of 2,284 whole blood samples were collected from 2012 to 2019 in preweaning piglets (n = 518), nursery pigs (n = 1,704), and grower pigs (n = 60). Whole blood was collected into K2EDTA blood collection tubes and assayed using an automatic hematologic analyzer within 6 hours of collection. Data were analyzed by Mixed procedure of SAS with gender, parity group, and farrowing season as fixed effects. Body weight and age of pigs served as covariances. Farrowing season was grouped into summer (born during May to October) or winter (or November to April). Pigs that were born from first, second, and third parity, and four and above parity sows were assorted into parity group 1, 2 to 3, and 4+, respectively. Barrows had a greater concentration of total white blood cells (P < 0.01), lymphocytes (P < 0.01), and neutrophils (P < 0.01) compared to gilts. Barrows had lower mean corpuscular volume (P = 0.03), mean corpuscular hemoglobin (P < 0.01), and mean corpuscular hemoglobin concentration (P = 0.02) compared to gilts. Pigs that were farrowed in the winter season had a greater concentration of white blood cells (P = 0.01), neutrophils (P = 0.01), and the percentage of neutrophils (P = 0.03), but were lower in the percentage of lymphocytes (P = 0.03) compared to pigs farrowed during summer. Pigs born to parity four and above sows obtained a greater lymphocyte count (P = 0.01), percentage of neutrophils (P = 0.02), and percentage of lymphocytes (P = 0.01). We concluded that peripheral complete blood cells count results were affected by gender, farrowing season, and sow parity.

scholarly journals Analysis of Platelet-Rich Plasma Extraction

2017 ◽  
Vol 5 (1) ◽  
pp. 232596711667527 ◽  
Author(s):  
Jane Fitzpatrick ◽  
Max K. Bulsara ◽  
Paul Robert McCrory ◽  
Martin D. Richardson ◽  
Ming Hao Zheng
Keyword(s):  
Blood Cell ◽  
Cell Count ◽  
White Blood Cell Count ◽  
White Blood Cell ◽  
Blood Cells ◽  
Platelet Rich Plasma ◽  
White Blood Cells ◽  
Clinical Use ◽  
Blood Cell Count ◽  
High Concentrations

Background: Platelet-rich plasma (PRP) has been extensively used as a treatment in tissue healing in tendinopathy, muscle injury, and osteoarthritis. However, there is variation in methods of extraction, and this produces different types of PRP. Purpose: To determine the composition of PRP obtained from 4 commercial separation kits, which would allow assessment of current classification systems used in cross-study comparisons. Study Design: Controlled laboratory study. Methods: Three normal adults each donated 181 mL of whole blood, some of which served as a control and the remainder of which was processed through 4 PRP separation kits: GPS III (Biomet Biologics), Smart-Prep2 (Harvest Terumo), Magellan (Arteriocyte Medical Systems), and ACP (Device Technologies). The resultant PRP was tested for platelet count, red blood cell count, and white blood cell count, including differential in a commercial pathology laboratory. Glucose and pH measurements were obtained from a blood gas autoanalyzer machine. Results: Three kits taking samples from the “buffy coat layer” were found to have greater concentrations of platelets (3-6 times baseline), while 1 kit taking samples from plasma was found to have platelet concentrations of only 1.5 times baseline. The same 3 kits produced an increased concentration of white blood cells (3-6 times baseline); these consisted of neutrophils, leukocytes, and monocytes. This represents high concentrations of platelets and white blood cells. A small drop in pH was thought to relate to the citrate used in the sample preparation. Interestingly, an unexpected increase in glucose concentrations, with 3 to 6 times greater than baseline levels, was found in all samples. Conclusion: This study reveals the variation of blood components, including platelets, red blood cells, leukocytes, pH, and glucose in PRP extractions. The high concentrations of cells are important, as the white blood cell count in PRP samples has frequently been ignored, being considered insignificant. The lack of standardization of PRP preparation for clinical use has contributed at least in part to the varying clinical efficacy in PRP use. Clinical Relevance: The variation of platelet and other blood component concentrations between commercial PRP kits may affect clinical treatment outcomes. There is a need for standardization of PRP for clinical use.

