Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Parasitic infections are one of the leading causes of deaths and other ailments worldwide. Detecting such infections using traditional diagnostic procedures requires experienced medical technologists together with a significant amount of time and effort. An automated procedure with the ability to accurately detect parasitic diseases can greatly accelerate the process. This work proposes a deep learning-based object detection for parasitic egg detection and classification. We show that multitask learning via pseudo-mask generation improves the single model performance. Moreover, we show that a combination of multitask learning, pseudo-label generation, and ensembling model predictions can accurately detect parasitic egg cells. Continuous training via pseudo-label generation and ensemble predictions improves the accuracy of single-model detection. Our final model achieved a mean precision score (mAP) of 0.956 on a validation set of 1,650 images. Our best model obtained mIoU and mF1 scores of 0.934 and 0.988 respectively. We discuss its technical implementation in this paper.
Neglected tropical diseases (NTDs) affect over a billion people worldwide. The 2021–2030 NTD road map calls for innovative and highly efficient interventions to eliminate or significantly reduce the burden of NTDs. These include sensitive and cost-effective diagnostic techniques for disease surveillance. Environmental surveillance has been employed effectively in this regard to measure and track infectious diseases such as polio on a population-wide scale. In this study, environmental surveillance was used as a cost-effective tool for the detection of soil-transmitted helminths (STHs) in Accra, Ghana, in an area that is populated by urban vegetable farmers. The activities of urban farmers expose them to the risk of STH infection, as well as impact the transmission in urban areas since leafy vegetables could carry infective stages of STHs. A total of 32 wastewater samples were collected from eight points on the Nima Creek (the main source of irrigation for the farmers) over a 7-week period. Real-time PCR and melt peak analysis were used to screen four STHs (i.e., Ascaris lumbricoides, Necator americanus, Ancylostoma duodenale, and Trichuris trichiura). This study revealed that A. lumbricoides (17 out of 32 wastewater samples, 53.3%) was the most prevalent STH, followed by A. duodenale (31.2%), T. trichiura (21.9%), and N. americanus (12.5%). Environmental surveillance helps in the detection of the types of STH pathogens circulating within the community and in the design of mass drug administration (MDA) strategies. This surveillance technique can also provide preliminary information for environmental modifications to help reduce STH transmission in line with the One Health approach recommended in the 2021–2030 NTD road map.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.