Classification of aortic stenosis based on AI in MRI scans
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/31135 |
Resumo: | Aortic stenosis (AS) stands as a significant cardiovascular ailment necessitating accurate diagnosis for effective patient management. This study introduces an innovative AI-based approach for AS detection in MRI scans. Our research aims to find a robust CNN model combined with computer vision techniques for the classification of AS in MRI, further refined through fine tuning. We evaluated five CNN models combined with computer vision techniques, where VGG16 model got the best results in our research work, with 95% in recall and 95% in F1-score. In this test four Data Augmentation techniques were implemented including Translation, Rotation, Flip and Brightness, enhancing the model’s robustness and generalization, encompassing real-world image variations encountered in clinical settings. This validation reaffirms the model's clinical applicability, promising streamlined diagnostics while allowing medical professionals to focus on intricate decision-making and personalized care. In conclusion, our study underscores the potential of AI-driven AS detection in MRI. The merger of transfer learning and data augmentation yields high accuracy rates, validated in real clinical cases, signifying a significant advancement in precise cardiovascular diagnosis. |
id |
RCAP_5e6c7dea49ace7f2b5e77b72d8ff7daf |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/31135 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Classification of aortic stenosis based on AI in MRI scansMRI imaging techniquesAortic disease classificationInteligência artificial -- Artificial intelligenceDeep learningTécnicas de imagem por RMClassificação de doenças da aortaAortic stenosis (AS) stands as a significant cardiovascular ailment necessitating accurate diagnosis for effective patient management. This study introduces an innovative AI-based approach for AS detection in MRI scans. Our research aims to find a robust CNN model combined with computer vision techniques for the classification of AS in MRI, further refined through fine tuning. We evaluated five CNN models combined with computer vision techniques, where VGG16 model got the best results in our research work, with 95% in recall and 95% in F1-score. In this test four Data Augmentation techniques were implemented including Translation, Rotation, Flip and Brightness, enhancing the model’s robustness and generalization, encompassing real-world image variations encountered in clinical settings. This validation reaffirms the model's clinical applicability, promising streamlined diagnostics while allowing medical professionals to focus on intricate decision-making and personalized care. In conclusion, our study underscores the potential of AI-driven AS detection in MRI. The merger of transfer learning and data augmentation yields high accuracy rates, validated in real clinical cases, signifying a significant advancement in precise cardiovascular diagnosis.A estenose aórtica (EA) é uma doença cardiovascular significativa, que requer um diagnóstico exato para uma gestão eficaz dos doentes. Este estudo apresenta uma abordagem inovadora baseada em IA para a deteção de EA em exames de RM. A nossa investigação tem como objetivo encontrar um modelo CNN robusto, combinado com técnicas de visão por computador, para a classificação de EA em RM, aperfeiçoado através de Fine Tuning. Avaliámos cinco modelos CNN combinados com técnicas de visão computacional, tendo o modelo VGG16 obtido os melhores resultados no nosso trabalho de investigação, com 95% de recall e 95% de F1-Score. Neste teste foram implementadas quatro técnicas de Data Augmentation, incluindo Translação, Rotação, Inverter e Brilho, aumentando a robustez e a generalização do modelo, abrangendo variações de imagens do mundo real encontradas em ambientes clínicos. Esta validação reafirma a aplicabilidade clínica do modelo, prometendo diagnósticos simplificados e permitindo que os profissionais médicos se concentrem na tomada de decisões complexas e nos cuidados personalizados. Em conclusão, nosso estudo ressalta o potencial da deteção de EA orientada por IA em RM. A fusão de aprendizagem por transferência e aumento de dados produz taxas de precisão elevadas, validadas em casos clínicos reais, significando um avanço significativo no diagnóstico cardiovascular preciso.2025-06-11T00:00:00Z2023-12-11T00:00:00Z2023-12-112023-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/31135TID:203441826engÁguas, Pedro Miguel Ferreira Viegasinfo:eu-repo/semantics/embargoedAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-25T01:19:14Zoai:repositorio.iscte-iul.pt:10071/31135Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:11:21.931824Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Classification of aortic stenosis based on AI in MRI scans |
title |
Classification of aortic stenosis based on AI in MRI scans |
spellingShingle |
Classification of aortic stenosis based on AI in MRI scans Águas, Pedro Miguel Ferreira Viegas MRI imaging techniques Aortic disease classification Inteligência artificial -- Artificial intelligence Deep learning Técnicas de imagem por RM Classificação de doenças da aorta |
title_short |
Classification of aortic stenosis based on AI in MRI scans |
title_full |
Classification of aortic stenosis based on AI in MRI scans |
title_fullStr |
Classification of aortic stenosis based on AI in MRI scans |
title_full_unstemmed |
Classification of aortic stenosis based on AI in MRI scans |
title_sort |
Classification of aortic stenosis based on AI in MRI scans |
author |
Águas, Pedro Miguel Ferreira Viegas |
author_facet |
Águas, Pedro Miguel Ferreira Viegas |
author_role |
author |
dc.contributor.author.fl_str_mv |
Águas, Pedro Miguel Ferreira Viegas |
dc.subject.por.fl_str_mv |
MRI imaging techniques Aortic disease classification Inteligência artificial -- Artificial intelligence Deep learning Técnicas de imagem por RM Classificação de doenças da aorta |
topic |
MRI imaging techniques Aortic disease classification Inteligência artificial -- Artificial intelligence Deep learning Técnicas de imagem por RM Classificação de doenças da aorta |
description |
Aortic stenosis (AS) stands as a significant cardiovascular ailment necessitating accurate diagnosis for effective patient management. This study introduces an innovative AI-based approach for AS detection in MRI scans. Our research aims to find a robust CNN model combined with computer vision techniques for the classification of AS in MRI, further refined through fine tuning. We evaluated five CNN models combined with computer vision techniques, where VGG16 model got the best results in our research work, with 95% in recall and 95% in F1-score. In this test four Data Augmentation techniques were implemented including Translation, Rotation, Flip and Brightness, enhancing the model’s robustness and generalization, encompassing real-world image variations encountered in clinical settings. This validation reaffirms the model's clinical applicability, promising streamlined diagnostics while allowing medical professionals to focus on intricate decision-making and personalized care. In conclusion, our study underscores the potential of AI-driven AS detection in MRI. The merger of transfer learning and data augmentation yields high accuracy rates, validated in real clinical cases, signifying a significant advancement in precise cardiovascular diagnosis. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-12-11T00:00:00Z 2023-12-11 2023-10 2025-06-11T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/31135 TID:203441826 |
url |
http://hdl.handle.net/10071/31135 |
identifier_str_mv |
TID:203441826 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
eu_rights_str_mv |
embargoedAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137763428139008 |