Blood Smear Samples Research Articles

Fusion of Color Correction and HSV Segmentation Techniques for Automated Segmentation of Acute Lymphoblastic Leukemia.

This article presents an enhanced segmentation methodology for the accurate detection of acute lymphoblastic leukemia (ALL) in blood smear images. The proposed approach integrates color correction techniques with HSV color space segmentation to improve white blood cell analysis. Our method addresses common challenges in microscopic image processing, including sensor nonlinearity, uneven illumination, and color distortions. The key objectives of this study are to develop a robust preprocessing pipeline that normalizes blood smear images for consistent analysis, implement an HSV-based segmentation technique optimized for leukocyte detection, and validate the method's effectiveness across various ALL subtypes using clinical samples. The proposed technique was evaluated using real-world blood smear samples from ALL patients. Quantitative analysis demonstrates significant improvements in segmentation accuracy compared to traditional methods. Our approach shows strong capability in reliably detecting and segmenting ALL subtypes, offering the potential for enhanced diagnostic support in clinical settings.

An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images.

Malaria is a serious public health concern worldwide. Early and accurate diagnosis is essential for controlling the disease's spread and avoiding severe health complications. Manual examination of blood smear samples by skilled technicians is a time-consuming aspect of the conventional malaria diagnosis toolbox. Malaria persists in many parts of the world, emphasising the urgent need for sophisticated and automated diagnostic instruments to expedite the identification of infected cells, thereby facilitating timely treatment and reducing the risk of disease transmission. This study aims to introduce a more lightweight and quicker model-but with improved accuracy-for diagnosing malaria using a YOLOv4 (You Only Look Once v. 4) deep learning object detector. The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed. The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone. The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.

The Taxonomıc Research of the Prımıtıve Blood Parasıtes and Transmıttıng Ixodıdae Tıcks of the Small Ruminants in the Shırvan-Salyan Economıc Regıon of Azerbaıjan

The primitive blood parasites - piroplasmids are pathogens transmitted to the agricultural animals by the ticks and caused the death and serious economic damage. In Azerbaijan, in the economic regions where the animal husbandry is developed, the systematic investigation and epizootology of these parasites in small ruminants, were researched by us for the first time. For this purpose, the research work was conducted in the Shirvan-Salyan economic region. For this purpose, researches were conducted on the taxonomic study of primitive blood parasites and their transmitters - Ixodidae ticks of small ruminants in the Shirvan-Salyan economic region. Out of 887 sick and suspected diseases sheep, 483 heads (54.5%), and 125 heads (27.4%) of 456 goats had positive results of peripheral blood smear samples attributed to primitive blood parasites. Babesia ovis and Anaplasma ovis parasites were detected in the erythrocytes of sick sheep, and the infection was mostly associated. A.ovis parasite was detected in sero samples of goats. The organs of 56 sheep and 31 goats that died of high fever - spleen, kidney, liver - were examined for primitive blood parasites. The results of the classical examination method in the diagnosis of A.ovis and B.ovis parasites were compared with the effectiveness of the polymerase chain reaction (PCR). 2,875 sheep and goats (1,786 sheep, 1,089 goats) were examined for ectoparasites in livestock farms, 63.8 percent of sheep and 53.6 percent of goats were intensively infected with ticks. Tick infestation was mostly covered in spring, summer and autumn with high intensity. Rhipicephalus bursa ticks were dominant in sheep and Hyalomma plumbeum ticks in goats. In order to determine transovarial and transstadial transmission of disease agents, smears made from internal organs (salivary gland, ovary, intestine) and eggs of ticks were studied for A.ovis and B.ovis parasites.

