Application of image recognition technology in pathological diagnosis of blood smears.

Traditional manual blood smear diagnosis methods are time-consuming and prone to errors, often relying heavily on the experience of clinical laboratory analysts for accuracy. As breakthroughs in key technologies such as neural networks and deep learning continue to drive digital transformation in the medical field, image recognition technology is increasingly being leveraged to enhance existing medical processes. In recent years, advancements in computer technology have led to improved efficiency in the identification of blood cells in blood smears through the use of image recognition technology. This paper provides a comprehensive summary of the methods and steps involved in utilizing image recognition algorithms for diagnosing diseases in blood smears, with a focus on malaria and leukemia. Furthermore, it offers a forward-looking research direction for the development of a comprehensive blood cell pathological detection system.

Ultrasound as a triaging tool for the diagnosis of malaria and typhoid in a resource constrained setting: A proposed frame-work.

INTRODUCTION: Ultrasound has proven to have great potentials in the diagnosis and work-up of patients affected by tropical diseases. Its role in the diagnosis of malaria and typhoid abounds, but its value as a triaging tool in a resource-constrained settings is indistinct. Our review aimed is aimed at assessing the utility of ultrasound in diagnosis and prognosis of malaria and typhoid. MATERIALS AND METHOD: Extensive literature search was conducted using the PubMed electronic database, for original peer reviewed articles in English language within 1964-2023. Keywords like "malaria", "typhoid", "S. Typhi", "Salmonella Typhi", "enteric fever", "ultrasound", "sonography" and "ultrasonography" were searched, using Boolean operators such as (OR, AND) applying the following filters (English, Human). A systematic synthesis of the literature was done. RESULT: Our initial search yielded 749 potentially relevant references out of which 55 were found to be eligible. Organs assessed include the liver, spleen, kidneys, intestines, mesenteric lymph nodes, among others. For malaria, pathognomonic conditions like splenic enlargement, hepatomegaly, renal abnormalities as well as mesenteric lymph nodes and intestinal wall thickening in patients with typhoid fever. CONCLUSION: Ultrasound by experienced clinicians adds significantly to the diagnosis and work-up of patients with malaria and typhoid fever. However, it is important to note that ultrasound alone may not be sufficient for definitive diagnosis as laboratory tests may still be required for confirmatory diagnosis. IMPLICATION FOR PRACTICE: This study provide information on ultrasound in diagnosis of Malaria and typhoid by evaluating the morphological changes in abdominal and other organs of the body. This can be a guide to clinicians and other healthcare providers for early diagnosis and work-up of patients in endemic areas where resources are scarce.

Tile-based microscopic image processing for malaria screening using a deep learning approach.

BACKGROUND: Manual microscopic examination remains the golden standard for malaria diagnosis. But it is laborious, and pathologists with experience are needed for accurate diagnosis. The need for computer-aided diagnosis methods is driven by the enormous workload and difficulties associated with manual microscopy based examination. While the importance of computer-aided diagnosis is increasing at an enormous pace, fostered by the advancement of deep learning algorithms, there are still challenges in detecting small objects such as malaria parasites in microscopic images of blood films. The state-of-the-art (SOTA) deep learning-based object detection models are inefficient in detecting small objects accurately because they are underrepresented on benchmark datasets. The performance of these models is affected by the loss of detailed spatial information due to in-network feature map downscaling. This is due to the fact that the SOTA models cannot directly process high-resolution images due to their low-resolution network input layer. METHODS: In this study, an efficient and robust tile-based image processing method is proposed to enhance the performance of malaria parasites detection SOTA models. Three variants of YOLOV4-based object detectors are adopted considering their detection accuracy and speed. These models were trained using tiles generated from 1780 high-resolution P. falciparum-infected thick smear microscopic images. The tiling of high-resolution images improves the performance of the object detection models. The detection accuracy and the generalization capability of these models have been evaluated using three datasets acquired from different regions. RESULTS: The best-performing model using the proposed tile-based approach outperforms the baseline method significantly (Recall, [95.3%] vs [57%] and Average Precision, [87.1%] vs [76%]). Furthermore, the proposed method has outperformed the existing approaches that used different machine learning techniques evaluated on similar datasets. CONCLUSIONS: The experimental results show that the proposed method significantly improves P. falciparum detection from thick smear microscopic images while maintaining real-time detection speed. Furthermore, the proposed method has the potential to assist and reduce the workload of laboratory technicians in malaria-endemic remote areas of developing countries where there is a critical skill gap and a shortage of experts.

