Dataset Information

A novel deep learning-based point-of-care diagnostic method for detecting Plasmodium falciparum with fluorescence digital microscopy.

ABSTRACT: BACKGROUND:Malaria remains a major global health problem with a need for improved field-usable diagnostic tests. We have developed a portable, low-cost digital microscope scanner, capable of both brightfield and fluorescence imaging. Here, we used the instrument to digitize blood smears, and applied deep learning (DL) algorithms to detect Plasmodium falciparum parasites. METHODS:Thin blood smears (n = 125) were collected from patients with microscopy-confirmed P. falciparum infections in rural Tanzania, prior to and after initiation of artemisinin-based combination therapy. The samples were stained using the 4',6-diamidino-2-phenylindole fluorogen and digitized using the prototype microscope scanner. Two DL algorithms were trained to detect malaria parasites in the samples, and results compared to the visual assessment of both the digitized samples, and the Giemsa-stained thick smears. RESULTS:Detection of P. falciparum parasites in the digitized thin blood smears was possible both by visual assessment and by DL-based analysis with a strong correlation in results (r = 0.99, p < 0.01). A moderately strong correlation was observed between the DL-based thin smear analysis and the visual thick smear-analysis (r = 0.74, p < 0.01). Low levels of parasites were detected by DL-based analysis on day three following treatment initiation, but a small number of fluorescent signals were detected also in microscopy-negative samples. CONCLUSION:Quantification of P. falciparum parasites in DAPI-stained thin smears is feasible using DL-supported, point-of-care digital microscopy, with a high correlation to visual assessment of samples. Fluorescent signals from artefacts in samples with low infection levels represented the main challenge for the digital analysis, thus highlighting the importance of minimizing sample contaminations. The proposed method could support malaria diagnostics and monitoring of treatment response through automated quantification of parasitaemia and is likely to be applicable also for diagnostics of other Plasmodium species and other infectious diseases.

SUBMITTER: Holmstrom O

PROVIDER: S-EPMC7671488 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A novel deep learning-based point-of-care diagnostic method for detecting Plasmodium falciparum with fluorescence digital microscopy.

Holmström Oscar O Stenman Sebastian S Suutala Antti A Moilanen Hannu H Kücükel Hakan H Ngasala Billy B Mårtensson Andreas A Mhamilawa Lwidiko L Aydin-Schmidt Berit B Lundin Mikael M Diwan Vinod V Linder Nina N Lundin Johan J

PloS one 20201117 11

<h4>Background</h4>Malaria remains a major global health problem with a need for improved field-usable diagnostic tests. We have developed a portable, low-cost digital microscope scanner, capable of both brightfield and fluorescence imaging. Here, we used the instrument to digitize blood smears, and applied deep learning (DL) algorithms to detect Plasmodium falciparum parasites.<h4>Methods</h4>Thin blood smears (n = 125) were collected from patients with microscopy-confirmed P. falciparum infect ...[more]

PMID: 33201905

Similar Datasets

Project description:BackgroundAsymptomatic malaria infections can serve as potential reservoirs for malaria transmission. The density of parasites contained in these infections range from microscopic to submicroscopic densities, making the accurate detection of asymptomatic parasite carriage highly dependent on the sensitivity of the tools used for the diagnosis. This study sought to evaluate the sensitivities of a variety of molecular and serological diagnostic tools at determining the prevalence of asymptomatic Plasmodium falciparum parasite infections in two communities with varying malaria parasite prevalence.MethodsWhole blood was collected from 194 afebrile participants aged between 6 and 70 years old living in a high (Obom) and a low (Asutsuare) malaria transmission setting of Ghana. Thick and thin blood smears, HRP2 based malaria rapid diagnostic test (RDT) and filter paper dried blood spots (DBS) were prepared from each blood sample. Genomic DNA was extracted from the remaining blood and used in Plasmodium specific photo-induced electron transfer polymerase chain reaction (PET-PCR) and Nested PCR, whilst the HRP2 antigen content of the DBS was estimated using a bead immunoassay. A comparison of malaria parasite prevalence as determined by each method was performed.ResultsParasite prevalence in the high transmission site of Obom was estimated at 71.4%, 61.9%, 60%, 37.8% and 19.1% by Nested PCR, the HRP2 bead assay, PET-PCR, HRP2-RDT and microscopy respectively. Parasite prevalence in the low transmission site of Asutsuare was estimated at 50.1%, 11.2%, 5.6%, 0% and 2.2% by Nested PCR, the HRP2 bead assay, PET-PCR, RDT and microscopy, respectively. The diagnostic performance of Nested PCR, PET-PCR and the HRP2 bead assay was similar in Obom but in Asutsuare, Nested PCR had a significantly higher sensitivity than PET-PCR and the HRP2 bead assay, which had similar sensitivity.ConclusionsNested PCR exhibited the highest sensitivity by identifying the highest prevalence of asymptomatic P. falciparum in both the high and low parasite prevalence settings. However, parasite prevalence estimated by the HRP2 bead assay and PET-PCR had the highest level of inter-rater agreement relative to all the other tools tested and have the advantage of requiring fewer processing steps relative to Nested PCR and producing quantitative results.

Project description:Prompt, accurate diagnosis and treatment with artemisinin combination therapy remains vital to current malaria control. Blood film microscopy the current standard test for diagnosis of malaria has several limitations that necessitate field evaluation of alternative diagnostic methods especially in low income countries of sub-Saharan Africa where malaria is endemic.The accuracy of axillary temperature, health centre (HC) microscopy, expert microscopy and a HRP2-based rapid diagnostic test (Paracheck) was compared in predicting malaria infection using polymerase chain reaction (PCR) as the gold standard. Three hundred patients with a clinical suspicion of malaria based on fever and or history of fever from a low and high transmission setting in Uganda were consecutively enrolled and provided blood samples for all tests. Accuracy of each test was calculated overall with 95% confidence interval and then adjusted for age-groups and level of transmission intensity using a stratified analysis. The endpoints were: sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). This study is registered with Clinicaltrials.gov, NCT00565071.Of the 300 patients, 88(29.3%) had fever, 56(18.7%) were positive by HC microscopy, 47(15.7%) by expert microscopy, 110(36.7%) by Paracheck and 89(29.7%) by PCR. The overall sensitivity >90% was only shown by Paracheck 91.0% [95%CI: 83.1-96.0]. The sensitivity of expert microscopy was 46%, similar to HC microscopy. The superior sensitivity of Paracheck compared to microscopy was maintained when data was stratified for transmission intensity and age. The overall specificity rates were: Paracheck 86.3% [95%CI: 80.9-90.6], HC microscopy 93.4% [95%CI: 89.1-96.3] and expert microscopy 97.2% [95%CI: 93.9-98.9]. The NPV >90% was shown by Paracheck 95.8% [95%CI: 91.9-98.2]. The overall PPV was <88% for all methods.The HRP2-based RDT has shown superior sensitivity compared to microscopy in diagnosis of malaria and may be more suitable for screening of malaria infection.

Project description:BackgroundZambia continues to advance on the path to elimination with significant reductions in malaria morbidity and mortality. Crucial components that have contributed to progress thus far and are necessary for achieving the national malaria elimination goals include properly identifying and treating all malaria cases through accurate diagnosis. This study sought to compare and assess the diagnostic performance of Rapid Diagnostic Tests (RDT) and Light Microscopy (LM) with photo-induced electron transfer polymerase chain reaction (PET-PCR) as the gold standard using 2018 Malaria Indicator Survey (MIS) data across Zambia to better understand diagnostic accuracy metrics and how these vary across a transmission gradient.MethodsCross-sectional samples collected in a nationally representative survey from 7 provinces in Zambia were tested for the presence of malaria parasites by light microscopy (LM), rapid diagnostic test (RDT) and the gold standard PET-PCR. Diagnostic performance was assessed including sensitivity, specificity, negative- and positive-predictive values across a wide malaria transmission spectrum. Diagnostic accuracy metrics were measured, and statistically significant differences were calculated between test methods for different outcome variables.ResultsFrom the individuals included in the MIS, the overall prevalence of Plasmodium falciparum malaria was 32.9% by RDT, 19.4% by LM, and 23.2% by PET-PCR. Herein, RDT and LM diagnostic performance was compared against gold standard PET-PCR with LM displaying a higher diagnostic accuracy than RDTs (91.3% vs. 84.6% respectively) across the transmission spectrum in Zambia. However, the performance of both diagnostics was significantly reduced in low parasitaemia samples. Consistent with previous studies, RDT diagnostic accuracy was predominantly affected by a high rate of false positives.ConclusionsRDTs and LM both perform well across a range of transmission intensities within their respective target applications, i.e., in the community, for the former, where ease of use and speed of result is critical, and at the health facility, for the latter, where accuracy is prioritized. However, the performance of both diagnostic methods is adversely affected by low parasitaemia infections. As Zambia moves towards elimination more sensitive tools may be required to identify the last cases.

Dataset Information

A novel deep learning-based point-of-care diagnostic method for detecting Plasmodium falciparum with fluorescence digital microscopy.

Publications

A novel deep learning-based point-of-care diagnostic method for detecting Plasmodium falciparum with fluorescence digital microscopy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets