Cargando…

Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases

As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based meth...

Descripción completa

Detalles Bibliográficos
Autores principales: Maior, Caio B. S., Santana, João M. M., Lins, Isis D., Moura, Márcio J. C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7920391/
https://www.ncbi.nlm.nih.gov/pubmed/33647062
http://dx.doi.org/10.1371/journal.pone.0247839
_version_ 1783658266884046848
author Maior, Caio B. S.
Santana, João M. M.
Lins, Isis D.
Moura, Márcio J. C.
author_facet Maior, Caio B. S.
Santana, João M. M.
Lins, Isis D.
Moura, Márcio J. C.
author_sort Maior, Caio B. S.
collection PubMed
description As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based method to support COVID-19 diagnosis using convolutional neural networks (CNN). Because the availability of radiological data is rather limited due to the novelty of COVID-19, several methodologies consider reduced datasets, which may be inadequate, biasing the model. Here, we performed an analysis combining six different databases using chest X-ray images from open datasets to distinguish images of infected patients while differentiating COVID-19 and pneumonia from ‘no-findings’ images. In addition, the performance of models created from fewer databases, which may imperceptibly overestimate their results, is discussed. Two CNN-based architectures were created to process images of different sizes (512 × 512, 768 × 768, 1024 × 1024, and 1536 × 1536). Our best model achieved a balanced accuracy (BA) of 87.7% in predicting one of the three classes (‘no-findings’, ‘COVID-19’, and ‘pneumonia’) and a specific balanced precision of 97.0% for ‘COVID-19’ class. We also provided binary classification with a precision of 91.0% for detection of sick patients (i.e., with COVID-19 or pneumonia) and 98.4% for COVID-19 detection (i.e., differentiating from ‘no-findings’ or ‘pneumonia’). Indeed, despite we achieved an unrealistic 97.2% BA performance for one specific case, the proposed methodology of using multiple databases achieved better and less inflated results than from models with specific image datasets for training. Thus, this framework is promising for a low-cost, fast, and noninvasive means to support the diagnosis of COVID-19.
format Online
Article
Text
id pubmed-7920391
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-79203912021-03-09 Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases Maior, Caio B. S. Santana, João M. M. Lins, Isis D. Moura, Márcio J. C. PLoS One Research Article As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based method to support COVID-19 diagnosis using convolutional neural networks (CNN). Because the availability of radiological data is rather limited due to the novelty of COVID-19, several methodologies consider reduced datasets, which may be inadequate, biasing the model. Here, we performed an analysis combining six different databases using chest X-ray images from open datasets to distinguish images of infected patients while differentiating COVID-19 and pneumonia from ‘no-findings’ images. In addition, the performance of models created from fewer databases, which may imperceptibly overestimate their results, is discussed. Two CNN-based architectures were created to process images of different sizes (512 × 512, 768 × 768, 1024 × 1024, and 1536 × 1536). Our best model achieved a balanced accuracy (BA) of 87.7% in predicting one of the three classes (‘no-findings’, ‘COVID-19’, and ‘pneumonia’) and a specific balanced precision of 97.0% for ‘COVID-19’ class. We also provided binary classification with a precision of 91.0% for detection of sick patients (i.e., with COVID-19 or pneumonia) and 98.4% for COVID-19 detection (i.e., differentiating from ‘no-findings’ or ‘pneumonia’). Indeed, despite we achieved an unrealistic 97.2% BA performance for one specific case, the proposed methodology of using multiple databases achieved better and less inflated results than from models with specific image datasets for training. Thus, this framework is promising for a low-cost, fast, and noninvasive means to support the diagnosis of COVID-19. Public Library of Science 2021-03-01 /pmc/articles/PMC7920391/ /pubmed/33647062 http://dx.doi.org/10.1371/journal.pone.0247839 Text en © 2021 Maior et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Maior, Caio B. S.
Santana, João M. M.
Lins, Isis D.
Moura, Márcio J. C.
Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title_full Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title_fullStr Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title_full_unstemmed Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title_short Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases
title_sort convolutional neural network model based on radiological images to support covid-19 diagnosis: evaluating database biases
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7920391/
https://www.ncbi.nlm.nih.gov/pubmed/33647062
http://dx.doi.org/10.1371/journal.pone.0247839
work_keys_str_mv AT maiorcaiobs convolutionalneuralnetworkmodelbasedonradiologicalimagestosupportcovid19diagnosisevaluatingdatabasebiases
AT santanajoaomm convolutionalneuralnetworkmodelbasedonradiologicalimagestosupportcovid19diagnosisevaluatingdatabasebiases
AT linsisisd convolutionalneuralnetworkmodelbasedonradiologicalimagestosupportcovid19diagnosisevaluatingdatabasebiases
AT mouramarciojc convolutionalneuralnetworkmodelbasedonradiologicalimagestosupportcovid19diagnosisevaluatingdatabasebiases