Performance of a malaria microscopy image analysis slide reading device

The Laboratory Diagnosis of Malaria: A Focus on the Diagnostic Assays in Non-Endemic Areas

Even if malaria is rare in Europe, it is a medical emergency and programs for its control should ensure both an early diagnosis and a prompt treatment within 24-48 h from the onset of the symptoms. The increasing number of imported malaria cases as well as the risk of the reintroduction of autochthonous cases encouraged laboratories in non-endemic countries to adopt diagnostic methods/algorithms. Microscopy remains the gold standard, but with limitations. Rapid diagnostic tests have greatly expanded the ability to diagnose malaria for rapid results due to simplicity and low cost, but they lack sensitivity and specificity. PCR-based assays provide more relevant information but need well-trained technicians. As reported in the World Health Organization Global Technical Strategy for Malaria 2016-2030, the development of point-of-care testing is important for the improvement of diagnosis with beneficial consequences for prompt/accurate treatment and for preventing the spread of the disease. Despite their limitations, diagnostic methods contribute to the decline of malaria mortality. Recently, evidence suggested that artificial intelligence could be utilized for assisting pathologists in malaria diagnosis.

The temporal dynamics of Plasmodium species infection after artemisinin-based combination therapy (ACT) among asymptomatic children in the Hohoe municipality, Ghana

BACKGROUND

The routine surveillance of asymptomatic malaria using nucleic acid-based amplification tests is essential in obtaining reliable data that would inform malaria policy formulation and the implementation of appropriate control measures.

METHODS

In this study, the prevalence rate and the dynamics of Plasmodium species among asymptomatic children (n = 1697) under 5 years from 30 communities within the Hohoe municipality in Ghana were determined.

RESULTS AND DISCUSSION

The observed prevalence of Plasmodium parasite infection by polymerase chain reaction (PCR) was 33.6% (571/1697), which was significantly higher compared to that obtained by microscopy [26.6% (451/1697)] (P < 0.0001). Based on species-specific analysis by nested PCR, Plasmodium falciparum infection [33.6% (570/1697)] was dominant, with Plasmodium malariae, Plasmodium ovale and Plasmodium vivax infections accounting for 0.1% (1/1697), 0.0% (0/1697), and 0.0% (0/1697), respectively. The prevalence of P. falciparum infection among the 30 communities ranged from 0.0 to 82.5%. Following artesunate-amodiaquine (AS + AQ, 25 mg/kg) treatment of a sub-population of the participants (n = 184), there was a substantial reduction in Plasmodium parasite prevalence by 100% and 79.2% on day 7 based on microscopy and nested PCR analysis, respectively. However, there was an increase in parasite prevalence from day 14 to day 42, with a subsequent decline on day 70 by both microscopy and nested PCR. For parasite clearance rate analysis, we found a significant proportion of the participants harbouring residual Plasmodium parasites or parasite genomic DNA on day 1 [65.0% (13/20)], day 2 [65.0% (13/20)] and day 3 [60.0% (12/20)] after initiating treatment. Of note, gametocyte carriage among participants was low before and after treatment.

CONCLUSION

Taken together, the results indicate that a significant number of individuals could harbour residual Plasmodium parasites or parasite genomic DNA after treatment. The study demonstrates the importance of routine surveillance of asymptomatic malaria using sensitive nucleic acid-based amplification techniques.

Performance Evaluation of Biozentech Malaria Scanner in Plasmodium knowlesi and P. falciparum as a New Diagnostic Tool

The computer vision diagnostic approach currently generates several malaria diagnostic tools. It enhances the accessible and straightforward diagnostics that necessary for clinics and health centers in malaria-endemic areas. A new computer malaria diagnostics tool called the malaria scanner was used to investigate living malaria parasites with easy sample preparation, fast and user-friendly. The cultured Plasmodium parasites were used to confirm the sensitivity of this technique then compared to fluorescence-activated cell sorting (FACS) analysis and light microscopic examination. The measured percentage of parasitemia by the malaria scanner revealed higher precision than microscopy and was similar to FACS. The coefficients of variation of this technique were 1.2–6.7% for Plasmodium knowlesi and 0.3–4.8% for P. falciparum. It allowed determining parasitemia levels of 0.1% or higher, with coefficient of variation smaller than 10%. In terms of the precision range of parasitemia, both high and low ranges showed similar precision results. Pearson’s correlation test was used to evaluate the correlation data coming from all methods. A strong correlation of measured parasitemia (r²=0.99, P<0.05) was observed between each method. The parasitemia analysis using this new diagnostic tool needs technical improvement, particularly in the differentiation of malaria species.

An Automated Microscopic Malaria Parasite Detection System Using Digital Image Analysis

Rapid diagnosis and parasitemia measurement is crucial for management of malaria. Microscopic examination of peripheral blood (PB) smears is the gold standard for malaria detection. However, this method is labor-intensive. Here, we aimed to develop a completely automated microscopic system for malaria detection and parasitemia measurement. The automated system comprises a microscope, plastic chip, fluorescent dye, and an image analysis program. Analytical performance was evaluated regarding linearity, precision, and limit of detection and was compared with that of conventional microscopic PB smear examination and flow cytometry. The automated microscopic malaria parasite detection system showed a high degree of linearity for Plasmodium falciparum culture (R² = 0.958, p = 0.005) and Plasmodium vivax infected samples (R² = 0.931, p = 0.008). Precision was defined as the %CV of the assay results at each level of parasitemia and the %CV value for our system was lower than that for microscopic examination for all densities of parasitemia. The limit of detection analysis showed 95% probability for parasite detection was 0.00066112%, and a high correlation was observed among all three methods. The sensitivity and specificity of the system was both 100% (n = 21/21) and 100% (n = 50/50), respectively, and the system correctly identified all P. vivax and P. falciparum samples. The automated microscopic malaria parasite detection system offers several advantages over conventional microscopy for rapid diagnosis and parasite density monitoring of malaria.

Diagnosis of Malaria Parasites Plasmodium spp. in Endemic Areas: Current Strategies for an Ancient Disease

Fast and effective detection of the causative agent of malaria in humans, protozoan Plasmodium parasites, is of crucial importance for increasing the effectiveness of treatment and to control a devastating disease that affects millions of people living in endemic areas. The microscopic examination of Giemsa-stained blood films still remains the gold-standard in Plasmodium detection today. However, there is a high demand for alternative diagnostic methods that are simple, fast, highly sensitive, ideally do not rely on blood-drawing and can potentially be conducted by the patients themselves. Here, the history of Plasmodium detection is discussed, and advantages and disadvantages of diagnostic methods that are currently being applied are assessed.

Diagnostic performance of CellaVision DM96 for Plasmodium vivax and Plasmodium falciparum screening in peripheral blood smears

Microscopic examination of blood smears is the standard method for malaria diagnosis but is labor-intensive and requires expert staff. CellaVision DM96 (CellaVision, Lund, Sweden) is a digital hematology analyzer available for advanced morphological analysis of blood films including intracellular parasites. Here, we evaluated the CellaVision DM96 Advanced RBC Application for malaria detection in stained peripheral blood (PB) smears. Two hundred and twenty thin PB smear slides (84 P. vivax, 14 P. falciparum, 122 negative controls) were stained with Wright-Giemsa using automated slidemaker/strainers of Beckman Coulter hematology systems (LH780, Beckman Coulter Inc., Miami, FL). The slides were automatically analyzed by CellaVision, and images were manually reviewed by experts. The results of automatic and manual detection by CellaVision were compared to those of microscopic examination. The sensitivity and specificity of automatic detection by CellaVision were 23.5% (23/98) and 81.1% (99/122), respectively. When CellaVision images were manually reviewed, the sensitivity and specificity increased to 65.3% (64/98) and 90.2% (110/122), respectively. The detection of P. falciparum showed the highest sensitivity by both the automated (33.3%) and the manual (85.7%) method. CellaVision misinterpreted malaria parasites as Howell-Jolly bodies in 57.1%, as Pappenheimer bodies in 84.7%, and as basophilic stipplings in 75.5% of the slides. Malaria diagnosis using CellaVision DM96 requires further improvements. Manual review improves CellaVision performance, but confirmation by conventional microscopy remains essential.

Performance evaluation of laboratory professionals on malaria microscopy at health facilities in Bahir Dar city administration, Northwest Ethiopia

BACKGROUND

Microscopic diagnosis of Giemsa stained thick and thin blood films by skilled microscopists has remained the gold standard laboratory method for the diagnosis of malaria. However, there is a scarcity of qualified laboratory professionals for correctly diagnosing malaria using microscopy. The aim of this study was to evaluate the performance of laboratory professionals on malaria microscopy at health facilities in Bahir Dar city administration, Northwest Ethiopia.

METHODS

A cross-sectional study was conducted from January to March 2017 in Bahir Dar City. A total of 87 laboratory professionals participated in the selected health facilities, with a response rate of (100%). Standardized pre-validated slide panels and questionnaire were distributed to laboratory professionals by the principal investigator. The panel slides were comprised of 5 positives and 3 negative blood films. The laboratory professionals were requested to report the parasite density using semi-quantitative (+) and per micro-liter methods. Their performances of slide readings were compared with the experts' readings. Agreement in detecting malaria parasites between laboratory professionals and expert was estimated using the kappa score.

RESULTS

The overall sensitivity and specificity of the laboratory professionals in detecting malaria parasites were 83% and 97%, respectively. Similarly, positive predictive values of 98.1% and negative predictive values of 77.7% were reported. The percent agreement between laboratory professionals and expert microscopist in the detection of malaria parasites was 88.5% with a Kappa index of 0.78. Percent agreement in species identification and reporting of Pf/Pv mixed infections were 27.2% and 22.4%, respectively. About 62.2% of the laboratory professionals reported parasite density using semi-quantitative method. While none of them reported per micro-liter method.

CONCLUSIONS

The current study showed that laboratory professionals had good performance in parasite detection. However, poor performance was seen in both species identification and reporting of Pf/Pv mixed infections.

Image analysis and machine learning for detecting malaria

Malaria remains a major burden on global health, with roughly 200 million cases worldwide and more than 400,000 deaths per year. Besides biomedical research and political efforts, modern information technology is playing a key role in many attempts at fighting the disease. One of the barriers toward a successful mortality reduction has been inadequate malaria diagnosis in particular. To improve diagnosis, image analysis software and machine learning methods have been used to quantify parasitemia in microscopic blood slides. This article gives an overview of these techniques and discusses the current developments in image analysis and machine learning for microscopic malaria diagnosis. We organize the different approaches published in the literature according to the techniques used for imaging, image preprocessing, parasite detection and cell segmentation, feature computation, and automatic cell classification. Readers will find the different techniques listed in tables, with the relevant articles cited next to them, for both thin and thick blood smear images. We also discussed the latest developments in sections devoted to deep learning and smartphone technology for future malaria diagnosis.

High-throughput and label-free parasitemia quantification and stage differentiation for malaria-infected red blood cells

This work reports a high throughput and label-free microfluidic cell deformability sensor for quantitative parasitemia measurement and stage determination for Plasmodium falciparum-infected red blood cells (Pf-iRBCs). The sensor relies on differentiating the RBC deformability (a mechanical biomarker) that is highly correlated with the infection status. The cell deformability is measured by evaluating the transit time when each individual RBC squeezes through a microscale constriction (cross-section ~5µm×5µm). More than 30,000 RBCs can be analyzed for parasitemia quantification in under 1min with a throughput ~500 cells/s. Moreover, the device can also differentiate various malaria stages (ring, trophozoite, and schizont stage) due to their varied deformability. Using Pf-iRBCs at 0.1% parasitemia as a testing sample, the microfluidic deformability sensor achieved an excellent sensitivity (94.29%), specificity (86.67%) and accuracy (92.00%) in a blind test, comparable to the gold standard of the blood smear microscopy. As a supplement technology to the microscopy and flow cytometry, the microfluidic deformability sensor would possibly allow for label-free, rapid and cost-effective parasitemia quantification and stage determination for malaria in remote regions.

Immediate assessment of performance of medical laboratory scientists following a 10-day malaria microscopy training programme in Nigeria

BACKGROUND

Rapid and precise diagnosis of malaria is an essential element in effective case management and control of malaria. Malaria microscopy is used as the gold standard for malaria diagnosis, however results remain poor as positivity rate in Nigeria is consistently over 90%. The United States President's Malaria Initiative (PMI) through the Malaria Action Program for States (MAPS) supported selected states in Nigeria to build capacity for malaria microscopy. This study demonstrates the effectiveness of in-service training on malaria microscopy amongst medical laboratory scientists.

METHOD

The training was based on the World Health Organization (WHO) basic microscopy training manual. The 10-day training utilized a series of didactic lectures and examination of teaching slides using a CX 21 Olympus binocular microscope. All 108 medical laboratory scientists trained from 2012 to 2015 across five states in Nigeria supported by PMI were included in the study. Evaluation of the training using a pre-and post-test method was based on written test questions; reading photographic slide images of malaria parasites; and prepared slides.

RESULT

There was a significant improvement in the mean written pre-and post-tests scores from 37.9% (95% CI 36.2-39.6%) to 70.7% (95% CI 68.4-73.1%) (p < 0.001). The mean counting post-test score improved significantly from 4.2% (95% CI 2.6-5.7%) to 27.9% (95% CI 25.3-30.5%) (p < 0.001). Mean post-test score for computer-based picture speciation test (63.0%) and picture detection test (89.2%) were significantly higher than the mean post-test score for slide reading speciation test (38.3%) and slide reading detection test (70.7%), p < 0.001 in both cases.

CONCLUSION

Parasite detection and speciation using enhanced visual imaging was significantly improved compared with using direct microscopy. Regular in-service training and provision of functional and high resolution microscopes are needed to ensure quality routine malaria microscopy.

Computer Vision Malaria Diagnostic Systems-Progress and Prospects

Accurate malaria diagnosis is critical to prevent malaria fatalities, curb overuse of antimalarial drugs, and promote appropriate management of other causes of fever. While several diagnostic tests exist, the need for a rapid and highly accurate malaria assay remains. Microscopy and rapid diagnostic tests are the main diagnostic modalities available, yet they can demonstrate poor performance and accuracy. Automated microscopy platforms have the potential to significantly improve and standardize malaria diagnosis. Based on image recognition and machine learning algorithms, these systems maintain the benefits of light microscopy and provide improvements such as quicker scanning time, greater scanning area, and increased consistency brought by automation. While these applications have been in development for over a decade, recently several commercial platforms have emerged. In this review, we discuss the most advanced computer vision malaria diagnostic technologies and investigate several of their features which are central to field use. Additionally, we discuss the technological and policy barriers to implementing these technologies in low-resource settings world-wide.

Performance evaluation of malaria microscopists working at rechecking laboratories in Ethiopia

BACKGROUND

Microscopic diagnosis of Giemsa-stained thick and thin blood films has remained the standard laboratory method for diagnosing malaria. High quality performance of microscopists that examine blood slides in health facilities remains critically important.

MATERIALS AND METHODS

A cross-sectional study was conducted to assess the performance of 107 malaria microscopists working at 23 malaria rechecking laboratories in Ethiopia. A set of 12 blood film slides was distributed to each microscopist. Data was collected and exported to SPSS version 20 for analysis. Chi-square, sensitivity, specificity, percent agreement, and kappa scores were calculated to assess performance in detecting and identification of Plasmodium species.

RESULTS

The mean age of the participants was 30 ± 5 yrs and most of them (54; 50.5%) were working at regional reference laboratories. Overall, the sensitivity of participants in detecting and identifying malaria parasite species was 96.8% and 56.7%, respectively. The overall agreement on detection and identification of malaria species was 96.8% (Kappa = 0.9) and 64.8% (Kappa = 0.33), respectively. The least accurately identified malaria parasite species was P. malariae (3/107; 2.8%) followed by P. ovale (35/107; 32.7%). Participants working at hospital laboratories had the highest percentage (72.3 %, Kappa=0.51) of accurate species identification. Study participants that had participated in malaria microscopy and quality assurance trainings were significantly better at quantifying parasite densities (P<0.001).

CONCLUSION

The accuracy of parasite identification and quantification differed strongly between participants and expert microscopists. Therefore, regular competency assessment and training for malaria microscopists should be mandatory to assure proper diagnosis and management of malaria in Ethiopia.

Performance Evaluation of Malaria Microscopists at Defense Health Facilities in Addis Ababa and Its Surrounding Areas, Ethiopia

Background

Blood film microscopy is the gold standard approach for malaria diagnosis, and preferred method for routine patient diagnosis in health facilities. However, the inability of laboratory professionals to correctly detect and identify malaria parasites microscopically leads to an inappropriate administration of anti-malarial drugs to the patients and incorrect findings in research areas. This study was carried out to evaluate the performance of laboratory professionals in malaria diagnosis in health facilities under the Defense Health Main Department in Addis Ababa and its surroundings, Ethiopia.

