LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.eswa.2016.02.019 http://hdl.handle.net/11449/172704 |
Resumo: | In computer-aided diagnosis one of the crucial steps to classify suspicious lesions is the extraction of features. Texture analysis methods have been used in the analysis and interpretation of medical images. In this work we present a method based on the association among curvelet transform, local binary patterns, feature selection by statistical analysis and distinct classification methods, in order to support the development of computer aided diagnosis system. The similar features were removed by the statistical analysis of variance (ANOVA). The understanding of the features was evaluated by applying the decision tree, random forest, support vector machine and polynomial (PL) classifiers, considering the metrics accuracy (AC) and area under the ROC curve (AUC): the rates were calculated on images of breast tissues with different physical properties (commonly observed in clinical practice). The datasets were the Digital Database for Screening Mammography, Breast Cancer Digital Repository and UCSB biosegmentation benchmark. The investigated groups were normal-abnormal and benign-malignant. The association of curvelet transform, local binary pattern and ANOVA with the PL classifier achieved higher AUC and AC values for all cases: the obtained rates were among 91% and 100%. These results are relevant, specially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed association is useful as an automated protocol for the diagnosis of breast tissues and may contribute to the diagnosis of breast tissues (mammographic and histopathological images). |
id |
UNSP_9347265dbdf5fc807bb5845f3238f818 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/172704 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissuesBreast cancer tissuesComputer aided diagnosisCurvelet transformLocal binary patternPolynomial classifierTexture analysisIn computer-aided diagnosis one of the crucial steps to classify suspicious lesions is the extraction of features. Texture analysis methods have been used in the analysis and interpretation of medical images. In this work we present a method based on the association among curvelet transform, local binary patterns, feature selection by statistical analysis and distinct classification methods, in order to support the development of computer aided diagnosis system. The similar features were removed by the statistical analysis of variance (ANOVA). The understanding of the features was evaluated by applying the decision tree, random forest, support vector machine and polynomial (PL) classifiers, considering the metrics accuracy (AC) and area under the ROC curve (AUC): the rates were calculated on images of breast tissues with different physical properties (commonly observed in clinical practice). The datasets were the Digital Database for Screening Mammography, Breast Cancer Digital Repository and UCSB biosegmentation benchmark. The investigated groups were normal-abnormal and benign-malignant. The association of curvelet transform, local binary pattern and ANOVA with the PL classifier achieved higher AUC and AC values for all cases: the obtained rates were among 91% and 100%. These results are relevant, specially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed association is useful as an automated protocol for the diagnosis of breast tissues and may contribute to the diagnosis of breast tissues (mammographic and histopathological images).UFABC - CMCC, av. dos Estados 5001, Bl.BUFU - FACOM, av. João Neves de Ávila 2121, Bl.BUNIVASF - CENEL, av. Antoˆnio C. Magalhães 510UNESP - DCCE, r. Cristóvão Colombo 2265IFTM, r. Belarmino Vilela Junqueira S/NUNESP - DCCE, r. Cristóvão Colombo 2265Universidade Federal do ABC (UFABC)UFU - FACOMUNIVASF - CENELUniversidade Estadual Paulista (Unesp)IFTMTambasco Bruno, Daniel O.Do Nascimento, Marcelo Z.Ramos, Rodrigo P.Batista, Valério R.Neves, Leandro A. [UNESP]Martins, Alessandro S.2018-12-11T17:01:51Z2018-12-11T17:01:51Z2016-08-15info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article329-340application/pdfhttp://dx.doi.org/10.1016/j.eswa.2016.02.019Expert Systems with Applications, v. 55, p. 329-340.0957-4174http://hdl.handle.net/11449/17270410.1016/j.eswa.2016.02.0192-s2.0-849611730932-s2.0-84961173093.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengExpert Systems with Applications1,271info:eu-repo/semantics/openAccess2023-12-17T06:17:25Zoai:repositorio.unesp.br:11449/172704Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-12-17T06:17:25Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
title |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
spellingShingle |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues Tambasco Bruno, Daniel O. Breast cancer tissues Computer aided diagnosis Curvelet transform Local binary pattern Polynomial classifier Texture analysis |
title_short |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
title_full |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
title_fullStr |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
title_full_unstemmed |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
title_sort |
LBP operators on curvelet coefficients as an algorithm to describe texture in breast cancer tissues |
author |
Tambasco Bruno, Daniel O. |
author_facet |
Tambasco Bruno, Daniel O. Do Nascimento, Marcelo Z. Ramos, Rodrigo P. Batista, Valério R. Neves, Leandro A. [UNESP] Martins, Alessandro S. |
author_role |
author |
author2 |
Do Nascimento, Marcelo Z. Ramos, Rodrigo P. Batista, Valério R. Neves, Leandro A. [UNESP] Martins, Alessandro S. |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal do ABC (UFABC) UFU - FACOM UNIVASF - CENEL Universidade Estadual Paulista (Unesp) IFTM |
dc.contributor.author.fl_str_mv |
Tambasco Bruno, Daniel O. Do Nascimento, Marcelo Z. Ramos, Rodrigo P. Batista, Valério R. Neves, Leandro A. [UNESP] Martins, Alessandro S. |
dc.subject.por.fl_str_mv |
Breast cancer tissues Computer aided diagnosis Curvelet transform Local binary pattern Polynomial classifier Texture analysis |
topic |
Breast cancer tissues Computer aided diagnosis Curvelet transform Local binary pattern Polynomial classifier Texture analysis |
description |
In computer-aided diagnosis one of the crucial steps to classify suspicious lesions is the extraction of features. Texture analysis methods have been used in the analysis and interpretation of medical images. In this work we present a method based on the association among curvelet transform, local binary patterns, feature selection by statistical analysis and distinct classification methods, in order to support the development of computer aided diagnosis system. The similar features were removed by the statistical analysis of variance (ANOVA). The understanding of the features was evaluated by applying the decision tree, random forest, support vector machine and polynomial (PL) classifiers, considering the metrics accuracy (AC) and area under the ROC curve (AUC): the rates were calculated on images of breast tissues with different physical properties (commonly observed in clinical practice). The datasets were the Digital Database for Screening Mammography, Breast Cancer Digital Repository and UCSB biosegmentation benchmark. The investigated groups were normal-abnormal and benign-malignant. The association of curvelet transform, local binary pattern and ANOVA with the PL classifier achieved higher AUC and AC values for all cases: the obtained rates were among 91% and 100%. These results are relevant, specially when we consider the difficulties of clinical practice in distinguishing the studied groups. The proposed association is useful as an automated protocol for the diagnosis of breast tissues and may contribute to the diagnosis of breast tissues (mammographic and histopathological images). |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-08-15 2018-12-11T17:01:51Z 2018-12-11T17:01:51Z |
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.eswa.2016.02.019 Expert Systems with Applications, v. 55, p. 329-340. 0957-4174 http://hdl.handle.net/11449/172704 10.1016/j.eswa.2016.02.019 2-s2.0-84961173093 2-s2.0-84961173093.pdf |
url |
http://dx.doi.org/10.1016/j.eswa.2016.02.019 http://hdl.handle.net/11449/172704 |
identifier_str_mv |
Expert Systems with Applications, v. 55, p. 329-340. 0957-4174 10.1016/j.eswa.2016.02.019 2-s2.0-84961173093 2-s2.0-84961173093.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Expert Systems with Applications 1,271 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
329-340 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_ |
1799965313491533824 |