Desenvolvimento de algoritmos computacionais para quantificação e estruturas pulmonares

• Autor(a) principal: Oliveira, Marcela de [UNESP]
• Data de Publicação: 2012
• Outros Autores: Pina, Diana Rodrigues de [UNESP], Alvarez, Matheus [UNESP], Alves, Allan Felipe Fattori [UNESP], Miranda, José Ricardo de Arruda [UNESP]
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://www.rbfm.org.br/index.php/rbfm/article/view/216; http://hdl.handle.net/11449/140819
• topic: Algorithm; Semi-automatic quantification; HRCT; Fibrosis; Emphysema; Algoritmo; Quantificação semiautomática; TCAR; Fibrose; Enfisema

The high-resolution computed tomography has become the imaging diagnostic exam most commonly used for the evaluation of the squeals of Paracoccidioidomycosis. The subjective evaluations the radiological abnormalities found on HRCT images do not provide an accurate quantification. The computer-aided diagnosis systems produce a more objective assessment of the abnormal patterns found in HRCT images. Thus, this research proposes the development of algorithms in Matlab® computing environment can quantify semi-automatically pathologies such as pulmonary fibrosis and emphysema. The algorithm consists in selecting a region of interest (ROI), and by the use of masks, filter densities and morphological operators, to obtain a quantification of the injured area to the area of a healthy lung. The proposed method was tested on ten HRCT scans of patients with confirmed PCM. The results of semi-automatic measurements were compared with subjective evaluations performed by a specialist in radiology, falling to a coincidence of 80% for emphysema and 58% for fibrosis.