Automated recognition of lung diseases in CT images based on the optimum-path forest classifier
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/10.1007/s00521-017-3048-y http://hdl.handle.net/11449/186716 |
Resumo: | The World Health Organization estimated that around 300 million people have asthma, and 210 million people are affected by Chronic Obstructive Pulmonary Disease (COPD). Also, it is estimated that the number of deaths from COPD increased 30% in 2015 and COPD will become the third major cause of death worldwide by 2030. These statistics about lung diseases get worse when one considers fibrosis, calcifications and other diseases. For the public health system, the early and accurate diagnosis of any pulmonary disease is mandatory for effective treatments and prevention of further deaths. In this sense, this work consists in using information from lung images to identify and classify lung diseases. Two steps are required to achieve these goals: automatically extraction of representative image features of the lungs and recognition of the possible disease using a computational classifier. As to the first step, this work proposes an approach that combines Spatial Interdependence Matrix (SIM) and Visual Information Fidelity (VIF). Concerning the second step, we propose to employ a Gaussian-based distance to be used together with the optimum-path forest (OPF) classifier to classify the lungs under study as normal or with fibrosis, or even affected by COPD. Moreover, to confirm the robustness of OPF in this classification problem, we also considered Support Vector Machines and a Multilayer Perceptron Neural Network for comparison purposes. Overall, the results confirmed the good performance of the OPF configured with the Gaussian distance when applied to SIM- and VIF-based features. The performance scores achieved by the OPF classifier were as follows: average accuracy of 98.2%, total processing time of 117 microseconds in a common personal laptop, and F-score of 95.2% for the three classification classes. These results showed that OPF is a very competitive classifier, and suitable to be used for lung disease classification. |
id |
UNSP_4fcba72829b770f527bd97b04c754905 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/186716 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifierMedical imagingOptimum-path forestFeature extractionImage classificationThe World Health Organization estimated that around 300 million people have asthma, and 210 million people are affected by Chronic Obstructive Pulmonary Disease (COPD). Also, it is estimated that the number of deaths from COPD increased 30% in 2015 and COPD will become the third major cause of death worldwide by 2030. These statistics about lung diseases get worse when one considers fibrosis, calcifications and other diseases. For the public health system, the early and accurate diagnosis of any pulmonary disease is mandatory for effective treatments and prevention of further deaths. In this sense, this work consists in using information from lung images to identify and classify lung diseases. Two steps are required to achieve these goals: automatically extraction of representative image features of the lungs and recognition of the possible disease using a computational classifier. As to the first step, this work proposes an approach that combines Spatial Interdependence Matrix (SIM) and Visual Information Fidelity (VIF). Concerning the second step, we propose to employ a Gaussian-based distance to be used together with the optimum-path forest (OPF) classifier to classify the lungs under study as normal or with fibrosis, or even affected by COPD. Moreover, to confirm the robustness of OPF in this classification problem, we also considered Support Vector Machines and a Multilayer Perceptron Neural Network for comparison purposes. Overall, the results confirmed the good performance of the OPF configured with the Gaussian distance when applied to SIM- and VIF-based features. The performance scores achieved by the OPF classifier were as follows: average accuracy of 98.2%, total processing time of 117 microseconds in a common personal laptop, and F-score of 95.2% for the three classification classes. These results showed that OPF is a very competitive classifier, and suitable to be used for lung disease classification.Graduate Program in Computer Science from the Federal Institute of Education, Science and Technology of CearaDepartment of Computer Engineering from the Walter Cantidio University Hospital of the Federal University of Ceara, in BrazilFederal Institute of Education, Science and Technology of Ceara through grant PROINFRA/2013Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Project SciTech-Science and Technology for Competitive and Sustainable IndustriesPrograma Operacional Regional do Norte (NORTE2020), through Fundo Europeu de Desenvolvimento Regional (FEDER)Federal Institute of Education, Science and Technology of Ceara through grant PROAPP/2014Inst Fed Fed Educ Ciencia & Tecnol Ceara IFCE, Lab Processamento Digital Imagens & Simulacao Com, Campus Maracanau, Maracanau, Ceara, BrazilUniv Estadual Paulista, Dept Ciencia Comp, Bauru, SP, BrazilUniv Fortaleza, Programa Posgrad Informat Aplicada, Fortaleza, Ceara, BrazilUniv Porto, Fac Engn, Dept Engn Mecan, Inst Ciencia & Inovaco Engn Mecan & Engn Ind, Porto, PortugalUniv Estadual Paulista, Dept Ciencia Comp, Bauru, SP, BrazilCNPq: 470501/2013-8CNPq: 301928/2014-2CNPq: 306166/2014-3FAPESP: 2014/16250-9FAPESP: 2014/12236-1Project SciTech-Science