Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas
Збережено в:
| Автор: | |
|---|---|
| Дата публікації: | 2023 |
| Формат: | Doctoral thesis |
| Мова: | por |
| Джерело: | Repositório Institucional da UFG |
| Download full: | http://repositorio.bc.ufg.br/tede/handle/tede/13086 |
Резюме: | Pattern Recognition (PR) is a field of computer science that aims to develop techniques and algorithms capable of identifying regularities in complex data, enabling intelligent systems to perform complicated tasks with precision. In the context of diseases, PR plays a crucial role in diagnosis and detection, revealing patterns hidden from human eyes, assisting doctors in making decisions and identifying correlations. Infectious pulmonary diseases (IPD), such as pneumonia, tuberculosis, and COVID-19, challenge global public health, causing thousands of deaths annually, affecting healthcare systems, and demanding substantial financial resources. Diagnosing them can be challenging due to the vagueness of symptoms, similarities with other conditions, and subjectivity in clinical assessment. For instance, chest X-ray (CXR) examinations are a tedious and specialized process with significant variation among observers, leading to failures and delays in diagnosis and treatment, especially in underdeveloped countries with a scarcity of radiologists. In this thesis, we investigate PR and Artificial Intelligence (AI) techniques to support the diagnosis of IPID in CXRs. We follow the guidelines of the World Health Organization (WHO) to support the goals of the 2030 Agenda, which includes combating infectious diseases. The research questions involve selecting the best techniques, acquiring data, and creating intelligent models. As objectives, we propose low-cost, high-efficiency, and effective PR and AI methods that range from preprocessing to supporting the diagnosis of IPD in CXRs. The results so far align with the state of the art, and we believe they can contribute to the development of computer-assisted IPD diagnostic systems. |
| _version_ | 1871426434700935168 |
|---|---|
| author | Fonseca, Afonso Ueslei da |
| author_browse | Fonseca, Afonso Ueslei da |
| author_facet | Fonseca, Afonso Ueslei da |
| author_role | author |
| bitstream.checksum.fl_str_mv | 8a4605be74aa9ea9d79846c1fba20a33 4460e5956bc1d1639be9ae6146a50347 c74858bf984190ba1c5701d129c864dc |
| bitstream.checksumAlgorithm.fl_str_mv | MD5 MD5 MD5 |
| bitstream.url.fl_str_mv | http://repositorio.bc.ufg.br/tede/bitstreams/6bafb2b2-f2ec-44db-a049-4df12c179a2d/download http://repositorio.bc.ufg.br/tede/bitstreams/8012368d-f3cc-408b-bd3e-b38780c48908/download http://repositorio.bc.ufg.br/tede/bitstreams/ad1e8bcb-68c8-48ec-ac96-2c74c0bcc462/download |
| collection | Repositório Institucional da UFG |
| contributor_str_mv | Soares, Fabrízzio Alphonsus Alves de Melo Nunes Soares, Fabrízzio Alphonsus Alves de Melo Nunes Laureano, Gustavo Teodoro Pedrini, Hélio Rabahi, Marcelo Fouad Salvini, Rogerio Lopes |
| dc.contributor.advisor1.fl_str_mv | Soares, Fabrízzio Alphonsus Alves de Melo Nunes |
| dc.contributor.advisor1Lattes.fl_str_mv | http://lattes.cnpq.br/7206645857721831 |
| dc.contributor.author.fl_str_mv | Fonseca, Afonso Ueslei da |
| dc.contributor.authorLattes.fl_str_mv | http://lattes.cnpq.br/8486633197834367 |
| dc.contributor.referee1.fl_str_mv | Soares, Fabrízzio Alphonsus Alves de Melo Nunes |
| dc.contributor.referee2.fl_str_mv | Laureano, Gustavo Teodoro |
| dc.contributor.referee3.fl_str_mv | Pedrini, Hélio |
| dc.contributor.referee4.fl_str_mv | Rabahi, Marcelo Fouad |
| dc.contributor.referee5.fl_str_mv | Salvini, Rogerio Lopes |
| dc.date.accessioned.fl_str_mv | 2023-10-25T15:25:19Z |
| dc.date.available.fl_str_mv | 2023-10-25T15:25:19Z |
| dc.date.issued.fl_str_mv | 2023-09-29 |
| dc.identifier.citation.fl_str_mv | FONSECA, A. U. Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas. 2023. 183 f. Tese (Doutorado em Ciência da Computação) - Instituto de Informática, Universidade Federal de Goiás, Goiânia, 2023. |
| dc.identifier.uri.fl_str_mv | http://repositorio.bc.ufg.br/tede/handle/tede/13086 |
| dc.language.iso.fl_str_mv | por |
| dc.publisher.country.fl_str_mv | Brasil |
| dc.publisher.department.fl_str_mv | Instituto de Informática - INF (RMG) |
| dc.publisher.initials.fl_str_mv | UFG |
| dc.publisher.none.fl_str_mv | Universidade Federal de Goiás |
| dc.publisher.program.fl_str_mv | Programa de Pós-graduação em Ciência da Computação (INF) |
| dc.rights.driver.fl_str_mv | Attribution-NonCommercial-NoDerivatives 4.0 International info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:Repositório Institucional da UFG instname:Universidade Federal de Goiás (UFG) instacron:UFG |
| dc.subject.cnpq.fl_str_mv | CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
| dc.subject.eng.fl_str_mv | Pattern recognition Chest radiography Infectious pulmonary diseases Diagnostic support Artificial intelligence Machine learning |
| dc.subject.por.fl_str_mv | Reconhecimento de padrões Radiografia de tórax Doenças pulmonares infecciosas Suporte ao diagnóstico Inteligência artificial Aprendizagem de máquina |
