Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
Mostra el registre complet Registre parcial de l'ítem
- 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.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.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.doi http://dx.doi.org/10.1016/j.compmedimag.2022.102158
- dc.identifier.issn 0895-6111
- dc.identifier.uri http://hdl.handle.net/10230/56180
- dc.language.iso eng
- dc.publisher Elsevier
- dc.relation.ispartof Computerized Medical Imaging and Graphics. 2023 Mar;104:102158
- dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/825903
- 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.accessRights info:eu-repo/semantics/openAccess
- dc.rights.uri http://creativecommons.org/licenses/by/4.0/
- 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.title Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/publishedVersion