Evaluation of malaria microscopy diagnostic performance at private health facilities in Tanzania

A transfer learning approach to identify Plasmodium in microscopic images

Plasmodium parasites cause Malaria disease, which remains a significant threat to global health, affecting 200 million people and causing 400,000 deaths yearly. Plasmodium falciparum and Plasmodium vivax remain the two main malaria species affecting humans. Identifying the malaria disease in blood smears requires years of expertise, even for highly trained specialists. Literature studies have been coping with the automatic identification and classification of malaria. However, several points must be addressed and investigated so these automatic methods can be used clinically in a Computer-aided Diagnosis (CAD) scenario. In this work, we assess the transfer learning approach by using well-known pre-trained deep learning architectures. We considered a database with 6222 Region of Interest (ROI), of which 6002 are from the Broad Bioimage Benchmark Collection (BBBC), and 220 were acquired locally by us at Fundação Oswaldo Cruz (FIOCRUZ) in Porto Velho Velho, Rondônia-Brazil, which is part of the legal Amazon. We exhaustively cross-validated the dataset using 100 distinct partitions with 80% train and 20% test for each considering circular ROIs (rough segmentation). Our experimental results show that DenseNet201 has a potential to identify Plasmodium parasites in ROIs (infected or uninfected) of microscopic images, achieving 99.41% AUC with a fast processing time. We further validated our results, showing that DenseNet201 was significantly better (99% confidence interval) than the other networks considered in the experiment. Our results support claiming that transfer learning with texture features potentially differentiates subjects with malaria, spotting those with Plasmodium even in Leukocytes images, which is a challenge. In Future work, we intend scale our approach by adding more data and developing a friendly user interface for CAD use. We aim at aiding the worldwide population and our local natives living nearby the legal Amazon's rivers.

Evaluation of Malaria Microscopy Diagnostic Performance at 40 Public Health Facilities in Abidjan, Côte d'Ivoire in 2020

PURPOSE

Microscopic diagnosis of Giemsa-stained thick and thin blood films remained the gold standard laboratory method for the diagnosis of malaria. In this context, we felt it was important to conduct this evaluation with 40 public medical biology laboratories (MBLs) in the Abidjan 1 health region that perform blood parasitology tests to improve their implementation process.

METHODS

This descriptive and analytical study took place in July 2020 and involved participating laboratories (PLs) from the public sector in Abidjan. A set of 3 blood smear slides of variable parasite densities (PDs) with assigned values (AVs) of parasite densities and assigned Plasmodium species was used. The criterion for establishing the parasite density compliance interval was assigned values of ± 25%, and the performance rates were compared to the 80% recommended by the WHO for the African region.

RESULTS

Nearly a quarter (11/40) of the participating laboratories had a compliance rate greater than 80%, including 10 with a performance of 100% for the ability to identify parasites. Regarding identifying plasmodial species, a concordance rate of 100% was obtained for slide 1 for Plasmodium falciparum, while this rate was 20% for slide 2 for Plasmodium ovale. For parasite densities < 200/µl, 87.5% of the participating laboratories (PLs) had a performance rate lower than 80%, while 95% of these PLs had a performance rate higher than 80% for parasitaemia > 2000/µl.

CONCLUSIONS

There is a need to strengthen adapted to low parasitaemia, to improve the biological confirmation of malaria in Côte d'Ivoire.

Laboratory evaluation of the miniature direct-on-blood PCR nucleic acid lateral flow immunoassay (mini-dbPCR-NALFIA), a simplified molecular diagnostic test for Plasmodium

BACKGROUND

Point-of-care diagnosis of malaria is currently based on microscopy and rapid diagnostic tests. However, both techniques have their constraints, including poor sensitivity for low parasitaemias. Hence, more accurate diagnostic tests for field use and routine clinical settings are warranted. The miniature direct-on-blood PCR nucleic acid lateral flow immunoassay (mini-dbPCR-NALFIA) is an innovative, easy-to-use molecular assay for diagnosis of malaria in resource-limited settings. Unlike traditional molecular methods, mini-dbPCR-NALFIA does not require DNA extraction and makes use of a handheld, portable thermal cycler that can run on a solar-charged power pack. Result read-out is done using a rapid lateral flow strip enabling differentiation of Plasmodium falciparum and non-falciparum malaria infections. A laboratory evaluation was performed to assess the performance of the mini-dbPCR-NALFIA for diagnosis of pan-Plasmodium and P. falciparum infections in whole blood.

METHODS

Diagnostic accuracy of the mini-dbPCR-NALFIA was determined by testing a set of Plasmodium-positive blood samples from returned travellers (n = 29), and Plasmodium-negative blood samples from travellers with suspected malaria (n = 23), the Dutch Blood Bank (n = 19) and intensive care patients at the Amsterdam University Medical Centers (n = 16). Alethia Malaria (LAMP) with microscopy for species differentiation were used as reference. Limit of detection for P. falciparum was determined by 23 measurements of a dilution series of a P. falciparum culture. A fixed sample set was tested three times by the same operator to evaluate the repeatability, and once by five different operators to assess the reproducibility.

RESULTS

Overall sensitivity and specificity of the mini-dbPCR-NALFIA were 96.6% (95% CI, 82.2%-99.9%) and 98.3% (95% CI, 90.8%-100%). Limit of detection for P. falciparum was 10 parasites per microlitre of blood. The repeatability of the assay was 93.7% (95% CI, 89.5%-97.8%) and reproducibility was 84.6% (95% CI, 79.5%-89.6%).

CONCLUSIONS

Mini-dbPCR-NALFIA is a sensitive, specific and robust method for molecular diagnosis of Plasmodium infections in whole blood and differentiation of P. falciparum. Incorporation of a miniature thermal cycler makes the assay well-adapted to resource-limited settings. A phase-3 field trial is currently being conducted to evaluate the potential implementation of this tool in different malaria transmission areas.

Plasmodium falciparum infection prevalence among children aged 6-59 months from independent DHS and HIV surveys: Nigeria, 2018

Prevalence estimates are critical for malaria programming efforts but generating these from non-malaria surveys is not standard practice. Malaria prevalence estimates for 6-59-month-old Nigerian children were compared between two national household surveys performed simultaneously in 2018: a Demographic and Health Survey (DHS) and the Nigeria HIV/AIDS Indicator and Impact Survey (NAIIS). DHS tested via microscopy (n = 8298) and HRP2-based rapid diagnostic test (RDT, n = 11,351), and NAIIS collected dried blood spots (DBS) which were later tested for histidine-rich protein 2 (HRP2) antigen (n = 8029). National Plasmodium falciparum prevalence was 22.6% (95% CI 21.2- 24.1%) via microscopy and 36.2% (34.6- 37.8%) via RDT according to DHS, and HRP2 antigenemia was 38.3% (36.7-39.9%) by NAIIS DBS. Between the two surveys, significant rank-order correlation occurred for state-level malaria prevalence for RDT (Rho = 0.80, p < 0.001) and microscopy (Rho = 0.75, p < 0.001) versus HRP2. RDT versus HRP2 positivity showed 24 states (64.9%) with overlapping 95% confidence intervals from the two independent surveys. P. falciparum prevalence estimates among 6-59-month-olds in Nigeria were highly concordant from two simultaneous, independently conducted household surveys, regardless of malaria test utilized. This provides evidence for the value of post-hoc laboratory HRP2 detection to leverage non-malaria surveys with similar sampling designs to obtain accurate P. falciparum estimates.

Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools: A review

Malaria is an infectious disease caused by parasites of the genus Plasmodium spp. It is transmitted to humans by the bite of an infected female Anopheles mosquito. It is the most common disease in resource-poor settings, with 241 million malaria cases reported in 2020 according to the World Health Organization. Optical microscopy examination of blood smears is the gold standard technique for malaria diagnosis; however, it is a time-consuming method and a well-trained microscopist is needed to perform the microbiological diagnosis. New techniques based on digital imaging analysis by deep learning and artificial intelligence methods are a challenging alternative tool for the diagnosis of infectious diseases. In particular, systems based on Convolutional Neural Networks for image detection of the malaria parasites emulate the microscopy visualization of an expert. Microscope automation provides a fast and low-cost diagnosis, requiring less supervision. Smartphones are a suitable option for microscopic diagnosis, allowing image capture and software identification of parasites. In addition, image analysis techniques could be a fast and optimal solution for the diagnosis of malaria, tuberculosis, or Neglected Tropical Diseases in endemic areas with low resources. The implementation of automated diagnosis by using smartphone applications and new digital imaging technologies in low-income areas is a challenge to achieve. Moreover, automating the movement of the microscope slide and image autofocusing of the samples by hardware implementation would systemize the procedure. These new diagnostic tools would join the global effort to fight against pandemic malaria and other infectious and poverty-related diseases.

Difference between Microscopic and PCR Examination Result for Malaria Diagnosis and Treatment Evaluation in Sumba Barat Daya, Indonesia

Microscopic examination is the backbone of malaria diagnosis and treatment evaluation in Indonesia. This test has limited ability to detect malaria at low parasite density. Inversely, nested polymerase chain reaction (PCR) can detect parasites at a density below the microscopic examination’s detection limit. The objective of this study is to compare microscopic and PCR results when being used to identify malaria in suspected patients and patients who underwent dihydroartemisinin–piperaquine (DHP) therapy in the last 3–8 weeks with or without symptoms in Sumba Barat Daya, Nusa Tenggara Timur, Indonesia. Recruitment was conducted between April 2019 and February 2020. Blood samples were then taken for microscopic and PCR examinations. Participants (n = 409) were divided into three groups: suspected malaria (42.5%), post-DHP therapy with fever (4.9%), and post-DHP therapy without fever (52.6%). Microscopic examination found five cases of P. falciparum + P. vivax infection, while PCR found 346 cases. All microscopic examinations turned negative in the post-DHP-therapy group. Conversely, PCR result from the same group yielded 29 negative results. Overall, our study showed that microscopic examination and PCR generated different results in detecting Plasmodium species, especially in patients with mixed infection and in patients who recently underwent DHP therapy.

THE EFFECT OF DEXAMETHASONE ON HEMATOLOGIC PROFILES, HEMOSPORIDIAN INFECTION, AND SPLENIC HISTOLOGY IN HOUSE FINCHES (HAEMORHOUS MEXICANUS)

Research on host response to infectious disease often involves pharmacological induction of immunosuppression, frequently through administration of dexamethasone. Reports on the effect of dexamethasone in birds are largely restricted to poultry and pigeons. This study describes changes in white blood cell (WBC) differentials, hemoparasite counts, splenic histology, and splenic CD3 immunoreactivity in House Finches (Haemorhous mexicanus). Experimental group birds (n=9) were treated with a daily intramuscular injection of 25 µg of dexamethasone for 8 d; a control group (n=9) received daily saline solution. Smears were made with blood collected immediately before the first dose (day 0) and on d 4, 8, and 9, and stained with modified Wright. The WBC differential counts were performed by three blinded observers, parasite counts by two blinded observers, and histology by one blinded observer. Dexamethasone-treated birds experienced relative heterophilia and lymphopenia on d 4 (P=0.008); heterophilia was also present at d 8 (P=0.018). Hemosporidian counts were significantly increased in dexamethasone-treated birds on d 4 and 8 (P=0.048 and P=0.031, respectively). In contrast with control birds, all dexamethasone-treated birds lacked histologically apparent splenic lymphoid follicles (P<0.001). No significant difference was observed in splenic CD3 immunoreactivity between groups. Our results indicate that dexamethasone has an effect on the hematologic profile of House Finches and suggest that it may be a useful method to induce immunosuppression in this species.

Automated wide-field malaria parasite infection detection using Fourier ptychography on stain-free thin-smears

Diagnosis of malaria in endemic areas is hampered by the lack of a rapid, stain-free and sensitive method to directly identify parasites in peripheral blood. Herein, we report the use of Fourier ptychography to generate wide-field high-resolution quantitative phase images of erythrocytes infected with malaria parasites, from a whole blood sample. We are able to image thousands of erythrocytes (red blood cells) in a single field of view and make a determination of infection status of the quantitative phase image of each segmented cell based on machine learning (random forest) and deep learning (VGG16) models. Our random forest model makes use of morphology and texture based features of the quantitative phase images. In order to label the quantitative images of the cells as either infected or uninfected before training the models, we make use of a Plasmodium berghei strain expressing GFP (green fluorescent protein) in all life cycle stages. By overlaying the fluorescence image with the quantitative phase image we could identify the infected subpopulation of erythrocytes for labelling purposes. Our machine learning model (random forest) achieved 91% specificity and 72% sensitivity while our deep learning model (VGG16) achieved 98% specificity and 57% sensitivity. These results highlight the potential for quantitative phase imaging coupled with artificial intelligence to develop an easy to use platform for the rapid and sensitive diagnosis of malaria.

Malaria diagnostic methods with the elimination goal in view

Malaria control measures have been in use for years but have not completely curbed the spread of infection. Ultimately, global elimination is the goal. A major playmaker in the various approaches to reaching the goal is the issue of proper diagnosis. Various diagnostic techniques were adopted in different regions and geographical locations over the decades, and these have invariably produced diverse outcomes. In this review, we looked at the various approaches used in malaria diagnostics with a focus on methods favorably used during pre-elimination and elimination phases as well as in endemic regions. Microscopy, rapid diagnostic testing (RDT), loop-mediated isothermal amplification (LAMP), and polymerase chain reaction (PCR) are common methods applied depending on prevailing factors, each with its strengths and limitations. As the drive toward the elimination goal intensifies, the search for ideal, simple, fast, and reliable point-of-care diagnostic tools is needed more than ever before to be used in conjunction with a functional surveillance system supported by the ideal vaccine.

autohaem: 3D printed devices for automated preparation of blood smears

The process of making blood smears is common in both research and clinical settings for investigating the health of blood cells and the presence of blood-borne parasites. It is very often carried out manually. We focus here on smears for malaria diagnosis and research, which are frequently analyzed by optical microscopy and require a high quality. Automating the smear preparation promises to increase throughput and to improve the quality and consistency of the smears. We present here two devices (manual and motorized) designed to aid in the making of blood smears. These are fully documented, open-source hardware, and an important principle was to make them easily fabricated locally anywhere. Designs and assembly instructions are freely available under an open license. We also describe an image analysis pipeline for characterizing the quality of smears and use it to optimize the settings and tunable parameters in the two devices. The devices perform as well as expert human operators while not requiring a trained operator and offering potential advantages in reproducibility and standardization across facilities.

Multi-Omics Advancements towards Plasmodium vivax Malaria Diagnosis

Plasmodium vivax malaria is one of the most lethal infectious diseases, with 7 million infections annually. One of the roadblocks to global malaria elimination is the lack of highly sensitive, specific, and accurate diagnostic tools. The absence of diagnostic tools in particular has led to poor differentiation among parasite species, poor prognosis, and delayed treatment. The improvement necessary in diagnostic tools can be broadly grouped into two categories: technologies-driven and omics-driven progress over time. This article discusses the recent advancement in omics-based malaria for identifying the next generation biomarkers for a highly sensitive and specific assay with a rapid and antecedent prognosis of the disease. We summarize the state-of-the-art diagnostic technologies, the key challenges, opportunities, and emerging prospects of multi-omics-based sensors.

Assessment of Malaria Microscopy Competency at Primary Health Institutions in the Chongqing Municipality

Background: In April 2019, Chongqing passed the national malaria elimination assessment. However, around 30 imported malaria cases are still being reported every year, and Anopheles sinensis was widely distributed in Chongqing, meaning the risk of malaria resurgence still exists. Early diagnosis and treatment for malaria cases are effective measures to prevent malaria resurgence. The primary health institutions are the first station where potential malaria cases may seek treatment. The competency with which primary health institutions diagnose malaria will directly affect the timeliness of malaria diagnosis. Nowadays, most primary health institutions in Chongqing use microscopy to confirm malaria cases. This study assessed the microscopy competence of primary health institutions, studied and analyzed the results, and provided a scientific basis for malaria prevention and control after malaria elimination in Chongqing.

Methods: According to the stratified sampling principle, four plasmodium microscopy technicians (156 in total) were selected from each of the 39 districts/counties of Chongqing to test the plasmodium microscopy competence. Descriptive statistical analysis, correlation analysis, spatial self-correlation analysis, and ROC curve analysis were carried out on the test results.

Result: The average of the technicians' test scores was 4.33 ± 0.47 (min: 3, mid: 4.5, max: 5); The spatial clustering of the scores was significant (MoranI = 0.338, Z = 3.618, P < 0.01). The test scores were positively correlated with the “level of work institutions” (R = 0.21, P < 0.01) but were negatively correlated with “age” (R = −0.31, P < 0.01). The highest Sensitivity of the technicians' microscopy was in qualitative diagnosis (98.92%, CI: 98.00–99.69%). The Delong's test showed that the diagnostic efficiency of the technicians' microscopy to P. falciparum was the best (P < 0.01), however to P. ovale was the worst (P < 0.01).

Conclusion: The microscopy technicians in primary health institutions in Chongqing have good microscopy competency in qualitative diagnosis, but there were deficiencies in the identification of plasmodium species. Township level health institutions in Central China have weaker microscopy than those in other areas.

Malaria distribution and performance of malaria diagnostic methods in Malaysia (1980-2019): a systematic review

BACKGROUND

Malaysia has already achieved remarkable accomplishments in reaching zero indigenous human malaria cases in 2018. Prompt malaria diagnosis, surveillance and treatment played a key role in the country's elimination success. Looking at the dynamics of malaria distribution during the last decades might provide important information regarding the potential challenges of such an elimination strategy. This study was performed to gather all data available in term of prevalence or incidence on Plasmodium infections in Malaysia over the last four decades.

METHODS

A systematic review of the published English literature was conducted to identify malaria distribution from 1980 to June 2019 in Malaysia. Two investigators independently extracted data from PubMed, Scopus, Web of Science and Elsevier databases for original papers.

RESULTS

The review identified 46 epidemiological studies in Malaysia over the 39-year study period, on which sufficient information was available. The majority of studies were conducted in Malaysia Borneo (31/46; 67.4%), followed by Peninsular Malaysia (13/46; 28.3%) and in both areas (2/46; 4.3%). More than half of all studies (28/46; 60.9%) were assessed by both microscopy and PCR. Furthermore, there was a clear trend of decreases of all human malaria species with increasing Plasmodium knowlesi incidence rate throughout the year of sampling period. The summary estimates of sensitivity were higher for P. knowlesi than other Plasmodium species for both microscopy and PCR. Nevertheless, the specificities of summary estimates were similar for microscopy (40-43%), but varied for PCR (2-34%).

CONCLUSIONS

This study outlined the epidemiological changes in Plasmodium species distribution in Malaysia. Malaria cases shifted from predominantly caused by human malaria parasites to simian malaria parasites, which accounted for the majority of indigenous cases particularly in Malaysia Borneo. Therefore, malaria case notification and prompt malaria diagnosis in regions where health services are limited in Malaysia should be strengthened and reinforced to achieving the final goal of malaria elimination in the country.

