Microscopic Diagnosis Of Malaria Research Articles

Quality Control of Microscopic Diagnosis of Malaria in Healthcare Facilities and Submicroscopic Infections in Mossendjo, the Department of Niari, the Republic of the Congo.

The control and management of malaria are linked to the quality of diagnosis. We sought to estimate the performance of routine microscopy for malaria diagnosis and assess the prevalence of submicroscopic Plasmodium (P.) falciparum infection among febrile patients in two healthcare facilities in Mossendjo, the Republic of the Congo. A cross-sectional study was conducted between January and December 2022. A total of 650 and 234 patients with signs of uncomplicated malaria were enrolled at the Centre de Sante Intégré (CSIMSJ) and Hôpital de Base (HBMSJ), respectively. Two thick blood smears were performed for each patient, one analyzed by routine microscopists and the other by an expert. The msp-1 and msp-2 genes were genotyped to detect submicroscopic P. falciparum infection. At the CSIMSJ, the sensitivity was 49.5% and the specificity was 88.6%. The positive and negative predictive values were 77.7% and 68.7%, respectively. At the HBMSJ, the sensitivity was 32.9% and the specificity was 79.4%. The positive and negative predictive values were 44.8% and 69.5%, respectively. P. falciparum was the only species detected by routine microscopists, while experts identified some cases with P. malariae and P. ovale. The proportion of submicroscopic infections was 35.75%. Children under 5 years old had higher rates of parasitemia. However, submicroscopic infections were more pronounced in the adult group. The performance of routine malaria microscopists at Mossendjo was inaccurate at both sites. With the large proportion of submicroscopic infection, malaria management at Mossendjo requires the improvement of microscopists' skills and the concomitant use of RDTs.

Quality assessment of malaria microscopic diagnosis at the Aristide Le Dantec University Hospital of Dakar, Senegal, in 2020

BackgroundFollowing WHO guidelines, microscopy is the gold standard for malaria diagnosis in endemic countries. The Parasitology-Mycology laboratory (LPM) is the National Reference Laboratory and is currently undergoing ISO 15189 accreditation. In this context, we assessed the performance of the laboratory by confirming the reliability and the accuracy of results obtained in accordance with the requirements of the ISO 15189 standards. This study aimed to verify the method of microscopic diagnosis of malaria at the LPM, in the Aristide Le Dantec hospital (HALD) in Dakar, Senegal.MethodsThis is a validation/verification study conducted from June to August 2020. Twenty (20) microscopic slides of thick/thin blood smear with known parasite densities (PD) selected from the Cheick Anta Diop University malaria slide bank in Dakar were used for this assessment. Six (6) were used to assess microscopists’ ability to determine PD and fourteen (14) slides were used for detection (positive vs negative) and identification of parasites. Four (4) LPM-HALD microscopists read and recorded their results on prepared sheets. Data analysis was done with Microsoft Excel 2010 software.ResultsA minimum threshold of 50% concordance was used for comparison. Of the twenty (20) slides read, 100% concordance was obtained on eight (8) detection (positive vs negative) slides. Four (4) out of the six (6) parasite density evaluation slides obtained a concordance of less than 50%. Thirteen (13) out of the fourteen (14) identification slides obtained a concordance greater than 50%. Only one (1) identification slide obtained zero agreement from the microscopists. For species identification a concordance greater than 80% was noted and the microscopists obtained scores between 0.20 and 0.4 on a scale of 0 to 1 for parasite density reading. The microscopists obtained 100% precision, sensitivity, specificity and both negative and positive predictive values.ConclusionThis work demonstrated that the microscopic method of malaria diagnosis used in the LPM/HALD is in accordance with the requirements of WHO and ISO 15189. Further training of microscopists may be needed to maintain competency.

Evaluation of Malaria Microscopy Diagnostic Performance at the Public Health Center on the Border of Indonesia Timor-Leste.

Accurate diagnosis is a key strategy for controlling and preventing malaria. Regular evaluation of the performance of malaria microscopy diagnosis is essential to ensure its high quality. This study aims to assess the accuracy of malaria microscopy at selected public health facilities on the border of Indonesia and Timor-Leste. The design of this research is observational with a cross-sectional approach, conducted at five public health centers located on the Indonesia Timor-Leste border from July to September 2022. Stained slides were collected from patients with a fever (≥37°C). These stained slides were then examined for malaria diagnosis. The results revealed that all five public health centers showed perfect or nearly perfect agreement with the reference microscopist regarding malaria detection by microscopy (κ =0.9-1). To maintain the high quality of malaria microscopy diagnosis, it is imperative to conduct regular training, monitoring, and evaluation.