Method

A cross sectional study was conducted from June to July 2015. Totally, 60 laboratory professionals out of the selected 16 health facilities were included in the study. Data were collected by distributing standardized pre-validated malaria slide-panels and self-administered questionnaires among professionals, onsite in each study facility. Sensitivity, specificity, and strength of agreement (with kappa score) in performance among the study participants against WHO-certified expert malaria microscopists were calculated.

Result

Of the 60 study participants, 8.3% (5/60) correctly read all the distributed slides in terms of parasite detection, species identification and parasite counting; whereas, each of the remaining 55(91.7%) interpreted at least two slides incorrectly. The overall sensitivity and specificity of participants’ performance in detection of malaria parasites were 65.7% and 100%, respectively. Overall, fair agreement (71.4%; Kappa: 0.4) in detection of malaria parasite was observed between the study subjects and expert readers. The overall sensitivity and specificity of participants in species identification of malaria parasites were respectively 41.3% and 100%. Overall, slight agreement (51.1%; kappa: 0.04) in identification of malaria species was observed. Generally, agreement was lower in parasite detection and species identification at low parasite density and mixed infection cases.

Conclusion

The general agreement between the study participants and expert microscopists in malaria parasite detection and species identification was very low, particularly in the cases of low-parasite density and mixed infections. Therefore, regular external quality assessments and further refreshment trainings are crucial to enhance the skill of professionals in malaria microscopy; particularly for those in non-malarious areas where exposure to malaria diagnosis is low.

Computer-vision-based technology for fast, accurate and cost effective diagnosis of malaria

Background

Microscopy has long been considered to be the gold standard for diagnosis of malaria despite the introduction of newer assays. However, it has many challenges like requirement of trained microscopists and logistic issues. A vision based device that can diagnose malaria, provide speciation and estimate parasitaemia was evaluated.

Methods

The device was evaluated using samples from 431 consented patients, 361 of which were initially screened by RDT and microscopy and later analysed by PCR. It was a prospective, non-randomized, blinded trial. Quantification of parasitaemia was performed by two experienced technicians. Samples were subjected to diagnosis by Sight Dx digital imaging scanning.

Results

The sensitivity and specificity of the SightDx P1 device for analysed samples were found to be 97.05 and 96.33 %, respectively, when compared to PCR. When compared to microscopy, sensitivity and specificity were found to be 94.4 and 95.6 %, respectively. The device was able to speciate 73.3 % of the PCR Plasmodium falciparum positive samples and 91.4 % of PCR Plasmodium vivax positive samples.

Conclusion

The ability of the device to detect parasitaemia as compared with microscopy, was within 50 % in 71.3 % of cases and demonstrated a correlation coefficient of 0.89.

A malaria diagnostic tool based on computer vision screening and visualization of Plasmodium falciparum candidate areas in digitized blood smears

Introduction

Microscopy is the gold standard for diagnosis of malaria, however, manual evaluation of blood films is highly dependent on skilled personnel in a time-consuming, error-prone and repetitive process. In this study we propose a method using computer vision detection and visualization of only the diagnostically most relevant sample regions in digitized blood smears.

Methods

Giemsa-stained thin blood films with P. falciparum ring-stage trophozoites (n = 27) and uninfected controls (n = 20) were digitally scanned with an oil immersion objective (0.1 µm/pixel) to capture approximately 50,000 erythrocytes per sample. Parasite candidate regions were identified based on color and object size, followed by extraction of image features (local binary patterns, local contrast and Scale-invariant feature transform descriptors) used as input to a support vector machine classifier. The classifier was trained on digital slides from ten patients and validated on six samples.

Results

The diagnostic accuracy was tested on 31 samples (19 infected and 12 controls). From each digitized area of a blood smear, a panel with the 128 most probable parasite candidate regions was generated. Two expert microscopists were asked to visually inspect the panel on a tablet computer and to judge whether the patient was infected with P. falciparum. The method achieved a diagnostic sensitivity and specificity of 95% and 100% as well as 90% and 100% for the two readers respectively using the diagnostic tool. Parasitemia was separately calculated by the automated system and the correlation coefficient between manual and automated parasitemia counts was 0.97.

Conclusion

We developed a decision support system for detecting malaria parasites using a computer vision algorithm combined with visualization of sample areas with the highest probability of malaria infection. The system provides a novel method for blood smear screening with a significantly reduced need for visual examination and has a potential to increase the throughput in malaria diagnostics.

