GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)

PurposeThe study investigates the usefulness of Convolutional Neural Networks (CNNs) in accurately detecting arteriovenous malformations in pediatric medical imaging, particularly using arterial spin labeling sequences. It also aims to offer diagnostic explanations comparable to expert analysis.Meth...

Descripción completa

Detalles Bibliográficos
Autores: Romagosa, J, Mata, C, Benítez, R, Valls-Esteve, A, Bernaus, S, Ibnoulkhatib, M, Stephan-Otto, C, Munuera, J
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
Repositorio:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
OAI Identifier:oai:iibsantpau.fundanetsuite.com:p20291
Acceso en línea:https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=20291
Access Level:acceso abierto
Palabra clave:Explainable AI
Grad-CAM
Deep learning
CNN
Arteriovenous malformations
Arterial spin labeling
Magnetic resonance imaging
Medical imaging
id ES_ef66dbbe03f528cc2f06664c31db596d
oai_identifier_str oai:iibsantpau.fundanetsuite.com:p20291
network_acronym_str ES
network_name_str España
repository_id_str
spelling GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)Romagosa, JMata, CBenítez, RValls-Esteve, ABernaus, SIbnoulkhatib, MStephan-Otto, CMunuera, JExplainable AIGrad-CAMDeep learningCNNArteriovenous malformationsArterial spin labelingMagnetic resonance imagingMedical imagingPurposeThe study investigates the usefulness of Convolutional Neural Networks (CNNs) in accurately detecting arteriovenous malformations in pediatric medical imaging, particularly using arterial spin labeling sequences. It also aims to offer diagnostic explanations comparable to expert analysis.MethodsThe research analyzed three different CNN architectures to determine their performance in detecting arteriovenous malformations. The study focused on evaluating the relationship between model complexity and performance increase, using data to assess the accuracy and diagnostic usefulness of each model.ResultsThe findings indicated a nonlinear link between model complexity and performance. Sur- prisingly, more complex models frequently produced poor results and diagnostically useless answers. The simplest CNN models achieved the highest accuracy rate (90%), demonstrating the effectiveness of minimal complexity in model construction. Heat maps showed a strong association with the real locations of irregularities, indicating that the models were interpretable.ConclusionThe study highlights the usefulness of CNNs in medical diagnostics, emphasizing the importance of model simplicity and interpretability in clinical applications. It suggests a need for balancing technical sophistication with clinical value and presents options for future research into refining CNN structures for increased diagnostic precision in various medical imaging modalities.SPRINGER2025info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttps://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=20291Health Information Science and SystemsISSN: 20472501reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pauinstname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)Inglésinfo:eu-repo/semantics/openAccessoai:iibsantpau.fundanetsuite.com:p202912026-06-14T12:41:47Z
dc.title.none.fl_str_mv GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
title GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
spellingShingle GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
Romagosa, J
Explainable AI
Grad-CAM
Deep learning
CNN
Arteriovenous malformations
Arterial spin labeling
Magnetic resonance imaging
Medical imaging
title_short GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
title_full GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
title_fullStr GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
title_full_unstemmed GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
title_sort GradCAM as an explicability method to evaluate the performance of deep learning models in classifying pediatric arteriovenous malformations (AVM) in arterial spin labeling sequences (ASL)
dc.creator.none.fl_str_mv Romagosa, J
Mata, C
Benítez, R
Valls-Esteve, A
Bernaus, S
Ibnoulkhatib, M
Stephan-Otto, C
Munuera, J
author Romagosa, J
author_facet Romagosa, J
Mata, C
Benítez, R
Valls-Esteve, A
Bernaus, S
Ibnoulkhatib, M
Stephan-Otto, C
Munuera, J
author_role author
author2 Mata, C
Benítez, R
Valls-Esteve, A
Bernaus, S
Ibnoulkhatib, M
Stephan-Otto, C
Munuera, J
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Explainable AI
Grad-CAM
Deep learning
CNN
Arteriovenous malformations
Arterial spin labeling
Magnetic resonance imaging
Medical imaging
topic Explainable AI
Grad-CAM
Deep learning
CNN
Arteriovenous malformations
Arterial spin labeling
Magnetic resonance imaging
Medical imaging
description PurposeThe study investigates the usefulness of Convolutional Neural Networks (CNNs) in accurately detecting arteriovenous malformations in pediatric medical imaging, particularly using arterial spin labeling sequences. It also aims to offer diagnostic explanations comparable to expert analysis.MethodsThe research analyzed three different CNN architectures to determine their performance in detecting arteriovenous malformations. The study focused on evaluating the relationship between model complexity and performance increase, using data to assess the accuracy and diagnostic usefulness of each model.ResultsThe findings indicated a nonlinear link between model complexity and performance. Sur- prisingly, more complex models frequently produced poor results and diagnostically useless answers. The simplest CNN models achieved the highest accuracy rate (90%), demonstrating the effectiveness of minimal complexity in model construction. Heat maps showed a strong association with the real locations of irregularities, indicating that the models were interpretable.ConclusionThe study highlights the usefulness of CNNs in medical diagnostics, emphasizing the importance of model simplicity and interpretability in clinical applications. It suggests a need for balancing technical sophistication with clinical value and presents options for future research into refining CNN structures for increased diagnostic precision in various medical imaging modalities.
publishDate 2025
dc.date.none.fl_str_mv 2025
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://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=20291
url https://iibsantpau.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=20291
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv SPRINGER
publisher.none.fl_str_mv SPRINGER
dc.source.none.fl_str_mv Health Information Science and Systems
ISSN: 20472501
reponame:r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
instname:Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
instname_str Institut d’Investigació Biomèdica Sant Pau (IIB Sant Pau)
reponame_str r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
collection r-IIB SANT PAU. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica Sant Pau
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423860024082432
score 15.811543

Similares en LA Referencia