| dc.title.alternative.eng.fl_str_mv | Pattern recognition in chest X-ray images: supporting the diagnosis of infectious lung diseases |
| dc.title.none.fl_str_mv | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| dc.type.driver.fl_str_mv | info:eu-repo/semantics/doctoralThesis |
| dc.type.status.fl_str_mv | info:eu-repo/semantics/publishedVersion |
| description | Pattern Recognition (PR) is a field of computer science that aims to develop techniques and algorithms capable of identifying regularities in complex data, enabling intelligent systems to perform complicated tasks with precision. In the context of diseases, PR plays a crucial role in diagnosis and detection, revealing patterns hidden from human eyes, assisting doctors in making decisions and identifying correlations. Infectious pulmonary diseases (IPD), such as pneumonia, tuberculosis, and COVID-19, challenge global public health, causing thousands of deaths annually, affecting healthcare systems, and demanding substantial financial resources. Diagnosing them can be challenging due to the vagueness of symptoms, similarities with other conditions, and subjectivity in clinical assessment. For instance, chest X-ray (CXR) examinations are a tedious and specialized process with significant variation among observers, leading to failures and delays in diagnosis and treatment, especially in underdeveloped countries with a scarcity of radiologists. In this thesis, we investigate PR and Artificial Intelligence (AI) techniques to support the diagnosis of IPID in CXRs. We follow the guidelines of the World Health Organization (WHO) to support the goals of the 2030 Agenda, which includes combating infectious diseases. The research questions involve selecting the best techniques, acquiring data, and creating intelligent models. As objectives, we propose low-cost, high-efficiency, and effective PR and AI methods that range from preprocessing to supporting the diagnosis of IPD in CXRs. The results so far align with the state of the art, and we believe they can contribute to the development of computer-assisted IPD diagnostic systems. |
| eu_rights_str_mv | openAccess |
| format | doctoralThesis |
| id | UFG-2_f85fe9b72ae60e5efbbb36f5f3a45de2 |
| identifier_str_mv | FONSECA, A. U. Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas. 2023. 183 f. Tese (Doutorado em Ciência da Computação) - Instituto de Informática, Universidade Federal de Goiás, Goiânia, 2023. |
| instacron_str | UFG |
| institution | UFG |
| instname_str | Universidade Federal de Goiás (UFG) |
| language | por |
| network_acronym_str | UFG-2 |
| network_name_str | Repositório Institucional da UFG |
| oai_identifier_str | oai:repositorio.bc.ufg.br:tede/13086 |
| publishDate | 2023 |
| publishDateSort | 2023 |
| publisher.none.fl_str_mv | Universidade Federal de Goiás |
| reponame_str | Repositório Institucional da UFG |
| repository.mail.fl_str_mv | grt.bc@ufg.br |
| repository.name.fl_str_mv | Repositório Institucional da UFG - Universidade Federal de Goiás (UFG) |
| repository_id_str | oai:repositorio.bc.ufg.br:tede/1234 |
| rights_invalid_str_mv | Attribution-NonCommercial-NoDerivatives 4.0 International |
| spelling | Soares, Fabrízzio Alphonsus Alves de Melo Nuneshttp://lattes.cnpq.br/7206645857721831Soares, Fabrízzio Alphonsus Alves de Melo NunesLaureano, Gustavo TeodoroPedrini, HélioRabahi, Marcelo FouadSalvini, Rogerio Lopeshttp://lattes.cnpq.br/8486633197834367Fonseca, Afonso Ueslei da2023-10-25T15:25:19Z2023-10-25T15:25:19Z2023-09-29FONSECA, A. U. Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas. 2023. 183 f. Tese (Doutorado em Ciência da Computação) - Instituto de Informática, Universidade Federal de Goiás, Goiânia, 2023.http://repositorio.bc.ufg.br/tede/handle/tede/13086Pattern Recognition (PR) is a field of computer science that aims to develop techniques and algorithms capable of identifying regularities in complex data, enabling intelligent systems to perform complicated tasks with precision. In the context of diseases, PR plays a crucial role in diagnosis and detection, revealing patterns hidden from human eyes, assisting doctors in making decisions and identifying correlations. Infectious pulmonary diseases (IPD), such as pneumonia, tuberculosis, and COVID-19, challenge global public health, causing thousands of deaths annually, affecting healthcare systems, and demanding substantial financial resources. Diagnosing them can be challenging due to the vagueness of symptoms, similarities with other conditions, and subjectivity in clinical assessment. For instance, chest X-ray (CXR) examinations are a tedious and specialized process with significant variation among observers, leading to failures and delays in diagnosis and treatment, especially in underdeveloped countries with a scarcity of radiologists. In this thesis, we investigate PR and Artificial Intelligence (AI) techniques to support the diagnosis of IPID in CXRs. We follow the guidelines of the World Health Organization (WHO) to support the goals of the 2030 Agenda, which includes combating infectious diseases. The research questions involve selecting the best techniques, acquiring data, and creating intelligent