Sistema de visão computacional para detecção e quantificação de enfisema pulmonar

Detalhes bibliográficos
Ano de defesa: 2007
Autor(a) principal: Félix, John Hebert da Silva
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Não Informado pela instituição
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://www.repositorio.ufc.br/handle/riufc/16081
Resumo: The Chronic Obstructive Pulmonary Disease (COPD) is a worldwide public health problem with high rates of mortality, being the tabacco the main causer of this disease. COPD is underestimated and underdiagnosed globally, and consequently the patient receives an undertreatment. To avoid an increase of pathological cases with incorrect diagnoses, the computerized tomography should be used as an excellent tool for premature diagnosis of pulmonary emphysema component from COPD. However, the analysis on images accomplished by radiologists or doctors is subjective,leading them to accomplish inaccurate measurements, due to human vision limitation. The objective of this work is to develop a Computational Vision System for Detection and Quantification of the Pulmonary Emphysema (SDEP) capable of segment automatically the images of High-Resolution Computerized Tomography (HRCT) of the lungs, allowing its better view. Also, in this study are analysed the obtained results to evaluate the e±ciency of SDEP system comparing it with the Osiris 4 system, and with two segmentation algorithms. Results of the segmentation are analysed through the viewing of 102 images of 8 healthy volunteers and 141 images of 11 COPD patients. The SDEP system presents more e±cient than other methods considered in this work, evaluating the correct segmentation, the over segmentation, segmentation with losses, and wrong segmentation. The proposed system accomplishes the segmentation of zone from lung densities using colorful mask, applying several colors in a single image quantifying each color per area and percentage, while the Osiris system uses only one color on each image. The SDEP system has, beside of advantage presented, a tool that accomplish the overlap of histograms, which permit a more appropriate visual analysis of evolution of component on the emphysema. The proposed system offers to aided diagnosis, researchers, engineers, medical doctors and specialist and others of Medical Digital Image Processing field, one valid option for pulmonary emphysema analysis from HRCT images.