Skip navigation
Please use this identifier to cite or link to this item: https://repositorio.unb.br/handle/10482/21593
Files in This Item:
File Description SizeFormat 
ARTIGO_WebPlatformUsingDigital.pdf1,71 MBAdobe PDFView/Open
Title: Web platform using digital image processing and geographic information system tools : a Brazilian case study on dengue
Authors: Brasil, Lourdes Mattos
Gomes, Marília Miranda Forte
Miosso, Cristiano Jacques
Silva, Marlete M. da
Amvame-Nze, Georges
Assunto:: Dengue
Sistemas de informação geográfica
Processamento de imagens
Issue Date: 2015
Publisher: BioMed Central
Citation: BRASIL, Lourdes Mattos et al. Web platform using digital image processing and geographic information system tools: a Brazilian case study on dengue. Biomedical Engineering Online, v. 14, p. 1-14, 2015. Disponível em: <http://biomedical-engineering-online.biomedcentral.com/articles/10.1186/s12938-015-0052-2>. Acesso em: 20 out. 2016. DOI 10.1186/s12938-015-0052-2.
Abstract: Background: Dengue fever is endemic in Asia, the Americas, the East of the Mediterranean and the Western Pacific. According to the World Health Organization, it is one of the diseases of greatest impact on health, affecting millions of people each year worldwide. A fast detection of increases in populations of the transmitting vector, the Aedes aegypti mosquito, is essential to avoid dengue outbreaks. Unfortunately, in several countries, such as Brazil, the current methods for detecting populations changes and disseminating this information are too slow to allow efficient allocation of resources to fight outbreaks. To reduce the delay in providing the information regarding A. aegypti population changes, we propose, develop, and evaluate a system for counting the eggs found in special traps and to provide the collected data using a web structure with geographical location resources. Methods: One of the most useful tools for the detection and surveillance of arthropods is the ovitrap, a special trap built to collect the mosquito eggs. This allows for an egg counting process, which is still usually performed manually, in countries such as Brazil. We implement and evaluate a novel system for automatically counting the eggs found in the ovitraps’ cardboards. The system we propose is based on digital image processing (DIP) techniques, as well as a Web based Semi-Automatic Counting System (SCSA-WEB). All data collected are geographically referenced in a geographic information system (GIS) and made available on a Web platform. The work was developed in Gama’s administrative region, in Brasília/Brazil, with the aid of the Environmental Surveillance Directory (DIVAL-Gama) and Brasília’s Board of Health (SSDF), in partnership with the University of Brasília (UnB). The system was built based on a field survey carried out during three months and provided by health professionals. These professionals provided 84 cardboards from 84 ovitraps, sized 15 × 5 cm. In developing the system, we conducted the following steps: i. Obtain images from the eggs on an ovitrap’s cardboards, with a microscope. ii. Apply a proposed image-processing-based semi-automatic counting system. The system we developed uses the Java programming language and the Java Server Faces technology. This is a framework suite for web applications development. This approach will allow a simple migration to any Operating System platform and future applications on mobile devices. iii. Collect and store all data into a Database (DB) and then georeference them in a GIS. The Database Management System used to develop the DB is based on PostgreSQL. The GIS will assist in the visualization and spatial analysis of digital maps, allowing the location of Dengue outbreaks in the region of study. This will also facilitate the planning, analysis, and evaluation of temporal and spatial epidemiology, as required by the Brazilian Health Care Control Center. iv. Deploy the SCSA-WEB, DB and GIS on a single Web platform. Results: The statistical results obtained by DIP were satisfactory when compared with the SCSA-WEB’s semi-automated eggs count. The results also indicate that the time spent in manual counting has being considerably reduced when using our fully automated DIP algorithm and semi-automated SCSA-WEB. The developed georeferencing Web platform proves to be of great support for future visualization with statistical and trace analysis of the disease. Conclusions: The analyses suggest the efficiency of our algorithm for automatic eggs counting, in terms of expediting the work of the laboratory technician, reducing considerably its time and error counting rates. We believe that this kind of integrated platform and tools can simplify the decision making process of the Brazilian Health Care Control Center.
Licença:: © 2015 Brasil et al. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http:// creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/ zero/1.0/) applies to the data made available in this article, unless otherwise stated.
DOI: https://dx.doi.org/10.1186/s12938-015-0052-2
Appears in Collections:FGA - Artigos publicados em periódicos

Show full item record Recommend this item " class="statisticsLink btn btn-primary" href="/handle/10482/21593/statistics">



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.