Diagnóstico de Nódulo Pulmonar Solitário Utilizando Textura e Geometria em Imagens de Tomografia Computadorizada: Resultados Preliminares (Diagnosis of Solitary Lung Nodule Using Texture e Geometry in Computerized Tomography Images: Preliminary Results)

Aristofanes Correa Silva (ari@dee.ufma.br)1, Paulo Cezar Pinto Carvalho (pcezar@impa.br)2, Marcelo Gattass (mgattass@tecgraf.puc-rio.br)3


1University of Maranhão, Department of Electric Engineering - DEE/UFMA, Brazil
2Institute of Pure and Applied Mathematics - IMPA, Rio de Janeiro, Brazil
3Pontifical Catholic University of Rio de Janeiro - PUC-Rio, Department of Computer Science, RJ, Brazil

This paper appears in: Revista IEEE América Latina

Publication Date: June 2004
Volume: 2,   Issue: 2 
ISSN: 1548-0992


Abstract:
This paper analyzes measures based on texture by means of the Spatial Gray Level Dependence Method, and geometry using nodule' skeleton, with the purpose of characterizing solitary lung nodules as malignant or benign in computerized tomography images. Based on a sample of 31 nodules, 25 benign and 6 malignant, these methods are first analyzed individually and then jointly, with classification and analysis techniques (linear stepwise discriminant analysis, leave-one-out and ROC curve). We have concluded that the individual measures and their combinations produce good results in the diagnosis of solitary lung nodules. Nevertheless, there is the need to perform tests with a larger database and more complex cases in order to obtain a more precise behavior pattern.

Index Terms:
diagnosis of solitary lung nodules, texture, geometry, ROC curve, discriminant analysis   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (247)]