Edge Artificial Intelligence (AI) for real-time automatic quantification of filariasis in mobile microscopy

Filariasis, a neglected tropical disease caused by roundworms, is a significant public health concern in many tropical countries. Microscopic examination of blood samples can detect and differentiate parasite species, but it is time consuming and requires expert microscopists, a resource that is not always available. In this context, artificial intelligence (AI) can assist in the diagnosis of this disease by automatically detecting and differentiating microfilariae. In line with the target product profile for lymphatic filariasis as defined by the World Health Organization, we developed an edge AI system running on a smartphone whose camera is aligned with the ocular of an optical microscope that detects and differentiates filarias species in real time without the internet connection. Our object detection algorithm that uses the Single-Shot Detection (SSD) MobileNet V2 detection model was developed with 115 cases, 85 cases with 1903 fields of view and 3342 labels for model training, and 30 cases with 484 fields of view and 873 labels for model validation before clinical validation, is able to detect microfilariae at 10x magnification and distinguishes four species of them at 40x magnification: Loa loa, Mansonella perstans, Wuchereria bancrofti, and Brugia malayi. We validated our augmented microscopy system in the clinical environment by replicating the diagnostic workflow encompassed examinations at 10x and 40x with the assistance of the AI models analyzing 18 samples with the AI running on a middle range smartphone. It achieved an overall precision of 94.14%, recall of 91.90% and F1 score of 93.01% for the screening algorithm and 95.46%, 97.81% and 96.62% for the species differentiation algorithm respectively. This innovative solution has the potential to support filariasis diagnosis and monitoring, particularly in resource-limited settings where access to expert technicians and laboratory equipment is scarce.

Combining collective and artificial intelligence for global health diseases diagnosis using crowdsourced annotated medical images

Visual inspection of microscopic samples is still the gold standard diagnostic methodology for many global health diseases. Soil-transmitted helminth infection affects 1.5 billion people worldwide, and is the most prevalent disease among the Neglected Tropical Diseases. It is diagnosed by manual examination of stool samples by microscopy, which is a time-consuming task and requires trained personnel and high specialization. Artificial intelligence could automate this task making the diagnosis more accessible. Still, it needs a large amount of annotated training data coming from experts.In this work, we proposed the use of crowdsourced annotated medical images to train AI models (neural networks) for the detection of soil-transmitted helminthiasis in microscopy images from stool samples leveraging non-expert knowledge collected through playing a video game. We collected annotations made by both school-age children and adults, and we showed that, although the quality of crowdsourced annotations made by school-age children are sightly inferior than the ones made by adults, AI models trained on these crowdsourced annotations perform similarly (AUC of 0.928 and 0.939 respectively), and reach similar performance to the AI model trained on expert annotations (AUC of 0.932). We also showed the impact of the training sample size and continuous training on the performance of the AI models.In conclusion, the workflow proposed in this work combined collective and artificial intelligence for detecting soil-transmitted helminthiasis. Embedded within a digital health platform can be applied to any other medical image analysis task and contribute to reduce the burden of disease.

The Mars Environmental Dynamics Analyzer, MEDA. A Suite of Environmental Sensors for the Mars 2020 Mission

NASA's Mars 2020 (M2020) rover mission includes a suite of sensors to monitor current environmental conditions near the surface of Mars and to constrain bulk aerosol properties from changes in atmospheric radiation at the surface. The Mars Environmental Dynamics Analyzer (MEDA) consists of a set of meteorological sensors including wind sensor, a barometer, a relative humidity sensor, a set of 5 thermocouples to measure atmospheric temperature at ∼1.5 m and ∼0.5 m above the surface, a set of thermopiles to characterize the thermal IR brightness temperatures of the surface and the lower atmosphere. MEDA adds a radiation and dust sensor to monitor the optical atmospheric properties that can be used to infer bulk aerosol physical properties such as particle size distribution, non-sphericity, and concentration. The MEDA package and its scientific purpose are described in this document as well as how it responded to the calibration tests and how it helps prepare for the human exploration of Mars. A comparison is also presented to previous environmental monitoring payloads landed on Mars on the Viking, Pathfinder, Phoenix, MSL, and InSight spacecraft.

