Classification of breast and colorectal tumors based on percolation of color normalized images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.cag.2019.08.008 http://hdl.handle.net/11449/199448 |
Resumo: | Percolation is a fractal descriptor that has been applied recently on computer vision problems. We applied this descriptor on 58 colored histological breast images, and 165 colored histological colorectal images, both stained with Hematoxylin and Eosin, in order to extract features to differentiate between benign and malignant cases. The experiments were also performed over normalized images, aiming to analyze the influence of different color normalization techniques on percolation-based features and whether they can provide better classification results. The feature sets obtained from the application of the method on the original images and on the normalized images with three different techniques were tested using 12 different classifiers. We compared the obtained results with other relevant methods in the area and observed significant contributions, with AUC rates above 0.900 in both normalized and non-normalized images. We also verified that color normalization does not contribute to the classification of breast tumors when associated with percolation features. However, color normalized images from the colorectal tumor's dataset provided better results than the original images. |
id |
UNSP_bfdb2012c15c19a9ef9fd3c2e4da55d0 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/199448 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Classification of breast and colorectal tumors based on percolation of color normalized imagesBreast tumorsColor normalizationColorectal tumorsImage classificationPercolationPercolation is a fractal descriptor that has been applied recently on computer vision problems. We applied this descriptor on 58 colored histological breast images, and 165 colored histological colorectal images, both stained with Hematoxylin and Eosin, in order to extract features to differentiate between benign and malignant cases. The experiments were also performed over normalized images, aiming to analyze the influence of different color normalization techniques on percolation-based features and whether they can provide better classification results. The feature sets obtained from the application of the method on the original images and on the normalized images with three different techniques were tested using 12 different classifiers. We compared the obtained results with other relevant methods in the area and observed significant contributions, with AUC rates above 0.900 in both normalized and non-normalized images. We also verified that color normalization does not contribute to the classification of breast tumors when associated with percolation features. However, color normalized images from the colorectal tumor's dataset provided better results than the original images.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Faculty of Computation (FACOM) Federal University of Uberlândia (UFU), Av. João Naves de Ávila 2121, BLBFederal Institute of Triângulo Mineiro (IFTM), R. Belarmino Vilela Junqueira, S/NCenter of Mathematics Computing and Cognition Federal University of ABC (UFABC), Av. dos Estados, 5001Department of Histology and Morphology Institute of Biomedical Science Federal University of Uberlândia (UFU), Av. Amazonas, S/NDepartment of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), R. Cristóvão Colombo, 2265Department of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), R. Cristóvão Colombo, 2265CNPq: #304848/2018-2CNPq: #313365/2018-0CNPq: #427114/2016-0CNPq: #430965/2018-4FAPEMIG: #APQ-00578-18CAPES: 001Universidade Federal de Uberlândia (UFU)Federal Institute of Triângulo Mineiro (IFTM)Universidade Federal do ABC (UFABC)Universidade Estadual Paulista (Unesp)Roberto, Guilherme F.Nascimento, Marcelo Z.Martins, Alessandro S.Tosta, Thaína A.A.Faria, Paulo R.Neves, Leandro A. [UNESP]2020-12-12T01:39:57Z2020-12-12T01:39:57Z2019-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article134-143http://dx.doi.org/10.1016/j.cag.2019.08.008Computers and Graphics (Pergamon), v. 84, p. 134-143.0097-8493http://hdl.handle.net/11449/19944810.1016/j.cag.2019.08.0082-s2.0-85072573634Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengComputers and Graphics (Pergamon)info:eu-repo/semantics/openAccess2021-10-23T03:12:37Zoai:repositorio.unesp.br:11449/199448Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T03:12:37Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Classification of breast and colorectal tumors based on percolation of color normalized images |
title |
Classification of breast and colorectal tumors based on percolation of color normalized images |
spellingShingle |
Classification of breast and colorectal tumors based on percolation of color normalized images Roberto, Guilherme F. Breast tumors Color normalization Colorectal tumors Image classification Percolation |
title_short |
Classification of breast and colorectal tumors based on percolation of color normalized images |
title_full |
Classification of breast and colorectal tumors based on percolation of color normalized images |
title_fullStr |
Classification of breast and colorectal tumors based on percolation of color normalized images |
title_full_unstemmed |
Classification of breast and colorectal tumors based on percolation of color normalized images |
title_sort |
Classification of breast and colorectal tumors based on percolation of color normalized images |
author |
Roberto, Guilherme F. |
author_facet |
Roberto, Guilherme F. Nascimento, Marcelo Z. Martins, Alessandro S. Tosta, Thaína A.A. Faria, Paulo R. Neves, Leandro A. [UNESP] |
author_role |
author |
author2 |
Nascimento, Marcelo Z. Martins, Alessandro S. Tosta, Thaína A.A. Faria, Paulo R. Neves, Leandro A. [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Uberlândia (UFU) Federal Institute of Triângulo Mineiro (IFTM) Universidade Federal do ABC (UFABC) Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Roberto, Guilherme F. Nascimento, Marcelo Z. Martins, Alessandro S. Tosta, Thaína A.A. Faria, Paulo R. Neves, Leandro A. [UNESP] |
dc.subject.por.fl_str_mv |
Breast tumors Color normalization Colorectal tumors Image classification Percolation |
topic |
Breast tumors Color normalization Colorectal tumors Image classification Percolation |
description |
Percolation is a fractal descriptor that has been applied recently on computer vision problems. We applied this descriptor on 58 colored histological breast images, and 165 colored histological colorectal images, both stained with Hematoxylin and Eosin, in order to extract features to differentiate between benign and malignant cases. The experiments were also performed over normalized images, aiming to analyze the influence of different color normalization techniques on percolation-based features and whether they can provide better classification results. The feature sets obtained from the application of the method on the original images and on the normalized images with three different techniques were tested using 12 different classifiers. We compared the obtained results with other relevant methods in the area and observed significant contributions, with AUC rates above 0.900 in both normalized and non-normalized images. We also verified that color normalization does not contribute to the classification of breast tumors when associated with percolation features. However, color normalized images from the colorectal tumor's dataset provided better results than the original images. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-11-01 2020-12-12T01:39:57Z 2020-12-12T01:39:57Z |
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.cag.2019.08.008 Computers and Graphics (Pergamon), v. 84, p. 134-143. 0097-8493 http://hdl.handle.net/11449/199448 10.1016/j.cag.2019.08.008 2-s2.0-85072573634 |
url |
http://dx.doi.org/10.1016/j.cag.2019.08.008 http://hdl.handle.net/11449/199448 |
identifier_str_mv |
Computers and Graphics (Pergamon), v. 84, p. 134-143. 0097-8493 10.1016/j.cag.2019.08.008 2-s2.0-85072573634 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Computers and Graphics (Pergamon) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
134-143 |
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_ |
1792962038948954112 |