Unsupervised segmentation method for cuboidal cell nuclei in histological prostate images based on minimum cross entropy

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorDe Oliveira, Domingos Lucas Latorre
dc.creatorDo Nascimento, Marcelo Zanchetta
dc.creatorNeves, Leandro Alves
dc.creatorDe Godoy, Moacir Fernandes
dc.creatorDe Arruda, Pedro Francisco Ferraz
dc.creatorDe Santi Neto, Dalisio
dc.date2014-05-27T11:30:09Z
dc.date2016-10-25T18:52:34Z
dc.date2014-05-27T11:30:09Z
dc.date2016-10-25T18:52:34Z
dc.date2013-08-12
dc.date.accessioned2017-04-06T02:34:21Z
dc.date.available2017-04-06T02:34:21Z
dc.identifierExpert Systems with Applications, v. 40, n. 18, p. 7331-7340, 2013.
dc.identifier0957-4174
dc.identifierhttp://hdl.handle.net/11449/76252
dc.identifierhttp://acervodigital.unesp.br/handle/11449/76252
dc.identifier10.1016/j.eswa.2013.06.079
dc.identifierWOS:000324663000018
dc.identifier2-s2.0-84881181456
dc.identifierhttp://dx.doi.org/10.1016/j.eswa.2013.06.079
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/896953
dc.descriptionThis paper presents a novel segmentation method for cuboidal cell nuclei in images of prostate tissue stained with hematoxylin and eosin. The proposed method allows segmenting normal, hyperplastic and cancerous prostate images in three steps: pre-processing, segmentation of cuboidal cell nuclei and post-processing. The pre-processing step consists of applying contrast stretching to the red (R) channel to highlight the contrast of cuboidal cell nuclei. The aim of the second step is to apply global thresholding based on minimum cross entropy to generate a binary image with candidate regions for cuboidal cell nuclei. In the post-processing step, false positives are removed using the connected component method. The proposed segmentation method was applied to an image bank with 105 samples and measures of sensitivity, specificity and accuracy were compared with those provided by other segmentation approaches available in the specialized literature. The results are promising and demonstrate that the proposed method allows the segmentation of cuboidal cell nuclei with a mean accuracy of 97%. © 2013 Elsevier Ltd. All rights reserved.
dc.languageeng
dc.relationExpert Systems with Applications
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectMinimum cross entropy
dc.subjectProstate cancer
dc.subjectSegmentation of cuboidal cells
dc.subjectSegmentation of nuclei
dc.subjectConnected component
dc.subjectContrast stretching
dc.subjectGlobal thresholding
dc.subjectPre-processing step
dc.subjectProstate cancers
dc.subjectSegmentation methods
dc.subjectUnsupervised segmentation method
dc.subjectEntropy
dc.subjectImage segmentation
dc.titleUnsupervised segmentation method for cuboidal cell nuclei in histological prostate images based on minimum cross entropy
dc.typeOtro


Este ítem pertenece a la siguiente institución