A Hybrid Approach for Breast Mass Categorization
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Capítulo de livro |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/978-3-030-32040-9_17 http://hdl.handle.net/11449/201220 |
Resumo: | Breast cancer is one of the most frequent fatal diseases among women around the world. Early diagnosis is paramount for easing such statistics, increasing the probability of successful treatment and cure. This paper proposes a hybrid approach composed of a convolutional neural network with a supervised classifier on the top capable of predicting eight specific cases of the breast tumor, being four of them malignant and four benign. The model employs the BreastNet convolution neural network to the task of mammogram images feature extraction, and it compares three distinct supervised-learning algorithms for classification purposes: (i) Optimum-Path Forest, (ii) Support Vector Machines (SVM) with Radial Basis Function, and (iii) SVM with a linear kernel. Moreover, since BreastNet is also capable of performing classification tasks, its results are further compared against the other three techniques. Experimental results demonstrate the robustness of the model, achieving 86 % of accuracy over the public LAPIMO dataset. |
id |
UNSP_c910e357fdf28043ef82d847ffd2cefb |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/201220 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Hybrid Approach for Breast Mass CategorizationBreast cancerConvolutional Neural NetworksOptimum-path forestBreast cancer is one of the most frequent fatal diseases among women around the world. Early diagnosis is paramount for easing such statistics, increasing the probability of successful treatment and cure. This paper proposes a hybrid approach composed of a convolutional neural network with a supervised classifier on the top capable of predicting eight specific cases of the breast tumor, being four of them malignant and four benign. The model employs the BreastNet convolution neural network to the task of mammogram images feature extraction, and it compares three distinct supervised-learning algorithms for classification purposes: (i) Optimum-Path Forest, (ii) Support Vector Machines (SVM) with Radial Basis Function, and (iii) SVM with a linear kernel. Moreover, since BreastNet is also capable of performing classification tasks, its results are further compared against the other three techniques. Experimental results demonstrate the robustness of the model, achieving 86 % of accuracy over the public LAPIMO dataset.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)School of Sciences UNESP - São Paulo State UniversityDepartment of Computing UFSCar - Federal University of São CarlosSchool of Sciences UNESP - São Paulo State UniversityFAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2016/19403-6CNPq: 307066/2017-7CNPq: 427968/2018-6Universidade Estadual Paulista (Unesp)Universidade Federal de São Carlos (UFSCar)Passos, Leandro Aparecido [UNESP]Santos, ClaudioPereira, Clayton Reginaldo [UNESP]Afonso, Luis Claudio SugiPapa, João P. [UNESP]2020-12-12T02:27:08Z2020-12-12T02:27:08Z2019-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookPart159-168http://dx.doi.org/10.1007/978-3-030-32040-9_17Lecture Notes in Computational Vision and Biomechanics, v. 34, p. 159-168.2212-94132212-9391http://hdl.handle.net/11449/20122010.1007/978-3-030-32040-9_172-s2.0-85073171028Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengLecture Notes in Computational Vision and Biomechanicsinfo:eu-repo/semantics/openAccess2024-04-23T16:11:01Zoai:repositorio.unesp.br:11449/201220Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11:01Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Hybrid Approach for Breast Mass Categorization |
title |
A Hybrid Approach for Breast Mass Categorization |
spellingShingle |
A Hybrid Approach for Breast Mass Categorization Passos, Leandro Aparecido [UNESP] Breast cancer Convolutional Neural Networks Optimum-path forest |
title_short |
A Hybrid Approach for Breast Mass Categorization |
title_full |
A Hybrid Approach for Breast Mass Categorization |
title_fullStr |
A Hybrid Approach for Breast Mass Categorization |
title_full_unstemmed |
A Hybrid Approach for Breast Mass Categorization |
title_sort |
A Hybrid Approach for Breast Mass Categorization |
author |
Passos, Leandro Aparecido [UNESP] |
author_facet |
Passos, Leandro Aparecido [UNESP] Santos, Claudio Pereira, Clayton Reginaldo [UNESP] Afonso, Luis Claudio Sugi Papa, João P. [UNESP] |
author_role |
author |
author2 |
Santos, Claudio Pereira, Clayton Reginaldo [UNESP] Afonso, Luis Claudio Sugi Papa, João P. [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade Federal de São Carlos (UFSCar) |
dc.contributor.author.fl_str_mv |
Passos, Leandro Aparecido [UNESP] Santos, Claudio Pereira, Clayton Reginaldo [UNESP] Afonso, Luis Claudio Sugi Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Breast cancer Convolutional Neural Networks Optimum-path forest |
topic |
Breast cancer Convolutional Neural Networks Optimum-path forest |
description |
Breast cancer is one of the most frequent fatal diseases among women around the world. Early diagnosis is paramount for easing such statistics, increasing the probability of successful treatment and cure. This paper proposes a hybrid approach composed of a convolutional neural network with a supervised classifier on the top capable of predicting eight specific cases of the breast tumor, being four of them malignant and four benign. The model employs the BreastNet convolution neural network to the task of mammogram images feature extraction, and it compares three distinct supervised-learning algorithms for classification purposes: (i) Optimum-Path Forest, (ii) Support Vector Machines (SVM) with Radial Basis Function, and (iii) SVM with a linear kernel. Moreover, since BreastNet is also capable of performing classification tasks, its results are further compared against the other three techniques. Experimental results demonstrate the robustness of the model, achieving 86 % of accuracy over the public LAPIMO dataset. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-01-01 2020-12-12T02:27:08Z 2020-12-12T02:27:08Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bookPart |
format |
bookPart |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1007/978-3-030-32040-9_17 Lecture Notes in Computational Vision and Biomechanics, v. 34, p. 159-168. 2212-9413 2212-9391 http://hdl.handle.net/11449/201220 10.1007/978-3-030-32040-9_17 2-s2.0-85073171028 |
url |
http://dx.doi.org/10.1007/978-3-030-32040-9_17 http://hdl.handle.net/11449/201220 |
identifier_str_mv |
Lecture Notes in Computational Vision and Biomechanics, v. 34, p. 159-168. 2212-9413 2212-9391 10.1007/978-3-030-32040-9_17 2-s2.0-85073171028 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Lecture Notes in Computational Vision and Biomechanics |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
159-168 |
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_ |
1797789797435047936 |