Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10662/19917
Registro completo de Metadatos
Campo DC | Valor | idioma |
---|---|---|
dc.contributor.author | Sánchez Peralta, Luisa Fernanda | - |
dc.contributor.author | Picón Ruiz, Artzai | - |
dc.contributor.author | Antequera Barroso, Juan Antonio | - |
dc.contributor.author | Ortega Morán, Juan Francisco | - |
dc.contributor.author | Sánchez Margallo, Francisco Miguel | - |
dc.contributor.author | Pagador Carrasco, José Blas | - |
dc.date.accessioned | 2024-02-05T12:07:55Z | - |
dc.date.available | 2024-02-05T12:07:55Z | - |
dc.date.issued | 2020-08-07 | - |
dc.identifier.uri | http://hdl.handle.net/10662/19917 | - |
dc.description.abstract | Colorectal cancer is one of the leading cancer death causes worldwide, but its early diagnosis highly improves the survival rates. The success of deep learning has also benefited this clinical field. When training a deep learning model, it is optimized based on the selected loss function. In this work, we consider two networks (U-Net and LinkNet) and two backbones (VGG-16 and Densnet121). We analyzed the influence of seven loss functions and used a principal component analysis (PCA) to determine whether the PCA-based decomposition allows for the defining of the coe cients of a non-redundant primal loss function that can outperform the individual loss functions and di erent linear combinations. The eigenloss is defined as a linear combination of the individual losses using the elements of the eigenvector as coe cients. Empirical results show that the proposed eigenloss improves the general performance of individual loss functions and outperforms other linear combinations when Linknet is used, showing potential for its application in polyp segmentation problems. | es_ES |
dc.description.sponsorship | This work was partially supported by PICCOLO project. This project has received funding from the European Union’s Horizon2020 research and innovation programme under grant agreement No 732111. The sole responsibility of this publication lies with the author. The European Union is not responsible for any use that may be made of the information contained therein. | es_ES |
dc.format.extent | 19 p. | es_ES |
dc.format.mimetype | application/pdf | en_US |
dc.language.iso | eng | es_ES |
dc.publisher | MDPI | es_ES |
dc.subject | Deep learning | es_ES |
dc.subject | Loss functions | es_ES |
dc.subject | Principal component analysis | es_ES |
dc.subject | Polyp segmentation | es_ES |
dc.subject | Aprendizaje profundo | es_ES |
dc.subject | Funciones de pérdida | es_ES |
dc.subject | Análisis de componentes principales | es_ES |
dc.subject | Segmentación de polípos | es_ES |
dc.title | Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation | es_ES |
dc.type | article | es_ES |
dc.description.version | peerReviewed | es_ES |
europeana.type | TEXT | en_US |
dc.rights.accessRights | openAccess | es_ES |
dc.subject.unesco | 3201.01 Oncología | es_ES |
europeana.dataProvider | Universidad de Extremadura. España | es_ES |
dc.identifier.bibliographicCitation | Sánchez-Peralta LF, Picón A, Antequera-Barroso JA, Ortega-Morán JF, Sánchez-Margallo FM, Pagador JB. Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation. Mathematics. 2020; 8(8):1316. https://doi.org/10.3390/math8081316 | es_ES |
dc.type.version | publishedVersion | es_ES |
dc.contributor.affiliation | N/A | es_ES |
dc.relation.publisherversion | https://www.mdpi.com/2227-7390/8/8/1316 | es_ES |
dc.identifier.doi | 10.3390/math8081316 | - |
dc.identifier.publicationtitle | Mathematics | es_ES |
dc.identifier.publicationissue | 8 | es_ES |
dc.identifier.publicationfirstpage | 1316-1 | es_ES |
dc.identifier.publicationlastpage | 1319-19 | es_ES |
dc.identifier.publicationvolume | 8 | es_ES |
dc.identifier.orcid | 0000-0002-7630-353X | es_ES |
dc.identifier.orcid | 0000-0002-3316-6571 | es_ES |
dc.identifier.orcid | 0000-0001-8259-8963 | es_ES |
dc.identifier.orcid | 0000-0003-2138-988X | es_ES |
dc.identifier.orcid | 0000-0002-4382-5075 | es_ES |
Colección: | DDCEM - Artículos |
Este elemento está sujeto a una licencia Licencia Creative Commons