Blood Smear Microscopy Research Articles

HRP2 and PLDH Performance Comparison as Rapid Diagnostic Tools for Symptomatic Malaria Patients at Rugazi HC IV in Rubirizi District

Background: Rapid and precise laboratory diagnosis is essential for effectively diagnosing and managing malaria patients. Malaria rapid diagnostic tests (mRDTs) play a critical role in malaria diagnosis in resource-constrained settings with limited access to labs and trained staff. The efficiency of two mRDTs (HRP2 and pLDH) was compared against microscopy, the gold standard for malaria diagnosis, in this study. Methods: In a cross-sectional study, 308 participants were tested for malaria parasites using two mRDTs and blood smear microscopy as the gold standard. STATA software version 17 was used for data analysis. Results: Out of the 308 participants, 82 tested positive for HRP2 mRDT (26.62% (95% CI: 21.97-31.86) positivity rate, 73.38% (95% CI: 68.14-78.83) negativity rate), and 99 tested positive for pLDH mRDT (32.14% (95% CI: 27.14-37.59) positivity rate, 67.86% (95% CI: 62.41-72.86) negativity rate). Using microscopy as the gold standard, the sensitivity, specificity, PPV, and NPV were determined. For HRP2 mRDT, sensitivity was 77.78% (95%CI: 73.13-82.42), specificity 97.61% (95%CI: 95.90 - 99.31), PPV 93.90% (95%CI: 91.23 – 96.56), and NPV 90.27% (95%CI: 86.96-93.58). For pLDH mRDT, the sensitivity was 94.95% (95% CI: 92.50-97.40), specificity was 97.61% (95% CI: 95.90-99.31), PPV was 94.95% (95% CI: 92.50 – 97.40), and NPV was 97.61% (95% CI: 95.90 - 99.31). The dominant malaria species was Plasmodium falciparum (74.7%), followed by Plasmodium vivax (12.1%) and Plasmodium ovale (1%). Mixed infections of plasmodium falciparum and plasmodium vivax (7.1%) and plasmodium falciparum and plasmodium ovale (5.1%) were also observed. Conclusion: There was no significant difference in the positivity rate, negativity rate, specificity or PPV in both mRDTs. However, a significant difference in the NPV and sensitivity of HRP2 and pLDH mRDTs was observed where HRP2’s sensitivity was below the WHO recommendation of ≥95% in this study population; thus, there is a need to improve the sensitivity of this mRDT kit. In our study, most malaria infections were caused by Plasmodium falciparum, followed by P. vivax and P. ovale. We therefore recommend the use of pLDH mRDTs over HRP2 mRDTs based on the results of our study

Challenges in Diagnosing and Treating Acutely Febrile Children with Suspected Malaria at Health Care Facilities in the Lake Mwanza Region of Tanzania.

Acute febrile diseases transmitted by mosquitos are a diagnostic challenge for pediatricians working in sub-Saharan Africa. Misclassification due to the lack of rapid, reliable diagnostic tests leads to the overuse of antibiotics and antimalarials. Children presenting with acute fever and suspected of having malaria were examined at health care facilities in the Mwanza Region of Tanzania. The sensitivity and specificity of blood smear microscopy and malaria rapid diagnostic tests that targeted histidine-rich protein 2 and Plasmodium lactate dehydrogenase were compared with a multiplex reverse transcriptase-polymerase chain reaction (PCR)-ELISA. Six hundred ninety-eight children presented with acute fever and met the criteria for inclusion; 23% received antibiotics and 23% received antimalarials prior to admission. Subsequently, 20% were confirmed by PCR to have Plasmodium falciparum infection. Blood smear microscopy exhibited 33% sensitivity and 93% specificity. The malaria rapid test provided 87% sensitivity and 98% specificity in detecting acute malaria infections. Only 7% of malaria-negative children received antimalarials at Sengerema Designated District Hospital when treatment was guided by the results of rapid testing. In contrast, 75% of malaria-negative patients were treated with antimalarial drugs at health facilities that used blood smears as the standard diagnostic test. Misclassification and premedication of nonmalarial, febrile illnesses contribute to the emergence of antimalarial and antimicrobial resistance. The incorporation of malaria rapid diagnostic tests into the clinical routine translated into improved treatment and a significant reduction in antimalarial drug prescriptions.