scholarly journals Effects of dietary Mannan oligosaccharide (MOS) on grown, survival rate, intestinal morphology and blood cell count of the golden trevally fish (Gnathanodon specious)

2019 ◽  
Vol 19 (4A) ◽  
pp. 241-250
Author(s):  
Dang Tran Tu Tram ◽  
Nguyen Thi Nguyet Hue ◽  
Ho Son Lam ◽  
Nguyen Truong Tan Tai ◽  
Dao Thi Hong Ngoc
Keyword(s):  
Survival Rate ◽  
Blood Cell ◽  
Blood Cells ◽  
White Blood Cells ◽  
Intestinal Morphology ◽  
The Other ◽  
Control Group ◽  
Blood Cell Count ◽  
Mannan Oligosaccharide ◽  
Erythrocyte Density

The golden trevally fishes (Gnathanodon specious) (2.19 ± 0.23 g) were cultured in glass tanks with density of 20 fishes/tank and they were fed supplemental diets of different MOS concentrations (0; 0.2; 0.4 and 0.6%) for 90 days. Collected data included growth rate, survival rate and some hematological characteristics of this fish. The results demonstrated that MOS supplementation did not affect growth performance, erythrocyte density and blood cell size, however the survival rate was significantly increased. On the other hand, the total number of white blood cells (BC) on the 60th day in the fish fed with MOS supplements (5.78–6.96 × 104TB/mm3) was higher than that in the control group (only 5.43 × 104TB/mm3) with the largest total leukocytes (6.96 ± 0.50 × 104TB /mm3) at 0.2% MOS (p < 0.05).

scholarly journals STUDIES ON THE PHYSIOLOGY OF THE WHITE BLOOD CELL

Blood ◽  
1947 ◽  
Vol 2 (3) ◽  
pp. 235-243 ◽  
Author(s):  
RICHARD WAGNER
Keyword(s):  
Blood Cell ◽  
White Blood Cell ◽  
Blood Cells ◽  
Glycogen Content ◽  
Striated Muscle ◽  
White Blood Cells ◽  
Glycogen Storage ◽  
Different Types ◽  
Blast Cells ◽  
Reducing Substances

Abstract The technic of determining glycogen in isolated white blood cells was applied to the study of the different types of leukemia and of polycythemia, in order to obtain information on the physiology of the white blood cell. From this study it is concluded that the granulated leukocyte is the only carrier of glycogen in whole blood. The "reducing substances" in lymphocytes and blast cells are not considered as true glycogen. The glycogen content of wet white blood cells in the rabbit amounts to about 1 per cent. In the human being a range of from 0.17 to 0.67 per cent was calculated. In disease higher percentages occur, in polycythemia up to 1.64 per cent and in glycogen storage disease up to 3.05 per cent. The glycogen concentration of normal white blood cells is within the same range as that of the striated muscle.

Adaptation to intermittent hypoxia: dynamics of blood oxygen saturation and some hematological parameters

2020 ◽  
Author(s):  
VP Katuntsev ◽  
SYu Zakharov ◽  
TV Sukhostavtseva ◽  
AA Puchkova
Keyword(s):  
Blood Cell ◽  
Oxygen Saturation ◽  
Cell Count ◽  
Red Blood Cell ◽  
Blood Cells ◽  
Reticulocyte Count ◽  
Blood Oxygen ◽  
Blood Cell Count ◽  
Blood Oxygen Saturation ◽  
Red Blood Cell Count

