Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/341857
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.contributor.authorunicampGarcía Herrera, William Javier-
dc.contributor.authorunicampPereira, Mariana Eugênia de Carvalho-
dc.contributor.authorunicampLapa, Aline Tamires-
dc.contributor.authorunicampRittner, Leticia-
dc.typeArtigopt_BR
dc.titleA framework for quality control of corpus callosum segmentation in large-scale studiespt_BR
dc.contributor.authorHerrera, W.G.-
dc.contributor.authorPereira, M.-
dc.contributor.authorBento, M.-
dc.contributor.authorLapa, A.T.-
dc.contributor.authorAppenzeller, S.-
dc.contributor.authorRittner, L.-
dc.subjectImagem de ressonância magnéticapt_BR
dc.subject.otherlanguageMagnetic resonance imagingpt_BR
dc.description.abstractThe corpus callosum (CC) is the largest white matter structure in the brain, responsible for the interconnection of the brain hemispheres. Its segmentation is a required preliminary step for any posterior analysis, such as parcellation, registration, and feature extraction. In this context, the quality control (QC) of CC segmentation allows studies on large datasets with no human interaction, and the proper usage of available automated and semi-automated algorithms. New method: We propose a framework for QC of CC segmentation based on the shape signature, computed at 49 distinct resolutions. At each resolution, a support vector machine (SVM) classifier was trained, generating 49 individual classifiers. Then, a disagreement metric was used to cluster these individual classifiers. The final ensemble was constructed by selecting one representation from each cluster. Results: The proposed framework achieved an area under the curve (AUC) metric of 98.25% on the test set (207 subjects) employing an ensemble composed of 12 components. This ensemble outperformed all individual classifiers. Comparison with existing methods: To the best of our knowledge, this is the first approach to assess quality of CC segmentations on large datasets without the need for a ground-truth. Conclusions: The shape descriptor is robust and versatile, describing the segmentation at different resolutions. The selection of classifiers and the disagreement measure lead to an ensemble composed of high-quality and heterogeneous classifiers, ensuring an optimal trade-off between the ensemble size and high AUCpt_BR
dc.relation.ispartofJournal of neuroscience methodspt_BR
dc.relation.ispartofabbreviationJ. neurosci. methodspt_BR
dc.publisher.cityAmsterdampt_BR
dc.publisher.countryPaíses Baixospt_BR
dc.publisherElsevierpt_BR
dc.date.issued2020-
dc.date.monthofcirculationMar.pt_BR
dc.language.isoengpt_BR
dc.description.volume334pt_BR
dc.rightsFechadopt_BR
dc.sourceSCOPUSpt_BR
dc.identifier.issn0165-0270pt_BR
dc.identifier.eissn1872-678Xpt_BR
dc.identifier.doi10.1016/j.jneumeth.2020.108593pt_BR
dc.identifier.urlhttps://www.sciencedirect.com/science/article/pii/S0165027020300157pt_BR
dc.description.sponsorshipCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQpt_BR
dc.description.sponsorshipFUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESPpt_BR
dc.description.sponsordocumentnumber190557/2014-1; 308311/2016-7pt_BR
dc.description.sponsordocumentnumber2013/07559-3pt_BR
dc.date.available2020-05-20T23:45:42Z-
dc.date.accessioned2020-05-20T23:45:42Z-
dc.description.provenanceSubmitted by Sanches Olivia (olivias@unicamp.br) on 2020-05-20T23:45:42Z No. of bitstreams: 0. Added 1 bitstream(s) on 2020-08-27T19:15:52Z : No. of bitstreams: 1 2-s2.0-85078408203.pdf: 3295169 bytes, checksum: d195d76ad06ba99663c49bc9ac7790b5 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-05-20T23:45:42Z (GMT). No. of bitstreams: 0 Previous issue date: 2020en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/341857-
dc.contributor.departmentsem informaçãopt_BR
dc.contributor.departmentsem informaçãopt_BR
dc.contributor.departmentsem informaçãopt_BR
dc.contributor.departmentDepartamento de Engenharia de Computação e Automação Industrialpt_BR
dc.contributor.unidadeFaculdade de Engenharia Elétrica e da Computaçãopt_BR
dc.contributor.unidadeFaculdade de Engenharia Elétrica e da Computaçãopt_BR
dc.contributor.unidadeFaculdade de Ciências Médicaspt_BR
dc.contributor.unidadeFaculdade de Engenharia Elétrica e da Computaçãopt_BR
dc.subject.keywordCorpus callosumpt_BR
dc.subject.keywordSegmentationpt_BR
dc.subject.keywordQuality controlpt_BR
dc.subject.keywordEnsemblept_BR
dc.subject.keywordSupport vector machinept_BR
dc.identifier.source2-s2.0-85078408203pt_BR
dc.creator.orcidsem informaçãopt_BR
dc.creator.orcid0000-0002-3771-2787pt_BR
dc.creator.orcidsem informaçãopt_BR
dc.creator.orcid0000-0001-8182-5554pt_BR
dc.type.formArtigopt_BR
dc.identifier.articleid108593pt_BR
Appears in Collections:FCM - Artigos e Outros Documentos
FEEC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-85078408203.pdf3.22 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.