Desenvolvimento de técnicas de pré-processamento de radiografias digitais de tórax infantil : uma abordagem orientada a segmentação para sistemas de diagnóstico assistido por computador

• Ano de defesa: 2017
• Autor(a) principal: Fonseca, Afonso Ueslei da
• Orientador(a): Oliveira, Leandro Luís Galdino de
• Banca de defesa: Oliveira, Leandro Luís Galdino de , Soares, Fabrízzio Alphonsus Alves de Melo Nunes , Costa, Ronaldo Martins da, Vieira, Marcus Fraga
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• dARK ID: ark:/38995/00130000044d1
• Idioma: por
• Instituição de defesa: Universidade Federal de Goiás
• Programa de Pós-Graduação: Programa de Pós-graduação em Ciência da Computação (INF)
• Departamento: Instituto de Informática - INF (RG)
• País: Brasil
• Palavras-chave em Português: Melhoramento de imagem; Padronização; Segmentação; Radiografia pediátricas de tórax; Pneumonia
• Palavras-chave em Inglês: Image enhancement; Standardization; Segmentation; Pediatric chest radiographs; Pneumonia
• Área do conhecimento CNPq: CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO
• Link de acesso: http://repositorio.bc.ufg.br/tede/handle/tede/7079

According to the World Health Organization (WHO), more than 900,000 children, younger than five years old, have died in 2015 due to pneumonia. Many of these deaths could be avoided with earlier and more accurate diagnosis to provide proper medicine administration. Chest radiography is one of the most recommended test by the WHO in order to detect childhood pneumonia, and it is commonly used in computer aided diagnostic (CAD) systems. A science role is to develop systems that require a more precise medical diagnosis and treatment cost reducing, but mainly death rate decreasing. It is highlighted that quality radiography demands equipments very well installed and calibrated and staff trained to handle them. However, due limited budget resources, mainly in most vulnerable areas, the image quality is significantly damaged, so turning the medical diagnosis harder. Therefore, this work presents a method composed of a set of preprocessing techniques for pediatric radiography. These techniques intend to have simple implementation and low computational cost. The main goal of this work is to increase performance, accuracy and robustness of CAD systems, to improve database standardization and also to collaborate with the professionals training. Thus, techniques were developed, such as, visual quality enhancement, removal of unnecessary or confidential information, reconstruction of degraded areas due to the information removal, orientation correction and definition of a region of interest. All techniques were evaluated using a children chest X-ray database divided into three classes and results show significantly improve when compared to methods presented in literature. We expect these contributions will assist to development and improvement of new systems, construction of more standardized databases, staff training and the development of new techniques.