Randomly positioned gold nanoparticles as fluorescence enhancers in apta-immunosensor for malaria test.

A plasmon-enhanced fluorescence-based antibody-aptamer biosensor - consisting of gold nanoparticles randomly immobilized onto a glass substrate via electrostatic self-assembly - is described for specific detection of proteins in whole blood. Analyte recognition is realized through a sandwich scheme with a capture bioreceptor layer of antibodies - covalently immobilized onto the gold nanoparticle surface in upright orientation and close-packed configuration by photochemical immobilization technique (PIT) - and a top bioreceptor layer of fluorescently labelled aptamers. Such a sandwich configuration warrants not only extremely high specificity, but also an ideal fluorophore-nanostructure distance (approximately 10-15 nm) for achieving strong fluorescence amplification. For a specific application, we tested the biosensor performance in a case study for the detection of malaria-related marker Plasmodium falciparum lactate dehydrogenase (PfLDH). The proposed biosensor can specifically detect PfLDH in spiked whole blood down to 10 pM (0.3 ng/mL) without any sample pretreatment. The combination of simple and scalable fabrication, potentially high-throughput analysis, and excellent sensing performance provides a new approach to biosensing with significant advantages compared to conventional fluorescence immunoassays.

Performance of malaria microscopy external quality assessment and networking among health facilities in west Amhara region, Ethiopia.

BACKGROUND: Microscopic examination of peripheral blood smear produces reliable results both about the malaria infection status and level of parasitemia. However, test results are affected by skill of the laboratory personnel, workload, condition of microscopes and quality of laboratory supplies. Therefore, continuous monitoring of the performance of laboratories is of pivotal importance in order to make timely correction. METHODS: A facility based cross-sectional study was conducted from July 2017 to July 2019 to assess malaria microscopy performance among thirty malaria diagnostic laboratories in west Amhara region. Thirty slides were collected from participating laboratories every quarter. Collected slides were taken to Amhara Public Health Institute reference laboratory and re-checked by malaria microscopists who were blind to the results from health facilities. Percentage of test agreement, rates of false positive, false negative and species misdiagnosis were calculated using Excel 2010. RESULTS: Among a total of 6689 slides re-checked, results of 6146 slides were the same with that of participating laboratories. The test agreement was 97.31 and 94.6% for parasite detection and species identification, respectively. Variations in the overall performance of individual laboratories were seen within a range of 81.55 to 97.27% test agreement. Results of 543 (8.12%) slides were discordant, of which 363 (5.4%), 93 (1.4%) and 87 (1.3%) slides were due to species misdiagnosis, false positive and false negative results, respectively. CONCLUSION: There was good test agreement between participated laboratories and Amhara Public Health Institute. More accurate performance is expected as the country is tracking to malaria elimination. Hence, further strengthening the external quality assurance program is recommended.

Cerebral Blood Flow Velocity is Not Associated with Serum Hemoglobin in Children with Malaria-Associated Anemia.

BACKGROUND AND PURPOSE: Hemoglobin (Hbg) is often thought to impact cerebral blood flow velocity (CBFV). This study was performed to investigate the relationship between Hbg value and CBFV in African children with malaria. METHODS: In this prospective, observational study, children aged 3 months to 18 years with malaria and a normal Blantyre coma score underwent a single transcranial Doppler ultrasound (TCD) examination with a concurrent Hbg check. RESULTS: One hundred fifty-six children with a mean age of 43 months were enrolled. Thirty-three children (21%) had severe anemia (Hbg <5g/dL), 46 (29%) had moderate anemia (Hbg 5-6.9 g/dL), 63 children (41%) had mild anemia (7-9.9 g/dL), and 14 children (9%) had no anemia (Hbg >10 g/dL) at the time of TCD examination. Mean averaged CBFV in the middle cerebral artery (MCA) for the cohort was 99% of predicted based on normative values standardized for age. There was no significant correlation between Hbg levels and measured CBFV in the MCA (r = -.09; 95% CI, -.24-.07; P = .29). CONCLUSION: In a large sample of African children with malaria, Hbg did not correlate with CBFVs as measured by TCD. Future work that includes baseline TCD measurements and Hbg values as well as other physiological parameters known to influence CBFVs is necessary to confirm these findings.

