Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images

Detalhes bibliográficos
Autor(a) principal: Azevedo Tosta, Thaína A.
Data de Publicação: 2018
Outros Autores: Faria, Paulo Rogério, Batista, Valério Ramos, Neves, Leandro Alves [UNESP], do Nascimento, Marcelo Zanchetta
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1016/j.asoc.2017.11.039
http://hdl.handle.net/11449/179434
Resumo: Histological images analysis is an important procedure to diagnose different types of cancer. One of them is the chronic lymphocytic leukemia (CLL), which can be identified by applying image segmentation techniques. This study presents an unsupervised method to segment neoplastic nuclei in CLL images. Firstly, deconvolution, histogram equalization and mean filter were applied to enhance nuclear regions. Then, a segmentation technique based on a combination of wavelet transform, fuzzy 2-partition entropy and genetic algorithm was used, followed by removal of false positive regions, and application of valley-emphasis and morphological operations. In order to evaluate the proposed algorithm H&E-stained histological images were used. In the accuracy metric, the proposed method attained more than 80%, which can surpass similar methods. This proposal presents spatial distribution that has a good consistency with a manual segmentation and lower overlapping rate than other techniques in the literature.
id UNSP_2495656e0fc5b88061bbec7ae26fbbda
oai_identifier_str oai:repositorio.unesp.br:11449/179434
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia imagesChronic lymphocytic leukemiaGenetic algorithmH&E-stained histological imagesNuclei segmentationWavelet transformHistological images analysis is an important procedure to diagnose different types of cancer. One of them is the chronic lymphocytic leukemia (CLL), which can be identified by applying image segmentation techniques. This study presents an unsupervised method to segment neoplastic nuclei in CLL images. Firstly, deconvolution, histogram equalization and mean filter were applied to enhance nuclear regions. Then, a segmentation technique based on a combination of wavelet transform, fuzzy 2-partition entropy and genetic algorithm was used, followed by removal of false positive regions, and application of valley-emphasis and morphological operations. In order to evaluate the proposed algorithm H&E-stained histological images were used. In the accuracy metric, the proposed method attained more than 80%, which can surpass similar methods. This proposal presents spatial distribution that has a good consistency with a manual segmentation and lower overlapping rate than other techniques in the literature.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)Federal University of ABC Centre of Mathematics Computer Science and Cognition, Av. dos Estados, 5001Federal University of Uberlândia Department of Histology and Morphology Institute of Biomedical Science, Av. Amazonas, S/NSão Paulo State University (UNESP) Department of Computer Science and Statistics, R. Cristóvão Colombo 2265Federal University of Uberlândia Faculty of Computer Science, Av. João Naves de Ávila, 2121São Paulo State University (UNESP) Department of Computer Science and Statistics, R. Cristóvão Colombo 2265CAPES: 1575210FAPEMIG: TEC-APQ-02885-15Computer Science and CognitionUniversidade Federal de Uberlândia (UFU)Universidade Estadual Paulista (Unesp)Azevedo Tosta, Thaína A.Faria, Paulo RogérioBatista, Valério RamosNeves, Leandro Alves [UNESP]do Nascimento, Marcelo Zanchetta2018-12-11T17:35:10Z2018-12-11T17:35:10Z2018-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article49-58application/pdfhttp://dx.doi.org/10.1016/j.asoc.2017.11.039Applied Soft Computing Journal, v. 64, p. 49-58.1568-4946http://hdl.handle.net/11449/17943410.1016/j.asoc.2017.11.0392-s2.0-850379999452-s2.0-85037999945.pdf2139053814879312Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengApplied Soft Computing Journal1,199info:eu-repo/semantics/openAccess2024-01-15T06:17:54Zoai:repositorio.unesp.br:11449/179434Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T23:00:45.027727Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
title Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
spellingShingle Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
Azevedo Tosta, Thaína A.
Chronic lymphocytic leukemia
Genetic algorithm
H&E-stained histological images
Nuclei segmentation
Wavelet transform
title_short Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
title_full Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
title_fullStr Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
title_full_unstemmed Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
title_sort Using wavelet sub-band and fuzzy 2-partition entropy to segment chronic lymphocytic leukemia images
author Azevedo Tosta, Thaína A.
author_facet Azevedo Tosta, Thaína A.
Faria, Paulo Rogério
Batista, Valério Ramos
Neves, Leandro Alves [UNESP]
do Nascimento, Marcelo Zanchetta
author_role author
author2 Faria, Paulo Rogério
Batista, Valério Ramos
Neves, Leandro Alves [UNESP]
do Nascimento, Marcelo Zanchetta
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Computer Science and Cognition
Universidade Federal de Uberlândia (UFU)
Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Azevedo Tosta, Thaína A.
Faria, Paulo Rogério
Batista, Valério Ramos
Neves, Leandro Alves [UNESP]
do Nascimento, Marcelo Zanchetta
dc.subject.por.fl_str_mv Chronic lymphocytic leukemia
Genetic algorithm
H&E-stained histological images
Nuclei segmentation
Wavelet transform
topic Chronic lymphocytic leukemia
Genetic algorithm
H&E-stained histological images
Nuclei segmentation
Wavelet transform
description Histological images analysis is an important procedure to diagnose different types of cancer. One of them is the chronic lymphocytic leukemia (CLL), which can be identified by applying image segmentation techniques. This study presents an unsupervised method to segment neoplastic nuclei in CLL images. Firstly, deconvolution, histogram equalization and mean filter were applied to enhance nuclear regions. Then, a segmentation technique based on a combination of wavelet transform, fuzzy 2-partition entropy and genetic algorithm was used, followed by removal of false positive regions, and application of valley-emphasis and morphological operations. In order to evaluate the proposed algorithm H&E-stained histological images were used. In the accuracy metric, the proposed method attained more than 80%, which can surpass similar methods. This proposal presents spatial distribution that has a good consistency with a manual segmentation and lower overlapping rate than other techniques in the literature.
publishDate 2018
dc.date.none.fl_str_mv 2018-12-11T17:35:10Z
2018-12-11T17:35:10Z
2018-03-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1016/j.asoc.2017.11.039
Applied Soft Computing Journal, v. 64, p. 49-58.
1568-4946
http://hdl.handle.net/11449/179434
10.1016/j.asoc.2017.11.039
2-s2.0-85037999945
2-s2.0-85037999945.pdf
2139053814879312
url http://dx.doi.org/10.1016/j.asoc.2017.11.039
http://hdl.handle.net/11449/179434
identifier_str_mv Applied Soft Computing Journal, v. 64, p. 49-58.
1568-4946
10.1016/j.asoc.2017.11.039
2-s2.0-85037999945
2-s2.0-85037999945.pdf
2139053814879312
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Applied Soft Computing Journal
1,199
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 49-58
application/pdf
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1808129481639985152