Mostrar el registro sencillo del ítem
dc.contributor.author | Silva-Rodríguez, Julio | es_ES |
dc.contributor.author | Naranjo Ornedo, Valeriana | es_ES |
dc.contributor.author | Dolz, Jose | es_ES |
dc.date.accessioned | 2023-10-05T18:01:40Z | |
dc.date.available | 2023-10-05T18:01:40Z | |
dc.date.issued | 2022-08 | es_ES |
dc.identifier.issn | 1361-8415 | es_ES |
dc.identifier.uri | http://hdl.handle.net/10251/197770 | |
dc.description.abstract | [EN] Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. To address the limitations of residual-based anomaly localization, very recent literature has focused on attention maps, by integrating supervision on them in the form of homogenization constraints. In this work, we propose a novel formulation that addresses the problem in a more principled manner, leveraging well-known knowledge in constrained optimization. In particular, the equality constraint on the attention maps in prior work is replaced by an inequality constraint, which allows more flexibility. In addition, to address the limitations of penalty-based functions we employ an extension of the popular log-barrier methods to handle the constraint. Last, we propose an alternative regularization term that maximizes the Shannon entropy of the attention maps, reducing the amount of hyperparameters of the proposed model. Comprehensive experiments on two publicly available datasets on brain lesion segmentation demonstrate that the proposed approach substantially outperforms relevant literature, establishing new state-of-the-art results for unsupervised lesion segmentation. | es_ES |
dc.description.sponsorship | J. Silva-Rodriguez work was supported by the Spanish Government under FPI Grant PRE2018-083443. The DGX-A100 used in this work was partially funded by Generalitat Valenciana/European Union through the European Regional Development Fund (ERDF) of the Valencian Community (IDIFEDER/2020/030). | es_ES |
dc.language | Inglés | es_ES |
dc.publisher | Elsevier | es_ES |
dc.relation.ispartof | Medical Image Analysis | es_ES |
dc.rights | Reconocimiento (by) | es_ES |
dc.subject | Unsupervised anomaly localization | es_ES |
dc.subject | Constraint segmentation | es_ES |
dc.subject | Brain lesions | es_ES |
dc.subject.classification | TEORÍA DE LA SEÑAL Y COMUNICACIONES | es_ES |
dc.title | Constrained unsupervised anomaly segmentation | es_ES |
dc.type | Artículo | es_ES |
dc.identifier.doi | 10.1016/j.media.2022.102526 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/AEI//PRE2018-083443//AYUDA PARA CONTRATOS PREDOCTORALES PARA LA FORMACION DE DOCTORES-SILVA RODRIGUEZ, JULIO. PROYECTO: METODOS INTELIGENTES DE AUSCULTACION DINAMICA DE VIA EN BASE AL TRATAMIENTO DIGITAL DE IMAGENES/ | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/GVA//IDIFEDER%2F2020%2F030/ | es_ES |
dc.rights.accessRights | Abierto | es_ES |
dc.contributor.affiliation | Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros de Telecomunicación - Escola Tècnica Superior d'Enginyers de Telecomunicació | es_ES |
dc.contributor.affiliation | Universitat Politècnica de València. Departamento de Comunicaciones - Departament de Comunicacions | es_ES |
dc.description.bibliographicCitation | Silva-Rodríguez, J.; Naranjo Ornedo, V.; Dolz, J. (2022). Constrained unsupervised anomaly segmentation. Medical Image Analysis. 80:1-12. https://doi.org/10.1016/j.media.2022.102526 | es_ES |
dc.description.accrualMethod | S | es_ES |
dc.relation.publisherversion | https://doi.org/10.1016/j.media.2022.102526 | es_ES |
dc.description.upvformatpinicio | 1 | es_ES |
dc.description.upvformatpfin | 12 | es_ES |
dc.type.version | info:eu-repo/semantics/publishedVersion | es_ES |
dc.description.volume | 80 | es_ES |
dc.identifier.pmid | 35780592 | es_ES |
dc.relation.pasarela | S\468212 | es_ES |
dc.contributor.funder | Generalitat Valenciana | es_ES |
dc.contributor.funder | AGENCIA ESTATAL DE INVESTIGACION | es_ES |
dc.contributor.funder | European Regional Development Fund | es_ES |
dc.contributor.funder | Universitat Politècnica de València | es_ES |