Diagnosis of clinical malaria in endemic settings

INTRODUCTION

Malaria continues to be a major global health problem, with over 228 million cases and 405,000 deaths estimated to occur annually. Rapid and accurate diagnosis of malaria is essential to decrease the burden and impact of this disease, particularly in children. We aimed to review the main available techniques for the diagnosis of clinical malaria in endemic settings and explore possible future options to improve its rapid recognition.

AREAS COVERED

literature relevant to malaria diagnosis was identified through electronic searches in Pubmed, with no language or date restrictions and limited to humans.

EXPERT OPINION

Light microscopy is still considered the gold standard method for malaria diagnosis and continues to be at the frontline of malaria diagnosis. However, technologies as rapid diagnostic tests, mainly those who detect histidine-rich protein-2, offer an accurate, rapid and affordable alternative for malaria diagnosis in endemic areas. They are now the technique most extended in endemic areas for parasitological confirmation. In these settings, PCR-based assays are usually restricted to research and they are not currently helpful in the management of clinical malaria. Other technologies, such as isothermal methods could be an interesting and alternative approach to PCR in the future.

Comprehensive competency assessment of malaria microscopists and laboratory diagnostic service capacity in districts stratified for malaria elimination in Ethiopia​

BACKGROUND

Federal Ministry of Health (FMoH) Ethiopia achieved significant declines in malaria mortality and incidence and has recently launched malaria elimination in selected low transmission settings. Successful malaria elimination calls for rapid and accurate diagnosis of cases so that the patients can promptly be treated before the occurrence of transmission. Therefore, this study assessed the competency of malaria microscopists using panal slides, and laboratory service availability and readiness in terms of supplies and equipments in malaria elimination targeted districts in Ethiopia.

METHOD

A cross-sectional study was conducted from February to June 2018 in all hospitals, health centers and private clinics in 20 malaria elimination targeted districts, selected out of the 6 regional states in Ethiopia. All malaria microscopists available in the study health facilities during the study period were included in the study. Questionnaires were used for interviewing sociodemography of personnel and laboratory supplies. Per World Health Organization (WHO) criteria set for proficiency testing, 10 Giemsa stained malaria slide panels (8 positive low/high density pf/pv/Mixed and 2 negative slides) were administered to each study participant for performance assessment on malaria parasite detection, species identification and parasite count using light microscopy. The slide panels are PCR confirmed and WHO approved ones, which have been stored in the slide banks at the national reference laboratory in Ethiopian Public Health Institute.

RESULT

In this assessment, 17(16%) district hospitals, 71(67%) health centers (HCs) and 18(17%) private clinics (PCs) were included. Of the 18 PCs, only 10(55.6%) had license certificate. Of the study facilities, 91.5%(97) use light microscopy, 2.83%(3) use RDTs and 2.9%(3) use both microscopy and RDT to detect malaria. Accessible and appropriate storage of Giemsa was reported by 58.8%(10) hospitals, 81.7%(58) HCs & 72.2%(13) private clinics. Of the 1896 malaria positive & 474 negative slides administered to 237 study participants, 318(16.8%) slides reported falsely negative & 47(9.9%) reported falsely positive. The participants achieved "good" grade [Agreement(A): 84.6%, Kappa(K): 0.6] on parasite detection and "poor" agreement (A: 43.8%; K: 0.11) on every species identification. No or slight agreement seen on differentiation of P. falciparum from other species (A: 28.41%; K:0.29). Above 95%(201) of participants, did not count or used plus system of parasite estimation which is the least accurate and unreccomended method per WHO guideline.

CONCLUSION

In the current study, low performance of malaria microscopists particularly in species identification & poor to moderate capacity of laboratories observed. This is really a great obstacle to malaria elimination strategy of the country. Therefore, national malaria control and elimination program in collaboration with partners is supposed to provide comprehensive training for professionals giving laboratory service and to fulfill laboratory supplies to have the gold standard service.