Welcome to the UPF Digital Repository

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

Show simple item record

dc.contributor.author Cetin, Irem
dc.contributor.author Stephens, Maialen
dc.contributor.author Camara, Oscar
dc.contributor.author González Ballester, Miguel Ángel, 1973-
dc.date.accessioned 2023-03-13T07:44:49Z
dc.date.available 2023-03-13T07:44:49Z
dc.date.issued 2023
dc.identifier.citation Cetin I, Stephens M, Camara O, González MA. Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders. Computerized Medical Imaging and Graphics. 2023 Mar;104:102158. DOI: 10.1016/j.compmedimag.2022.102158
dc.identifier.issn 0895-6111
dc.identifier.uri http://hdl.handle.net/10230/56180
dc.description.abstract 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.
dc.description.sponsorship This work was partly funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825903 (euCanSHare project).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Elsevier
dc.relation.ispartof Computerized Medical Imaging and Graphics. 2023 Mar;104:102158
dc.rights © 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/).
dc.rights.uri http://creativecommons.org/licenses/by/4.0/
dc.title Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
dc.type info:eu-repo/semantics/article
dc.identifier.doi http://dx.doi.org/10.1016/j.compmedimag.2022.102158
dc.subject.keyword Deep learning
dc.subject.keyword Interpretability
dc.subject.keyword Attribute regularization
dc.subject.keyword Variational autoencoder
dc.subject.keyword Cardiac image analysis
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/825903
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account


Compliant to Partaking