Neuroimaging modality fusion in Alzheimer's classification using convolutional neural networks.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2019
2019
Historique:
received:
19
02
2019
accepted:
12
11
2019
entrez:
6
12
2019
pubmed:
6
12
2019
medline:
25
3
2020
Statut:
epublish
Résumé
Automated methods for Alzheimer's disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer's dementia classification using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.
Identifiants
pubmed: 31805160
doi: 10.1371/journal.pone.0225759
pii: PONE-D-19-04978
pmc: PMC6894831
doi:
Substances chimiques
Amyloid
0
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0225759Subventions
Organisme : NIA NIH HHS
ID : T32 AG020506
Pays : United States
Organisme : NLM NIH HHS
ID : T32 LM012203
Pays : United States
Organisme : NIA NIH HHS
ID : U01 AG024904
Pays : United States
Organisme : CIHR
Pays : Canada
Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Alzheimers Dement. 2018 Apr;14(4):535-562
pubmed: 29653606
Neuroimage. 2011 Jan 1;54(1):313-27
pubmed: 20656036
Neurology. 2004 May 11;62(9):1645
pubmed: 15136705
Neuroimage. 2014 Nov 1;101:569-82
pubmed: 25042445
IEEE Trans Med Imaging. 1998 Feb;17(1):87-97
pubmed: 9617910
Med Image Comput Comput Assist Interv. 2013;16(Pt 2):583-90
pubmed: 24579188
Ann Neurol. 2012 Oct;72(4):578-86
pubmed: 23109153
Med Image Comput Comput Assist Interv. 2014;17(Pt 3):305-12
pubmed: 25320813
Neurobiol Aging. 1991 Jul-Aug;12(4):295-312
pubmed: 1961359
Neuroimage. 2014 Oct 15;100:91-105
pubmed: 24911377
Neuroimage. 2011 May 15;56(2):766-81
pubmed: 20542124
IEEE Trans Biomed Eng. 2015 Apr;62(4):1132-40
pubmed: 25423647
Lancet Neurol. 2013 Feb;12(2):207-16
pubmed: 23332364
Neuroimage. 2009 Oct 1;47(4):1476-86
pubmed: 19463957
Brain Imaging Behav. 2016 Dec;10(4):1148-1159
pubmed: 26572145
Hum Brain Mapp. 2002 Nov;17(3):143-55
pubmed: 12391568
IEEE J Biomed Health Inform. 2015 Sep;19(5):1610-6
pubmed: 25955998
J Magn Reson Imaging. 2008 Apr;27(4):685-91
pubmed: 18302232
Acta Neuropathol. 2011 May;121(5):571-87
pubmed: 21516511
Brain. 2008 Mar;131(Pt 3):681-9
pubmed: 18202106
IEEE Trans Biomed Eng. 2016 Jul;63(7):1473-82
pubmed: 26540666
IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20
pubmed: 20378467
Neuroimage. 2002 Oct;17(2):825-41
pubmed: 12377157
Neurology. 2006 Jun 27;66(12):1837-44
pubmed: 16801647
IEEE Trans Biomed Eng. 2019 Aug;66(8):2362-2371
pubmed: 30582522
Neuroimage. 2007 Oct 15;38(1):95-113
pubmed: 17761438
Neuroinformatics. 2015 Jan;13(1):31-46
pubmed: 25048627
Med Phys. 1986 Nov-Dec;13(6):806-14
pubmed: 3796476
Nature. 2000 Jun 22;405(6789):947-51
pubmed: 10879535
IEEE Trans Med Imaging. 2001 Jan;20(1):70-80
pubmed: 11293693
IEEE J Biomed Health Inform. 2018 Jan;22(1):173-183
pubmed: 28113353
Lancet Neurol. 2018 Mar;17(3):241-250
pubmed: 29397305
Neuroimage. 2012 Aug 15;62(2):774-81
pubmed: 22248573