Discriminating VCID subgroups: A diffusion MRI multi-model fusion approach.
Constrained spherical deconvolution model
Diffusion kurtosis imaging
Diffusion tensor imaging
Fusion
Tractography
Vascular cognitive impairment and dementia
Journal
Journal of neuroscience methods
ISSN: 1872-678X
Titre abrégé: J Neurosci Methods
Pays: Netherlands
ID NLM: 7905558
Informations de publication
Date de publication:
01 04 2020
01 04 2020
Historique:
received:
22
08
2019
revised:
06
12
2019
accepted:
17
01
2020
pubmed:
1
2
2020
medline:
22
6
2021
entrez:
1
2
2020
Statut:
ppublish
Résumé
Vascular cognitive impairment and dementia (VCID) and Alzheimer's disease are predominant diseases among the aging population resulting in decline of various cognitive domains. Diffusion weighted MRI (DW-MRI) has been shown to be a promising aid in the diagnosis of such diseases. However, there are various models of DW-MRI and the interpretation of diffusion metrics depends on the model used in fitting data. Most previous studies are entirely based on parameters calculated from a single diffusion model. We employ a data fusion framework wherein diffusion metrics from different models such as diffusion tensor imaging, diffusion kurtosis imaging and constrained spherical deconvolution model are fused using well known blind source separation approach to investigate white matter microstructural changes in population comprising of controls and VCID subgroups. Multiple comparisons between subject groups and prediction analysis using features from individual models and proposed fusion model are carried out to evaluate performance of proposed method. Diffusion features from individual models successfully distinguished between controls and disease groups, but failed to differentiate between disease groups, whereas fusion approach showed group differences between disease groups too. WM tracts showing significant differences are superior longitudinal fasciculus, anterior thalamic radiation, arcuate fasciculus, optic radiation and corticospinal tract. ROC analysis showed increased AUC for fusion (AUC = 0.913, averaged across groups and tracts) compared to that of uni-model features (AUC = 0.77) demonstrating increased sensitivity of proposed method. Overall our results highlight the benefits of multi-model fusion approach, providing improved sensitivity in discriminating VCID subgroups.
Sections du résumé
BACKGROUND
Vascular cognitive impairment and dementia (VCID) and Alzheimer's disease are predominant diseases among the aging population resulting in decline of various cognitive domains. Diffusion weighted MRI (DW-MRI) has been shown to be a promising aid in the diagnosis of such diseases. However, there are various models of DW-MRI and the interpretation of diffusion metrics depends on the model used in fitting data. Most previous studies are entirely based on parameters calculated from a single diffusion model.
NEW METHOD
We employ a data fusion framework wherein diffusion metrics from different models such as diffusion tensor imaging, diffusion kurtosis imaging and constrained spherical deconvolution model are fused using well known blind source separation approach to investigate white matter microstructural changes in population comprising of controls and VCID subgroups. Multiple comparisons between subject groups and prediction analysis using features from individual models and proposed fusion model are carried out to evaluate performance of proposed method.
RESULTS
Diffusion features from individual models successfully distinguished between controls and disease groups, but failed to differentiate between disease groups, whereas fusion approach showed group differences between disease groups too. WM tracts showing significant differences are superior longitudinal fasciculus, anterior thalamic radiation, arcuate fasciculus, optic radiation and corticospinal tract.
COMPARISON WITH EXISTING METHOD
ROC analysis showed increased AUC for fusion (AUC = 0.913, averaged across groups and tracts) compared to that of uni-model features (AUC = 0.77) demonstrating increased sensitivity of proposed method.
CONCLUSION
Overall our results highlight the benefits of multi-model fusion approach, providing improved sensitivity in discriminating VCID subgroups.
Identifiants
pubmed: 32004594
pii: S0165-0270(20)30020-0
doi: 10.1016/j.jneumeth.2020.108598
pmc: PMC7443575
mid: NIHMS1616651
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
108598Subventions
Organisme : NINDS NIH HHS
ID : R01 NS052305
Pays : United States
Organisme : NIA NIH HHS
ID : RF1 AG063153
Pays : United States
Organisme : NINDS NIH HHS
ID : UH3 NS100598
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001449
Pays : United States
Informations de copyright
Copyright © 2020 Elsevier B.V. All rights reserved.