Adaptation to hypoxia is an important object of medical research. The aim of this study was to investigate the dynamics of blood oxygen saturation (SpO2), arterial blood pressure (BP), red blood cells, reticulocytes, hemoglobin and erythropoietin (EPO) concentrations during intermittent hypoxic training (IHT). The study was conducted in 11 healthy male volunteers; 2 regimens were tested: 11 and 14 days of IHT at FIO2 = 9%. Exposure to the hypoxic gas mixture caused a reduction in SpO2 by an average of 20.4% (p < 0.05), a 22% increase in the heart rate (p < 0.05) and a 4.5% decrease in diastolic BP (p < 0.05) relative to the initial levels. After 11 days of IHT training, the reticulocyte count was increased by 16.6% (p < 0.05), and there was a distinct tendency to elevated red blood cells (p > 0.05) and hemoglobin (p > 0.05). EPO concentrations declined by 44.2% (p < 0.05) relative to the initial level. Extending the regimen to 14 days resulted in a 3.9% increase in red blood cell count (p < 0.05) and a 4.7% elevation of hemoglobin concentrations (p < 0.05), accompanied by the recovery of the initial reticulocyte count. The applied 2-week IHT regimen resulted in the increased red blood cell count and elevated hemoglobin, suggesting an improvement in the oxygen-carrying capacity of the blood. The proposed regimen can be used to improve physical performance of individuals working in extreme environmental conditions.

scholarly journals HEMATOLOGIC PROFILE OF LABORATORY RATS FED WITH BAKERY PRODUCTS

2017 ◽  
Vol 5 (5) ◽  
pp. 221-231
Author(s):  
Muhamed Katica ◽  
Nedzad Gradascevic
Keyword(s):  
Blood Cell ◽  
Red Blood Cells ◽  
Cell Count ◽  
Peripheral Blood ◽  
Blood Cells ◽  
Bakery Products ◽  
Blood Cell Count ◽  
Physiological Limits ◽  
Blood Smears ◽  
Peripheral Blood Smears

The laboratory rat, as important biomedical model, was often fed with unconventional diet usually made up of products from the bakery industry. Such diet consisted of insufficient caloric and nutritionally unbalanced meals could cause unreliable results in biomedical research. The study investigates the effects of malnutrition on the haematological profile of rats. The study is performed on Wistar male and female rats which were fed for 4 weeks exclusively with bakery products ad libidum. The following hematological parameters were observed in peripheral blood smears: red blood cell count, content of haemoglobin, haematocrit, MCV, MCH, MCHC, white blood cell count, differential blood count, diameter of red blood cells, as well as the presence of atypical forms of red blood cells. Despite there were no statistically significant differences in overall haematological results (p > 0.05, with > 0.05), the significant part of obtained results were below physiological limits (HGB, MCHC and MCH). Other haematological parameters, including white blood corpuscles were kept in physiological limits, except for mild neutrophils in males. Also, the forms of anulocytes and spherocytes were recorded in peripheral blood smears. The results indicated the beginning of normocytic hypochromic anaemia which was caused by unbalanced meals.

scholarly journals Computational Intelligence Method for Detection of White Blood Cells Using Hybrid of Convolutional Deep Learning and SIFT

2022 ◽  
Vol 2022 ◽  
pp. 1-8
Author(s):  
Mohammad Manthouri ◽  
Zhila Aghajari ◽  
Sheida Safary
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Blood Cells ◽  
Feature Detection ◽  
White Blood Cells ◽  
Processing System ◽  
Health Economy ◽  
Microscopic Images ◽  
Global Issues ◽  
Different Types

Infection diseases are among the top global issues with negative impacts on health, economy, and society as a whole. One of the most effective ways to detect these diseases is done by analysing the microscopic images of blood cells. Artificial intelligence (AI) techniques are now widely used to detect these blood cells and explore their structures. In recent years, deep learning architectures have been utilized as they are powerful tools for big data analysis. In this work, we are presenting a deep neural network for processing of microscopic images of blood cells. Processing these images is particularly important as white blood cells and their structures are being used to diagnose different diseases. In this research, we design and implement a reliable processing system for blood samples and classify five different types of white blood cells in microscopic images. We use the Gram-Schmidt algorithm for segmentation purposes. For the classification of different types of white blood cells, we combine Scale-Invariant Feature Transform (SIFT) feature detection technique with a deep convolutional neural network. To evaluate our work, we tested our method on LISC and WBCis databases. We achieved 95.84% and 97.33% accuracy of segmentation for these data sets, respectively. Our work illustrates that deep learning models can be promising in designing and developing a reliable system for microscopic image processing.

Sign in / Sign up

Export Citation Format

Share Document