Comparative Study of Rapid Diagnostic Test (RDT) and Microscopic Diagnosis of Malaria Infection among Patients Attending General Hospital Minna, Niger State

Malaria is a global public health problem known to be a common cause of under five children mortality in the tropical area of Africa. The aim of this study was to compare rapid diagnostic test (RDT) and microscopy technique of malaria infection among patients attending General Hospital Minna, Niger State. A convenience sampling qualitative study was carried out on 300 consenting outpatients of general hospital, Minna in Niger state. Results of the study showed that most of the respondents were females 212(71%) and Most of the participants were within the age bracket of 11-20 years (41%). This demonstrated that transmission was higher among the young age than the elderly. Microscopy was positive in 179(59%) patients and RDT was positive in 185(61%) of the total study population while 6(3%) of those negative by microscopy were also positive with RDT. There was no significant difference when the efficacy of both tests was compared. The RDT used had a sensitivity of 87%, a specificity of 98% while microscopy had sensitivity of 95% and specificity of 72%. The RDT performance was extremely high compared to microscopy in this study. RDT can still serve as the first screening test for malaria diagnosis. However, the gold standard for confirmation of clinical diagnosis for malaria is microscopy examination. Rapid diagnostic test (RDT) offers rapid, timely, accurate and accessible detection of malaria parasites which is important for prevention and treatment. Keywords: Rapid diagnostic test, microscopic diagnosis of Malaria, Malaria fever.

Utility of Rapid Diagnostic Test for the Diagnosis of Malaria in Children: A Cross-sectional Study

Introduction: Malaria is one of the primary causes of paediatric deaths. Rapid and accurate diagnosis, followed by effective treatment, is the main strategy for malaria control. Microscopy has been the gold standard test for diagnosing malaria for over a century. It offers good sensitivity, identifies various species, and measures parasitaemia levels. However, microscopy is time-consuming, labour-intensive, and requires technical expertise. Therefore, there is a need for an easily performed test that is more sensitive and reliable, especially in resource- limited settings. Rapid Diagnostic Tests (RDTs) are a viable alternative due to their simplicity, ease of use, accuracy, and reproducibility. Aim: To compare RDT with microscopy for diagnosis of malaria in children. Materials and Methods: This cross-sectional study was conducted in the Paediatric Ward of Government Stanley Medical College and Hospital, Chennai, Tamil Nadu, India, from September 2020 to February 2021. The study included children under 12 years of age with acute febrile illness, hepatosplenomegaly/ splenomegaly, or anaemia and thrombocytopenia. Thick and thin blood smears, as well as RDT, were performed using venous samples. The collected data were analysed using the Statistical Package for the Social Sciences (SPSS) software version 23.0. To determine significance in categorical data, the Chi-square test/Fisher’s exact test was used. The efficacy was evaluated using the Receiver Operating Characteristic (ROC) curve, which provided sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Results: Among the 71 participants, 49 (69%) were males and 22 (31%) were females. Malaria presence, as determined by microscopy and RDT, was observed in 20 (28.2%) and 47 (66.2%) children, respectively, out of the total 71 enrolled in this study. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of RDT compared to microscopy were 100%, 48%, 44.7%, 100%, and 63.4%, respectively. The Area under the ROC (AUC) curve of RDT for diagnosing malaria was 0.740 (95% CI, 0.628 to 0.852; p-value=0.001). There was a statistically significant association between clinical response to antimalarials in microscopy-negative but RDT-positive subjects (p-value=0.0005). Conclusion: The present study demonstrates that RDT could be used as an alternative to microscopy in the diagnosis of malaria.

Assessing the Performance of CareStart™ Malaria Rapid Diagnostic Tests in Northwest Ethiopia: A Cross-Sectional Study.

