Please use this identifier to cite or link to this item:
Title: Multicriterion Homogeneity Metric for Nodule Segmentation and Detection in Computed Tomography.
Authors: Campos, Vanessa de Oliveira
Silva, Aristófanes Corrêa
Nunes, Rodolfo Acatauassu
Feitosa, Raul Queiroz
Keywords: Computer-aided detection;
pulmonary nodule;
multicriterion segmentation;
computed tomography
Issue Date: 2010
Citation: Vanessa de Oliveira Campos ; Silva, Aristófanes Corrêa;Nunes, Rodolfo Acatauassu; Feitosa, Raul Queiroz. Multicriterion Homogeneity Metric for Nodule Segmentation and Detection in Computed Tomography. In: 17th International Conference on Systems, Signals and Image Processing (IWSSIP 2010), 2010, Rio de Janeiro. 17th InternationalConference on Systems, Signals and Image Processing. Niterói : EdUFF Editora da Universidade Federal Fluminense, 2010. p. 344-347.
Abstract: This work proposes a novel segmentation algorithm for lung nodules detection in thoracic computed tomography (CT) which uses more than one criterion in order to decide at each iteration whether two adjacent objects should be merged or not in a region growing procedure. In experiments conducted upon 33 thoracic CTs, support vector machine was used to discriminate nodules and non-nodules. The method achieved 80.9% sensitivity with 0.23 false positives per slice
Description: Também disponível em:
Appears in Collections:Mestrado em Engenharia de Eletricidade/Trabalhos Apresentados em Eventos Cientificos

Files in This Item:
File Description SizeFormat 
paper_107.pdf294,24 kBAdobe PDFView/Open

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