Microcalcification enhancement and classification on mammograms using the wavelet transform

dc.contributorUniversidade Estadual Paulista (Unesp)
dc.contributorUniversidade de São Paulo (USP)
dc.contributorShu-Te University
dc.date.accessioned2014-05-27T11:23:42Z
dc.date.available2014-05-27T11:23:42Z
dc.date.created2014-05-27T11:23:42Z
dc.date.issued2008-11-24
dc.identifierProceedings of the International Joint Conference on Neural Networks, p. 3181-3186, 2008.
dc.identifierhttp://hdl.handle.net/11449/70639
dc.identifier10.1109/IJCNN.2008.4634248
dc.identifierWOS:000263827202008
dc.identifier2-s2.0-56349133254
dc.identifier2098623262892719
dc.identifier6542086226808067
dc.identifier0000-0003-1086-3312
dc.identifier0000-0002-0924-8024
dc.description.abstractThis paper presents a method to enhance microcalcifications and classify their borders by applying the wavelet transform. Decomposing an image and removing its low frequency sub-band the microcalcifications are enhanced. Analyzing the effects of perturbations on high frequency subband it's possible to classify its borders as smooth, rugged or undefined. Results show a false positive reduction of 69.27% using a region growing algorithm. © 2008 IEEE.
dc.languageeng
dc.relationProceedings of the International Joint Conference on Neural Networks
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectWavelet transforms
dc.subjectFalse positives
dc.subjectHigh frequencies
dc.subjectLow frequencies
dc.subjectMicrocalcification
dc.subjectMicrocalcifications
dc.subjectRegion growing algorithms
dc.subjectSub bands
dc.subjectNeural networks
dc.titleMicrocalcification enhancement and classification on mammograms using the wavelet transform
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución