Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Research, Society and Development |
Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/27919 |
Resumo: | In late 2019, a new type of coronavirus emerged in China and was named SARS-CoV-2. It first impacted the country where it emerged and then spread around the world. SARS-CoV-2 is the cause of COVID-19 disease that leaves characteristic impressions on chest CT images of infected patients. In this article, we propose a classification model, based on CNN and wavelet transform, to classify images of COVID-19 patients. It was named WCNN-COVID. The model was applied and tested in open and private TC image repositories. A total of 25534 images of 200 patients were processed. The confusion matrix was generated by calculating Accuracy (ACC), Sensitivity (Sen) and Specificity (Sp). The Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUCs) were also plotted and used for evaluation. Metric results were ACC = 0.9950, Sen = 99.16% and Sp = 99.89%. |
id |
UNIFEI_9974501a0c07c4850427669f9e8d97f8 |
---|---|
oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/27919 |
network_acronym_str |
UNIFEI |
network_name_str |
Research, Society and Development |
repository_id_str |
|
spelling |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT imagesHacia un Modelo de Clasificación usando CNN y Wavelets aplicado a imágenes de TC de COVID-19Por um modelo de classificação usando CNN e Wavelets aplicados a imagens de TC COVID-19CT imagesConvolutional Neural NetworksCOVID-19WaveletsWCN-COVID.Redes Neuronales ConvolucionalesCOVID-19WaveletsImágenes de TCWCN-COVID.Redes Neurais ConvolucionaisCOVID-19WaveletsImagens de TCWCNN-COVID.In late 2019, a new type of coronavirus emerged in China and was named SARS-CoV-2. It first impacted the country where it emerged and then spread around the world. SARS-CoV-2 is the cause of COVID-19 disease that leaves characteristic impressions on chest CT images of infected patients. In this article, we propose a classification model, based on CNN and wavelet transform, to classify images of COVID-19 patients. It was named WCNN-COVID. The model was applied and tested in open and private TC image repositories. A total of 25534 images of 200 patients were processed. The confusion matrix was generated by calculating Accuracy (ACC), Sensitivity (Sen) and Specificity (Sp). The Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUCs) were also plotted and used for evaluation. Metric results were ACC = 0.9950, Sen = 99.16% and Sp = 99.89%.A fines de 2019, surgió un nuevo tipo de coronavirus en China y se denominó SARS-CoV-2. Primero impactó en el país donde surgió y luego se extendió por todo el mundo. El SARS-CoV-2 es la causa de la enfermedad COVID-19 que deja impresiones características en las imágenes de TC de tórax de pacientes infectados. En este artículo, proponemos un modelo de clasificación, basado en CNN y transformada wavelet, para clasificar imágenes de pacientes con COVID-19. Se llamó WCNN-COVID. El modelo fue aplicado y probado en repositorios de imágenes TC abiertos y privados. Se procesaron 25534 imágenes de 200 pacientes. La matriz de confusión se generó calculando la Precisión (ACC), la Sensibilidad (Sen) y la Especificidad (Sp). La curva característica operativa del receptor (ROC) y el área bajo la curva (AUC) también se trazaron y utilizaron para la evaluación. Los resultados métricos fueron ACC = 0,9950, Sen = 99,16 % y Sp = 99,89 %.No final de 2019, um novo tipo de coronavírus surgiu na China e recebeu o nome de SARS-CoV-2. Primeiro impactou o país onde surgiu e depois se espalhou pelo mundo. O SARS-CoV-2 é a causa da doença COVID-19 que deixa impressões características nas imagens de TC de tórax dos pacientes infectados. Neste artigo, propomos um modelo de classificação, baseado em CNN e transformada wavelet, para classificar imagens de pacientes COVID-19. Ele foi denominado WCNN-COVID. O modelo foi aplicado e testado em repositórios de imagens de TC abertos e privados. Foram processadas 25534 imagens de 200 pacientes. A matriz de confusão foi gerada pelo cálculo de Acurácia (ACC), Sensibilidade (Sen) e Especificidade (Sp). A curva Receiver Operating Characteristic (ROC) e a Área Sob a Curva (AUCs) também foram plotadas e usadas para avaliação. Os resultados das métricas foram ACC = 0,9950, Sen = 99,16% e Sp = 99,89%.Research, Society and Development2022-03-28info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/2791910.33448/rsd-v11i5.27919Research, Society and Development; Vol. 11 No. 5; e2411527919Research, Society and Development; Vol. 11 Núm. 5; e2411527919Research, Society and Development; v. 11 n. 5; e24115279192525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIenghttps://rsdjournal.org/index.php/rsd/article/view/27919/24283Copyright (c) 2022 Pedro Moises de Sousa; Pedro Cunha Carneiro; Gabrielle Macedo Pereira; Mariane Modesto Oliveira; Carlos Aberto da Costa Junior; Luis Vinicius de Moura; Christian Mattjie; Ana Maria da Silva; Túlio Augusto Alves Macedo; Ana Claudia Patrociniohttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessSousa, Pedro Moises deCarneiro, Pedro CunhaPereira, Gabrielle MacedoOliveira, Mariane ModestoCosta Junior, Carlos Aberto daMoura, Luis Vinicius deMattjie, ChristianSilva, Ana Maria daMacedo, Túlio Augusto AlvesPatrocinio, Ana Claudia2022-04-17T18:18:56Zoai:ojs.pkp.sfu.ca:article/27919Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2024-01-17T09:45:29.963886Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
