Classification of masses in mammographic image using wavelet domain features and polynomial classifier

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorNascimento, Marcelo Zanchetta Do
dc.creatorMartins, Alessandro Santana
dc.creatorNeves, Leandro Alves
dc.creatorRamos, Rodrigo Pereira
dc.creatorFlores, Edna Lúcia
dc.creatorCarrijo, Gilberto Arantes
dc.date2014-05-27T11:29:46Z
dc.date2016-10-25T18:50:08Z
dc.date2014-05-27T11:29:46Z
dc.date2016-10-25T18:50:08Z
dc.date2013-06-21
dc.date.accessioned2017-04-06T02:27:57Z
dc.date.available2017-04-06T02:27:57Z
dc.identifierExpert Systems with Applications, v. 40, n. 15, p. 6213-6221, 2013.
dc.identifier0957-4174
dc.identifierhttp://hdl.handle.net/11449/75693
dc.identifierhttp://acervodigital.unesp.br/handle/11449/75693
dc.identifier10.1016/j.eswa.2013.04.036
dc.identifierWOS:000322051600042
dc.identifier2-s2.0-84879043579
dc.identifierhttp://dx.doi.org/10.1016/j.eswa.2013.04.036
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/896429
dc.descriptionBreast cancer is the most common cancer among women. In CAD systems, several studies have investigated the use of wavelet transform as a multiresolution analysis tool for texture analysis and could be interpreted as inputs to a classifier. In classification, polynomial classifier has been used due to the advantages of providing only one model for optimal separation of classes and to consider this as the solution of the problem. In this paper, a system is proposed for texture analysis and classification of lesions in mammographic images. Multiresolution analysis features were extracted from the region of interest of a given image. These features were computed based on three different wavelet functions, Daubechies 8, Symlet 8 and bi-orthogonal 3.7. For classification, we used the polynomial classification algorithm to define the mammogram images as normal or abnormal. We also made a comparison with other artificial intelligence algorithms (Decision Tree, SVM, K-NN). A Receiver Operating Characteristics (ROC) curve is used to evaluate the performance of the proposed system. Our system is evaluated using 360 digitized mammograms from DDSM database and the result shows that the algorithm has an area under the ROC curve Az of 0.98 ± 0.03. The performance of the polynomial classifier has proved to be better in comparison to other classification algorithms. © 2013 Elsevier Ltd. All rights reserved.
dc.languageeng
dc.relationExpert Systems with Applications
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectMammography
dc.subjectPolynomial classifier
dc.subjectTexture analysis
dc.subjectWavelet CAD
dc.subjectArea under the ROC curve
dc.subjectArtificial intelligence algorithms
dc.subjectClassification algorithm
dc.subjectDigitized mammograms
dc.subjectReceiver operating characteristics curves (ROC)
dc.subjectWavelet domain features
dc.subjectAlgorithms
dc.subjectArtificial intelligence
dc.subjectComputer aided diagnosis
dc.subjectDecision trees
dc.subjectDiscrete wavelet transforms
dc.subjectDiseases
dc.subjectMultiresolution analysis
dc.subjectOrthogonal functions
dc.subjectTextures
dc.subjectX ray screens
dc.subjectPolynomials
dc.titleClassification of masses in mammographic image using wavelet domain features and polynomial classifier
dc.typeOtro


Este ítem pertenece a la siguiente institución