Please use this identifier to cite or link to this item:
Author(s): Pedro Pedrosa Rebouças Filho
Paulo César Cortez
Antônio C. da Silva Barros
Victor Hugo C. Albuquerque
João Manuel R. S. Tavares
Title: Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images
Issue Date: 2017-01
Abstract: The World Health Organization estimates that 300 million people have asthma, 210 million people haveChronic Obstructive Pulmonary Disease (COPD), and, according to WHO, COPD will become the third majorcause of death worldwide in 2030. Computational Vision systems are commonly used in pulmonologyto address the task of image segmentation, which is essential for accurate medical diagnoses. Segmentationdefines the regions of the lungs in CT images of the thorax that must be further analyzed bythe system or by a specialist physician. This work proposes a novel and powerful technique named 3DAdaptive Crisp Active Contour Method (3D ACACM) for the segmentation of CT lung images. The methodstarts with a sphere within the lung to be segmented that is deformed by forces acting on it towardsthe lung borders. This process is performed iteratively in order to minimize an energy function associatedwith the 3D deformable model used. In the experimental assessment, the 3D ACACM is comparedagainst three approaches commonly used in this field: the automatic 3D Region Growing, the level-setalgorithm based on coherent propagation and the semi-automatic segmentation by an expert using the3D OsiriX toolbox. When applied to 40 CT scans of the chest the 3D ACACM had an average F-measureof 99.22%, revealing its superiority and competency to segment lungs in CT images.
Subject: Ciências Tecnológicas, Ciências da engenharia e tecnologias
Technological sciences, Engineering and technology
Scientific areas: Ciências da engenharia e tecnologias
Engineering and technology
Document Type: Artigo em Revista Científica Internacional
Rights: openAccess
Appears in Collections:FEUP - Artigo em Revista Científica Internacional

Files in This Item:
File Description SizeFormat 
143847.png1st Page413.65 kBimage/pngThumbnail
143847.1.pdfPaper6.98 MBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons