Brain Age Estimation on a Dementia Cohort Using FLAIR MRI Biomarkers.
Journal
AJNR. American journal of neuroradiology
ISSN: 1936-959X
Titre abrégé: AJNR Am J Neuroradiol
Pays: United States
ID NLM: 8003708
Informations de publication
Date de publication:
11 Dec 2023
11 Dec 2023
Historique:
received:
26
05
2023
accepted:
13
10
2023
pmc-release:
01
12
2024
pubmed:
5
12
2023
medline:
5
12
2023
entrez:
5
12
2023
Statut:
epublish
Résumé
The prodromal stage of Alzheimer's disease presents an imperative intervention window. This work focuses on using brain age prediction models and biomarkers from FLAIR MR imaging to identify subjects who progress to Alzheimer's disease (converting mild cognitive impairment) or those who remain stable (stable mild cognitive impairment). A machine learning model was trained to predict the age of normal control subjects on the basis of volume, intensity, and texture features from 3239 FLAIR MRI volumes. The brain age gap estimation (BrainAGE) was computed as the difference between the predicted and true age, and it was used as a biomarker for both cross-sectional and longitudinal analyses. Differences in biomarker means, slopes, and intercepts were investigated using ANOVA and Tukey post hoc test. Correlation analysis was performed between brain age gap estimation and established Alzheimer's disease indicators. The brain age prediction model showed accurate results (mean absolute error = 2.46 years) when testing on held out normal control data. The computed BrainAGE metric showed significant differences between the stable mild cognitive impairment and converting mild cognitive impairment groups in cross-sectional and longitudinal analyses, most notably showing significant differences up to 4 years before conversion to Alzheimer's disease. A significant correlation was found between BrainAGE and previously established Alzheimer's disease conversion biomarkers. The BrainAGE metric can allow clinicians to consider a single explainable value that summarizes all the biomarkers because it considers many dimensions of disease and can determine whether the subject has normal aging patterns or if he or she is trending into a high-risk category using a single value.
Sections du résumé
BACKGROUND AND PURPOSE
OBJECTIVE
The prodromal stage of Alzheimer's disease presents an imperative intervention window. This work focuses on using brain age prediction models and biomarkers from FLAIR MR imaging to identify subjects who progress to Alzheimer's disease (converting mild cognitive impairment) or those who remain stable (stable mild cognitive impairment).
MATERIALS AND METHODS
METHODS
A machine learning model was trained to predict the age of normal control subjects on the basis of volume, intensity, and texture features from 3239 FLAIR MRI volumes. The brain age gap estimation (BrainAGE) was computed as the difference between the predicted and true age, and it was used as a biomarker for both cross-sectional and longitudinal analyses. Differences in biomarker means, slopes, and intercepts were investigated using ANOVA and Tukey post hoc test. Correlation analysis was performed between brain age gap estimation and established Alzheimer's disease indicators.
RESULTS
RESULTS
The brain age prediction model showed accurate results (mean absolute error = 2.46 years) when testing on held out normal control data. The computed BrainAGE metric showed significant differences between the stable mild cognitive impairment and converting mild cognitive impairment groups in cross-sectional and longitudinal analyses, most notably showing significant differences up to 4 years before conversion to Alzheimer's disease. A significant correlation was found between BrainAGE and previously established Alzheimer's disease conversion biomarkers.
CONCLUSIONS
CONCLUSIONS
The BrainAGE metric can allow clinicians to consider a single explainable value that summarizes all the biomarkers because it considers many dimensions of disease and can determine whether the subject has normal aging patterns or if he or she is trending into a high-risk category using a single value.
Identifiants
pubmed: 38050032
pii: ajnr.A8059
doi: 10.3174/ajnr.A8059
pmc: PMC10714845
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1384-1390Informations de copyright
© 2023 by American Journal of Neuroradiology.
Références
Med Image Anal. 2018 Apr;45:68-82
pubmed: 29414437
Magn Reson Imaging. 2019 Oct;62:59-69
pubmed: 31102612
J Intern Med. 2004 Sep;256(3):183-94
pubmed: 15324362
Neuroimage. 2023 Apr 15;270:119947
pubmed: 36801372
Alzheimers Dement. 2007 Jul;3(3):186-91
pubmed: 19595937
J Magn Reson Imaging. 2008 Apr;27(4):685-91
pubmed: 18302232
Front Neurol. 2019 Aug 14;10:789
pubmed: 31474922
Neurobiol Aging. 2020 Aug;92:34-42
pubmed: 32380363
Sci Transl Med. 2021 Mar 3;13(583):
pubmed: 33658354
Front Aging Neurosci. 2018 Oct 24;10:317
pubmed: 30405393
Cold Spring Harb Perspect Med. 2012 Aug 01;2(8):
pubmed: 22908189
Mol Neurodegener. 2019 Aug 2;14(1):32
pubmed: 31375134
Neurology. 2002 Jun 25;58(12):1791-800
pubmed: 12084879
Neurobiol Aging. 2008 Oct;29(10):1466-73
pubmed: 17512092
Neuroimage Clin. 2020;26:102229
pubmed: 32120292
Alzheimers Dement. 2016 Apr;12(4):459-509
pubmed: 27570871
Lancet. 2006 Apr 15;367(9518):1262-70
pubmed: 16631882
Neuroimage Clin. 2022;34:102955
pubmed: 35180579
Cell. 2013 Jun 6;153(6):1194-217
pubmed: 23746838
Neurology. 2017 Jan 24;88(4):403-413
pubmed: 27986875
Brain. 2023 Mar 1;146(3):842-849
pubmed: 36655336
Hum Brain Mapp. 2019 Aug 1;40(11):3143-3152
pubmed: 30924225
PLoS One. 2013 Jun 27;8(6):e67346
pubmed: 23826273
Stroke. 2009 Mar;40(3 Suppl):S48-52
pubmed: 19064767
Theranostics. 2022 Jan 31;12(5):2041-2062
pubmed: 35265198