Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/92326
Type: Artigo de periódico
Title: Comparative Study Of Computacional Models Generated From Representations Of Colonoscopic Images: Normal Mucosal Tissues Vs Mucosal Tissues Of Colic Polyp [estudo Comparativo De Modelos Computacionais Gerados Sobre Representações De Imagens De Coloscopia: Tecido De Mucosa Normal Vs Tecido De Mucosa De Pólipo Cólico]
Author: Ferrero C.A.
Lee H.D.
Spolaor N.
Coy C.S.R.
Fagundes J.J.
Machado R.B.
Cherman E.A.
Wu F.C.
Abstract: Purpose: to evaluate the predictive quality of computational models to differentiate colic tissues, based on Co-occorrurence Matrices (MC) representation of Coloscopic Images (IC). Materials and Methods: Image analysis and artificial intelligence methods were employed to construct computational models. Sixty seven IC images, containing polyp, were considered in this work, from which a part containing a polypus and another without it were collected given origin to 134 images. For each one of these, different MC were constructed considering five distance parameters (D = 1 to 5) and the extraction of 11 texture characteristics. With this representation, five computational models were generated based on decision trees. These models were evaluated using two techniques: (a) cross-validation and (b) contingency tables. Results: for the (a) analysis, the model with D = 3 presented the smaller average error (22.25% ± 11.85%). For the (b) analysis, models with D = 1 and 3 presented the best precision values. Conclusion: parameters D = 1 and 3 presented models with the best predictive qualities. Results showed that the constructed models were promising to be applied within decision making computational systems.
Editor: 
Rights: aberto
Identifier DOI: 
Address: http://www.scopus.com/inward/record.url?eid=2-s2.0-70349823272&partnerID=40&md5=87a2732ed261d864c2cd921fc26f016a
Date Issue: 2009
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-70349823272.pdf207.61 kBAdobe PDFView/Open


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