Multivariate prediction of functional outcome using lesion topography characterized by acute diffusion tensor imaging.
Acute stroke
Diffusion tensor imaging
Functional outcome
Prediction
Prognosis
Journal
NeuroImage. Clinical
ISSN: 2213-1582
Titre abrégé: Neuroimage Clin
Pays: Netherlands
ID NLM: 101597070
Informations de publication
Date de publication:
2019
2019
Historique:
received:
14
12
2018
revised:
03
04
2019
accepted:
08
04
2019
pubmed:
17
4
2019
medline:
3
4
2020
entrez:
17
4
2019
Statut:
ppublish
Résumé
The relationship between stroke topography and functional outcome has largely been studied with binary manual lesion segmentations. However, stroke topography may be better characterized by continuous variables capable of reflecting the severity of ischemia, which may be more pertinent for long-term outcome. Diffusion Tensor Imaging (DTI) constitutes a powerful means of quantifying the degree of acute ischemia and its potential relation to functional outcome. Our aim was to investigate whether using more clinically pertinent imaging parameters with powerful machine learning techniques could improve prediction models and thus provide valuable insight on critical brain areas important for long-term outcome. Eighty-seven thrombolyzed patients underwent a DTI sequence at 24 h post-stroke. Functional outcome was evaluated at 3 months post-stroke with the modified Rankin Score and was dichotomized into good (mRS ≤ 2) and poor (mRS > 2) outcome. We used support vector machines (SVM) to classify patients into good vs. poor outcome and evaluate the accuracy of different models built with fractional anisotropy, mean diffusivity, axial diffusivity, radial diffusivity asymmetry maps, and lesion segmentations in combination with lesion volume, age, recanalization status, and thrombectomy treatment. SVM classifiers built with axial diffusivity maps yielded the best accuracy of all imaging parameters (median [IQR] accuracy = 82.8 [79.3-86.2]%), compared to that of lesion segmentations (76.7 [73.3-82.8]%) when predicting 3-month functional outcome. The analysis revealed a strong contribution of clinical variables, notably - in descending order - lesion volume, thrombectomy treatment, and recanalization status, in addition to the deep white matter at the crossroads of major white matter tracts, represented by brain regions where model weights were highest. Axial diffusivity is a more appropriate imaging marker to characterize stroke topography for predicting long-term outcome than binary lesion segmentations.
Identifiants
pubmed: 30991303
pii: S2213-1582(19)30171-8
doi: 10.1016/j.nicl.2019.101821
pmc: PMC6462821
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
101821Informations de copyright
Copyright © 2019. Published by Elsevier Inc.
Références
Neuroimage. 2017 Jan 15;145(Pt B):166-179
pubmed: 27989847
Proc Natl Acad Sci U S A. 2010 Aug 10;107(32):14472-7
pubmed: 20660718
Nat Neurosci. 2003 May;6(5):448-50
pubmed: 12704393
Stroke. 2016 Jan;47(1):66-73
pubmed: 26585396
Hum Brain Mapp. 2002 Nov;17(3):143-55
pubmed: 12391568
J Neurol Neurosurg Psychiatry. 2004 Dec;75(12):1714-8
pubmed: 15548489
Neuroimage Clin. 2016 Aug 02;12:372-80
pubmed: 27595065
PLoS One. 2015 Nov 12;10(11):e0142910
pubmed: 26562509
Cereb Cortex. 2014 Mar;24(3):691-706
pubmed: 23162045
NMR Biomed. 2002 Nov-Dec;15(7-8):561-9
pubmed: 12489102
Stroke. 1999 Nov;30(11):2382-90
pubmed: 10548675
Med Image Anal. 2011 Oct;15(5):729-37
pubmed: 21752695
J Neurol Neurosurg Psychiatry. 2017 Sep;88(9):737-743
pubmed: 28642286
Front Neuroinform. 2014 Feb 21;8:14
pubmed: 24600388
Restor Neurol Neurosci. 2018;36(2):173-182
pubmed: 29526853
Neuroimage. 2018 Oct 15;180(Pt A):68-77
pubmed: 28655633
Neuroimage. 2010 Jan 1;49(1):127-33
pubmed: 19660556
Neuroimage. 2006 Sep;32(3):1195-204
pubmed: 16797189
Stroke. 2013 Mar;44(3):870-947
pubmed: 23370205
Nat Rev Neurosci. 2003 Jan;4(1):37-48
pubmed: 12511860
Neuroimage. 2016 Nov 15;142:394-406
pubmed: 27523449
IEEE Trans Med Imaging. 2001 Jan;20(1):45-57
pubmed: 11293691
Neurorehabil Neural Repair. 2015 Mar-Apr;29(3):287-95
pubmed: 25096274
Neuroimage. 2018 Dec;183:504-521
pubmed: 30130647
Magn Reson Med. 2016 Nov;76(5):1582-1593
pubmed: 26599599
Neuroradiology. 2011 Oct;53(10):763-71
pubmed: 21789602
Magn Reson Imaging. 2008 Jun;26(5):683-93
pubmed: 18440747
Stroke. 2010 Aug;41(8):1728-35
pubmed: 20595665
Neurosurg Focus. 2007 May 15;22(5):E2
pubmed: 17613233
Stroke. 2000 Jun;31(6):1429-38
pubmed: 10835468
Neuroimage Clin. 2018 Aug 10;20:506-522
pubmed: 30167371
Stroke. 2005 May;36(5):986-91
pubmed: 15817891
Hum Brain Mapp. 2015 Nov;36(11):4553-65
pubmed: 26381168
Neuron. 2015 Mar 4;85(5):927-41
pubmed: 25741721
J Magn Reson B. 1994 Mar;103(3):247-54
pubmed: 8019776
Proc Natl Acad Sci U S A. 2016 Jul 26;113(30):E4367-76
pubmed: 27402738
Neuroimage. 2004;23 Suppl 1:S208-19
pubmed: 15501092
AJNR Am J Neuroradiol. 2017 Jul;38(7):1328-1334
pubmed: 28473339
Stroke. 2016 Jun;47(6):1520-6
pubmed: 27217504
Neuroimage. 2018 Dec;183:186-199
pubmed: 30086410
Stroke. 2015 Sep;46(9):2438-44
pubmed: 26199314
Hum Brain Mapp. 2014 Dec;35(12):5861-76
pubmed: 25044213
Neuroimage. 2016 Nov 1;141:556-572
pubmed: 27393418
Neuroimage. 2017 Jan 15;145(Pt B):200-208
pubmed: 27502048
Stroke. 2011 Aug;42(8):2251-6
pubmed: 21719773
Stroke. 2014 Jun;45(6):1695-702
pubmed: 24781084
Stroke. 2015 Aug;46(8):2136-41
pubmed: 26152297
Neuroimage. 2016 Jan 15;125:1063-1078
pubmed: 26481672
Cortex. 2015 Dec;73:203-15
pubmed: 26465238
Neurorehabil Neural Repair. 2014 Oct;28(8):751-60
pubmed: 24519021
Neuroimage. 2011 May 15;56(2):387-99
pubmed: 21172442
Cereb Cortex. 2015 Sep;25(9):3046-56
pubmed: 24836690
Brain. 2010 Apr;133(Pt 4):1252-64
pubmed: 20299389
NMR Biomed. 2002 Nov-Dec;15(7-8):435-55
pubmed: 12489094
Brain. 2014 Sep;137(Pt 9):2522-31
pubmed: 24974384