Predictors of birth weight in pregnant women with malaria: a prospective cohort facility-based study in Webuye-Kenya

In sub-Saharan Africa, malaria, which remains a major public health burden, has a prevalence of 9 to 28% and malaria in pregnancy is associated with severe adverse outcomes for the mother and her baby. Here, we sought to determine the predictors of birth weight in a cohort of 140 women with malaria in pregnancy, who were recruited at the Webuye County hospital in Western Kenya. All study participants underwent malaria diagnosis through microscopic examination of blood smear samples and were grouped into the malaria-positive and malaria-negative groups. Both groups were followed up beginning at the first antenatal visit (March 2022) until delivery (December 2022) and various data, including demographic, parity, gravidity, socioeconomic, maternal and fetal outcomes were collected. Data analyses were done using SPSS version 27. Chi-square and Fisher’s Exact tests were used for bivariate and relative risk analyses at a p-value of ≤0.05 (95%) confidence level. Most of the participants were aged 18–25 years, were primigravidas and married, had secondary school-level education, earned 20–30 thousand Kenya shillings, resided in rural areas, and were in the second trimester. There were 6 (4.6%) cases of low birth weight, 3 (4.5%) in the malaria-negative group and 3 (4.7%) in the malaria-positive group. During pregnancy, 41 (31.5%) were anaemic, 5 (3.8%) were HIV-positive, 5 (3.8%) had preeclampsia, and 2 (1.5%) had gestational diabetes. Our analyses show that confounding factors like anaemia, HIV, pre-eclampsia and gestational diabetes did not influence birthweight (p ≥ 0.923). The malaria-positive and malaria-negative groups did not differ significantly with regard to the low birth weight (relative risk: 0.999, 95% confidence interval: 0.926–1.077). Marital status, gestational age, and area of residence were associated with malaria p ≤ 0.001, ≤ 0.001 and 0.028 respectively. In both groups, 124 of the 140 deliveries had normal birth weights and of these 63 (95.4%, n = 70) were in the malaria-negative group, whereas 61 (95.3%, n = 70) belonged to the malaria-positive group.

Crowdsourced human-based computational approach for tagging peripheral blood smear sample images from Sickle Cell Disease patients using non-expert users

In this paper, we present a human-based computation approach for the analysis of peripheral blood smear (PBS) images images in patients with Sickle Cell Disease (SCD). We used the Mechanical Turk microtask market to crowdsource the labeling of PBS images. We then use the expert-tagged erythrocytesIDB dataset to assess the accuracy and reliability of our proposal. Our results showed that when a robust consensus is achieved among the Mechanical Turk workers, probability of error is very low, based on comparison with expert analysis. This suggests that our proposed approach can be used to annotate datasets of PBS images, which can then be used to train automated methods for the diagnosis of SCD. In future work, we plan to explore the potential integration of our findings with outcomes obtained through automated methodologies. This could lead to the development of more accurate and reliable methods for the diagnosis of SCD.

A Cross-sectional Analysis of Conventional Leishman’s Stain versus Modified Leishman’s Stain: A Study Protocol

Introduction: The conventional Leishman’s stain and modified Leishman’s stain are widely used in medical laboratories for the microscopic examination of blood smears. The conventional stain provides good visualisation of cellular morphology, aiding in the identification of various blood cell types. The modified Leishman’s stain, on the other hand, incorporates alterations to enhance specific cellular structures, improving diagnostic accuracy. Need of the study: In the present study, the authors will observe the differences between the conventional staining method and the modified Leishman's stain method, as well as the advantages of the modified Leishman's staining over the conventional staining method. Aim: To compare Conventional Leishman’s Stain with Modified Leishman’s Stain. Materials and Methods: The cross-sectional study will be conducted from October 2022 to October 2024 at the Department of Pathology, Jawaharlal Nehru Medical College (JNMC), Sawangi (Meghe), Wardha, Maharashtra, India. Ethylenediamine Tetraacetic Acid (EDTA) blood samples will be used for staining. Conventional Leishman’s Stain employs the traditional Leishman’s staining method, while Modified Leishman’s Stain incorporates specific modifications aimed at improving staining quality and enhancing the detection of eosinophils and leukocytes. Several quality control parameters will be assessed, including staining quality, eosinophil and leukocyte visibility, and overall diagnostic accuracy for both peripheral blood smear samples. A panel of experienced haematologists, blinded to the staining technique, independently examines the slides to minimise potential bias. The numbers and morphological characteristics of eosinophils and leukocytes are meticulously recorded, and statistical analysis will be conducted to compare the two staining methods.

