Learning non-linear patch embeddings with neural networks for label fusion

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Sanromà, Gerardca
• dc.contributor.author Benkarim, Oualid M.ca
• dc.contributor.author Piella Fenoy, Gemmaca
• dc.contributor.author Camara, Oscarca
• dc.contributor.author Wu, Guorongca
• dc.contributor.author Shen, Dinggangca
• dc.contributor.author Gispert López, Juan Domingoca
• dc.contributor.author Molinuevo, José Luisca
• dc.contributor.author González Ballester, Miguel Ángel, 1973-ca
• dc.date.accessioned 2018-08-28T08:48:07Z
• dc.date.issued 2018
• dc.description.abstract In brain structural segmentation, multi-atlas strategies are increasingly being used over single-atlas strategies because of their ability to fit a wider anatomical variability. Patch-based label fusion (PBLF) is a type of such multi-atlas approaches that labels each target point as a weighted combination of neighboring atlas labels, where atlas points with higher local similarity to the target contribute more strongly to label fusion. PBLF can be potentially improved by increasing the discriminative capabilities of the local image similarity measurements. We propose a framework to compute patch embeddings using neural networks so as to increase discriminative abilities of similarity-based weighted voting in PBLF. As particular cases, our framework includes embeddings with different complexities, namely, a simple scaling, an affine transformation, and non-linear transformations. We compare our method with state-of-the-art alternatives in whole hippocampus and hippocampal subfields segmentation experiments using publicly available datasets. Results show that even the simplest versions of our method outperform standard PBLF, thus evidencing the benefits of discriminative learning. More complex transformation models tended to achieve better results than simpler ones, obtaining a considerable increase in average Dice score compared to standard PBLF.
• dc.description.sponsorship he first author is co-financed by the Marie Curie FP7-PEOPLE-2012-COFUND Action, Grant agreement no: 600387. This work is partly supported by the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502). Part of the data used for this project was funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012).
• dc.format.mimetype application/pdf
• dc.identifier.citation Sanroma G, Menkarim OM, Piella G, Camara O, Wu G, Shen D, Gispert JD, Molinuevo JL, González Ballester MA. Learning non-linear patch embeddings with neural networks for label fusion. Med Image Anal. 2018;44: 143-55. DOI: 10.1016/j.media.2017.11.013
• dc.identifier.doi http://dx.doi.org/10.1016/j.media.2017.11.013
• dc.identifier.issn 1361-8415
• dc.identifier.uri http://hdl.handle.net/10230/35395
• dc.language.iso eng
• dc.publisher Elsevierca
• dc.relation.ispartof Medical Image Analysis. 2018;44:143-55
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/600387
• dc.rights © Elsevier http://dx.doi.org/10.1016/j.media.2017.11.013
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Patch-based label fusion
• dc.subject.keyword Multi-atlas segmentation
• dc.subject.keyword Neural networks
• dc.subject.keyword Embedding
• dc.subject.keyword Brain MRI
• dc.subject.keyword Hippocampus
• dc.title Learning non-linear patch embeddings with neural networks for label fusionca
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion