Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space rep...

Descripción completa

Detalles Bibliográficos
Autores: Cetin, Irem, Stephens, Maialen, Camara, Oscar, González Ballester, Miguel Ángel, 1973-
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/56180
Acceso en línea:http://hdl.handle.net/10230/56180
http://dx.doi.org/10.1016/j.compmedimag.2022.102158
Access Level:acceso abierto
Palabra clave:Deep learning
Interpretability
Attribute regularization
Variational autoencoder
Cardiac image analysis
id ES_ff25bcbc1bc28ec8b413be7efe0d364b
oai_identifier_str oai:recercat.cat:10230/56180
network_acronym_str ES
network_name_str España
repository_id_str
spelling Attri-VAE: attribute-based interpretable representations of medical images with variational autoencodersCetin, IremStephens, MaialenCamara, OscarGonzález Ballester, Miguel Ángel, 1973-Deep learningInterpretabilityAttribute regularizationVariational autoencoderCardiac image analysisDeep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.This work was partly funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825903 (euCanSHare project).Elsevier202320232023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/56180http://dx.doi.org/10.1016/j.compmedimag.2022.102158reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésComputerized Medical Imaging and Graphics. 2023 Mar;104:102158info:eu-repo/grantAgreement/EC/H2020/825903© 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/).http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10230/561802026-05-29T05:05:01Z
dc.title.none.fl_str_mv Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
title Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
spellingShingle Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
Cetin, Irem
Deep learning
Interpretability
Attribute regularization
Variational autoencoder
Cardiac image analysis
title_short Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
title_full Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
title_fullStr Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
title_full_unstemmed Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
title_sort Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
dc.creator.none.fl_str_mv Cetin, Irem
Stephens, Maialen
Camara, Oscar
González Ballester, Miguel Ángel, 1973-
author Cetin, Irem
author_facet Cetin, Irem
Stephens, Maialen
Camara, Oscar
González Ballester, Miguel Ángel, 1973-
author_role author
author2 Stephens, Maialen
Camara, Oscar
González Ballester, Miguel Ángel, 1973-
author2_role author
author
author
dc.subject.none.fl_str_mv Deep learning
Interpretability
Attribute regularization
Variational autoencoder
Cardiac image analysis
topic Deep learning
Interpretability
Attribute regularization
Variational autoencoder
Cardiac image analysis
description Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in the reasoning behind the medical decisions. Latent space representations built with variational autoencoders (VAE) do not ensure individual control of data attributes. Attribute-based methods enforcing attribute disentanglement have been proposed in the literature for classical computer vision tasks in benchmark data. In this paper, we propose a VAE approach, the Attri-VAE, that includes an attribute regularization term to associate clinical and medical imaging attributes with different regularized dimensions in the generated latent space, enabling a better-disentangled interpretation of the attributes. Furthermore, the generated attention maps explained the attribute encoding in the regularized latent space dimensions. Using the Attri-VAE approach we analyzed healthy and myocardial infarction patients with clinical, cardiac morphology, and radiomics attributes. The proposed model provided an excellent trade-off between reconstruction fidelity, disentanglement, and interpretability, outperforming state-of-the-art VAE approaches according to several quantitative metrics. The resulting latent space allowed the generation of realistic synthetic data in the trajectory between two distinct input samples or along a specific attribute dimension to better interpret changes between different cardiac conditions.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023
2023
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 http://hdl.handle.net/10230/56180
http://dx.doi.org/10.1016/j.compmedimag.2022.102158
url http://hdl.handle.net/10230/56180
http://dx.doi.org/10.1016/j.compmedimag.2022.102158
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Computerized Medical Imaging and Graphics. 2023 Mar;104:102158
info:eu-repo/grantAgreement/EC/H2020/825903
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425748566081536
score 15.812455

Similares en LA Referencia