Using deep belief network modelling to characterize differences in brain morphometry in schizophrenia

Página do item simplificado
dc.citation.volume6
dc.contributor.authorPinaya, Walter H. L.
dc.contributor.authorGadelha, Ary [UNIFESP]
dc.contributor.authorDoyle, Orla M.
dc.contributor.authorNoto, Cristiano [UNIFESP]
dc.contributor.authorZugman, Andre [UNIFESP]
dc.contributor.authorCordeiro, Quirino [UNIFESP]
dc.contributor.authorJackowski, Andrea Parolin [UNIFESP]
dc.contributor.authorBressan, Rodrigo Affonseca [UNIFESP]
dc.contributor.authorSato, Joao Ricardo [UNIFESP]
dc.coverageLondon
dc.date.accessioned2020-07-31T12:47:03Z
dc.date.available2020-07-31T12:47:03Z
dc.date.issued2016
dc.description.abstractNeuroimaging-based models contribute to increasing our understanding of schizophrenia pathophysiology and can reveal the underlying characteristics of this and other clinical conditions. However, the considerable variability in reported neuroimaging results mirrors the heterogeneity of the disorder. Machine learning methods capable of representing invariant features could circumvent this problem. In this structural MRI study, we trained a deep learning model known as deep belief network (DBN) to extract features from brain morphometry data and investigated its performance in discriminating between healthy controls (N = 83) and patients with schizophrenia (N = 143). We further analysed performance in classifying patients with a first-episode psychosis (N = 32). The DBN highlighted differences between classes, especially in the frontal, temporal, parietal, and insular cortices, and in some subcortical regions, including the corpus callosum, putamen, and cerebellum. The DBN was slightly more accurate as a classifier (accuracy = 73.6%) than the support vector machine (accuracy = 68.1%). Finally, the error rate of the DBN in classifying first-episode patients was 56.3%, indicating that the representations learned from patients with schizophrenia and healthy controls were not suitable to define these patients. Our data suggest that deep learning could improve our understanding of psychiatric disorders such as schizophrenia by improving neuromorphometric analyses.en
dc.description.affiliationUniv Fed ABC, Ctr Math Computat & Cognit, Santo Andre, Brazil
dc.description.affiliationUniv Fed Sao Paulo, Dept Psychiat, Sao Paulo, Brazil
dc.description.affiliationKings Coll London, Inst Psychiat Psychol & Neurosci, Dept Neuroimaging, London, England
dc.description.affiliationUniv Fed Sao Paulo, Interdisciplinary Lab Clin Neurosci LiNC, Sao Paulo, Brazil
dc.description.affiliationFac Ciencias Med Santa Casa Sao Paulo, Dept Psychiat, Sao Paulo, Brazil
dc.description.affiliationUnifespDepartment of Psychiatry. Universidade Federal de São Paulo, São Paulo, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.description.sponsorshipIDFAPESP: 2013/05168-7
dc.description.sponsorshipIDFAPESP: 2013/10498-6
dc.format.extent-
dc.identifierhttp://dx.doi.org/10.1038/srep38897
dc.identifier.citationScientific Reports. London, v. 6, p. -, 2016.
dc.identifier.doi10.1038/srep38897
dc.identifier.fileWOS000389656800001.pdf
dc.identifier.issn2045-2322
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/56553
dc.identifier.wosWOS:000389656800001
dc.language.isoeng
dc.publisherNature Publishing Group
dc.relation.ispartofScientific Reports
dc.rightsinfo:eu-repo/semantics/openAccess
dc.titleUsing deep belief network modelling to characterize differences in brain morphometry in schizophreniaen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
WOS000389656800001.pdf
Tamanho:
743.86 KB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Coleções
EPM - Artigos