Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/SIBGRAPI.2018.00054 http://hdl.handle.net/11449/188789 |
Resumo: | In this work, a method is proposed to analyze the influence of color normalization in the classification lymphoma images. The approach combines multidimensional fractal techniques, curvelet transforms and Haralick features. The method considered a feature selection technique and different classification approaches to evaluate the combinations, such as decision tree, random forest, support vector machine, naive bayes and k-star. The classifications were analyzed considering three common lymphoma classes: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia. The best result was achieved for the extraction from input images, features obtained mostly from lacunarity and percolation from curvelet sub-images, using random forest classifier. The tests were considered with 10-fold cross-validation and the result was a rate of AUC=0.963. The color normalization was not able to provide relevant classification rates. The obtained performance with the analysis over different types of features, classifiers and color normalization influence are important contributions to the identification of the lymphoma cancer. |
id |
UNSP_b4d68b55455ce8e3886140cca65e85ac |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/188789 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma ImagesAnalysis of the Influenceclassificationcolor normalizationnon Hodgkin LymphomaIn this work, a method is proposed to analyze the influence of color normalization in the classification lymphoma images. The approach combines multidimensional fractal techniques, curvelet transforms and Haralick features. The method considered a feature selection technique and different classification approaches to evaluate the combinations, such as decision tree, random forest, support vector machine, naive bayes and k-star. The classifications were analyzed considering three common lymphoma classes: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia. The best result was achieved for the extraction from input images, features obtained mostly from lacunarity and percolation from curvelet sub-images, using random forest classifier. The tests were considered with 10-fold cross-validation and the result was a rate of AUC=0.963. The color normalization was not able to provide relevant classification rates. The obtained performance with the analysis over different types of features, classifiers and color normalization influence are important contributions to the identification of the lymphoma cancer.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP)Faculty of Computation (FACOM) Federal University of Uberlândia (UFU)Center of Mathematics Computing and Cognition Federal University of ABCFederal Institute of Triângulo Mineiro (IFTM)Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP)CAPES: 1646248CNPq: 427114/20160FAPEMIG: TEC - APQ-02885-15Universidade Estadual Paulista (Unesp)Universidade Federal de Uberlândia (UFU)Federal University of ABCFederal Institute of Triângulo Mineiro (IFTM)Goncalves Ribeiro, Matheus [UNESP]Alves Neves, Leandro [UNESP]Freire Roberto, GuilhermeTosta, Thaina A. A.Martins, Alessandro S.Do Nascimento, Marcelo Z.2019-10-06T16:19:15Z2019-10-06T16:19:15Z2019-01-15info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject369-376http://dx.doi.org/10.1109/SIBGRAPI.2018.00054Proceedings - 31st Conference on Graphics, Patterns and Images, SIBGRAPI 2018, p. 369-376.http://hdl.handle.net/11449/18878910.1109/SIBGRAPI.2018.000542-s2.0-85062237452Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - 31st Conference on Graphics, Patterns and Images, SIBGRAPI 2018info:eu-repo/semantics/openAccess2021-10-23T17:23:50Zoai:repositorio.unesp.br:11449/188789Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T17:23:50Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
title |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
spellingShingle |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images Goncalves Ribeiro, Matheus [UNESP] Analysis of the Influence classification color normalization non Hodgkin Lymphoma |
title_short |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
title_full |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
title_fullStr |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
title_full_unstemmed |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
title_sort |
Analysis of the Influence of Color Normalization in the Classification of Non-Hodgkin Lymphoma Images |
author |
Goncalves Ribeiro, Matheus [UNESP] |
author_facet |
Goncalves Ribeiro, Matheus [UNESP] Alves Neves, Leandro [UNESP] Freire Roberto, Guilherme Tosta, Thaina A. A. Martins, Alessandro S. Do Nascimento, Marcelo Z. |
author_role |
author |
author2 |
Alves Neves, Leandro [UNESP] Freire Roberto, Guilherme Tosta, Thaina A. A. Martins, Alessandro S. Do Nascimento, Marcelo Z. |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade Federal de Uberlândia (UFU) Federal University of ABC Federal Institute of Triângulo Mineiro (IFTM) |
dc.contributor.author.fl_str_mv |
Goncalves Ribeiro, Matheus [UNESP] Alves Neves, Leandro [UNESP] Freire Roberto, Guilherme Tosta, Thaina A. A. Martins, Alessandro S. Do Nascimento, Marcelo Z. |
dc.subject.por.fl_str_mv |
Analysis of the Influence classification color normalization non Hodgkin Lymphoma |
topic |
Analysis of the Influence classification color normalization non Hodgkin Lymphoma |
description |
In this work, a method is proposed to analyze the influence of color normalization in the classification lymphoma images. The approach combines multidimensional fractal techniques, curvelet transforms and Haralick features. The method considered a feature selection technique and different classification approaches to evaluate the combinations, such as decision tree, random forest, support vector machine, naive bayes and k-star. The classifications were analyzed considering three common lymphoma classes: mantle cell lymphoma, follicular lymphoma and chronic lymphocytic leukemia. The best result was achieved for the extraction from input images, features obtained mostly from lacunarity and percolation from curvelet sub-images, using random forest classifier. The tests were considered with 10-fold cross-validation and the result was a rate of AUC=0.963. The color normalization was not able to provide relevant classification rates. The obtained performance with the analysis over different types of features, classifiers and color normalization influence are important contributions to the identification of the lymphoma cancer. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-06T16:19:15Z 2019-10-06T16:19:15Z 2019-01-15 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/SIBGRAPI.2018.00054 Proceedings - 31st Conference on Graphics, Patterns and Images, SIBGRAPI 2018, p. 369-376. http://hdl.handle.net/11449/188789 10.1109/SIBGRAPI.2018.00054 2-s2.0-85062237452 |
url |
http://dx.doi.org/10.1109/SIBGRAPI.2018.00054 http://hdl.handle.net/11449/188789 |
identifier_str_mv |
Proceedings - 31st Conference on Graphics, Patterns and Images, SIBGRAPI 2018, p. 369-376. 10.1109/SIBGRAPI.2018.00054 2-s2.0-85062237452 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - 31st Conference on Graphics, Patterns and Images, SIBGRAPI 2018 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
369-376 |
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_ |
1799965661956407296 |