A paper microfluidic cartridge for automated staining of malaria parasites with an optically transparent microscopy window

A paper microfluidic cartridge for the automated staining of malaria parasites (Plasmodium) with acridine orange prior to microscopy is presented. The cartridge enables simultaneous, sub-minute generation of both thin and thick smears of acridine orange stained parasites. Parasites are stained in a cellulose matrix, after which the parasites are ejected via capillary forces into an optically transparent chamber. The unique slanted design of the chamber ensures that a high percentage of the stained blood will be of the required thickness for a thin smear, without resorting to spacers or other methods that can increase production cost or require tight quality controls. A hydrophobic snorkel facilitates the removal of air bubbles during filling. The cartridge contains both a thin smear region, where a single layer of cells is presented unobstructed, for ease of species identification, and a thick smear region, containing multiple cell layers, for enhanced limit of detection.

Limitations of haemozoin-based diagnosis of Plasmodium falciparum using dark-field microscopy

Background

The haemozoin crystal continues to be investigated extensively for its potential as a biomarker for malaria diagnostics. In order for haemozoin to be a valuable biomarker, it must be present in detectable quantities in the peripheral blood and distinguishable from false positives. Here, dark-field microscopy coupled with sophisticated image processing algorithms is used to characterize the abundance of detectable haemozoin within infected erythrocytes from field samples in order to determine the window of detection in peripheral blood.

Methods

Thin smears from Plasmodium falciparum-infected and uninfected patients were imaged in both dark field (DF) unstained and bright field (BF) Giemsa-stained modes. The images were co-registered such that each parasite had thumbnails in both BF and DF modes, providing an accurate map between parasites and DF objects. This map was used to find the abundance of haemozoin as a function of parasite stage through careful parasite staging and correlation with DF objects. An automated image-processing and classification algorithm classified the bright spots in the DF images as either haemozoin or non-haemozoin objects.

Results

The algorithm distinguishes haemozoin from non-haemozoin objects in DF images with an object-level sensitivity of 95% and specificity of 97%. Ring stages older than about 6 hours begin to show detectable haemozoin, and rings between 10–16 hours reliably contain detectable haemozoin. However, DF microscopy coupled with the image-processing algorithm detect no haemozoin in rings younger than six hours.

Discussion

Although this method demonstrates the most sensitive detection of haemozoin in field samples reported to date, it does not detect haemozoin in ring-stage parasites younger than six hours. Thus, haemozoin is a poor biomarker for field samples primarily composed of young ring-stage parasites because the crystal is not present in detectable quantities by the methods described here. Based on these results, the implications for patient-level diagnosis and recommendations for future work are discussed.

Malaria diagnostics in clinical trials

Malaria diagnostics are widely used in epidemiologic studies to investigate natural history of disease and in drug and vaccine clinical trials to exclude participants or evaluate efficacy. The Malaria Laboratory Network (MLN), managed by the Office of HIV/AIDS Network Coordination, is an international working group with mutual interests in malaria disease and diagnosis and in human immunodeficiency virus/acquired immunodeficiency syndrome clinical trials. The MLN considered and studied the wide array of available malaria diagnostic tests for their suitability for screening trial participants and/or obtaining study endpoints for malaria clinical trials, including studies of HIV/malaria co-infection and other malaria natural history studies. The MLN provides recommendations on microscopy, rapid diagnostic tests, serologic tests, and molecular assays to guide selection of the most appropriate test(s) for specific research objectives. In addition, this report provides recommendations regarding quality management to ensure reproducibility across sites in clinical trials. Performance evaluation, quality control, and external quality assessment are critical processes that must be implemented in all clinical trials using malaria tests.

Spectrophotometric detection of susceptibility to anti-malarial drugs

BACKGROUND

With malaria drug resistance increasing in prevalence and severity, new technologies are needed to aid and improve the accuracy and clinical relevance of laboratory or field testing for malaria drug resistance. This study presents a method based on simple and reagentless spectroscopic measurements coupled with comprehensive spectral interpretation analysis that provides valuable quantitative information on the morphological and compositional responses of Plasmodium falciparum and infected red blood cells (IRBCs) to anti-malarial treatment.

METHODS

The changes in the size, internal structure, nucleotide and haemozoin composition of the parasites as well as the morphology (size and shape) and haemoglobin composition of the IRBCs treated with dihydroartemisinin (DHA) and mefloquine (MFQ) were investigated using a spectral interpretation analysis.

