Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images

Covid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China in late 2019 and swiftly spreading globally. Since the virus primarily impacts the lungs, analyzing chest X-rays stands as a reliable and widely accessible means of diagnosing the infection. In computer vision...

ver descrição completa

Detalhes bibliográficos
Autores: Roberto, Guilherme F., Pereira, Danilo C., Martins, Alessandro S., Tosta, Thaína A.A., Soares, Carlos, Lumini, Alessandra, Rozendo, Guilherme B. [UNESP], Neves, Leandro A. [UNESP], Nascimento, Marcelo Z.
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:Brasil
Recursos:Universidade Estadual Paulista (UNESP)
Repositorio:Repositório Institucional da UNESP
Idioma:inglés
OAI Identifier:oai:repositorio.unesp.br:11449/309198
Acesso em linha:http://dx.doi.org/10.1016/j.patrec.2024.07.022
https://hdl.handle.net/11449/309198
Access Level:acceso abierto
Palavra-chave:Chest X-ray images
Computer vision
Covid-19
Handcrafted features
Percolation
id BR_4fdda4e1e3107a29ec943fa8eb5f8ecb
oai_identifier_str oai:repositorio.unesp.br:11449/309198
network_acronym_str BR
network_name_str Brasil
repository_id_str
dc.title.none.fl_str_mv Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
title Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
spellingShingle Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
Roberto, Guilherme F.
Chest X-ray images
Computer vision
Covid-19
Handcrafted features
Percolation
title_short Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
title_full Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
title_fullStr Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
title_full_unstemmed Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
title_sort Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images
dc.creator.none.fl_str_mv Roberto, Guilherme F.
Pereira, Danilo C.
Martins, Alessandro S.
Tosta, Thaína A.A.
Soares, Carlos
Lumini, Alessandra
Rozendo, Guilherme B. [UNESP]
Neves, Leandro A. [UNESP]
Nascimento, Marcelo Z.
author Roberto, Guilherme F.
author_facet Roberto, Guilherme F.
Pereira, Danilo C.
Martins, Alessandro S.
Tosta, Thaína A.A.
Soares, Carlos
Lumini, Alessandra
Rozendo, Guilherme B. [UNESP]
Neves, Leandro A. [UNESP]
Nascimento, Marcelo Z.
author_role author
author2 Pereira, Danilo C.
Martins, Alessandro S.
Tosta, Thaína A.A.
Soares, Carlos
Lumini, Alessandra
Rozendo, Guilherme B. [UNESP]
Neves, Leandro A. [UNESP]
Nascimento, Marcelo Z.
author2_role author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv University of Porto (FEUP)
Science and Technology of São Paulo (IFSP)
Universidade de São Paulo (USP)
University of Bologna
Universidade Estadual Paulista (UNESP)
Universidade Federal de Uberlândia (UFU)
dc.subject.por.fl_str_mv Chest X-ray images
Computer vision
Covid-19
Handcrafted features
Percolation
topic Chest X-ray images
Computer vision
Covid-19
Handcrafted features
Percolation
description Covid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China in late 2019 and swiftly spreading globally. Since the virus primarily impacts the lungs, analyzing chest X-rays stands as a reliable and widely accessible means of diagnosing the infection. In computer vision, deep learning models such as CNNs have been the main adopted approach for detection of Covid-19 in chest X-ray images. However, we believe that handcrafted features can also provide relevant results, as shown previously in similar image classification challenges. In this study, we propose a method for identifying Covid-19 in chest X-ray images by extracting and classifying local and global percolation-based features. This technique was tested on three datasets: one comprising 2,002 segmented samples categorized into two groups (Covid-19 and Healthy); another with 1,125 non-segmented samples categorized into three groups (Covid-19, Healthy, and Pneumonia); and a third one composed of 4,809 non-segmented images representing three classes (Covid-19, Healthy, and Pneumonia). Then, 48 percolation features were extracted and give as input into six distinct classifiers. Subsequently, the AUC and accuracy metrics were assessed. We used the 10-fold cross-validation approach and evaluated lesion sub-types via binary and multiclass classification using the Hermite polynomial classifier, a novel approach in this domain. The Hermite polynomial classifier exhibited the most promising outcomes compared to five other machine learning algorithms, wherein the best obtained values for accuracy and AUC were 98.72% and 0.9917, respectively. We also evaluated the influence of noise in the features and in the classification accuracy. These results, based in the integration of percolation features with the Hermite polynomial, hold the potential for enhancing lesion detection and supporting clinicians in their diagnostic endeavors.
publishDate 2025
dc.date.none.fl_str_mv 2025-04-29T20:14:37Z
2025-03-01
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/10.1016/j.patrec.2024.07.022
Pattern Recognition Letters, v. 189, p. 248-255.
0167-8655
https://hdl.handle.net/11449/309198
10.1016/j.patrec.2024.07.022
2-s2.0-85201392255
url http://dx.doi.org/10.1016/j.patrec.2024.07.022
https://hdl.handle.net/11449/309198
identifier_str_mv Pattern Recognition Letters, v. 189, p. 248-255.
0167-8655
10.1016/j.patrec.2024.07.022
2-s2.0-85201392255
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Pattern Recognition Letters
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 248-255
dc.source.none.fl_str_mv Scopus
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 repositoriounesp@unesp.br
_version_ 1853672144656924672
spelling Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray imagesChest X-ray imagesComputer visionCovid-19Handcrafted featuresPercolationCovid-19 is a severe illness caused by the Sars-CoV-2 virus, initially identified in China in late 2019 and swiftly spreading globally. Since the virus primarily impacts the lungs, analyzing chest X-rays stands as a reliable and widely accessible means of diagnosing the infection. In computer vision, deep learning models such as CNNs have been the main adopted approach for detection of Covid-19 in chest X-ray images. However, we believe that handcrafted features can also provide relevant results, as shown previously in similar image classification challenges. In this study, we propose a method for identifying Covid-19 in chest X-ray images by extracting and classifying local and global percolation-based features. This technique was tested on three datasets: one comprising 2,002 segmented samples categorized into two groups (Covid-19 and Healthy); another with 1,125 non-segmented samples categorized into three groups (Covid-19, Healthy, and Pneumonia); and a third one composed of 4,809 non-segmented images representing three classes (Covid-19, Healthy, and Pneumonia). Then, 48 percolation features were extracted and give as input into six distinct classifiers. Subsequently, the AUC and accuracy metrics were assessed. We used the 10-fold cross-validation approach and evaluated lesion sub-types via binary and multiclass classification using the Hermite polynomial classifier, a novel approach in this domain. The Hermite polynomial classifier exhibited the most promising outcomes compared to five other machine learning algorithms, wherein the best obtained values for accuracy and AUC were 98.72% and 0.9917, respectively. We also evaluated the influence of noise in the features and in the classification accuracy. These results, based in the integration of percolation features with the Hermite polynomial, hold the potential for enhancing lesion detection and supporting clinicians in their diagnostic endeavors.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)Faculty of Engineering University of Porto (FEUP)Federal Institute of Education Science and Technology of São Paulo (IFSP), SPScience and Technology Institute Federal University of São Paulo (UNIFESP), SPDepartment of Computer Science and Engineering (DISI) University of Bologna, FCDepartment of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), SPFaculty of Computer Science (FACOM) Federal University of Uberlândia (UFU), MGDepartment of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), SPCNPq: #132940/2019-1FAPESP: #2022/03020-1CNPq: #311404/2021-9CNPq: #313643/2021-0FAPEMIG: #APQ-00578-18FAPEMIG: #APQ-01129-21University of Porto (FEUP)Science and Technology of São Paulo (IFSP)Universidade de São Paulo (USP)University of BolognaUniversidade Estadual Paulista (UNESP)Universidade Federal de Uberlândia (UFU)2025-04-29T20:14:37Z2025-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article248-255http://dx.doi.org/10.1016/j.patrec.2024.07.022Pattern Recognition Letters, v. 189, p. 248-255.0167-8655https://hdl.handle.net/11449/30919810.1016/j.patrec.2024.07.0222-s2.0-85201392255Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPattern Recognition Lettersinfo:eu-repo/semantics/openAccessRoberto, Guilherme F.Pereira, Danilo C.Martins, Alessandro S.Tosta, Thaína A.A.Soares, CarlosLumini, AlessandraRozendo, Guilherme B. [UNESP]Neves, Leandro A. [UNESP]Nascimento, Marcelo Z.2025-04-30T14:00:42Zoai:repositorio.unesp.br:11449/309198Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462025-04-30T14:00:42Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
score 15.301629

Registos relacionados