Dual-Luciferase-Based Fast and Sensitive Detection of Malaria Hypnozoites for the Discovery of Antirelapse Compounds.

Efforts to eradicate Plasmodium vivax malaria are hampered by the presence of hypnozoites, persisting stages in the liver that can reactivate after prolonged periods of time enabling further transmission and causing renewed disease. Large-scale drug screening is needed to identify compounds with antihypnozoite activity, but current platforms rely on time-consuming high-content fluorescence imaging as read-out, limiting assay throughput. We here report an ultrafast and sensitive dual-luciferase-based method to differentiate hypnozoites from liver stage schizonts using a transgenic P. cynomolgi parasite line that contains Nanoluc driven by the constitutive hsp70 promoter, as well as firefly luciferase driven by the schizont-specific lisp2 promoter. The transgenic parasite line showed similar fitness and drug sensitivity profiles of selected compounds to wild type. We demonstrate robust bioluminescence-based detection of hypnozoites in 96-well and 384-well plate formats, setting the stage for implementation in large scale drug screens.

Sequential classification system for recognition of malaria infection using peripheral blood cell images.

AIMS: Morphological recognition of red blood cells infected with malaria parasites is an important task in the laboratory practice. Nowadays, there is a lack of specific automated systems able to differentiate malaria with respect to other red blood cell inclusions. This study aims to develop a machine learning approach able to discriminate parasitised erythrocytes not only from normal, but also from other erythrocyte inclusions, such as Howell-Jolly and Pappenheimer bodies, basophilic stippling as well as platelets overlying red blood cells. METHODS: A total of 15 660 erythrocyte images from 87 smears were segmented using histogram thresholding and watershed techniques, which allowed the extraction of 2852 colour and texture features. Dataset was split into a training and assessment sets. Training set was used to develop the whole system, in which several classification approaches were compared with obtain the most accurate recognition. Afterwards, the recognition system was evaluated with the assessment set, performing two steps: (1) classifying each individual cell image to assess the system's recognition ability and (2) analysing whole smears to obtain a malaria infection diagnosis. RESULTS: The selection of the best classification approach resulted in a final sequential system with an accuracy of 97.7% for the six groups of red blood cell inclusions. The ability of the system to detect patients infected with malaria showed a sensitivity and specificity of 100% and 90%, respectively. CONCLUSIONS: The proposed method achieves a high diagnostic performance in the recognition of red blood cell infected with malaria, along with other frequent erythrocyte inclusions.

Discovery of a natural fluorescent probe targeting the Plasmodium falciparum cysteine protease falcipain-2.

The Plasmodium falciparum cysteine protease falcipain-2 (FP-2) is an attractive antimalarial target. Here, we discovered that the natural compound NP1024 is a nonpeptidic inhibitor of FP-2 with an IC50 value of 0.44 µmol L-1. The most exciting finding is that both in vitro and in vivo, NP1024 directly targets FP-2 in malaria parasite-infected erythrocytes as a natural fluorescent probe, thereby paving the way for an integration of malaria diagnosis and treatment.

Novel broad-spectrum activity-based probes to profile malarial cysteine proteases.

Clan CA cysteine proteases, also known as papain-like proteases, play important roles throughout the malaria parasite life cycle and are therefore potential drug targets to treat this disease and prevent its transmission. In order to study the biological function of these proteases and to chemically validate some of them as viable drug targets, highly specific inhibitors need to be developed. This is especially challenging given the large number of clan CA proteases present in Plasmodium species (ten in Plasmodium falciparum), and the difficulty of designing selective inhibitors that do not cross-react with other members of the same family. Additionally, any efforts to develop antimalarial drugs targeting these proteases will also have to take into account potential off-target effects against the 11 human cysteine cathepsins. Activity-based protein profiling has been a very useful tool to determine the specificity of inhibitors against all members of an enzyme family. However, current clan CA proteases broad-spectrum activity-based probes either target endopeptidases or dipeptidyl aminopeptidases, but not both subfamilies efficiently. In this study, we present a new series of dipeptydic vinyl sulfone probes containing a free N-terminal tryptophan and a fluorophore at the P1 position that are able to label both subfamilies efficiently, both in Plasmodium falciparum and in mammalian cells, thus making them better broad-spectrum activity-based probes. We also show that some of these probes are cell permeable and can therefore be used to determine the specificity of inhibitors in living cells. Interestingly, we show that the choice of fluorophore greatly influences the specificity of the probes as well as their cell permeability.

Detection of red and white blood cells from microscopic blood images using a region proposal approach.

In this paper, we propose a novel and efficient method for detecting and quantifying red and white blood cells from microscopic blood images. Laboratory tests that use a cell counter or a flow cytometer can perform a complete blood count (CBC) rapidly. Nonetheless, a manual blood smear inspection is still needed, both to have a human check on the counter results and to monitor patients under therapy. Moreover, it allows for describing the cells' appearance as well as any abnormalities. However, manual analysis is lengthy and repetitive, and its result can be subjective and error-prone. In contrast, by using image processing techniques, the proposed system is entirely automated. The main effort is devoted to both achieving high accuracy and finding a way to overcome the typical differences in the condition of blood smear images that computer-aided methods encounter. It is based on the Edge Boxes method, which is considered a state-of-art region proposal approach. By incorporating knowledge-based constraints into the detection process using Edge Boxes, we can find cell proposals rapidly and efficiently. We tested the proposed approach on the Acute Lymphoblastic Leukaemia Image Database (ALL-IDB), a well-known public dataset proposed for leukaemia detection, and the Malaria Parasite Image Database (MP-IDB), a recently proposed dataset for malaria detection. Experimental results were excellent in both cases, outperforming the state-of-the-art on ALL-IDB and creating a strong baseline on MP-IDB, demonstrating that the proposed method can work well on different datasets and different types of images.

Is there a role for bedside ultrasound in malaria? A survey of the literature.

PURPOSE: Point-of-care ultrasound (POCUS) has proven utility in the evaluation and treatment of many tropical diseases. Its role in malaria has been studied, but its value for the clinician at the bedside is unclear. Our review aimed at summarizing the existing studies to assess the usefulness, if any, of POCUS in treating malaria. METHODS: We used Boolean operators using keywords "malaria", "acoustic", "ultrasound", "echography", and "ultrasonography" to search PubMed, Scopus, and Science Direct in three languages (Italian, French, and English). RESULTS: We found 22 eligible references. Organs explored include the liver, spleen, heart, optic nerve sheath diameter (ONSD), kidney, lungs, and cerebral vasculature. Multiple pathologic findings by ultrasound are reported, but few demonstrate clinical utility. Current studies involve small numbers of patients, and a few trends emerge when studies are compared. The ability to combine study results is limited due to the significant heterogeneity that exists between studies in regards to both methods of evaluation and the reporting of organ pathology and malaria severity. CONCLUSIONS AND ASSESSMENT: A review of the current literature indicates that the use of ultrasound by clinicians adds little to the diagnostic evaluation of patients with malaria. Our review did find that measurements of the spleen, lungs, optic nerve sheath diameter, and cerebral blood flow have potential utility in specific patient populations. Further studies are needed to evaluate whether this utility persists when a larger sample size is used.

Updating the modified Thompson test by using whole-body bioluminescence imaging to replace traditional efficacy testing in experimental models of murine malaria.