First report of dengue virus among febrile malaria positive and negative patients in Nyala city, Western Sudan

Background: The mosquito borne dengue fever and malaria -; are major public health concerns in tropical settings. They are highly prevalent and considered one of the main etiology of febrile illnesses in Sudan. Aim: This study aimed to determine seroprevalence of dengue virus among febrile malaria positive and negative patients in Nyala city, Western Sudan by using Enzyme linked immuno sorbent assay (ELISA) to detect dengue virus IgM and IgG antibodies. It also aimed to study possible risk factors that may be associated with dengue virus and malaria infections. Methods: This cross sectional study, which was undertaken in different Hospitals in Nyala city, South Darfur state Sudan during June to December 2021. A total of 93 blood samples from febrile patients were collected in EDTA containers. Plasma was obtained by centrifugation and tested by ELISA (EUROIMMUN, Germany) according to manufactures instructions for dengue virus IgG and IgM antibodies. Malaria parasites were detected using microscopy of stained blood smears. Generated data was analyzed using the statistical package (SPSS) version 21. Results: Forty six (49.5%) out of 93 febrile patients were found infected with malaria parasites using blood smear microscopy. Among these malaria infected patients, the prevalence of dengue anti-virus IgG (49 .5%) was higher than that of IgM (16.1%) but was statistically insignificant (p>0.05). In the present study dengue infection was higher in males than in females but was statistically insignificant (P> 0.05) and the Age group 21-40 years was the most affected with dengue virus infection. Conclusion: The present study showed higher prevalance rate of dengue IgG among the participants of study more than IgM but was statistically insignificant There was no association between age and gender with seroplevance of dengue virus among febrile patients with and without malaria. The frequent existence of infections of DENV requires improved surveillance and control measures to combat this disease in Nyala, Sudan.

Subclinical malaria among pregnant women living in refugee settlements in Northern Uganda.

Malaria during pregnancy contributes to significant perinatal morbidity and mortality, accounting for almost 25% of global maternal mortality. However, the epidemiology and risk factors for subclinical malaria among pregnant women living in refugee settlements is poorly understood. To determine the prevalence and predictors of subclinical malaria among pregnant women in refugee settlements in Northern Uganda. We conducted a multi-center, cross-sectional study. The study was conducted between April and June 2023 and involved pregnant women aged 18-45 years attending routine antenatal care (ANC) at three health facilities serving refugee communities in Adjumani district, Uganda. We collected sociodemographic, environmental, maternal, and obstetric factors using a structured questionnaire. Both CareStart Malaria HRP-2/pLDH (Pf/Pan) combo rapid diagnostic test (RDT) and blood smear microscopy with 3% Giemsa staining were simultaneously performed on samples from each patient. Logistic regression analysis identified factors independently associated with subclinical malaria, reported as adjusted odds ratios (aORs) and 95% confidence intervals (CIs). We enrolled 304 pregnant women, with a mean age of 25 years. In total, 68.8% (n = 209) had lived in the settlement for over 12 months, 25.7% (n = 78) were primigravida, and 1.0% (n = 3) were living with HIV. Malaria prevalence was 5.3% (n = 16) by RDT and 3.2% (n = 10; seven Plasmodium falciparum and three P. malariae) by microscopy. Only 4 (25.0%) of the RDT-positive cases were also positive by microscopy (Cohen's kappa: 0.278-Fair agreement). All participants were asymptomatic. Factors associated with higher odds of subclinical malaria included primiparity (aOR: 2.79, 95% CI: 1.25-6.25, p = 0.013), ⩾4 ANC visits (aOR: 2.41, 95% CI: 1.34-4.34, p = 0.003), and residence in the settlement for less than 12 months (aOR: 2.54, 95% CI: 2.0-3.22, p < 0.001). Living in the settlement for over 3 years, being primigravida, and being married were associated with 68%, 50%, and 68% lower odds of subclinical malaria, respectively (aOR: 0.32, 95% CI: 0.13-0.79, p = 0.014; aOR: 0.50, 95% CI: 1.22-5.52, p = 0.016; aOR: 0.32, 95% CI: 0.13-0.78, p = 0.012). Our study reveals the high prevalence of subclinical malaria among pregnant women in refugee settlements, particularly among primiparous women and recent arrivals. The poor agreement between RDT and microscopy suggests the need for dual screening in asymptomatic pregnant women.

РАСПРОСТРАНЕНИЕ, ЛЕЧЕБНО-ПРОФИЛАКТИЧЕСКИЕ МЕРОПРИЯТИЯ, ПРОВОДИМЫЕ ПРИ БАБЕЗИОЗЕ СОБАК В ВЕТЕРИНАРНЫХ КЛИНИКАХ ГОРОДА АСТАНА

The article shows the results of study of 94 dogs in Astana, where the presence of babesiosis was confirmed. The disease clinically manifested as apathy (100%), anorexia (85%), increase in overall body temperature (78%), hemoglobinuria (64%), vomiting (42%), diarrhea (41%), icteric mucous membranes (35%), and paresis of the hind legs (28%). Microscopy of peripheral blood smears stained using the Romanowsky-Giemsa method revealed the presence of Babesia canis. Complete blood count and blood chemistry conducted in the animals showed a reduced number of erythrocytes, hemoglobin, as well as bilirubinemia, and increased levels of AST and ALT enzymes. The peak of incidence occurs in May (Epidemiological Index (EI) 93.3%), in April and summer the infestation rate is above average (EI 73.3-79.2%). In August and September, ticks in animals are two times less common than in May, and the prevalence is reduced to 66.7%. The dogs received comprehensive treatment, including the reduction of intoxication and dehydration, broad-spectrum antibiotics, antiemetic drugs, a lytic cocktail to reduce elevated body temperature, and analgesics. When comparing the main drugs, Piro-stop and Azidin, the former was found to be more effective. For disease prevention, dog owners prefer to use Bravecto.

Molecular diversity and polyparasitism of avian trypanosomes in the Brazilian Atlantic Rainforest.

The current study proposes to investigate the diversity and phylogeny of trypanosomes parasitizing wild birds from the Brazilian Atlantic Forest. Cytological examination was carried out by light microscopy of blood smears and positive birds were selected for amplification of the 18S rDNA sequence through PCR. The resulting amplicons were subjected to purification, cloning, and sequencing analysis. Phylogenetic reconstruction was conducted, including all avian trypanosomes representative's lineages. A total of ten bird samples from species of Turdus flavipes (N=1/12), T. albicollis (N=1/8), Tachyphonus coronatus (N=6/121), Thamnophilus caerulescens (N=1/22) and Synallaxis spixi (N=1/8) were positive for Trypanosoma spp. In the six specimens of T. coronatus, five distinct lineages of Trypanosoma spp. 18S-rRNA were observed in ninety sequences obtained, and using the strategy of cloning independent PCR, it was possible to observe that two of them were related to T. avium (JB01/JB02), and three were closed related to T. bennetti (JB03/ JB04/JB05). Addionaly, all fifteen sequences obtained from T. caerulescens/ S. spixi/T. flavipes/T. albicollis were identical. The present research is the first study to access molecular diversity and polyparasitism by avian trypanosomes in Brazil. The current research exhibits the wide genetic variability in avian trypanosomes and its non-specific relationship with its avian hosts.

Detection of Trypanosoma lewisi from rodents residing in the densely populated residential regions along the coastal areas of Banyuwangi Sub District, Indonesia.

Extensive attention has been devoted to studies of Trypanosoma lewisi in rodents ever since it became recognised as a zoonotic pathogen known as atypical human trypanosomiasis. Regrettably, although T. lewisi infections of small mammals remain significant public health concerns for humans, there is a lack of comprehensive study in Indonesia. The aim of the study was to detect T. lewisi from rodents residing in the densely populated residential regions along the coastal areas of Banyuwangi Sub District. A total of 169 rodents were captured across three villages of Kampung Mandar, Lateng and Kepatihan, using rat single live traps. After being euthanized and identified, the blood samples were collected from each rodent via cardiac puncture. Subsequently, the samples were subjected to native (direct blood microscopic examination), microscopic blood smear examination, and molecular analyses utilizing TRYP1S-TRYP1R (623 bp) and LEW1S-LEW1R (220 bp). The results demonstrated that two species of rodents were successfully captured: Rattus norvegicus (65.68%) and Rattus tanezumi (34.32%). Based on the native and microscopic blood smear examinations, the prevalence of T. lewisi across three villages was 23.08% and 24.26% for molecular analysis employing both primers, respectively. The highest prevalence was found in Kampung Mandar Village (31.18%), followed by Kepatihan (16.67%) and Lateng Villages (15.71%). Statistical analysis revealed that T. lewisi was more prevalent in R. tanezumi compared to R. norvegicus. In terms of sex, no statistically significant distinction was observed between female and male infected rodents of either species (p > 0.05), indicating both species can serve as a source of T. lewisi for humans in the surveyed villages.

Asymptomatic Malaria among Pregnant Women Attending Ante-Natal Clinic in Osogbo, Nigeria

Background: Pregnant women are in danger from malaria infection during pregnancy, which is a serious public health issue. A key obstacle to eradicating malaria is the reservoir host for the parasite, and is also regarded as one of the main obstacles to eliminating malaria. This study assessed the prevalence of asymptomatic malaria and associated factors among pregnant women attending antenatal clinics in Osogbo, Southwestern Nigeria. Methods: A hospital-based cross-sectional study was conducted between July and October 2020 to assess the prevalence and predictors of asymptomatic malaria among 294 consenting pregnant women. Socio-demographic data, Intermittent Preventive Treatment in pregnancy with SP (IPTp-SP), and information on insecticide-treated nets use were collected using a structured questionnaire. SD BIOLINE Malaria rapid diagnostic test kits and Giemsa-stained blood smear microscopy were used to diagnose Plasmodium infections. Anaemia status was determined using microhematocrit centrifugation. Data were analysed using SPSS version 20.0 statistical software. In all comparisons, p-values ≤ 0.05 were considered statistically significant. Results: The prevalence of asymptomatic malaria infection was 20.4% (60/294) and 23.5% (69/ 294) using microscopy and RDT, respectively. Among those infected, 76.7% were anaemic (p=0.001). Asymptomatic malaria was significantly associated with not using insecticide-treated bed nets (ITN). Secundigravida women and being in third-trimester pregnancy were significant determinants of pregnancy-associated malaria. Conclusion: This study showed that malaria and anaemia are still prevalent among pregnant women in Southern Nigeria, and it is a significant concern for public health. Improved access to intermittent preventive treatment with sulphadoxine-pyrimethamine and the use of long-lasting insecticidal nets should be encouraged to help further diminish the risk of malaria infection amongst pregnant women in the region.

Can incorporating genotyping data into efficacy estimators improve efficiency of early phase malaria vaccine trials?

BackgroundEarly phase malaria vaccine field trials typically measure malaria infection by PCR or thick blood smear microscopy performed on serially sampled blood. Vaccine efficacy (VE) is the proportion reduction in an endpoint due to vaccination and is often calculated as VEHR = 1–hazard ratio or VERR = 1–risk ratio. Genotyping information can distinguish different clones and distinguish multiple infections over time, potentially increasing statistical power. This paper investigates two alternative VE endpoints incorporating genotyping information: VEmolFOI, the vaccine-induced proportion reduction in incidence of new clones acquired over time, and VEC, the vaccine-induced proportion reduction in mean number of infecting clones per exposure.MethodsPower of VEmolFOI and VEC was compared to that of VEHR and VERR by simulations and analytic derivations, and the four VE methods were applied to three data sets: a Phase 3 trial of RTS,S malaria vaccine in 6912 African infants, a Phase 2 trial of PfSPZ Vaccine in 80 Burkina Faso adults, and a trial comparing Plasmodium vivax incidence in 466 Papua New Guinean children after receiving chloroquine + artemether lumefantrine with or without primaquine (as these VE methods can also quantify effects of other prevention measures). By destroying hibernating liver-stage P. vivax, primaquine reduces subsequent reactivations after treatment completion.ResultsIn the trial of RTS,S vaccine, a significantly reduced number of clones at first infection was observed, but this was not the case in trials of PfSPZ Vaccine or primaquine, although the PfSPZ trial lacked power to show a reduction. Resampling smaller data sets from the large RTS,S trial to simulate phase 2 trials showed modest power gains from VEC compared to VEHR for data like those from RTS,S, but VEC is less powerful than VEHR for trials in which the number of clones at first infection is not reduced. VEmolFOI was most powerful in model-based simulations, but only the primaquine trial collected enough serial samples to precisely estimate VEmolFOI. The primaquine VEmolFOI estimate decreased after most control arm liver-stage infections reactivated (which mathematically resembles a waning vaccine), preventing VEmolFOI from improving power.ConclusionsThe power gain from the genotyping methods depends on the context. Because input parameters for early phase power calculations are often uncertain, these estimators are not recommended as primary endpoints for small trials unless supported by targeted data analysis.Trial registrations: NCT00866619, NCT02663700, NCT02143934.

Evaluating Thresholding-Based Segmentation and Humoment Feature Extraction in Acute Lymphoblastic Leukemia Classification using Gaussian Naive Bayes

This study, titled "Evaluating Thresholding-Based Segmentation and HuMoment Feature Extraction in Acute Lymphoblastic Leukemia Classification using Gaussian Naive Bayes," investigates the application of image processing and machine learning techniques in the classification of Acute Lymphoblastic Leukemia (ALL). Utilizing a dataset of microscopic blood smear images, the research focuses on the efficacy of thresholding-based segmentation and Hu moment feature extraction in distinguishing between benign and malignant cases of ALL. Gaussian Naive Bayes, known for its simplicity and effectiveness, is employed as the classification algorithm. The study adopts a 5-fold cross-validation approach to evaluate the model's performance, with particular emphasis on metrics such as accuracy, precision, recall, and F1-score. Results indicate a high precision rate across all folds, averaging approximately 84.13%, while exhibiting variability in accuracy, recall, and F1-scores. These findings suggest that while the model is effective in identifying malignant cases, further refinements are necessary for improving overall accuracy and consistency. This research contributes to the field of medical image analysis by demonstrating the potential of combining simple yet efficient techniques for the automated diagnosis of hepatological diseases. It highlights the importance of integrating image processing with machine learning to enhance diagnostic accuracy in medical applications.

A Deep Learning Framework for Classification of Immature White Blood Cells in Acute Myeloid Leukemia Using Convolutional Autoencoder and Transfer-Learning Ensemble

Acute myeloid leukemia (AML) is a type of acute leukemia that affects myeloid cells. It is characterized by uncontrolled proliferation of immature WBCs causing an accumulation of immature WBCs in the bone marrow and peripheral circulation. AML is an aggressive cancer that can be life-threatening if not treated promptly, therefore, early detection is crucial. Identification of immature WBCs and their subtypes is the first step towards AML diagnosis. Microscopic blood smear image analysis is commonly used to diagnose AML as it is less expensive non-invasive diagnostic tool compared to bone marrow biopsy and immunophenotype. Nonetheless, classifying immature WBCs presents challenges due to their high similarity and minimal interclass variation, especially for intermediate stages of myelopoiesis which make is susceptible to misclassification. The current diagnostic methods of AML are based on manual identification of immature WBCs using peripheral blood smear. These methos are time-consuming, prone to errors, and subject to inter-observer variation. Therefore, this study aims to develop a computer-aided diagnostic framework to accurately identify immature WBCs and classify them into various subtypes. The proposed framework consists of two main components: a binary classification system to classify cells into mature versus immature cells and a multiclassification system to further classify immature cells into four subtypes including myeloblast, monoblast, and promyelocytes. The proposed framework was designed to undergo four distinct phases: the first phase involves preprocessing, which includes data augmentation techniques aimed at addressing the imbalance distribution of WBCs. Augmentation encompasses geometric transformation and generation of synthetic images using convolutional Autoencoder (CAE). Feature extraction phase involves using image embedding and transfer-learning. Image embedding representation was obtained using CAE and then utilized by two pre-trained models: VGG19 and Resnet50. Classification phase was carried out using weighted ensemble of the VGG19 and Resnet50 with the optimal weights determined through Grid search. The validation phase evaluated the model performance using overall accuracy, precision, and sensitivity. The area under the ROC curve (AUC) was used to assess model discrimination ability. The proposed framework demonstrated excellent results, achieving an average accuracy of 99.5%, a sensitivity of 97.97%, and a precision of 94.12%. The model exhibited an excellent discriminatory capability, with an AUC of 99.9%. Furthermore, the proposed framework outperformed previous methods, showcasing improved performance. Key word: Acute myeloid leukemia, peripheral blood smear, immature white blood cells, deep learning, feature extraction, computer-aided diagnosis.

Babesia negevi infection in dogs and response to treatment

Canine babesiosis is an important protozoan tick-borne disease associated with anemia and thrombocytopenia and caused by several different Babesia spp. Babesia negevi was first reported to infect dogs in the Middle East in 2020. This study describes the presentation, clinical signs, parasitemia levels quantified by molecular techniques, laboratory findings and treatment of dogs infected with B. negevi following the first description of this species. Clinical findings in the infected dogs, a 3-year old female and two 8-week old male and female pups, included extreme lethargy and pale mucous membranes, anemia and thrombocytopenia found in all three animals. Fever was present in the older female and icterus in the female pup. Babesia parasites resembling B. negevi were detected by microscopy of blood smears from the dogs. PCR of blood targeting the 18S rRNA and cox1 genes confirmed that babesiosis was caused by B. negevi and PCR targeting the Borrelia flagellin gene indicated co-infection with Borrelia persica in two dogs. Treatment of the dogs with imidocarb dipropionate resulted in clinical improvement and initial decrease in the B. negevi parasite load as detected by quantitative PCR in two dogs, however the female pup continued to deteriorate and died. The parasite load in the 3-year old female decreased from 43,451 parasites/µl blood pre-imidocarb dipropionate treatment to 803 parasites/µl within two weeks. In the surviving pup, it decreased from 3,293,538 parasites/µl pre-treatment to 20,092 parasites/µl after two weeks. Babesia negevi DNA was still recovered from blood samples by PCR despite repeated treatment with imidocarb dipropionate one-month post-treatment in the surviving pup and up to seven months post-treatment in the 3-year old female. Only treatment with atovaquone and azithromycin for ten days eliminated B. negevi in both dogs as confirmed by negative PCR two weeks later. In conclusion, treatment with imidocarb dipropionate was helpful for recovery from clinical disease but did not facilitate parasite elimination, and it is therefore recommended to treat canine B. negevi infection with the combination of atovaquone and azithromycin.

Linking avian malaria parasitemia estimates from quantitative PCR and microscopy reveals new infection patterns in Hawai'i

Plasmodium parasites infect thousands of species and provide an exceptional system for studying host-pathogen dynamics, especially for multi-host pathogens. However, understanding these interactions requires an accurate assay of infection. Assessing Plasmodium infections using microscopy on blood smears often misses infections with low parasitemias (the fractions of cells infected), and biases in malaria prevalence estimates will differ among hosts that differ in mean parasitemias. We examined Plasmodium relictum infection and parasitemia using both microscopy of blood smears and quantitative polymerase chain reaction (qPCR) on 299 samples from multiple bird species in Hawai'i and fit models to predict parasitemias from qPCR cycle threshold (Ct) values. We used these models to quantify the extent to which microscopy underestimated infection prevalence and to more accurately estimate infection patterns for each species for a large historical study done by microscopy. We found that most qPCR-positive wild-caught birds in Hawaii had low parasitemias (Ct scores ≥35), which were rarely detected by microscopy. The fraction of infections missed by microscopy differed substantially among eight species due to differences in species’ parasitemia levels. Infection prevalence was likely 4–5-fold higher than previous microscopy estimates for three introduced species, including Zosterops japonicus, Hawaii’s most abundant forest bird, which had low average parasitemias. In contrast, prevalence was likely only 1.5–2.3-fold higher than previous estimates for Himatione sanguinea and Chlorodrepanis virens, two native species with high average parasitemias. Our results indicate that relative patterns of infection among species differ substantially from those observed in previous microscopy studies, and that differences depend on variation in parasitemias among species. Although microscopy of blood smears is useful for estimating the frequency of different Plasmodium stages and host attributes, more sensitive quantitative methods, including qPCR, are needed to accurately estimate and compare infection prevalence among host species.

Diagnostic value of rapid test for malaria among febrile neonates in a tertiary hospital in North-East Nigeria: a prospective cross-sectional study

ObjectiveThe WHO recommends testing using microscopy or rapid diagnostic test (RDT) before treatment for malaria. However, the use of RDT to diagnose neonatal malaria has not been widely validated with...