models. As objectives, we propose low-cost, high-efficiency, and effective PR and AI methods that range from preprocessing to supporting the diagnosis of IPD in CXRs. The results so far align with the state of the art, and we believe they can contribute to the development of computer-assisted IPD diagnostic systems.Reconhecimento de Padrões (RP) é uma área da computação que visa desenvolver técnicas e algoritmos capazes de identificar regularidades em dados complexos, permitindo sistemas inteligentes realizar tarefas difíceis com precisão. No contexto de doenças, RP tem papel crucial no diagnóstico e detecção, revelando padrões ocultos aos olhos humanos, ajudando médicos a tomar decisões e identificar correlações. Doenças pulmonares infecciosas (DPI), como pneumonia, tuberculose e COVID-19, são um desafio à saúde pública global, causam milhares de mortes anualmente, afetam sistemas de saúde e demandam vultuosos recursos financeiros. Diagnosticálas pode ser desafiador devido à vaguidade dos sintomas, à semelhança com outras condições e à subjetividade da avaliação clínica. Por exemplo, nos exames de radiografia do tórax (RXT), é um processo tedioso, especializado e com grande variação entre observadores, levando a falhas e retardo no diagnóstico e tratamento, especialmente em países subdesenvolvidos e com escassez de radiologistas. Nesta tese, investigamos técnicas de RP e Inteligência Artificial (IA) para apoiar o diagnóstico de DPI em RXT. Seguimos as diretrizes da Organização Mundial da Saúde (OMS) para apoiar as metas da Agenda 2030, que incluem o combate a doenças transmissíveis. As questões de pesquisa envolvem selecionar as melhores técnicas, adquirir dados e criar modelos inteligentes. Como objetivos, propomos métodos de RP e IA de baixo custo, alta eficiência e eficácia que vão desde o pré-processamento até o suporte ao diagnóstico de DPI em RXT. Os resultados até aqui mostram-se em linha com estado da arte, e acreditamos que podem contribuir com o desenvolvimento dos sistemas de diagnóstico de DPI assistidos por computador.porUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RMG)Attribution-NonCommercial-NoDerivatives 4.0 Internationalinfo:eu-repo/semantics/openAccessReconhecimento de padrõesRadiografia de tóraxDoenças pulmonares infecciosasSuporte ao diagnósticoInteligência artificialAprendizagem de máquinaPattern recognitionChest radiographyInfectious pulmonary diseasesDiagnostic supportArtificial intelligenceMachine learningCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOReconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosasPattern recognition in chest X-ray images: supporting the diagnosis of infectious lung diseasesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisreponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGLICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://repositorio.bc.ufg.br/tede/bitstreams/6bafb2b2-f2ec-44db-a049-4df12c179a2d/download8a4605be74aa9ea9d79846c1fba20a33MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805http://repositorio.bc.ufg.br/tede/bitstreams/8012368d-f3cc-408b-bd3e-b38780c48908/download4460e5956bc1d1639be9ae6146a50347MD52ORIGINALTese - Afonso Ueslei da Fonseca - 2023.pdfTese - Afonso Ueslei da Fonseca - 2023.pdfapplication/pdf57493753http://repositorio.bc.ufg.br/tede/bitstreams/ad1e8bcb-68c8-48ec-ac96-2c74c0bcc462/downloadc74858bf984190ba1c5701d129c864dcMD53tede/130862023-10-25 12:25:19.169http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accessoai:repositorio.bc.ufg.br:tede/13086http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttps://repositorio.bc.ufg.br/tedeserver/oai/requestgrt.bc@ufg.bropendoar:oai:repositorio.bc.ufg.br:tede/12342023-10-25T15:25:19Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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 |
| spellingShingle | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas Fonseca, Afonso Ueslei da Reconhecimento de padrões Radiografia de tórax Doenças pulmonares infecciosas Suporte ao diagnóstico Inteligência artificial Aprendizagem de máquina Pattern recognition Chest radiography Infectious pulmonary diseases Diagnostic support Artificial intelligence Machine learning CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
| status_str | publishedVersion |
| title | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| title_full | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| title_fullStr | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| title_full_unstemmed | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| title_short | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| title_sort | Reconhecimento de padrões em imagens radiográficas de tórax: apoiando o diagnóstico de doenças pulmonares infecciosas |
| topic | Reconhecimento de padrões Radiografia de tórax Doenças pulmonares infecciosas Suporte ao diagnóstico Inteligência artificial Aprendizagem de máquina Pattern recognition Chest radiography Infectious pulmonary diseases Diagnostic support Artificial intelligence Machine learning CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
| url | http://repositorio.bc.ufg.br/tede/handle/tede/13086 |