Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals

Detalhes bibliográficos
Autor(a) principal: Ferreira,Luiz K.
Data de Publicação: 2018
Outros Autores: Rondina,Jane M., Kubo,Rodrigo, Ono,Carla R., Leite,Claudia C., Smid,Jerusa, Bottino,Cassio, Nitrini,Ricardo, Busatto,Geraldo F., Duran,Fabio L., Buchpiguel,Carlos A.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Brazilian Journal of Psychiatry (São Paulo. 1999. Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-44462018000200181
Resumo: Objective: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer’s disease (AD). Method: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. Results: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. Conclusion: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.
id ABP-1_784e35654c7227adf8082dcd02443b38
oai_identifier_str oai:scielo:S1516-44462018000200181
network_acronym_str ABP-1
network_name_str Brazilian Journal of Psychiatry (São Paulo. 1999. Online)
repository_id_str
spelling Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individualsAlzheimer’s diseasesupport vector machineMRIFDG-PETSPECT Objective: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer’s disease (AD). Method: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. Results: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. Conclusion: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.Associação Brasileira de Psiquiatria2018-06-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-44462018000200181Brazilian Journal of Psychiatry v.40 n.2 2018reponame:Brazilian Journal of Psychiatry (São Paulo. 1999. Online)instname:Associação Brasileira de Psiquiatria (ABP)instacron:ABP10.1590/1516-4446-2016-2083info:eu-repo/semantics/openAccessFerreira,Luiz K.Rondina,Jane M.Kubo,RodrigoOno,Carla R.Leite,Claudia C.Smid,JerusaBottino,CassioNitrini,RicardoBusatto,Geraldo F.Duran,Fabio L.Buchpiguel,Carlos A.eng2018-05-28T00:00:00Zoai:scielo:S1516-44462018000200181Revistahttp://www.bjp.org.br/ahead_of_print.asphttps://old.scielo.br/oai/scielo-oai.php||rbp@abpbrasil.org.br1809-452X1516-4446opendoar:2018-05-28T00:00Brazilian Journal of Psychiatry (São Paulo. 1999. Online) - Associação Brasileira de Psiquiatria (ABP)false
dc.title.none.fl_str_mv Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
title Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
spellingShingle Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
Ferreira,Luiz K.
Alzheimer’s disease
support vector machine
MRI
FDG-PET
SPECT
title_short Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
title_full Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
title_fullStr Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
title_full_unstemmed Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
title_sort Support vector machine-based classification of neuroimages in Alzheimer’s disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals
author Ferreira,Luiz K.
author_facet Ferreira,Luiz K.
Rondina,Jane M.
Kubo,Rodrigo
Ono,Carla R.
Leite,Claudia C.
Smid,Jerusa
Bottino,Cassio
Nitrini,Ricardo
Busatto,Geraldo F.
Duran,Fabio L.
Buchpiguel,Carlos A.
author_role author
author2 Rondina,Jane M.
Kubo,Rodrigo
Ono,Carla R.
Leite,Claudia C.
Smid,Jerusa
Bottino,Cassio
Nitrini,Ricardo
Busatto,Geraldo F.
Duran,Fabio L.
Buchpiguel,Carlos A.
author2_role author
author
author
author
author
author
author
author
author
author
dc.contributor.author.fl_str_mv Ferreira,Luiz K.
Rondina,Jane M.
Kubo,Rodrigo
Ono,Carla R.
Leite,Claudia C.
Smid,Jerusa
Bottino,Cassio
Nitrini,Ricardo
Busatto,Geraldo F.
Duran,Fabio L.
Buchpiguel,Carlos A.
dc.subject.por.fl_str_mv Alzheimer’s disease
support vector machine
MRI
FDG-PET
SPECT
topic Alzheimer’s disease
support vector machine
MRI
FDG-PET
SPECT
description Objective: To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer’s disease (AD). Method: Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. Results: The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. Conclusion: In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.
publishDate 2018
dc.date.none.fl_str_mv 2018-06-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-44462018000200181
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-44462018000200181
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/1516-4446-2016-2083
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Associação Brasileira de Psiquiatria
publisher.none.fl_str_mv Associação Brasileira de Psiquiatria
dc.source.none.fl_str_mv Brazilian Journal of Psychiatry v.40 n.2 2018
reponame:Brazilian Journal of Psychiatry (São Paulo. 1999. Online)
instname:Associação Brasileira de Psiquiatria (ABP)
instacron:ABP
instname_str Associação Brasileira de Psiquiatria (ABP)
instacron_str ABP
institution ABP
reponame_str Brazilian Journal of Psychiatry (São Paulo. 1999. Online)
collection Brazilian Journal of Psychiatry (São Paulo. 1999. Online)
repository.name.fl_str_mv Brazilian Journal of Psychiatry (São Paulo. 1999. Online) - Associação Brasileira de Psiquiatria (ABP)
repository.mail.fl_str_mv ||rbp@abpbrasil.org.br
_version_ 1754212558143750144