Deep subsurface sulfate reduction and methanogenesis in the Iberian Pyrite Belt revealed through geochemistry and molecular biomarkers

The Iberian Pyrite Belt (IPB, southwest of Spain), the largest known massive sulfide deposit, fuels a rich chemolithotrophic microbial community in the Río Tinto area. However, the geomicrobiology of its deep subsurface is still unexplored. Herein, we report on the geochemistry and prokaryotic diversity in the subsurface (down to a depth of 166 m) of the Iberian Pyritic belt using an array of geochemical and complementary molecular ecology techniques. Using an antibody microarray, we detected polymeric biomarkers (lipoteichoic acids and peptidoglycan) from Gram-positive bacteria throughout the borehole. DNA microarray hybridization confirmed the presence of members of methane oxidizers, sulfate-reducers, metal and sulfur oxidizers, and methanogenic Euryarchaeota. DNA sequences from denitrifying and hydrogenotrophic bacteria were also identified. FISH hybridization revealed live bacterial clusters associated with microniches on mineral surfaces. These results, together with measures of the geochemical parameters in the borehole, allowed us to create a preliminary scheme of the biogeochemical processes that could be operating in the deep subsurface of the Iberian Pyrite Belt, including microbial metabolisms such as sulfate reduction, methanogenesis and anaerobic methane oxidation.

Differential transcription of the major antigenic protein 1 multigene family of Ehrlichia ruminantium in Amblyomma variegatum ticks

The rickettsial pathogen Ehrlichia ruminantium causes heartwater in ruminants and is transmitted by ticks of the genus Amblyomma. The map1 gene, encoding the major surface protein MAP1, is a member of a multigene family containing 16 paralogs. In order to investigate differential transcription of genes of the map1 multigene family in vivo in unfed and feeding ticks, RNA was extracted from midguts and salivary glands of E. ruminantium-infected adult female Amblyomma variegatum ticks and analysed by RT-PCR using MAP1 paralog-specific primers. In unfed ticks, only transcripts from the map1-1 gene were observed in midguts and no transcripts were detected in salivary glands. In feeding ticks, map1-1 transcripts were more abundant in midguts whereas high levels of map1 transcripts were observed in salivary glands. Our results show that differential transcription of genes of the E. ruminantium map1 cluster occurs in vivo in different tissues of infected ticks before and during transmission feeding, indicating that this multigene family may be involved in functions of biological relevance in different stages of the life cycle of E. ruminantium.

Molecular detection of Ehrlichia ruminantium infection in Amblyomma variegatum ticks in The Gambia

In West Africa, losses due to heartwater disease are not known because the incidence/prevalence has not been well studied or documented. To develop a diagnostic tool for molecular epidemiology, three PCR-based diagnostic assays, a nested pCS20 PCR, a nested map1 PCR and a nested reverse line blot (RLB) hybridization assay, were evaluated to determine their ability to detect infection in vector ticks, by applying them simultaneously to A. variegatum field ticks to detect Ehrlichia ruminantium, the causative agent of heartwater. The nested pCS20 PCR assay which amplified the pCS20 gene fragment showed the highest detection performance with a detection rate of 16.6%; the nested map1 PCR, which amplified the gene encoding the major antigenic protein1 (map1 gene) showed a detection rate of 11% and the RLB, based on the 16S rDNA sequence of anaplasma and ehrlichial species, detected 6.2%. The RLB, in addition, demonstrated molecular evidence of Ehrlichia ovina, Anaplasma marginale and Anaplasma ovis infections in The Gambia. Subsequently, the pCS20 assay was applied to study the prevalence and distribution of E. ruminantium tick infection rates at different sites in five divisions of The Gambia. The rates of infection in the country ranged from 1.6% to 15.1% with higher prevalences detected at sites in the westerly divisions (Western, Lower River and North Bank; range 8.3-15.1%) than in the easterly divisions (Central River and Upper River; range 1.6-7.5%). This study demonstrated a gradient in the distribution of heartwater disease risk for susceptible livestock in The Gambia which factor must be considered in the overall design of future upgrading programmes.

Malaria diagnosis by the polymerase chain reaction: a field study in south-eastern Venezuela

A polymerase chain reaction (PCR) method that amplifies genus- and species-specific sequences present within the small subunit of ribosomal ribonucleic acid (ssRNA) genes of the human malaria parasites was used for the diagnosis of malaria in south-eastern Venezuela. One hundred blood samples were submitted to deoxyribonucleic acid extraction, PCR amplification and electrophoretic analysis of the PCR products, and the results were compared to those of routine microscopical diagnosis. The sensitivity of PCR for detection of Plasmodium vivax and P. falciparum malaria was 99% and 100%, respectively. However, 6 patients (6%) harboured parasites undetected by microscopy. The PCR assay detected a high proportion of mixed infections: 29% (17/59) of the infections microscopically diagnosed as P. vivax were shown to be mixed infections of P. vivax and P. falciparum. Forty per cent (7/17) of the individuals with a missed P. falciparum infection had received chloroquine in the previous 30 d. These results suggest that, in places where transmission of both P. vivax and P. falciparum occurs, PCR detection of malaria parasites can be a very useful complement to microscopical diagnosis in order to ascertain the true incidence of each species and for the follow-up of patients after specific treatment.