BreastNet: Breast cancer categorization using convolutional neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
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/CBMS49503.2020.00094 http://hdl.handle.net/11449/205181 |
Resumo: | Breast cancer is usually classified as either benign or malignant, where the former is not considered hazardous to health. Nonetheless, the benign tumors must be periodically monitored to control their activity and to prevent them from becoming malignant eventually. Several automated techniques have been proposed to aid the diagnosis by indicating potential tumor locations or by providing a broader insight. Although benign and malignant tumors are divided into four categories each, most of the works cope with their classification as just benign and malignant. This work addresses the problem of providing a more detailed classification of the tumors by proposing a deep-based architecture able to distinguish between eight types of tumors (i.e., four benign and four malignant). The proposed approach relies on the fusion of traditional convolution kernels with dilated convolutions before pooling, which can learn better spatial information, thus providing better feature detection prior to classification. Experimental results showed that the proposed approach outperformed the techniques compared in this work. |
id |
UNSP_97e09fd6746a076d32c4600571168fdd |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/205181 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
BreastNet: Breast cancer categorization using convolutional neural networksBreast cancerConvolutional neural networksDeep learningBreast cancer is usually classified as either benign or malignant, where the former is not considered hazardous to health. Nonetheless, the benign tumors must be periodically monitored to control their activity and to prevent them from becoming malignant eventually. Several automated techniques have been proposed to aid the diagnosis by indicating potential tumor locations or by providing a broader insight. Although benign and malignant tumors are divided into four categories each, most of the works cope with their classification as just benign and malignant. This work addresses the problem of providing a more detailed classification of the tumors by proposing a deep-based architecture able to distinguish between eight types of tumors (i.e., four benign and four malignant). The proposed approach relies on the fusion of traditional convolution kernels with dilated convolutions before pooling, which can learn better spatial information, thus providing better feature detection prior to classification. Experimental results showed that the proposed approach outperformed the techniques compared in this work.Department of Computing UFSCar - Federal University of São CarlosSchool of Sciences UNESP - São Paulo State UniversitySchool of Sciences UNESP - São Paulo State UniversityUniversidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Santos, ClaudioAfonso, LuisPereira, Clayton [UNESP]Papa, Joao [UNESP]2021-06-25T10:11:11Z2021-06-25T10:11:11Z2020-07-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject463-468http://dx.doi.org/10.1109/CBMS49503.2020.00094Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2020-July, p. 463-468.1063-7125http://hdl.handle.net/11449/20518110.1109/CBMS49503.2020.000942-s2.0-85091147820Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - IEEE Symposium on Computer-Based Medical Systemsinfo:eu-repo/semantics/openAccess2021-10-23T11:39:03Zoai:repositorio.unesp.br:11449/205181Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T11:39:03Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
BreastNet: Breast cancer categorization using convolutional neural networks |
title |
BreastNet: Breast cancer categorization using convolutional neural networks |
spellingShingle |
BreastNet: Breast cancer categorization using convolutional neural networks Santos, Claudio Breast cancer Convolutional neural networks Deep learning |
title_short |
BreastNet: Breast cancer categorization using convolutional neural networks |
title_full |
BreastNet: Breast cancer categorization using convolutional neural networks |
title_fullStr |
BreastNet: Breast cancer categorization using convolutional neural networks |
title_full_unstemmed |
BreastNet: Breast cancer categorization using convolutional neural networks |
title_sort |
BreastNet: Breast cancer categorization using convolutional neural networks |
author |
Santos, Claudio |
author_facet |
Santos, Claudio Afonso, Luis Pereira, Clayton [UNESP] Papa, Joao [UNESP] |
author_role |
author |
author2 |
Afonso, Luis Pereira, Clayton [UNESP] Papa, Joao [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Santos, Claudio Afonso, Luis Pereira, Clayton [UNESP] Papa, Joao [UNESP] |
dc.subject.por.fl_str_mv |
Breast cancer Convolutional neural networks Deep learning |
topic |
Breast cancer Convolutional neural networks Deep learning |
description |
Breast cancer is usually classified as either benign or malignant, where the former is not considered hazardous to health. Nonetheless, the benign tumors must be periodically monitored to control their activity and to prevent them from becoming malignant eventually. Several automated techniques have been proposed to aid the diagnosis by indicating potential tumor locations or by providing a broader insight. Although benign and malignant tumors are divided into four categories each, most of the works cope with their classification as just benign and malignant. This work addresses the problem of providing a more detailed classification of the tumors by proposing a deep-based architecture able to distinguish between eight types of tumors (i.e., four benign and four malignant). The proposed approach relies on the fusion of traditional convolution kernels with dilated convolutions before pooling, which can learn better spatial information, thus providing better feature detection prior to classification. Experimental results showed that the proposed approach outperformed the techniques compared in this work. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-07-01 2021-06-25T10:11:11Z 2021-06-25T10:11:11Z |
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/CBMS49503.2020.00094 Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2020-July, p. 463-468. 1063-7125 http://hdl.handle.net/11449/205181 10.1109/CBMS49503.2020.00094 2-s2.0-85091147820 |
url |
http://dx.doi.org/10.1109/CBMS49503.2020.00094 http://hdl.handle.net/11449/205181 |
identifier_str_mv |
Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2020-July, p. 463-468. 1063-7125 10.1109/CBMS49503.2020.00094 2-s2.0-85091147820 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - IEEE Symposium on Computer-Based Medical Systems |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
463-468 |
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_ |
1797790153814573056 |