Background While rapid diagnostic tests are an alternative diagnostic tests for microscopy in the diagnosis of malaria in rural settings, their performance has been inconsistent. Performance of rapid diagnostic tests might be affected by manufacturing process, transportation and storage, parasitemia level, and skill of personnel who perform the tests. Therefore, periodic evaluation of the local field performance of rapid diagnostic tests is mandatory in order to make early corrections in case of decreased performance. Methods A facility-based cross-sectional study was conducted from January to May 2020 among 257 malaria-suspected patients attending selected health centers in Bahir Dar Zuria district. Capillary blood was collected from each participant and tested for Plasmodium infection by CareStart™ rapid diagnostic test kit and thin and thick blood film microscopy. Data were analyzed using statistical software for social sciences version 20 and MedCalc software version 19.3. Sensitivity, specificity, positive and negative predictive values, and kappa value were calculated to evaluate the performance of rapid diagnostic tests against microscopy. Results Among 257 study participants, 47 (18.3%) were tested positive for Plasmodium infection by at least one of the diagnostic methods. Rapid diagnostic tests revealed 3 false positive and 3 false negative results. The sensitivity and specificity of CareStart Malaria Pf/Pv Combo test were 93.2% and 98.6%, respectively (kappa = 0.918). Conclusion CareStart™ rapid diagnostic test has comparable performance with microscopy for malaria diagnosis. We recommend continued use of CareStart Malaria Pf/Pv Combo test at health posts in Ethiopia where microscopy is not available.

Performance Evaluation of Malaria HRP-2 Rapid Diagnostic Test among Febrile Patients with Malaria in Iwo, Osun State, Nigeria

Diagnosis of malaria is a fundamental component of malaria case management. Parasitological confirmation of malaria before treatment was recommended for endemic countries. Microscopy diagnosis of malaria, the gold standard as constraints such as: level of expertise, quality of equipment and reagents may lead to misdiagnosis. The histidine rich protein 2 (HRP-2) based rapid diagnostic test (RDT) detects <em>Plasmodium falciparum</em> only.

&lt;p&gt;Evaluation of Malaria Microscopy Diagnosis Performance in Public Hospitals of Eastern and Central Part of Oromia Region, Ethiopia, 2019&lt;/p&gt;

&lt;p&gt;Evaluation of Malaria Microscopy Diagnosis Performance in Public Hospitals of Eastern and Central Part of Oromia Region, Ethiopia, 2019&lt;/p&gt;

Comparison of the fluorescence microscopy Cyscope\xae with light microscopy for malaria diagnosis in a small and active surveillance in Cameroon

BackgroundMalaria has a negative impact on the activities of companies in endemic countries especially in Cameroon. In this regard, an increasingly growing number of companies have started to include management of malarious patients in their health policies. In the present study, we will evaluate the diagnostic performances of a fluorescence microscopy (FM), Cyscope® microscope, in the detection of malaria parasites.MethodsA cross-sectional study was conducted among employees of two companies of the town of Douala on 21 and 22 March 2017. Sociodemographic information of employees was collected using a questionnaire form. Blood samples of ~ 10 μL were collected by venipuncture for the diagnosis of malaria using FM and light microscopy (LM). Performances of FM with respect to sensitivity (Se), specificity (Sp), positive and negative predictive values (PPV and NPV), positive and negative likelihood rates (PLR and NLR), accuracy, reliability, and Kappa index were calculated using LM as gold standard.ResultsIn total, 442 employees, aged 37.8 ± 9.7 years old on average, were included in the study. Prevalence of malaria using FM and LM was 39.2% and 17%, respectively (p < 0.01). Plasmodium falciparum and P. vivax were the two species involved in malaria infection cases. In terms of developmental stages, 68%, 45.3%, and 1.3% of employees carried gametocytes, trophozoites, and schizonts, respectively. Findings on diagnostic performances of FM were as follows: Se = 84%, Sp = 69.95%, PPV = 63.58%, NPV = 95.5%, accuracy = 89.36%, and reliability = 53.95%. Sensitivity of Cyscope® microscope increased as a function of parasitemia with values ranging from 76.92% at parasitemia between 1 and 500 parasites/μL to 91.11% at parasitemia between 501 and 5000 parasites/μL. The geometric mean parasite density was1850 parasites per μL of blood (range 1600–40,000), and most of employees (60.8%) had moderate parasitemia. The performances of FM were similar between febrile and afebrile patients.ConclusionsThis study showed good performances of Cyscope® microscope and outlines that this diagnostic tool could be used in management of malaria at workplace.