Automated Platelet Counter with Detection Using K-Means Clustering

Platelet is a blood cell type that is stored and circulated in the human body. It acts as a blood thickening agent and prevents blood from overflowing whenever bleeding occurs. An excessive or inadequate number of platelets could lead to platelet-related diseases. The current practice of platelet counting involves the manual counting process using a haemocytometer, Wright’s Stain which uses the dyes to facilitate the differentiation of blood cell types, and a tally counter. Yet, this process can be time-consuming, demanding, and exhausting for haematologists, and likely to be prone to errors. Thus, this paper presents a study on automated platelet counter and detection using image processing techniques. The K-Means Clustering was employed to count and detect the presence of platelets in microscopic blood smear images. Several processes were performed prior to the K-means clustering, including image enhancement and YCbCr image formatting. Subsequently, image masking, as well as area thresholding were applied to eliminate every unwanted entity and highlight the visibility of the platelets before the number of platelets could be detected and counted. A comparative experiment was designed in which the K-Means Clustering platelet count and detection were compared with the actual number of platelets reported by haematologists. The platelet counts and detection were categorized into three detection categories which are Less Detection (LD), Accurate Detection (AD), and Over Detection (OD). The proposed study was evaluated to 90 testing platelet images. Out of the 90 testing images, 75 platelet images were perfectly counted and detected which returned 91.67% of accuracy. This signifies that the K-Means Clustering algorithm was discovered to be efficient and dependable for automated platelet counter and detection

Deep learning approach for detection of Dengue fever from the microscopic images of blood smear

Dengue virus (DENV), known to cause dengue fever is a global public health concern. A safe and effective anti-viral drug or vaccine that can protect humans from dengue fever currently does not exist. Today, severe dengue has become a leading cause of serious illness in most Asian and Latin American countries. This digital pathology-related research focuses on the automatic detection of dengue by utilizing digital microscopic peripheral blood smears (PBS). This paper explored pre-trained convolution neural network (CNN) architectures for automatic dengue fever detection. Transfer learning (TL) was performed on two widely used pre-trained CNNs - SqueezeNet and GoogleNet, and employed to differentiate the dengue-infected and normal blood smears. The last few layers were replaced and retrained to customize the architectures for this task. Leishman’s stained dengue-infected and normal control 100x magnified PBS images were included in the study. The best performance was rendered by GoogleNet (Learn Rate, 0.0001; Batch Size, 8) with an Accuracy 91.30%, Sensitivity 84.62%, Specificity 100%, Precision 100%, and F1 score 91.67%. Promising results show that this approach can be an essential adjunct to other clinical methods, namely CBC test & NS1 antigen capture, and can significantly support dengue diagnosis in low-resource setups.

Classification of Red Blood Cell Abnormality in Thin Blood Smear Images using Convolutional Neural Networks

One of the most common morphological red blood cell abnormalities encountered during routine thin blood smear microscopy for the detection of malaria parasite is the rouleaux formation, which is the stacking together of red blood cells to form a chain. Rouleaux formation signifies an underlying infection and as such microscopists are mandated to report its presence. A lot of work has been done in automating malaria diagnosis using deep learning, but no model has been developed which is capable of detecting rouleaux formation in malaria infected red blood cells. Thus, this study collected 231 peripheral blood smear (PBS) images of normal red blood cell morphology and 231 PBS images with rouleaux morphology. The images were pre-processed and segmented into equal instances of 3044 coloured images of size 750×750 pixels. Two convolutional neural network (CNN) models were developed and trained to classify the images into normal red blood cell morphology or rouleaux morphology. The CNN models were trained on two different image sizes: 300×300 and 500×500. The first CNN model achieved validation accuracy/loss values of 87.91%/0.8177 and 56.58%/1.4090 when trained on images of sizes 300×300 and 500×500 respectively. In the second CNN model, the CNN layers of the first model were replaced with depthwise separable CNN layers, it was also trained on images of sizes 300×300 and 500×500 achieving validation accuracy/loss values of 90.95%/0.2804 and 87.75%/0.5904 respectively. This study demonstrates the capability of CNN models in detecting red blood cell morphology abnormality in thin smear images at an optimal image size of 300×300.