and Technology for Competitive and Sustainable Industries: NORTE-01-0145-FEDER-000022SpringerInst Fed Fed Educ Ciencia & Tecnol Ceara IFCEUniversidade Estadual Paulista (Unesp)Univ FortalezaUniv PortoReboucas Filho, Pedro P.Silva Barros, Antonio C. daRamalho, Geraldo L. B.Pereira, Clayton R. [UNESP]Papa, Joao Paulo [UNESP]Albuquerque, Victor Hugo C. deTavares, Joao Manuel R. S.2019-10-05T22:02:15Z2019-10-05T22:02:15Z2019-02-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article901-914http://dx.doi.org/10.1007/s00521-017-3048-yNeural Computing & Applications. London: Springer London Ltd, v. 31, p. 901-914, 2019.0941-0643http://hdl.handle.net/11449/18671610.1007/s00521-017-3048-yWOS:000464766200019Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengNeural Computing & Applicationsinfo:eu-repo/semantics/openAccess2024-04-23T16:10:45Zoai:repositorio.unesp.br:11449/186716Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:02:01.766622Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
title |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
spellingShingle |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier Reboucas Filho, Pedro P. Medical imaging Optimum-path forest Feature extraction Image classification |
title_short |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
title_full |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
title_fullStr |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
title_full_unstemmed |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
title_sort |
Automated recognition of lung diseases in CT images based on the optimum-path forest classifier |
author |
Reboucas Filho, Pedro P. |
author_facet |
Reboucas Filho, Pedro P. Silva Barros, Antonio C. da Ramalho, Geraldo L. B. Pereira, Clayton R. [UNESP] Papa, Joao Paulo [UNESP] Albuquerque, Victor Hugo C. de Tavares, Joao Manuel R. S. |
author_role |
author |
author2 |
Silva Barros, Antonio C. da Ramalho, Geraldo L. B. Pereira, Clayton R. [UNESP] Papa, Joao Paulo [UNESP] Albuquerque, Victor Hugo C. de Tavares, Joao Manuel R. S. |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Inst Fed Fed Educ Ciencia & Tecnol Ceara IFCE Universidade Estadual Paulista (Unesp) Univ Fortaleza Univ Porto |
dc.contributor.author.fl_str_mv |
Reboucas Filho, Pedro P. Silva Barros, Antonio C. da Ramalho, Geraldo L. B. Pereira, Clayton R. [UNESP] Papa, Joao Paulo [UNESP] Albuquerque, Victor Hugo C. de Tavares, Joao Manuel R. S. |
dc.subject.por.fl_str_mv |
Medical imaging Optimum-path forest Feature extraction Image classification |
topic |
Medical imaging Optimum-path forest Feature extraction Image classification |
description |
The World Health Organization estimated that around 300 million people have asthma, and 210 million people are affected by Chronic Obstructive Pulmonary Disease (COPD). Also, it is estimated that the number of deaths from COPD increased 30% in 2015 and COPD will become the third major cause of death worldwide by 2030. These statistics about lung diseases get worse when one considers fibrosis, calcifications and other diseases. For the public health system, the early and accurate diagnosis of any pulmonary disease is mandatory for effective treatments and prevention of further deaths. In this sense, this work consists in using information from lung images to identify and classify lung diseases. Two steps are required to achieve these goals: automatically extraction of representative image features of the lungs and recognition of the possible disease using a computational classifier. As to the first step, this work proposes an approach that combines Spatial Interdependence Matrix (SIM) and Visual Information Fidelity (VIF). Concerning the second step, we propose to employ a Gaussian-based distance to be used together with the optimum-path forest (OPF) classifier to classify the lungs under study as normal or with fibrosis, or even affected by COPD. Moreover, to confirm the robustness of OPF in this classification problem, we also considered Support Vector Machines and a Multilayer Perceptron Neural Network for comparison purposes. Overall, the results confirmed the good performance of the OPF configured with the Gaussian distance when applied to SIM- and VIF-based features. The performance scores achieved by the OPF classifier were as follows: average accuracy of 98.2%, total processing time of 117 microseconds in a common personal laptop, and F-score of 95.2% for the three classification classes. These results showed that OPF is a very competitive classifier, and suitable to be used for lung disease classification. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-05T22:02:15Z 2019-10-05T22:02:15Z 2019-02-01 |
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/10.1007/s00521-017-3048-y Neural Computing & Applications. London: Springer London Ltd, v. 31, p. 901-914, 2019. 0941-0643 http://hdl.handle.net/11449/186716 10.1007/s00521-017-3048-y WOS:000464766200019 |
url |
http://dx.doi.org/10.1007/s00521-017-3048-y http://hdl.handle.net/11449/186716 |
identifier_str_mv |
Neural Computing & Applications. London: Springer London Ltd, v. 31, p. 901-914, 2019. 0941-0643 10.1007/s00521-017-3048-y WOS:000464766200019 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Neural Computing & Applications |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
901-914 |
dc.publisher.none.fl_str_mv |
Springer |
publisher.none.fl_str_mv |
Springer |
dc.source.none.fl_str_mv |
Web of Science 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_ |
1808128596159496192 |