Références
Neuropsychol Rev. 2009 Dec;19(4):415-35
pubmed: 19705281
Neuroimage. 2014 Oct 1;99:498-508
pubmed: 24956065
Front Aging Neurosci. 2017 Jun 12;9:185
pubmed: 28659787
Front Aging Neurosci. 2017 Jul 07;9:215
pubmed: 28736521
Front Neuroinform. 2014 Feb 21;8:8
pubmed: 24600385
Biol Psychiatry Cogn Neurosci Neuroimaging. 2016 May;1(3):230-244
pubmed: 27347565
Neuroimage. 2007 May 1;35(4):1459-72
pubmed: 17379540
Hum Brain Mapp. 2016 Jan;37(1):300-10
pubmed: 26466741
Hum Brain Mapp. 2019 Feb 15;40(3):765-776
pubmed: 30267634
Stroke. 2008 Jul;39(7):1999-2005
pubmed: 18436880
Dement Geriatr Cogn Disord. 2017;44(5-6):268-282
pubmed: 29353280
Brain Res Bull. 2018 May;139:91-98
pubmed: 29378223
Neurology. 2016 Mar 22;86(12):1112-9
pubmed: 26888983
Neuroimage. 2010 Dec;53(4):1233-43
pubmed: 20643215
Lancet Neurol. 2013 Aug;12(8):822-38
pubmed: 23867200
Neuroimage. 2004 Nov;23(3):1176-85
pubmed: 15528117
Neuroimage. 2017 Jan 1;144(Pt A):58-73
pubmed: 27639350
Magn Reson Med. 2011 Jun;65(6):1532-56
pubmed: 21469191
Hum Brain Mapp. 2016 Jul;37(7):2446-54
pubmed: 27004840
Neuroimage. 2012 Feb 1;59(3):2494-503
pubmed: 21925280
Hum Brain Mapp. 2014 Jun;35(6):2836-51
pubmed: 24115179
J Neurosci Methods. 2012 Feb 15;204(1):68-81
pubmed: 22108139
J Neurol Neurosurg Psychiatry. 2004 Mar;75(3):441-7
pubmed: 14966162
Neuroscience. 2015 Aug 20;301:79-89
pubmed: 26026680
BMC Neurol. 2011 Feb 28;11:29
pubmed: 21356112
Neuroimage. 2009 Jun;46(2):486-99
pubmed: 19385016
NMR Biomed. 2006 Apr;19(2):236-47
pubmed: 16521095
Lancet Neurol. 2003 Feb;2(2):89-98
pubmed: 12849265
Rev Neurol (Paris). 2017 Apr;173(4):201-210
pubmed: 28392060
Hum Brain Mapp. 2007 Nov;28(11):1251-66
pubmed: 17274023
Neuroimage. 2011 Apr 1;55(3):880-90
pubmed: 21182970
J Magn Reson Imaging. 2001 Apr;13(4):534-46
pubmed: 11276097
Neuroimage. 2013 Feb 1;66:119-32
pubmed: 23108278
Biochim Biophys Acta. 2012 Mar;1822(3):401-7
pubmed: 21549191
J Alzheimers Dis. 2012;32(3):667-76
pubmed: 22850313
Neuroimage. 2017 May 15;152:476-481
pubmed: 28315741
PLoS One. 2013 Apr 22;8(4):e61014
pubmed: 23613774
Neuroimage Clin. 2017 Sep 29;17:60-68
pubmed: 29527473
Clin Imaging. 2016 Jul-Aug;40(4):732-8
pubmed: 27317218
IEEE Trans Med Imaging. 2018 Jan;37(1):93-105
pubmed: 28708547
Neuroimage. 2012 Sep;62(3):1924-38
pubmed: 22705374
Neuroimage Clin. 2018;20:808-822
pubmed: 30268990
Neuroimage Clin. 2013 Nov 09;4:64-71
pubmed: 24319654
PLoS One. 2014 Mar 10;9(3):e91400
pubmed: 24614676
Neuroradiology. 2007 Jan;49(1):1-22
pubmed: 17115204
Neuroimage. 2004;23 Suppl 1:S208-19
pubmed: 15501092
Stroke. 2010 Oct;41(10 Suppl):S154-8
pubmed: 20876494
Neuroimage. 2011 Mar 1;55(1):133-41
pubmed: 21147236
Neurosci Lett. 2019 Feb 16;694:198-207
pubmed: 30528980
Neuroimage. 2002 Oct;17(2):825-41
pubmed: 12377157
Sci Rep. 2017 Mar 24;7:45131
pubmed: 28338052
Neuroimage. 2015 Oct 1;119:338-51
pubmed: 26163802
AJR Am J Roentgenol. 2014 Jan;202(1):W26-33
pubmed: 24370162
Hum Brain Mapp. 2018 Apr;39(4):1475-1488
pubmed: 29315951
Braz J Psychiatry. 2003 Sep;25(3):188-91
pubmed: 12975695
Brain Sci. 2019 Aug 01;9(8):
pubmed: 31374883
AJNR Am J Neuroradiol. 2008 Apr;29(4):632-41
pubmed: 18339720
J Neurosurg. 2013 Jun;118(6):1367-77
pubmed: 23540269
Neuroimage. 2017 Aug 1;156:286-292
pubmed: 28533118
J Neurotrauma. 2017 Jul 1;34(13):2109-2118
pubmed: 28152648
Neuroimage. 2014 Dec;103:411-426
pubmed: 25109526
Neuroimage Clin. 2018 Feb 22;18:608-616
pubmed: 29845009
Front Hum Neurosci. 2013 May 29;7:235
pubmed: 23755002
Neurology. 2014 Jul 22;83(4):304-11
pubmed: 24951477
Neuroimage. 2010 Oct 1;52(4):1289-301
pubmed: 20570617
Alzheimers Dement. 2015 Jun;11(6):710-7
pubmed: 25510382
Neuropsychologia. 2017 Sep;104:1-7
pubmed: 28750873
Brain. 2018 Mar 1;141(3):888-902
pubmed: 29309541