Does Two-Class Training Extract Real Features? A COVID-19 Case Study

Diagnosis aid systems that use image analysis are currently very useful due to the large workload of health professionals involved in making diagnoses. In recent years, Convolutional Neural Networks (CNNs) have been used to help in these tasks. For this reason, multiple studies that analyze the dete...

Descripción completa

Detalles Bibliográficos
Autores: Muñoz Saavedra, Luis, Civit Masot, Javier, Luna Perejón, Francisco, Domínguez Morales, Manuel Jesús, Civit Balcells, Antón
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/104932
Acceso en línea:https://hdl.handle.net/11441/104932
https://doi.org/10.3390/app11041424
Access Level:acceso abierto
Palabra clave:COVID-19
Pandemic
Deep learning
Neural networks
X-ray
Medical images
id ES_4da5f582bdf310ff44ac68b60efced0e
oai_identifier_str oai:idus.us.es:11441/104932
network_acronym_str ES
network_name_str España
repository_id_str
spelling Does Two-Class Training Extract Real Features? A COVID-19 Case StudyMuñoz Saavedra, LuisCivit Masot, JavierLuna Perejón, FranciscoDomínguez Morales, Manuel JesúsCivit Balcells, AntónCOVID-19PandemicDeep learningNeural networksX-rayMedical imagesDiagnosis aid systems that use image analysis are currently very useful due to the large workload of health professionals involved in making diagnoses. In recent years, Convolutional Neural Networks (CNNs) have been used to help in these tasks. For this reason, multiple studies that analyze the detection precision for several diseases have been developed. However, many of these works distinguish between only two classes: healthy and with a specific disease. Based on this premise, in this work, we try to answer the questions: When training an image classification system with only two classes (healthy and sick), does this system extract the specific features of this disease, or does it only obtain the features that differentiate it from a healthy patient? Trying to answer these questions, we analyze the particular case of COVID-19 detection. Many works that classify this disease using X-ray images have been published; some of them use two classes (with and without COVID-19), while others include more classes (pneumonia, SARS, influenza, etc.). In this work, we carry out several classification studies with two classes, using test images that do not belong to those classes, in order to try to answer the previous questions. The first studies indicate problems in these two-class systems when using a third class as a test, being classified inconsistently. Deeper studies show that deep learning systems trained with two classes do not correctly extract the characteristics of pathologies, but rather differentiate the classes based on the physical characteristics of the images. After the discussion, we conclude that these two-class trained deep learning systems are not valid if there are other diseases that cause similar symptoms.Junta de Andalucía and FEDER research project MSF-PHIA (US-1263715)MDPIArquitectura y Tecnología de ComputadoresTEP108: Robótica y Tecnología de ComputadoresTelefónica Chair “Intelligence in Network”2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/104932https://doi.org/10.3390/app11041424reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésApplied Sciences, 11 (4), 1424-.MSF-PHIA (US-1263715)https://www.mdpi.com/2076-3417/11/4/1424info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1049322026-06-17T12:51:07Z
dc.title.none.fl_str_mv Does Two-Class Training Extract Real Features? A COVID-19 Case Study
title Does Two-Class Training Extract Real Features? A COVID-19 Case Study
spellingShingle Does Two-Class Training Extract Real Features? A COVID-19 Case Study
Muñoz Saavedra, Luis
COVID-19
Pandemic
Deep learning
Neural networks
X-ray
Medical images
title_short Does Two-Class Training Extract Real Features? A COVID-19 Case Study
title_full Does Two-Class Training Extract Real Features? A COVID-19 Case Study
title_fullStr Does Two-Class Training Extract Real Features? A COVID-19 Case Study
title_full_unstemmed Does Two-Class Training Extract Real Features? A COVID-19 Case Study
title_sort Does Two-Class Training Extract Real Features? A COVID-19 Case Study
dc.creator.none.fl_str_mv Muñoz Saavedra, Luis
Civit Masot, Javier
Luna Perejón, Francisco
Domínguez Morales, Manuel Jesús
Civit Balcells, Antón
author Muñoz Saavedra, Luis
author_facet Muñoz Saavedra, Luis
Civit Masot, Javier
Luna Perejón, Francisco
Domínguez Morales, Manuel Jesús
Civit Balcells, Antón
author_role author
author2 Civit Masot, Javier
Luna Perejón, Francisco
Domínguez Morales, Manuel Jesús
Civit Balcells, Antón
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Arquitectura y Tecnología de Computadores
TEP108: Robótica y Tecnología de Computadores
Telefónica Chair “Intelligence in Network”
dc.subject.none.fl_str_mv COVID-19
Pandemic
Deep learning
Neural networks
X-ray
Medical images
topic COVID-19
Pandemic
Deep learning
Neural networks
X-ray
Medical images
description Diagnosis aid systems that use image analysis are currently very useful due to the large workload of health professionals involved in making diagnoses. In recent years, Convolutional Neural Networks (CNNs) have been used to help in these tasks. For this reason, multiple studies that analyze the detection precision for several diseases have been developed. However, many of these works distinguish between only two classes: healthy and with a specific disease. Based on this premise, in this work, we try to answer the questions: When training an image classification system with only two classes (healthy and sick), does this system extract the specific features of this disease, or does it only obtain the features that differentiate it from a healthy patient? Trying to answer these questions, we analyze the particular case of COVID-19 detection. Many works that classify this disease using X-ray images have been published; some of them use two classes (with and without COVID-19), while others include more classes (pneumonia, SARS, influenza, etc.). In this work, we carry out several classification studies with two classes, using test images that do not belong to those classes, in order to try to answer the previous questions. The first studies indicate problems in these two-class systems when using a third class as a test, being classified inconsistently. Deeper studies show that deep learning systems trained with two classes do not correctly extract the characteristics of pathologies, but rather differentiate the classes based on the physical characteristics of the images. After the discussion, we conclude that these two-class trained deep learning systems are not valid if there are other diseases that cause similar symptoms.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/104932
https://doi.org/10.3390/app11041424
url https://hdl.handle.net/11441/104932
https://doi.org/10.3390/app11041424
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Applied Sciences, 11 (4), 1424-.
MSF-PHIA (US-1263715)
https://www.mdpi.com/2076-3417/11/4/1424
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407705473482752
score 15.300724

Similares en LA Referencia