Detection and Classification of Leukemia using Machine Learning

Abstract—Leukemia is a haematological malignancy characterized by the abnormal proliferation of cancerous cells inside the bone marrow, resulting in the disruption of normal blood cell production. It induces a rise in the number of leukocytes. Leukemia is characterized by an aberrant proliferation of white blood cells. Leukemia is a heterogeneous disease characterized by the presence of several subtypes. Certain forms of leukemia have been observed to impact the paediatric population. Adults can be affected by several forms of leukemia. Leukemia is categorized according to the progressive elevation of white blood cell counts. There are two main classifications of leukemia, namely Acute leukemia and Chronic leukemia. When the rate of progression is gradual, individuals are diagnosed with chronic leukemia. Acute leukemia is characterized by a rapid proliferation of white blood cells. These two categories are further subdivided into two distinct subtypes for each form of leukemia. Our models were constructed using a customized version of the VGG13 architecture. The VGG13 architecture is a widely used Convolutional Neural Network (CNN) model that consists of many layers. The object recognition model is considered to be innovative. The models are utilized to categorize the microscopic blood smear images provided as input into three distinct categories: Acute Lymphocytic Leukemia or normal cells. The model achieves 92% accuracy in classifying ALL cells assisting automated identification of leukemic cells. Keywords— leukemia detection, leukemia classification, VGG, CNN, Acute leukemia

Development and evaluation of PlasmoPod: A cartridge-based nucleic acid amplification test for rapid malaria diagnosis and surveillance.

Malaria surveillance is hampered by the widespread use of diagnostic tests with low sensitivity. Adequate molecular malaria diagnostics are often only available in centralized laboratories. PlasmoPod is a novel cartridge-based nucleic acid amplification test for rapid, sensitive, and quantitative detection of malaria parasites. PlasmoPod is based on reverse-transcription quantitative polymerase chain reaction (RT-qPCR) of the highly abundant Plasmodium spp. 18S ribosomal RNA/DNA biomarker and is run on a portable qPCR instrument which allows diagnosis in less than 30 minutes. Our analytical performance evaluation indicates that a limit-of-detection as low as 0.02 parasites/μL can be achieved and no cross-reactivity with other pathogens common in malaria endemic regions was observed. In a cohort of 102 asymptomatic individuals from Bioko Island with low malaria parasite densities, PlasmoPod accurately detected 83 cases, resulting in an overall detection rate of 81.4%. Notably, there was a strong correlation between the Cq values obtained from the reference RT-qPCR assay and those obtained from PlasmoPod. In an independent cohort, using dried blood spots from malaria symptomatic children living in the Central African Republic, we demonstrated that PlasmoPod outperforms malaria rapid diagnostic tests based on the PfHRP2 and panLDH antigens as well as thick blood smear microscopy. Our data suggest that this 30-minute sample-to-result RT-qPCR procedure is likely to achieve a diagnostic performance comparable to a standard laboratory-based RT-qPCR setup. We believe that the PlasmoPod rapid NAAT could enable widespread accessibility of high-quality and cost-effective molecular malaria surveillance data through decentralization of testing and surveillance activities, especially in elimination settings.

Comparison of visual assessments of anisocytosis in canine blood smears and analyzer-calculated red blood cell distribution width.

Red blood cell distribution width (RDW) and visual assessments of anisocytosis assess variability in erythrocyte size. Veterinary studies on the correlation between the two methods and on observer agreement are scarce. The objectives were to assess the correlation of the grading of anisocytosis by means of conventional microscopy of canine blood smears to RDW, and to assess intra- and inter-observer variation in assessing the degree of anisocytosis. The study included 100 canine blood samples on which blood smear examination and RDW measurement were performed. RDW was measured on the Advia 2120i analyzer. The degree of anisocytosis was based on a human grading scheme assessing the ratio between the size of the representative largest red blood cell and that of the representative smallest red blood cell (1+ if <2x, 2+ if 2-3x, 3+ if 3-4x, and 4+ if >4x). Three observers participated and assessed the blood smears by conventional microscopy twice, 3 weeks apart by each observer. The correlation was assessed for each observer on each occasion using Kendahl-tau-b analysis. Intra-observer agreement was assessed using quadratically weighted kappa. Inter-observer agreement was assessed using free-marginal multi-rater kappa. Anisocytosis graded on blood smears correlated significantly with RDW values as assessed by Kendahl-tau-b ranging between 0.37 and 0.51 (p < 0.0001). Intra-observer agreement ranged from weak to moderate with resulting kappa-coefficients being 0.58, 0.68, and 0.75, respectively. Inter-observer agreement was weak (Kappa-values 0.44). The weak to moderate observer agreement in the visual assessment of anisocytosis indicates that the more precise and more repeatable RDW measurement should be used for clinical decision-making.