Leveraging Deep Learning Techniques for Malaria Parasite Detection Using Mobile Application

Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an experienced person and careful inspection to discriminate healthy and infected red blood cells (RBCs). It is also very time-consuming and may produce inaccurate reports due to human errors. Cognitive computing and deep learning algorithms simulate human intelligence to make better human decisions in applications like sentiment analysis, speech recognition, face detection, disease detection, and prediction. Due to the advancement of cognitive computing and machine learning techniques, they are now widely used to detect and predict early disease symptoms in healthcare field. With the early prediction results, healthcare professionals can provide better decisions for patient diagnosis and treatment. Machine learning algorithms also aid the humans to process huge and complex medical datasets and then analyze them into clinical insights. This paper looks for leveraging deep learning algorithms for detecting a deadly disease, malaria, for mobile healthcare solution of patients building an effective mobile system. The objective of this paper is to show how deep learning architecture such as convolutional neural network (CNN) which can be useful in real-time malaria detection effectively and accurately from input images and to reduce manual labor with a mobile application. To this end, we evaluate the performance of a custom CNN model using a cyclical stochastic gradient descent (SGD) optimizer with an automatic learning rate finder and obtain an accuracy of 97.30% in classifying healthy and infected cell images with a high degree of precision and sensitivity. This outcome of the paper will facilitate microscopy diagnosis of malaria to a mobile application so that reliability of the treatment and lack of medical expertise can be solved.

Assessment of Expert-Level Automated Detection of Plasmodium falciparum in Digitized Thin Blood Smear Images

Decades of effort have been devoted to establishing an automated microscopic diagnosis of malaria, but there are challenges in achieving expert-level performance in real-world clinical settings because publicly available annotated data for benchmark and validation are required. To assess an expert-level malaria detection algorithm using a publicly available benchmark image data set. In this diagnostic study, clinically validated malaria image data sets, the Taiwan Images for Malaria Eradication (TIME), were created by digitizing thin blood smears acquired from patients with malaria selected from the biobank of the Taiwan Centers for Disease Control from January 1, 2003, to December 31, 2018. These smear images were annotated by 4 clinical laboratory scientists who worked in medical centers in Taiwan and trained for malaria microscopic diagnosis at the national reference laboratory of the Taiwan Centers for Disease Control. With TIME, a convolutional neural network-based object detection algorithm was developed for identification of malaria-infected red blood cells. A diagnostic challenge using another independent data set within TIME was performed to compare the algorithm performance against that of human experts as clinical validation. Performance on detecting Plasmodium falciparum-infected blood cells was measured by average precision, and performance on detecting P falciparum infection at the image level was measured using sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). The TIME data sets contained 8145 images of 36 blood smears from patients with suspected malaria (30 P falciparum-positive and 6 P falciparum-negative smears) that had reliable annotations. For clinical validation, the average precision was 0.885 for detecting P falciparum-infected blood cells and 0.838 for ring form. For detecting P falciparum infection on blood smear images, the algorithm had expert-level performance (sensitivity, 0.995; specificity, 0.900; AUC, 0.997 [95% CI, 0.993-0.999]), especially in detecting ring form (sensitivity, 0.968; specificity, 0.960; AUC, 0.995 [95% CI, 0.990-0.998]) compared with experienced microscopists (mean sensitivity, 0.995 [95% CI, 0.993-0.998]; mean specificity, 0.955 [95% CI, 0.885-1.000]). The findings suggest that a clinically validated expert-level malaria detection algorithm can be developed by using reliable data sets.

Texture Based Classification of Malaria Parasites from Giemsa-Stained Thin Blood Films

Quantification of parasitemia is an important part of a microscopic malaria diagnosis. Giemsa-stained thin blood smear is the gold standard method for detecting malaria parasite enumeration. However, manual counting reveals the limitations of human inconsistency and fatigue, as well as the unreliability of accuracy and non-reproducibility. Inaccurate parasitemia affects clinical diagnosis and therapeutic procedure. Automated quantification is therefore useful to improve the performance of quantifying parasite density. In this paper, the texture-based classification approach is investigated. The methods consist of the following processes: pre-processing, segmentation, feature extraction and the classification of erythrocytes. The pre-processing is applied for image conversion and enhancement. The segmentation combines local adaptive thresholding, morphological process and watershed transform to extract red blood cells, separate touching and overlapping cells. Texture analysis is performed to establish parameters obtained from first-order, second-order and higher-order statistical analysis and wavelet transform. Two feature selection approaches, the sequential forward selection method and sequential backward elimination method, integrated with a support vector machine classifier are examined to obtain the optimal feature set for identifying the Plasmodium falciparum stages. We found that gray-level co-occurrence matrices based textural features were highly selected. The optimal feature set selected by the sequential forward selection yields lesser number of features and tends to give a higher degree of accuracy than the feature set selected by sequential backward elimination. The proposed method produces 98.87% accuracy for binary classification, 99.56% accuracy for ring stage classification, and 99.48% accuracy for tropozoite stage classification. Grey-level co-occurrence matrices based texture analysis is the dominant method compared to first-order and higher-order statistical texture analysis as well as wavelet transform.

Epidemiological and clinical characteristics of patients with malaria admitted to a hospital in Mérida, Venezuela.

Malaria is expanding rapidly across Venezuela, spreading outwards from traditional high transmission regions in the southeast of the country, but the lack of official data make it impossible to understand the reasons for this expansion and to estimate its real magnitude. This study aims to evaluate the epidemiological characteristics driving the re-emergence of malaria in Mérida, a state in the west of Venezuela, where no cases have been reported since 2003, and also to study the clinical presentation of the disease in patients presenting with malaria. Thirty-three patients who presented with anemia and fever and with a microscopic diagnosis of malaria were examined and interviewed. Data were collected in standardized forms and analyzed. One-way analysis of variance was used to study differences among patients infected with different parasites. Twenty-two patients were from the Zulia state and eleven were from the Mérida state, mainly from the lowlands south of Lake Maracaibo. Six of these patients traveled to the Bolívar state between 2017 and 2019. Thirteen patients presented with the WHO criteria for severe malaria.Conclusions:Domestic migration to the southeast of Venezuela may have played an important role in the expansion of malaria in previously existing endemic areas of transmission and also in the increase in the number of cases of severe malaria.

Performance assessment in microscopic diagnosis of malaria in the laboratory network of the National Institute of Health of Peru, 2012-2017

Timely diagnosis of malaria is a strategy proposed by the World Health Organization to reduce malaria morbidity and mortality. A study was conducted to assess performance in microscopic diagnosis of malaria in the network of laboratories under the National Malaria Reference Laboratory of the National Institute of Health between 2012 and 2017. In the years of study, the laboratories obtained a rating of "acceptable" in the diagnosis of Plasmodium by 38.4%, 43.7%, 60.0%, 83.3%, 90.9%, and 95.8%, respectively, in the evaluation of species by 0%, 6.2%, 15.0%, 50.0%, 40.9%, and 54.1%, respectively; in stage assessment by 23.0%, 25.0%, 35.0%, 83.3%, 54.5%, and 79.1%, respectively; and in parasitic density assessment by 0%, 6.2%, 10.0%, 33.3%, 0%, and 12.5%, respectively. We conclude that in the period under evaluation, the percentage of laboratories that diagnosed and recognized the species and stage increases, which is not the case for recognition of parasitic density.

Importance of quality assurance testing of malaria rapid diagnostic test in the case management of malaria

Prompt and rapid diagnosis of malaria has gained importance in health programmes in endemic countries, and recognition of the importance of early, correct treatment to the reduction in malaria morbidity and mortality. Blood-based diagnosis using lateral-flow immunochromatographic tests, commonly called rapid diagnostics tests (RDTs), offer great promise in extending rapid diagnosis to areas where traditional microscopy is not accessible. Large-scale operational use has raised questions about the accuracy of current RDT technology in tropical conditions. As utilization of RDTs has increased rapidly in the last few years, there is a clear and urgent need to address issues on quality performance and appropriateness of use, particularly in remote endemic areas. The need for Quality Assurance (QA) systems to maintain the quality of microscopy diagnosis of malaria is well established but the extent of implementation varies widely. Quality assurance process must become an integral part of RDT budgets, procurement and implementation plans. Responsibility for overseeing QA processes, extending from post purchase testing of RDTs to training and supervision of users and control of storage and transport, should be clearly defined and coordinated from a central level. A system of regional and referral laboratories, based on standard operating procedures would test RDTs after purchase and for the duration of shelf-life using quality control (QC) panels prepared from wild-type parasites. The use of positive control wells (PCW) containing recombinant antigens would assist in assuring the performance of RDTs in the field and this would assist in the parasite-base confirmation and in the case management of malaria. Quality assurance processes must be transparent, and good communication with manufacturers and end-users during QA development is necessary.