RESULTS

DHA treatment reduced the sizes of the parasites and their structural organelles. The haemoglobin composition of the host IRBCs determined from spectroscopic analysis changed negligibly following DHA treatment. MFQ treated parasites grew to the same size as those from parallel non-treated cultures but lacked haemozoin. Lesser deformation of the cell shape and no haemoglobin depletion were detected for the IRBCs of MFQ treated cultures.

CONCLUSIONS

The spectroscopic analysis method proved to be sensitive for recognition of the effects of anti-malarial treatment on the structure and composition of the parasites and IRBCs. The method can have significant potential for research and clinical applications such as evaluating patient specimens for drug action, drug effects or for therapeutic monitoring.

Crowdsourcing malaria parasite quantification: an online game for analyzing images of infected thick blood smears

Background

There are 600,000 new malaria cases daily worldwide. The gold standard for estimating the parasite burden and the corresponding severity of the disease consists in manually counting the number of parasites in blood smears through a microscope, a process that can take more than 20 minutes of an expert microscopist’s time.

Objective

This research tests the feasibility of a crowdsourced approach to malaria image analysis. In particular, we investigated whether anonymous volunteers with no prior experience would be able to count malaria parasites in digitized images of thick blood smears by playing a Web-based game.

Methods

The experimental system consisted of a Web-based game where online volunteers were tasked with detecting parasites in digitized blood sample images coupled with a decision algorithm that combined the analyses from several players to produce an improved collective detection outcome. Data were collected through the MalariaSpot website. Random images of thick blood films containing Plasmodium falciparum at medium to low parasitemias, acquired by conventional optical microscopy, were presented to players. In the game, players had to find and tag as many parasites as possible in 1 minute. In the event that players found all the parasites present in the image, they were presented with a new image. In order to combine the choices of different players into a single crowd decision, we implemented an image processing pipeline and a quorum algorithm that judged a parasite tagged when a group of players agreed on its position.

Results

Over 1 month, anonymous players from 95 countries played more than 12,000 games and generated a database of more than 270,000 clicks on the test images. Results revealed that combining 22 games from nonexpert players achieved a parasite counting accuracy higher than 99%. This performance could be obtained also by combining 13 games from players trained for 1 minute. Exhaustive computations measured the parasite counting accuracy for all players as a function of the number of games considered and the experience of the players. In addition, we propose a mathematical equation that accurately models the collective parasite counting performance.

Conclusions

This research validates the online gaming approach for crowdsourced counting of malaria parasites in images of thick blood films. The findings support the conclusion that nonexperts are able to rapidly learn how to identify the typical features of malaria parasites in digitized thick blood samples and that combining the analyses of several users provides similar parasite counting accuracy rates as those of expert microscopists. This experiment illustrates the potential of the crowdsourced gaming approach for performing routine malaria parasite quantification, and more generally for solving biomedical image analysis problems, with future potential for telediagnosis related to global health challenges.

A mathematical framework for combining decisions of multiple experts toward accurate and remote diagnosis of malaria using tele-microscopy

We propose a methodology for digitally fusing diagnostic decisions made by multiple medical experts in order to improve accuracy of diagnosis. Toward this goal, we report an experimental study involving nine experts, where each one was given more than 8,000 digital microscopic images of individual human red blood cells and asked to identify malaria infected cells. The results of this experiment reveal that even highly trained medical experts are not always self-consistent in their diagnostic decisions and that there exists a fair level of disagreement among experts, even for binary decisions (i.e., infected vs. uninfected). To tackle this general medical diagnosis problem, we propose a probabilistic algorithm to fuse the decisions made by trained medical experts to robustly achieve higher levels of accuracy when compared to individual experts making such decisions. By modelling the decisions of experts as a three component mixture model and solving for the underlying parameters using the Expectation Maximisation algorithm, we demonstrate the efficacy of our approach which significantly improves the overall diagnostic accuracy of malaria infected cells. Additionally, we present a mathematical framework for performing ‘slide-level’ diagnosis by using individual ‘cell-level’ diagnosis data, shedding more light on the statistical rules that should govern the routine practice in examination of e.g., thin blood smear samples. This framework could be generalized for various other tele-pathology needs, and can be used by trained experts within an efficient tele-medicine platform.