A ensemble methodology for automatic classification of chest X-rays using deep learning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/10216/140809 |
Resumo: | Chest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR). |
id |
RCAP_849df4030b0d71737b07ce700570fbdd |
---|---|
oai_identifier_str |
oai:repositorio-aberto.up.pt:10216/140809 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A ensemble methodology for automatic classification of chest X-rays using deep learningCiências Tecnológicas, Ciências médicas e da saúdeTechnological sciences, Medical and Health sciencesChest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR).2022-062022-06-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleimage/pngapplication/pdfhttps://hdl.handle.net/10216/140809eng0010-482510.1016/j.compbiomed.2022.105442Luis VogadoFlávio AraújoPedro Santos NetoJoão AlmeidaJoão Manuel R. S. TavaresRodrigo Verasinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-29T14:22:53Zoai:repositorio-aberto.up.pt:10216/140809Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:00:00.619409Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
title |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
spellingShingle |
A ensemble methodology for automatic classification of chest X-rays using deep learning Luis Vogado Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
title_short |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
title_full |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
title_fullStr |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
title_full_unstemmed |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
title_sort |
A ensemble methodology for automatic classification of chest X-rays using deep learning |
author |
Luis Vogado |
author_facet |
Luis Vogado Flávio Araújo Pedro Santos Neto João Almeida João Manuel R. S. Tavares Rodrigo Veras |
author_role |
author |
author2 |
Flávio Araújo Pedro Santos Neto João Almeida João Manuel R. S. Tavares Rodrigo Veras |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Luis Vogado Flávio Araújo Pedro Santos Neto João Almeida João Manuel R. S. Tavares Rodrigo Veras |
dc.subject.por.fl_str_mv |
Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
topic |
Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
description |
Chest radiographies, or chest X-rays, are the most standard imaging exams used in daily hospitals. Responsible for assisting in detecting numerous pathologies and findings that directly interfere in the patient's life, this exam is therefore crucial in screening patients. This work proposes a methodology based on a Convolutional Neural Networks (CNNs) ensemble to aid the diagnosis of chest X-ray exams by screening them with a high probability of being normal or abnormal. In the development of this study, a private dataset with frontal and lateral projections X-ray images was used. To build the ensemble model, VGG-16, ResNet50 and DenseNet121 architectures, which are commonly used in the classification of Chest X-rays, were evaluated. A Confidence Threshold (CTR) was used to define the predictions into High Confidence Normal (HCn), Borderline classification (BC), or High Confidence Abnormal (HCa). In the tests performed, very promising results were achieved: 54.63% of the exams were classified with high confidence; of the normal exams, 32% were classified as HCn with an false discovery rate (FDR) of 1.68%; and as to the abnormal exams, 23% were classified as HCa with 4.91% false omission rate (FOR). |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-06 2022-06-01T00:00:00Z |
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 |
https://hdl.handle.net/10216/140809 |
url |
https://hdl.handle.net/10216/140809 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
0010-4825 10.1016/j.compbiomed.2022.105442 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
image/png application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799135923733004288 |