A diagnostic performance evaluation of rapid diagnostic tests and microscopy for malaria diagnosis using nested polymerase chain reaction as reference standard in a tertiary hospital in Jos, Nigeria.

Rapid diagnostic tests are frequently used in healthcare settings across Nigeria for diagnosis of Plasmodium falciparum malaria, which is the commonest form of malaria in the country. In this study, the performance of a rapid diagnostic test (RDT) was compared with expert microscopy using the polymerase chain reaction (PCR) as the reference standard in a tertiary hospital in Jos, Nigeria. This study was a prospective, cross-sectional, hospital-based study. A total of 200 participants of all ages presenting to Jos University Teaching Hospital with a history of fever or an axillary temperature of >37.5°C were recruited. Blood specimens were collected and malaria testing was done using RDT, microscopy and PCR. The prevalence of malaria in this study was 17%, 15% and 13% by PCR, microscopy and RDT, respectively. Compared with microscopy, RDT had lower sensitivity of 75% (95% CI: 56.60-88.54) vs 88.24% (95% CI: 72.55-96.70), lower specificity of 98.80% (95% CI: 95.72-99.85) vs 100.0% (95% CI: 97.80-100.0), lower positive predictive value 92.31 (95% CI: 74.89-97.97) vs 100 (95% CI: 98.0-100.0), and lower negative predictive value 95.35 (95% CI: 91.83-97.39) versus 97.65 (95% CI: 94.30-99.05). The diagnostic performance of expert microscopy was better than RDT in the diagnosis of Plasmodium falciparum malaria. Quality assurance procedures such as using expert microscopy to cross-check a proportion of RDT negative results in patients with clinical features of malaria is desirable.

External quality assessment of malaria microscopy diagnosis in selected health facilities in Western Oromia, Ethiopia

BackgroundAccurate early diagnosis and prompt treatment are one of the key strategies to control and prevent malaria disease. External quality assessment is the most effective method for evaluation of the quality of malaria microscopy diagnosis. The aim of this study was to assess the quality of malaria microscopy diagnosis and its associated factors in selected public health facility laboratories in East Wollega Zone, Western Ethiopia.MethodsFacility-based cross-sectional study design was conducted in 30 randomly selected public health facility laboratories from November 2014 to January 2015 in East Wollega Zone, Western Ethiopia. Ten validated stained malaria panel slides with known Plasmodium species, developmental stage and parasite density were distributed. Data were captured; cleaned and analyzed using SPSS version 20 statistical software-multivariate logistic regressions and the agreement in reading between the peripheral diagnostic centers and the reference laboratory were done using kappa statistics.ResultsA total of 30 health facility laboratories were involved in the study and the overall quality of malaria microscopy diagnosis was poor (62.3%). The associated predictors of quality in this diagnosis were in-service training [(AOR = 16, 95% CI (1.3, 1.96)], smearing quality [(AOR = 24, 95% CI (1.8, 3.13)], staining quality [(AOR = 15, 95% CI (2.35, 8.61), parasite detection [(AOR = 9, 95% CI (1.1, 8.52)] and identification skills [(AOR = 8.6, 95% CI (1.21, 1.63)]. Eighteen (60%) of health facility laboratories had in-service trained laboratory professionals on malaria microscopy diagnosis.ConclusionOverall quality of malaria microscopy diagnosis was poor and a significant gap in this service was observed that could impact on its diagnostic services.

Factors associated with malaria microscopy diagnostic performance following a pilot quality-assurance programme in health facilities in malaria low-transmission areas of Kenya, 2014

BackgroundMalaria accounts for ~21% of outpatient visits annually in Kenya; prompt and accurate malaria diagnosis is critical to ensure proper treatment. In 2013, formal malaria microscopy refresher training for microscopists and a pilot quality-assurance (QA) programme for malaria diagnostics were independently implemented to improve malaria microscopy diagnosis in malaria low-transmission areas of Kenya. A study was conducted to identify factors associated with malaria microscopy performance in the same areas.MethodsFrom March to April 2014, a cross-sectional survey was conducted in 42 public health facilities; 21 were QA-pilot facilities. In each facility, 18 malaria thick blood slides archived during January–February 2014 were selected by simple random sampling. Each malaria slide was re-examined by two expert microscopists masked to health-facility results. Expert results were used as the reference for microscopy performance measures. Logistic regression with specific random effects modelling was performed to identify factors associated with accurate malaria microscopy diagnosis.ResultsOf 756 malaria slides collected, 204 (27%) were read as positive by health-facility microscopists and 103 (14%) as positive by experts. Overall, 93% of slide results from QA-pilot facilities were concordant with expert reference compared to 77% in non-QA pilot facilities (p < 0.001). Recently trained microscopists in QA-pilot facilities performed better on microscopy performance measures with 97% sensitivity and 100% specificity compared to those in non-QA pilot facilities (69% sensitivity; 93% specificity; p < 0.01). The overall inter-reader agreement between QA-pilot facilities and experts was κ = 0.80 (95% CI 0.74–0.88) compared to κ = 0.35 (95% CI 0.24–0.46) between non-QA pilot facilities and experts (p < 0.001). In adjusted multivariable logistic regression analysis, recent microscopy refresher training (prevalence ratio [PR] = 13.8; 95% CI 4.6–41.4), ≥5 years of work experience (PR = 3.8; 95% CI 1.5–9.9), and pilot QA programme participation (PR = 4.3; 95% CI 1.0–11.0) were significantly associated with accurate malaria diagnosis.ConclusionsMicroscopists who had recently completed refresher training and worked in a QA-pilot facility performed the best overall. The QA programme and formal microscopy refresher training should be systematically implemented together to improve parasitological diagnosis of malaria by microscopy in Kenya.

Quantitation of Malarial parasitemia in Giemsa stained thin blood smears using Six Sigma threshold as preprocessor

Malaria is a precarious disease and a serious illness that can become life threatening very fast and can be incurable if not treated on time. According to the World Health Organization, Malaria causes 150–250 million infections and an estimated more than a million deaths each year. Microscopic image capture followed by visual observation as per the manual is the gold standard method for diagnosis of malaria. However, due to subjectivity and the complexity of manual assessment, microscopic diagnosis of malaria is tiring, time consuming and subject to human error. In this study, we have developed a novel automatic high performance method with minimal human dependence for detection and quantitation of malaria infected Red Blood Cells (RBC). The parasites detection test to identify malaria was computed using digital image processing techniques. This automated quantitation procedure was done in three parts: Segmentation, Identification and Detection. The methods used for the quantitation were Six Sigma threshold for segmenting Region of Interest followed by modified Hough transform to identify and count RBCs, and Kapur’s threshold method to detect malaria parasite infected RBCs. The developed package using Microsoft® VB.NET 2008 framework is executed on various Giemsa stained thin blood smears digitally acquired using a charge coupled device attached to a microscope. Following analysis performed on seven sets of thin blood smear images, the values of Precision, Recall and F-measures obtained were 96%, 97% and 97% respectively. This is the first attempt to use a combination of Six Sigma threshold, Chess-Board distance, Hough transform and Kapur’s threshold to find the RBCs by deriving information from the image itself. Further, Kapur’s entropy measure was successfully applied to distinguish parasitized from un-infected cells.

Advances in automatic detection technology for images of thin blood film of malaria parasite

This paper reviews the computer vision and image analysis studies aiming at automated diagnosis or screening of malaria in microscope images of thin blood film smears. On the basis of introducing the background and significance of automatic detection technology, the existing detection technologies are summarized and divided into several steps, including image acquisition, pre-processing, morphological analysis, segmentation, count, and pattern classification components. Then, the principles and implementation methods of each step are given in detail. In addition, the promotion and application in automatic detection technology of thick blood film smears are put forwarded as questions worthy of study, and a perspective of the future work for realization of automated microscopy diagnosis of malaria is provided.