IMAGING: a novel automated system for malaria diagnosis by using artificial intelligence tools and a universal low-cost robotized microscope

IntroductionMalaria is one of the most prevalent infectious diseases in sub-Saharan Africa, with 247 million cases reported worldwide in 2021 according to the World Health Organization. Optical microscopy remains the gold standard technique for malaria diagnosis, however, it requires expertise, is time-consuming and difficult to reproduce. Therefore, new diagnostic techniques based on digital image analysis using artificial intelligence tools can improve diagnosis and help automate it.MethodsIn this study, a dataset of 2571 labeled thick blood smear images were created. YOLOv5x, Faster R-CNN, SSD, and RetinaNet object detection neural networks were trained on the same dataset to evaluate their performance in Plasmodium parasite detection. Attention modules were applied and compared with YOLOv5x results. To automate the entire diagnostic process, a prototype of 3D-printed pieces was designed for the robotization of conventional optical microscopy, capable of auto-focusing the sample and tracking the entire slide.ResultsComparative analysis yielded a performance for YOLOv5x on a test set of 92.10% precision, 93.50% recall, 92.79% F-score, and 94.40% mAP0.5 for leukocyte, early and mature Plasmodium trophozoites overall detection. F-score values of each category were 99.0% for leukocytes, 88.6% for early trophozoites and 87.3% for mature trophozoites detection. Attention modules performance show non-significant statistical differences when compared to YOLOv5x original trained model. The predictive models were integrated into a smartphone-computer application for the purpose of image-based diagnostics in the laboratory. The system can perform a fully automated diagnosis by the auto-focus and X-Y movements of the robotized microscope, the CNN models trained for digital image analysis, and the smartphone device. The new prototype would determine whether a Giemsa-stained thick blood smear sample is positive/negative for Plasmodium infection and its parasite levels. The whole system was integrated into the iMAGING smartphone application.ConclusionThe coalescence of the fully-automated system via auto-focus and slide movements and the autonomous detection of Plasmodium parasites in digital images with a smartphone software and AI algorithms confers the prototype the optimal features to join the global effort against malaria, neglected tropical diseases and other infectious diseases.

Characterizing Hematological Changes and Morphological Abnormalities in Hospitalized COVID-19 Patients of Hispanic Descent

Introduction COVID-19 infection is known to significantly impact hematopoiesis and hemostasis, resulting in a wide range of hematological abnormalities. Notably, the pandemic has demonstrated higher mortality rates among the Hispanic population compared to other groups. However, limited comprehensive data exist on specific alterations in COVID-19 patients of Hispanic descent, which could offer valuable insights. This study aims to conduct a thorough examination of hematological changes in hospitalized COVID-19 patients of Hispanic descent, shedding light on unique aspects of the disease within this specific population. Methods We conducted a single-center cross-sectional study in Lima, Peru, analyzing 133 hemogram and blood smear samples collected from hospitalized adult patients (age >18) with confirmed SARS-CoV-2 infection between January and March 2021. Pregnant women and those with pre-existing hematological or autoimmune disorders were excluded. Upon admission, laboratory tests included a complete blood count for assessment, while peripheral blood smears using Wright's staining technique were utilized to observe the morphology and differentiation of the blood cells. Within 24 hours of collection, we recorded basic demographics, blood cell counts, and morphological features. The study focused on hematological examinations taken during the first 4 days of hospitalization. Results Of the samples analyzed, 60.9% (n=81) of samples were from males, with median age 58 (47-68) years. COVID-19 patients showed altered cell counts, with elevated median hemoglobin (12.4 g/dl) and platelets (306 103/μl). White blood cell series had higher median leukocytes (12.4 103/μl), neutrophils (9.5 103/μl), and neutrophil-lymphocyte index (11.5 103/μl), while lymphocyte concentration decreased (0.8 103/μl). Hematological alterations included anemia (64.7%), neutrophilia (65.4%), leukocytosis (60.9%), lymphopenia (59.4%), eosinopenia (51.9%), and thrombocytosis (27.8%). Morphological analysis revealed anisocytosis (18.8%), with smaller proportions of echinocytosis (1.5%) and hypochromia (1.5%) in red blood cells. In the white blood cell lineage, toxic granulations (51.1%) were the most frequently observed characteristic, along with hypersegmentation of neutrophils (32.3%), atypical lymphocytes (15%), acquired Pelger Hüet abnormalities (9%), and circulating myeloblasts (9%). The most common platelet alteration was presence of macroplatelets (33.8%). Conclusion This study offers valuable insights into both quantitative and qualitative hematological alterations observed in hospitalized COVID-19 patients within a specific population. Notably, we identified a higher prevalence of leukocytosis, neutrophilia, lymphopenia, an elevated neutrophil-lymphocyte index, eosinopenia, and anemia, as compared to other cohorts. These alterations have been previously linked to severe cases and have served as prognostic indicators for disease progression and poor outcomes. Recognizing the hematological changes unique to COVID-19 patients of Hispanic descent holds significant importance in tailoring effective healthcare interventions. These findings contribute to the growing body of knowledge, emphasizing the need for further exploration to better inform patient care and global response strategies against COVID-19.