dc.title.none.fl_str_mv |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images Hacia un Modelo de Clasificación usando CNN y Wavelets aplicado a imágenes de TC de COVID-19 Por um modelo de classificação usando CNN e Wavelets aplicados a imagens de TC COVID-19 |
title |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
spellingShingle |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images Sousa, Pedro Moises de CT images Convolutional Neural Networks COVID-19 Wavelets WCN-COVID. Redes Neuronales Convolucionales COVID-19 Wavelets Imágenes de TC WCN-COVID. Redes Neurais Convolucionais COVID-19 Wavelets Imagens de TC WCNN-COVID. |
title_short |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
title_full |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
title_fullStr |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
title_full_unstemmed |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
title_sort |
Towards a Classification Model using CNN and Wavelets applied to COVID-19 CT images |
author |
Sousa, Pedro Moises de |
author_facet |
Sousa, Pedro Moises de Carneiro, Pedro Cunha Pereira, Gabrielle Macedo Oliveira, Mariane Modesto Costa Junior, Carlos Aberto da Moura, Luis Vinicius de Mattjie, Christian Silva, Ana Maria da Macedo, Túlio Augusto Alves Patrocinio, Ana Claudia |
author_role |
author |
author2 |
Carneiro, Pedro Cunha Pereira, Gabrielle Macedo Oliveira, Mariane Modesto Costa Junior, Carlos Aberto da Moura, Luis Vinicius de Mattjie, Christian Silva, Ana Maria da Macedo, Túlio Augusto Alves Patrocinio, Ana Claudia |
author2_role |
author author author author author author author author author |
dc.contributor.author.fl_str_mv |
Sousa, Pedro Moises de Carneiro, Pedro Cunha Pereira, Gabrielle Macedo Oliveira, Mariane Modesto Costa Junior, Carlos Aberto da Moura, Luis Vinicius de Mattjie, Christian Silva, Ana Maria da Macedo, Túlio Augusto Alves Patrocinio, Ana Claudia |
dc.subject.por.fl_str_mv |
CT images Convolutional Neural Networks COVID-19 Wavelets WCN-COVID. Redes Neuronales Convolucionales COVID-19 Wavelets Imágenes de TC WCN-COVID. Redes Neurais Convolucionais COVID-19 Wavelets Imagens de TC WCNN-COVID. |
topic |
CT images Convolutional Neural Networks COVID-19 Wavelets WCN-COVID. Redes Neuronales Convolucionales COVID-19 Wavelets Imágenes de TC WCN-COVID. Redes Neurais Convolucionais COVID-19 Wavelets Imagens de TC WCNN-COVID. |
description |
In late 2019, a new type of coronavirus emerged in China and was named SARS-CoV-2. It first impacted the country where it emerged and then spread around the world. SARS-CoV-2 is the cause of COVID-19 disease that leaves characteristic impressions on chest CT images of infected patients. In this article, we propose a classification model, based on CNN and wavelet transform, to classify images of COVID-19 patients. It was named WCNN-COVID. The model was applied and tested in open and private TC image repositories. A total of 25534 images of 200 patients were processed. The confusion matrix was generated by calculating Accuracy (ACC), Sensitivity (Sen) and Specificity (Sp). The Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUCs) were also plotted and used for evaluation. Metric results were ACC = 0.9950, Sen = 99.16% and Sp = 99.89%. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-03-28 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/27919 10.33448/rsd-v11i5.27919 |
url |
https://rsdjournal.org/index.php/rsd/article/view/27919 |
identifier_str_mv |
10.33448/rsd-v11i5.27919 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/27919/24283 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Research, Society and Development |
publisher.none.fl_str_mv |
Research, Society and Development |
dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 11 No. 5; e2411527919 Research, Society and Development; Vol. 11 Núm. 5; e2411527919 Research, Society and Development; v. 11 n. 5; e2411527919 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
instname_str |
Universidade Federal de Itajubá (UNIFEI) |
instacron_str |
UNIFEI |
institution |
UNIFEI |
reponame_str |
Research, Society and Development |
collection |
Research, Society and Development |
repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
repository.mail.fl_str_mv |
rsd.articles@gmail.com |
_version_ |
1797052708493983744 |