BACKGROUND: Rodent malaria models are extensively used to predict treatment outcomes in human infections. There is a constant need to improve and refine these models by innovating ways to apply new scientific findings and cutting edge technologies. In addition, and in accordance with the three R's of animal use in research, in vivo studies should be constantly refined to avoid unnecessary pain and distress to the experimental animals by using preemptive euthanasia as soon as the main scientific study objective has been accomplished. METHODS: The new methodology described in this manuscript uses the whole-body bioluminescence signal emitted by transgenic, luciferase-expressing Plasmodium berghei parasites to assess the parasite load predicted parasitaemia (PLPP) in drug and control treated female ICR-CD1 mice infected with 1 × 105 luciferase-expressing P. berghei (ANKA strain) infected erythrocytes. This methodology can replace other time-consuming and expensive methods that are routinely used to measure parasitaemia in infected animals, such as Giemsa-stained thin blood smears and flow cytometry. RESULTS: There is a good correlation between whole-body bioluminescence signal and parasitaemia measured using Giemsa-stained thin blood smears and flow cytometry respectively in donor and study mice in the modified Thompson test. The algebraic formulas which represent these correlations can be successfully used to assess PLPP in donor and study mice. In addition, the new methodology can pinpoint sick animals 2-8 days before they would have been otherwise diagnosed based on behavioural or any other signs of malaria disease. CONCLUSIONS: The new method for predicting parasitaemia in the modified Thompson test is simple, precise, objective, and minimizes false positive results that can lead to the premature removal of animals from study. Furthermore, from the animal welfare perspective of replace, reduce, and refine, this new method facilitates early removal of sick animals from study as soon as the study objective has been achieved, in many cases well before the clinical signs of disease are present.

Association of Plasmodium berghei With the Apical Domain of Hepatocytes Is Necessary for the Parasite's Liver Stage Development.

Plasmodium parasites undergo a dramatic transformation during the liver stage of their life cycle, amplifying over 10,000-fold inside infected hepatocytes within a few days. Such a rapid growth requires large-scale interactions with, and manipulations of, host cell functions. Whereas hepatocyte polarity is well-known to be critical for liver function, little is presently known about its involvement during the liver stage of Plasmodium development. Apical domains of hepatocytes are critical components of their polarity machinery and constitute the bile canalicular network, which is central to liver function. Here, we employed high resolution 3-D imaging and advanced image analysis of Plasmodium-infected liver tissues to show that the parasite associates preferentially with the apical domain of hepatocytes and induces alterations in the organization of these regions, resulting in localized changes in the bile canalicular architecture in the liver tissue. Pharmacological perturbation of the bile canalicular network by modulation of AMPK activity reduces the parasite's association with bile canaliculi and arrests the parasite development. Our findings using Plasmodium-infected liver tissues reveal a host-Plasmodium interaction at the level of liver tissue organization. We demonstrate for the first time a role for bile canaliculi, a central component of the hepatocyte polarity machinery, during the liver stage of Plasmodium development.

Malaria complicada por síndrome de dificultad respiratoria aguda en paciente embarazada: reporte de un caso / Malaria complicated by acute respiratory distress syndrome in a pregnant patient: case report

RESUMEN Introducción: El síndrome de dificultad respiratoria aguda del adulto se presenta como una rara complicación obstétrica, siendo una de sus posibles etiologías la infección derivada por Plasmodium falciparum. La malaria complicada es cada vez menos frecuente, pero se asocia a una alta morbilidad y mortalidad en regiones endémicas, especialmente en pacientes embarazadas, quienes presentan un mayor riesgo de contraerla. Caso clínico: Presentamos el caso clínico de una embarazada con síndrome de dificultad respiratoria aguda del adulto secundario a una malaria complicada y que tiene un aborto de 14 semanas de gestación como consecuencia de esta complicación materna. Discusión: Se realiza una descripción del manejo de la paciente, a quien, a pesar del resultado obstétrico desfavorable, evoluciona satisfactoriamente, sin secuelas a largo plazo. En los casos de malaria en gestantes, es crucial no solo el diagnóstico precoz, sino también el inicio inmediato del tratamiento, con el fin de evitar la progresión a sus formas más severas.

ABSTRACT Introduction: The acute respiratory distress syndrome of the adult presents as a rare obstetric complication, being one of its possible etiologies the Plasmodium falciparum infection. Complicated malaria cases are increasingly rare but are associated with a high morbidity and mortality in endemic regions, especially in pregnant patients who are at a high risk of contracting malaria. Clinical case: We present the case of a pregnant patient with acute respiratory distress syndrome due to complicated malaria with a 14 weeks miscarriage secondary to maternal complications Discussion: We describe the patient's approach, who despite of the unfavorable obstetric outcome, had a satisfactory evolution without long term sequels. In obstetric malaria cases, it is not only crucial the early diagnosis but also the immediate treatment, in order to avoid the development of severe stages.

Point-of-care lung ultrasound for the detection of pulmonary manifestations of malaria and sepsis: An observational study.

INTRODUCTION: Patients with severe malaria or sepsis are at risk of developing life-threatening acute respiratory distress syndrome (ARDS). The objective of this study was to evaluate point-of-care lung ultrasound as a novel tool to determine the prevalence and early signs of ARDS in a resource-limited setting among patients with severe malaria or sepsis. MATERIALS AND METHODS: Serial point-of-care lung ultrasound studies were performed on four consecutive days in a planned sub study of an observational cohort of patients with malaria or sepsis in Bangladesh. We quantified aeration patterns across 12 lung regions. ARDS was defined according to the Kigali Modification of the Berlin Definition. RESULTS: Of 102 patients enrolled, 71 had sepsis and 31 had malaria. Normal lung ultrasound findings were observed in 44 patients on enrolment and associated with 7% case fatality. ARDS was detected in 10 patients on enrolment and associated with 90% case fatality. All patients with ARDS had sepsis, 4 had underlying pneumonia. Two patients developing ARDS during hospitalisation already had reduced aeration patterns on enrolment. The SpO2/FiO2 ratio combined with the number of regions with reduced aeration was a strong prognosticator for mortality in patients with sepsis (AUROC 91.5% (95% Confidence Interval: 84.6%-98.4%)). CONCLUSIONS: This study demonstrates the potential usefulness of point-of-care lung ultrasound to detect lung abnormalities in patients with malaria or sepsis in a resource-constrained hospital setting. LUS was highly feasible and allowed to accurately identify patients at risk of death in a resource limited setting.

Next Generation Histology-Directed Imaging Mass Spectrometry Driven by Autofluorescence Microscopy.

Histology-directed imaging mass spectrometry (IMS) is a spatially targeted IMS acquisition method informed by expert annotation that provides rapid molecular characterization of select tissue structures. The expert annotations are usually determined on digital whole slide images of histological stains where the staining preparation is incompatible with optimal IMS preparation, necessitating serial sections: one for annotation, one for IMS. Registration is then used to align staining annotations onto the IMS tissue section. Herein, we report a next-generation histology-directed platform implementing IMS-compatible autofluorescence (AF) microscopy taken prior to any staining or IMS. The platform enables two histology-directed workflows, one that improves the registration process between two separate tissue sections using automated, computational monomodal AF-to-AF microscopy image registration, and a registration-free approach that utilizes AF directly to identify ROIs and acquire IMS on the same section. The registration approach is fully automated and delivers state of the art accuracy in histology-directed workflows for transfer of annotations (∼3-10 µm based on 4 organs from 2 species) while the direct AF approach is registration-free, allowing targeting of the finest structures visible by AF microscopy. We demonstrate the platform in biologically relevant case studies of liver stage malaria and human kidney disease with spatially targeted acquisition of sparsely distributed (composing less than one tenth of 1% of the tissue section area) malaria infected mouse hepatocytes and glomeruli in the human kidney case study.

Continuous stacking computational approach based automated microscope slide scanner.

Cost-effective and automated acquisition of whole slide images is a bottleneck for wide-scale deployment of digital pathology. In this article, a computation augmented approach for the development of an automated microscope slide scanner is presented. The realization of a prototype device built using inexpensive off-the-shelf optical components and motors is detailed. The applicability of the developed prototype to clinical diagnostic testing is demonstrated by generating good quality digital images of malaria-infected blood smears. Further, the acquired slide images have been processed to identify and count the number of malaria-infected red blood cells and thereby perform quantitative parasitemia level estimation. The presented prototype would enable cost-effective deployment of slide-based cyto-diagnostic testing in endemic areas.