Radiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke.
Journal
Neurology
ISSN: 1526-632X
Titre abrégé: Neurology
Pays: United States
ID NLM: 0401060
Informations de publication
Date de publication:
21 02 2023
21 02 2023
Historique:
received:
06
10
2021
accepted:
06
10
2022
pubmed:
29
11
2022
medline:
25
2
2023
entrez:
28
11
2022
Statut:
ppublish
Résumé
While chronological age is one of the most influential determinants of poststroke outcomes, little is known of the impact of neuroimaging-derived biological "brain age." We hypothesized that radiomics analyses of T2-FLAIR images texture would provide brain age estimates and that advanced brain age of patients with stroke will be associated with cardiovascular risk factors and worse functional outcomes. We extracted radiomics from T2-FLAIR images acquired during acute stroke clinical evaluation. Brain age was determined from brain parenchyma radiomics using an ElasticNet linear regression model. Subsequently, relative brain age (RBA), which expresses brain age in comparison with chronological age-matched peers, was estimated. Finally, we built a linear regression model of RBA using clinical cardiovascular characteristics as inputs and a logistic regression model of favorable functional outcomes taking RBA as input. We reviewed 4,163 patients from a large multisite ischemic stroke cohort (mean age = 62.8 years, 42.0% female patients). T2-FLAIR radiomics predicted chronological ages (mean absolute error = 6.9 years, T2-FLAIR radiomics can be used to predict brain age and derive RBA. Older-appearing brains, characterized by a higher RBA, reflect cardiovascular risk factor accumulation and are linked to worse outcomes after stroke.
Sections du résumé
BACKGROUND AND OBJECTIVES
While chronological age is one of the most influential determinants of poststroke outcomes, little is known of the impact of neuroimaging-derived biological "brain age." We hypothesized that radiomics analyses of T2-FLAIR images texture would provide brain age estimates and that advanced brain age of patients with stroke will be associated with cardiovascular risk factors and worse functional outcomes.
METHODS
We extracted radiomics from T2-FLAIR images acquired during acute stroke clinical evaluation. Brain age was determined from brain parenchyma radiomics using an ElasticNet linear regression model. Subsequently, relative brain age (RBA), which expresses brain age in comparison with chronological age-matched peers, was estimated. Finally, we built a linear regression model of RBA using clinical cardiovascular characteristics as inputs and a logistic regression model of favorable functional outcomes taking RBA as input.
RESULTS
We reviewed 4,163 patients from a large multisite ischemic stroke cohort (mean age = 62.8 years, 42.0% female patients). T2-FLAIR radiomics predicted chronological ages (mean absolute error = 6.9 years,
DISCUSSION
T2-FLAIR radiomics can be used to predict brain age and derive RBA. Older-appearing brains, characterized by a higher RBA, reflect cardiovascular risk factor accumulation and are linked to worse outcomes after stroke.
Identifiants
pubmed: 36443016
pii: WNL.0000000000201596
doi: 10.1212/WNL.0000000000201596
pmc: PMC9984219
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e822-e833Subventions
Organisme : NHLBI NIH HHS
ID : K01 HL128791
Pays : United States
Organisme : NIBIB NIH HHS
ID : P41 EB015902
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS086905
Pays : United States
Informations de copyright
© 2022 American Academy of Neurology.
Références
Front Neurol. 2021 Sep 10;12:700616
pubmed: 34566844
J Neurointerv Surg. 2021 Oct;13(10):865-868
pubmed: 33127734
Sci Rep. 2020 Nov 17;10(1):19940
pubmed: 33203906
Neurobiol Aging. 2016 Apr;40:138-144
pubmed: 26973113
Neurology. 2014 May 20;82(20):1776-83
pubmed: 24748670
Restor Neurol Neurosci. 2020;38(1):67-92
pubmed: 31929129
Cerebrovasc Dis. 2006;22(1):61-70
pubmed: 16645268
Neuroimage. 2017 Dec;163:115-124
pubmed: 28765056
Neurology. 2020 Jul 7;95(1):e79-e88
pubmed: 32493718
Neuroimage Clin. 2020;25:102159
pubmed: 31927499
Neurobiol Aging. 2020 Aug;92:34-42
pubmed: 32380363
Neuroimage. 2019 Oct 15;200:528-539
pubmed: 31201988
Med Image Anal. 2020 Jul;63:101698
pubmed: 32339896
Nat Rev Clin Oncol. 2017 Dec;14(12):749-762
pubmed: 28975929
Front Aging Neurosci. 2019 Dec 10;11:348
pubmed: 31920628
Front Aging Neurosci. 2013 Dec 17;5:90
pubmed: 24381557
Nat Commun. 2021 Jun 2;12(1):3289
pubmed: 34078897
Stroke. 2017 Oct;48(10):e284-e303
pubmed: 28883125
Med Image Anal. 2021 Feb;68:101871
pubmed: 33197716
Neuroimage Clin. 2019;23:101884
pubmed: 31200151
Radiol Artif Intell. 2020 Mar 25;2(2):e200029
pubmed: 33937821
Front Neurol. 2019 Aug 14;10:789
pubmed: 31474922
Front Neurol. 2019 Mar 21;10:274
pubmed: 30949127
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
J Stroke Cerebrovasc Dis. 2019 Jan;28(1):63-69
pubmed: 30269881
Front Neurosci. 2021 Jul 12;15:691244
pubmed: 34321995
Sci Rep. 2020 Jan 30;10(1):10
pubmed: 32001736
J Neuroimaging. 2022 Jan;32(1):63-67
pubmed: 34506667
Neuroimage. 2020 Nov 15;222:117292
pubmed: 32835819
Neuroimage. 2017 Mar 1;148:179-188
pubmed: 27890805
Neurology. 2020 Jul 14;95(2):e131-e139
pubmed: 32527972
Alzheimers Dement. 2020 Sep;16(9):1305-1311
pubmed: 30222945
Lancet. 2016 Apr 23;387(10029):1723-31
pubmed: 26898852