skip to main content

This content will become publicly available on March 1, 2023

Title: Deep Learning Segmentation of Satellite Imagery Identifies Aquatic Vegetation Associated with Snail Intermediate Hosts of Schistosomiasis in Senegal, Africa
Schistosomiasis is a debilitating parasitic disease of poverty that affects more than 200 million people worldwide, mostly in sub-Saharan Africa, and is clearly associated with the construction of dams and water resource management infrastructure in tropical and subtropical areas. Changes to hydrology and salinity linked to water infrastructure development may create conditions favorable to the aquatic vegetation that is suitable habitat for the intermediate snail hosts of schistosome parasites. With thousands of small and large water reservoirs, irrigation canals, and dams developed or under construction in Africa, it is crucial to accurately assess the spatial distribution of high-risk environments that are habitat for freshwater snail intermediate hosts of schistosomiasis in rapidly changing ecosystems. Yet, standard techniques for monitoring snails are labor-intensive, time-consuming, and provide information limited to the small areas that can be manually sampled. Consequently, in low-income countries where schistosomiasis control is most needed, there are formidable challenges to identifying potential transmission hotspots for targeted medical and environmental interventions. In this study, we developed a new framework to map the spatial distribution of suitable snail habitat across large spatial scales in the Senegal River Basin by integrating satellite data, high-definition, low-cost drone imagery, and an artificial intelligence (AI)-powered computer more » vision technique called semantic segmentation. A deep learning model (U-Net) was built to automatically analyze high-resolution satellite imagery to produce segmentation maps of aquatic vegetation, with a fast and robust generalized prediction that proved more accurate than a more commonly used random forest approach. Accurate and up-to-date knowledge of areas at highest risk for disease transmission can increase the effectiveness of control interventions by targeting habitat of disease-carrying snails. With the deployment of this new framework, local governments or health actors might better target environmental interventions to where and when they are most needed in an integrated effort to reach the goal of schistosomiasis elimination. « less
Authors:
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more » ; ; « less
Award ID(s):
2109293 2011179 2024383 2017785
Publication Date:
NSF-PAR ID:
10326481
Journal Name:
Remote Sensing
Volume:
14
Issue:
6
Page Range or eLocation-ID:
1345
ISSN:
2072-4292
Sponsoring Org:
National Science Foundation
More Like this
  1. The development of water management infrastructures, such as dams and canals, are important components of society’s response to feed a growing human population and to fight climate change. Yet, these changes in land use can also increase the transmission risk for waterborne diseases. Transmission risk associated with artificial reservoirs has been extensively documented for schistosomiasis, a parasitic disease of poverty that infects more than 240 million people worldwide. Over 90% of these cases are in sub-Saharan Africa, a region that is being steadily reshaped by climate change. Controlling the parasite’s obligate intermediate host snail is key to reducing transmission of this disease. Using commercial aquaculture to farm marketable species which predate upon these snails in vulnerable regions can have multiple positive effects, including the improved socioeconomic and nutritional health of surrounding communities. Here the authors assessed the viability of using the aquaculture of snail predators to simultaneously control schistosomiasis infection rates while alleviating economic and/or nutritional poverty in endemic regions of sub-Saharan Africa. A PRISMA-based 6-step systematic methodology was used to explore the primary literature using the case study of Côte d’Ivoire and two native species of snail predator to make evidence-based conclusions on the viability of this method formore »controlling schistosomiasis. This detailed thematic examination of the literature concluded that using specific approaches and species, aquaculture could be effective in reducing economic poverty and chronic malnourishment along with high levels of schistosomiasis infection. More current species-specific aquaculture data and consumer survey data are, however, needed to determine the economic and logistical effectiveness of farming native snail predators in-country. These and other opportunities for future research are highlighted.« less
  2. Secor, W. Evan (Ed.)
    Schistosome parasites infect more than 200 million people annually, mostly in sub-Saharan Africa, where people may be co-infected with more than one species of the parasite. Infection risk for any single species is determined, in part, by the distribution of its obligate intermediate host snail. As the World Health Organization reprioritizes snail control to reduce the global burden of schistosomiasis, there is renewed importance in knowing when and where to target those efforts, which could vary by schistosome species. This study estimates factors associated with schistosomiasis risk in 16 villages located in the Senegal River Basin, a region hyperendemic for Schistosoma haematobium and S . mansoni . We first analyzed the spatial distributions of the two schistosomes’ intermediate host snails ( Bulinus spp. and Biomphalaria pfeifferi , respectively) at village water access sites. Then, we separately evaluated the relationships between human S . haematobium and S . mansoni infections and (i) the area of remotely-sensed snail habitat across spatial extents ranging from 1 to 120 m from shorelines, and (ii) water access site size and shape characteristics. We compared the influence of snail habitat across spatial extents because, while snail sampling is traditionally done near shorelines, we hypothesized that snailsmore »further from shore also contribute to infection risk. We found that, controlling for demographic variables, human risk for S . haematobium infection was positively correlated with snail habitat when snail habitat was measured over a much greater radius from shore (45 m to 120 m) than usual. S . haematobium risk was also associated with large, open water access sites. However, S . mansoni infection risk was associated with small, sheltered water access sites, and was not positively correlated with snail habitat at any spatial sampling radius. Our findings highlight the need to consider different ecological and environmental factors driving the transmission of each schistosome species in co-endemic landscapes.« less
  3. Background: Schistosomiasis is an emerging disease associated with changes to the environment that have increased human contact rates with disease-causing parasites, flatworms that are released from freshwater snails. For example, schistosomiasis remains a major public health problem in Northern Senegal, where prevalence in schoolchildren often reaches 90%. Aim: This study focuses on the impact of seasonality on the risk of human exposure (RHE) to Schistosoma mansoni, defined as the total number of cercariae (the free-living life stage that infects humans) shed from all Biomphalaria pfeifferi snails collected at a site using standardized methods. We focus on RHE because it is rarely quantified and a recent study demonstrated that snails stop shedding cercariae when snail densities increase and thus per capita snail resources become limited [2], suggesting that densities of snails might not be directly proportional to RHE to schistosomes. Method: We sampled four water access points in three villages every other week during the early (Dry1) and later dry seasons (Dry2) and the rainy season, quantifying the abundance of infected and non-infected snail intermediate hosts, cercariae released per infected snail, and water chemistry. We used simple and multiple linear regressions to assess how seasonality and environmental parameters affect non-infected andmore »infected snail abundance and RHE. Results: Although RHE was found across all seasons, the abundance of infected and non-infected snail intermediate hosts and cercariae, as well as prevalence (23.71%), were all highest in the rainy season. In the rainy season, RHE was positively associated with the density of snail hosts and their periphyton food resource. Conclusion: Although previous studies have examined the influence of seasonality on snail densities, few studies have explored the effects of seasonality on cercarial densities, which is the primary source of infection to humans. Our study demonstrates that cercarial densities are greater in the rainy season than in the early or late dry seasons. Given that cercarial densities directly pose risk of infection to humans, unlike non-infected or infected snails, these finding should help to inform decision making and schistosomiasis control efforts in West Africa.« less
  4. Temperature constrains the transmission of many pathogens. Interventions that target temperature-sensitive life stages, such as vector control measures that kill intermediate hosts, could shift the thermal optimum of transmission, thereby altering seasonal disease dynamics and rendering interventions less effective at certain times of the year and with global climate change. To test these hypotheses, we integrated an epidemiological model of schistosomiasis with empirically determined temperature-dependent traits of the human parasiteSchistosoma mansoniand its intermediate snail host (Biomphalariaspp.). We show that transmission risk peaks at 21.7 °C (Topt), and simulated interventions targeting snails and free-living parasite larvae increasedToptby up to 1.3 °C because intervention-related mortality overrode thermal constraints on transmission. ThisToptshift suggests that snail control is more effective at lower temperatures, and global climate change will increase schistosomiasis risk in regions that move closer toTopt. Considering regional transmission phenologies and timing of interventions when local conditions approachToptwill maximize human health outcomes.

  5. In recent decades, computer vision has proven remarkably effective in addressing diverse issues in public health, from determining the diagnosis, prognosis, and treatment of diseases in humans to predicting infectious disease outbreaks. Here, we investigate whether convolutional neural networks (CNNs) can also demonstrate effectiveness in classifying the environmental stages of parasites of public health importance and their invertebrate hosts. We used schistosomiasis as a reference model. Schistosomiasis is a debilitating parasitic disease transmitted to humans via snail intermediate hosts. The parasite affects more than 200 million people in tropical and subtropical regions. We trained our CNN, a feed-forward neural network, on a limited dataset of 5,500 images of snails and 5,100 images of cercariae obtained from schistosomiasis transmission sites in the Senegal River Basin, a region in western Africa that is hyper-endemic for the disease. The image set included both images of two snail genera that are relevant to schistosomiasis transmission – that is, Bulinus spp. and Biomphalaria pfeifferi – as well as snail images that are non-component hosts for human schistosomiasis. Cercariae shed from Bi. pfeifferi and Bulinus spp. snails were classified into 11 categories, of which only two, S. haematobium and S. mansoni , are major etiological agentsmore »of human schistosomiasis. The algorithms, trained on 80% of the snail and parasite dataset, achieved 99% and 91% accuracy for snail and parasite classification, respectively, when used on the hold-out validation dataset – a performance comparable to that of experienced parasitologists. The promising results of this proof-of-concept study suggests that this CNN model, and potentially similar replicable models, have the potential to support the classification of snails and parasite of medical importance. In remote field settings where machine learning algorithms can be deployed on cost-effective and widely used mobile devices, such as smartphones, these models can be a valuable complement to laboratory identification by trained technicians. Future efforts must be dedicated to increasing dataset sizes for model training and validation, as well as testing these algorithms in diverse transmission settings and geographies.« less