Molecular detection and prevalence study of Neospora caninum isolated from blood of aborted cows in Babylon province of Iraq

Neosporosis is internationally documented as one of the most popular diseases in cattle that cause economic losses due to high levels of abortion cases. Although Neospora caninum has been recently classified as a new species, it is still sharing many features with Toxoplasma gondii. This study aimed to detect and Imaging N. caninum in the blood of aborted cows, and prevalence study of N. caninum infection based on age, region and month. Blood samples from 106 aborted cows were collected using the appropriate method. First, these samples were examined microscopically via blood smears using Giemsa dye to diagnose the N. caninum within RBC. A qPCR technique was carried out to detect accurately 18S rRNA gene accurately. The results revealed that 65% of total aborted cases were positive for 18S rRNA detection of N.caninum, although this parasite was found microscopically in 15% of blood smear samples. According to PCR results, the prevalence study showed that the highest rate of infection was signed in the Al-Qassim district (75%) followed by the Al-Mahaweel district (74%) and decreased in Western Hamza district (48%). According to study months, November recorded the peak of infection (88%), then August (71%), whereas July recorded the lowest percentage (50%). The statistical analysis revealed there was no significant difference between the subjected regions and study months based on (P<0.05). On the other hand, it was found that cows less than 3 years old were more susceptible to infection than those over 3 years old. the results revealed that 71% of infected cows were less than 3 years old, while 29% were at age over 3 years old with a significant difference (P<0.005). In conclusion, N. caninum can be detected through blood within RBC. Age and regional factors in cows play an important role in resisting infection with this pathogen

The effect of paracetamol on the parasitological diagnosis of Plasmodium falciparum malaria

Objectives: Up until the present time, malaria represents an immense public health problem worldwide with a significant morbidity and mortality rate in many developing countries including Sudan. The use of antipyretics and analgesics in the settings of malaria has been a matter of contention over a vast period of time. Now, it is widely believed among the public and some health professionals in Sudan that the antipyretic and analgesic paracetamol disturbs the accuracy of the parasitological diagnosis of malaria. This study investigates the magnitude and effects of that belief through a descriptive study and examines the actual effect of paracetamol on the parasitological diagnosis of falciparum malaria through a clinical trial. Material and Methods: This is a conjoined study that includes a prospective and descriptive study and a randomized, placebo-controlled, double-blind, and parallel-group clinical trial. The descriptive study included 846 participants from various states in Sudan. The targeted study subjects were the public and health professionals and the study was conducted utilizing an online-based questionnaire. The clinical trial included 325 patients with uncomplicated falciparum attending two primary healthcare outpatient clinics in Gezira state, Sudan. The patients were randomly allocated to receive either placebo tablets or 500 mg of oral paracetamol after the first blood smear sample was taken. The second blood smear samples were taken 2 h after taking treatment. Parasite density estimation and other parasitological data were obtained from each sample before and after treatment. Results: The majority of the public thinks that paracetamol affects the parasitological diagnosis of malaria (76.21%, n = 330/433). Personal experience and family and friends were the most dominant information sources for the public (31.20% and 28.01% respectively), while scholarly articles were the most common source of information for the health professional group (45.03%, n = 186/413). No significant differences between the parasitological findings acquired before and after taking the treatments among both the paracetamol group (P = 0.22) and the placebo group (P = 0.12). The parasite density mean for the paracetamol group differed by 16.31 P/μL after taking paracetamol, while the placebo group parasite density mean differed by 15.34 P/μL. The treatments did not inflict impacts on the advanced microscopic features of Plasmodium falciparum blood smears. Conclusion: Paracetamol does not affect the parasitological diagnosis of falciparum malaria.

ACCURATE MEASUREMENT OF HAEMOGLOBIN AND HAEMOCRIT BY USING 3 - PART HEMATOLOGY ANALYZER -SYSMEX XP-300

One of the most fundamental laboratory tests in haematology is the evaluation of blood smear because variations in blood cell counts from reference values might signal a number of illness problems. Based on CBC values and blood cell shape, R studio can aid technicians in the analysis and classification of blood cells as well as the identification of certain medical diseases. The objective of this project is to create software that can recognise and categorise haemoglobin and haematocrit in different blood cells from peripheral blood smear samples. Manually locating, recognising, and classifying the Hg and Hct can be tiresome, time-consuming, and erroneous. However, automatic haematology that solely perform quantitative analysis and rely on the flow cytometry categorization concept are expensive. This suggested study seeks to produce a preliminary framework of Automatic analysers Analysis of Human Blood Smear for identification, classification of Hg and HCT of blood cells by employing various data taking into consideration the broad range of data in the field of medicine. Key Words: Sysmex XP-300 Hematology analyser, blood samples, blood analyser, haematocrit.

Robust and compact digital Lensless Holographic microscope for Label-Free blood smear imaging

The lack of equipped healthcare infrastructure in isolated hard-to-reach zones exposes their population to a higher risk of complications in common diseases. With a timely diagnosis setting a life-altering difference, worldwide efforts have been conducted for the development of point-of-care testing (PoCT) with cost-effective devices. Among the most common interests in PoCT is the analysis of blood smear samples, as they can help to detect, diagnose, and monitor a wide range of diseases and disorders. With microscopy being the traditional tool for these analyses, a significative advance has been the development of cost-effective digital holographic microscopy systems, driven in part by its label-free imaging capabilities that waive the need for any sample preprocessing. Here, a robust and portable digital lensless holographic microscope, functionalized for the analysis of non-preprocessed blood smear samples in PoCT environments, is presented, and its viability is tested in the observation of red blood cells. The device uses an optical fiber with a cone-shaped tip instead of a pinhole, which ensures the sturdiness of the system and eliminates the need for challenging alignment. While the distances of the microscope can be tuned before fabrication, the herein-reported operational parameters are functionalized for the specific analysis of blood samples.

Classification of acute lymphoblastic leukaemia using machine learning algorithms

Acute Lymphoblastic Leukemia is a serious disease which may cause death if it is not detected at an early stage. It is common in children as well as adults. The detection of ALL is being done manually by examining the blood smear samples under a microscope. Manual blood testing has got several shortcomings such as it is slow and accuracy is also less. Generally, the inspection is done by an experienced pathologists and if there is any malformations the presence of lymphoblasts will be there. The accuracy of the diagnosis will be dependent on the experience of the operator. The Proposed research work aims in improving the diagnosis of ALL using Machine Learning Classifiers. Few classifiers haven been applied and compared on the segmented dataset images. The automated system can provide several advantages like it will minimize human intervention and it would provide more accurate results. In this research work EDES-SVM and EDSC-SVM have been used for classification. Experimental results obtained are then compared with the results of other machine learning classifiers such as SVM, ESVM, DSC-SVM, DES-SVM. From the experimental results it is analysed that the proposed method outperforms the conventional methods.

Digital Morphology Analyzer Sysmex DI-60 vs. Manual Counting for White Blood Cell Differentials in Leukopenic Samples: A Comparative Assessment of Risk and Turnaround Time.

BackgroundDigital morphology (DM) analyzers are increasingly being used for white blood cell (WBC) differentials. We assessed the laboratory efficiency of the Sysmex DI-60 system (DI-60; Sysmex, Kobe, Japan) in comparison with manual counting in leukopenic samples.MethodsIn total, 40 peripheral blood smear samples were divided into normal, mild leukopenia, moderate leukopenia, and severe leukopenia groups based on WBC count. In each group, the risk and turnaround time (TAT) were compared between DI-60 and manual counting. Risk was determined by failure mode and effect analysis using the risk priority number (RPN) score, and TAT was recorded for the analytical phase.ResultsOverall, DI-60 showed a five-fold lower risk (70 vs. 350 RPN) and longer TAT than manual counting. In severe leukopenic samples, DI-60 showed a shorter TAT/slide and a remarkably lower cell count/slide than manual counting. In all samples, the TAT/cell for DI-60 was substantially longer than that for manual counting (DI-60 vs. manual total, 1.8 vs. 1.0 sec; normal, 1.5 vs. 0.7 sec; mild leukopenia, 1.9 vs. 0.9 sec; moderate leukopenia, 1.8 vs. 1.0 sec; severe leukopenia, 28.8 vs. 19.0 sec).ConclusionsThis is the first comparative assessment of risk and TAT between DI-60 and manual counting in leukopenic samples. DI-60 decreases the laboratory risk and improves patient safety, but requires more time to count fewer cells, especially in severe leukopenic samples. DM analyzers should be applied selectively depending on the WBC count to optimize laboratory efficiency.

Automatic detection of the parasite Trypanosoma cruzi in blood smears using a machine learning approach applied to mobile phone images.

Chagas disease is a life-threatening illness caused by the parasite Trypanosoma cruzi. The diagnosis of the acute form of the disease is performed by trained microscopists who detect parasites in blood smear samples. Since this method requires a dedicated high-resolution camera system attached to the microscope, the diagnostic method is more expensive and often prohibitive for low-income settings. Here, we present a machine learning approach based on a random forest (RF) algorithm for the detection and counting of T. cruzi trypomastigotes in mobile phone images. We analyzed micrographs of blood smear samples that were acquired using a mobile device camera capable of capturing images in a resolution of 12 megapixels. We extracted a set of features that describe morphometric parameters (geometry and curvature), as well as color, and texture measurements of 1,314 parasites. The features were divided into train and test sets (4:1) and classified using the RF algorithm. The values of precision, sensitivity, and area under the receiver operating characteristic (ROC) curve of the proposed method were 87.6%, 90.5%, and 0.942, respectively. Automating image analysis acquired with a mobile device is a viable alternative for reducing costs and gaining efficiency in the use of the optical microscope.

Analysis of laboratory re-examination results in Sichuan Provincial Malaria Diagnostic Reference Laboratory from 2014 to 2020

To re-examine the diagnosis results of reported malaria cases in Sichuan Province from 2014 to 2020, so as to assess the malaria diagnostic capability of Sichuan Provincial Malaria Diagnostic Reference Laboratory. The blood and blood smear samples from reported malaria cases were collected by Sichuan Provincial Malaria Diagnostic Reference Laboratory from 2014 to 2020, and subjected to re-examinations using microscopy and nested PCR assay. The re-examination results were compared. A total of 1 710 samples from reported malaria cases were re-examined by Sichuan Provincial Malaria Diagnostic Reference Laboratory from 2014 to 2020, and 1 634 samples were identified positive, with a positive coincidence rate of 95.56% (1 634/1 710) and a 92.29% (1 508/1 634) total coincidence rate of the Plasmodium species. The coincidence rates with P. falciparum, P. vivax, P. malariae and P. ovale were 99.48% (961/966), 97.07% (430/443), 83.05% (98/118) and 67.86% (19/28), respectively, and the coincidence rate was 91.81% (1 513/1 648) between microscopic and nested-PCR results. The capability of microscopists remains weak at grassroot medical institutions in Sichuan Province. Further training is required among microscopists to improve the malaria surveillance capability in Sichuan Province during the post-elimination stage.

First report of Trypanosoma vivax infection in sheep from Nicaragua.

In Central America, outbreaks of trypanosomiasis by Trypanosoma vivax have been recorded only in cattle. This is the first report of an outbreak of trypanosomiasis by T. vivax in 30 Pelibuey sheep (2 to 7years old, male and female) from Nicaragua, which occurred in 2009. Clinical signs included fever, apathy, pale mucous membranes, weakness, progressive weight loss, and sudden death. Infection by T. vivax was detected in 22 (73.3%) sheep by blood smear analysis and/or PCR. Trypanosomes were morphologically identified in 11 (36.7%) blood smear samples, whereas 17 (85%) of the 20 samples subjected to PCR were positive for T. vivax. Eighteen (81.8%) of the 22 infected sheep presented a packed red cell volume (PCV) lower than 25%. Upon diagnosis, the treated animals were clinically recovered and no parasites could be observed in subsequent examinations. Tabanids were potential mechanical vectors of T. vivax in the farm. This is the first report of T. vivax in Nicaragua and for the first time this haemoparasite is recorded in sheep in Central America.

Multi-stage malaria parasite recognition by deep learning.

MotivationMalaria, a mosquito-borne infectious disease affecting humans and other animals, is widespread in tropical and subtropical regions. Microscopy is the most common method for diagnosing the malaria parasite from stained blood smear samples. However, this technique is time consuming and must be performed by a well-trained professional, yet it remains prone to errors. Distinguishing the multiple growth stages of parasites remains an especially challenging task.ResultsIn this article, we develop a novel deep learning approach for the recognition of malaria parasites of various stages in blood smear images using a deep transfer graph convolutional network (DTGCN). To our knowledge, this is the first application of graph convolutional network (GCN) on multi-stage malaria parasite recognition in such images. The proposed DTGCN model is based on unsupervised learning by transferring knowledge learnt from source images that contain the discriminative morphology characteristics of multi-stage malaria parasites. This transferred information guarantees the effectiveness of the target parasite recognition. This approach first learns the identical representations from the source to establish topological correlations between source class groups and the unlabelled target samples. At this stage, the GCN is implemented to extract graph feature representations for multi-stage malaria parasite recognition. The proposed method showed higher accuracy and effectiveness in publicly available microscopic images of multi-stage malaria parasites compared to a wide range of state-of-the-art approaches. Furthermore, this method is also evaluated on a large-scale dataset of unseen malaria parasites and the Babesia dataset.AvailabilityCode and dataset are available at https://github.com/senli2018/DTGCN_2021 under a MIT license.

Performance of digital morphology analyzer Vision Pro on white blood cell differentials.

Vision Pro (West Medica, Perchtoldsdorf, Austria) is a recently developed digital morphology analyzer. We evaluated the performance of Vision Pro on white blood cell (WBC) differentials. In a total of 200 peripheral blood smear samples (100 normal and 100 abnormal samples), WBC preclassification and reclassification by Vision Pro were evaluated and compared with manual WBC count, according to the Clinical and Laboratory Standards Institute guidelines (H20-A2). The overall sensitivity was high for normal WBCs and nRBCs (80.1-98.0%). The overall specificity andoverall efficiency were high for all cell classes (98.1-100.0% and 97.7-99.9%, respectively). The absolute values of mean differences between Vision Pro and manual count ranged from 0.01 to 1.31. In leukopenic samples, those values ranged from 0.09 to 2.01. For normal WBCs, Vision Pro preclassification and manualcount showed moderate or high correlations (r=0.52-0.88) except for basophils (r=0.34); after reclassification, the correlation between Vision Pro and manual count was improved (r=0.36-0.90). This is the first study that evaluated the performance of Vision Pro on WBC differentials. Vision Pro showed reliable analytical performance on WBC differentials with improvement after reclassification. Vision Pro could help improve laboratory workflow.

Acute Myeloid Leukemia (AML) Detection Using AlexNet Model

Acute Myeloid Leukemia (AML) is a kind of fatal blood cancer with a high death rate caused by abnormal cells’ rapid growth in the human body. The usual method to detect AML is the manual microscopic examination of the blood sample, which is tedious and time‐consuming and requires a skilled medical operator for accurate detection. In this work, we proposed an AlexNet‐based classification model to detect Acute Myeloid Leukemia (AML) in microscopic blood images and compared its performance with LeNet‐5‐based model in Precision, Recall, Accuracy, and Quadratic Loss. The experiments are conducted on a dataset of four thousand blood smear samples. The results show that AlexNet was able to identify 88.9% of images correctly with 87.4% precision and 98.58% accuracy, whereas LeNet‐5 correctly identified 85.3% of images with 83.6% precision and 96.25% accuracy.