The DOI matches its Crossref record; 70 of the 72 references it cites were found in a registry or an index.
Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
Open accessAbstract
&NA; Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people. Deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of ‘brain‐predicted age’ as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre‐processed and raw T1‐weighted MRI data. Firstly, we aimed to demonstrate the accuracy of CNN brain‐predicted age using a large dataset of healthy adults (N = 2001). Next, we sought to establish the heritability of brain‐predicted age using a sample of monozygotic and dizygotic female twins (N = 62). Thirdly, we examined the test‐retest and multi‐centre reliability of brain‐predicted age using two samples (within‐scanner N = 20; between‐scanner N = 11). CNN brain‐predicted ages were generated and compared to a Gaussian Process Regression (GPR) approach, on all datasets. Input data were grey matter (GM) or white matter (WM) volumetric maps generated by Statistical Parametric Mapping (SPM) or raw data. CNN accurately predicted chronological age using GM (correlation between brain‐predicted age and chronological age r = 0.96, mean absolute error [MAE] = 4.16 years) and raw (r = 0.94, MAE = 4.65 years) data. This was comparable to GPR brain‐predicted age using GM data (r = 0.95, MAE = 4.66 years). Brain‐predicted age was a heritable phenotype for all models and input data (h2 ≥ 0.5). Brain‐predicted age showed high test‐retest reliability (intraclass correlation coefficient [ICC] = 0.90–0.99). Multi‐centre reliability was more variable within high ICCs for GM (0.83–0.96) and poor‐moderate levels for WM and raw data (0.51–0.77). Brain‐predicted age represents an accurate, highly reliable and genetically‐influenced phenotype, that has potential to be used as a biomarker of brain ageing. Moreover, age predictions can be accurately generated on raw T1‐MRI data, substantially reducing computation time for novel data, bringing the process closer to giving real‐time information on brain health in clinical settings. HighlightsChronological age can be accurately predicted using convolutional neural networks.Age predicted is accurate even using raw structural neuroimaging data.Brain‐predicted age can be generated in a clinically applicable timeframe.Brain‐predicted age is significantly heritable.Brain‐predicted age is highly reliable, both within and between scanners.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879 · cited 1×
“In choosing between sub-models, variance components are excluded from the selection process if there is no significant deterioration in model fit after the component is dropped, as assessed by the Akaike Information Criterion (Akaike, 1974).”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“The architecture contains repeated 5 blocks of a (3 3 3) convolutional layer (with stride of 1), a rectified linear unit (ReLU), a (3 3 3) convolutional layer (with stride of 1), a 3D batch-normalization layer (Ioffe and Szegedy, 2015), a ReLU and finally a (2 2 2) max-pooling layer (with stride of 2).”
BackgroundIntraclass correlations: Uses in assessing rater reliability.
Shrout, P. E., & Fleiss, J. L. (1979) · Psychological Bulletin · doi:10.1037/0033-2909.86.2.420 · Cited by 24,532
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
A fast diffeomorphic image registration algorithm
Ashburner, J. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.07.007 · Cited by 8,122
A global optimisation method for robust affine registration of brain images
Jenkinson, M., & Smith, S. M. (2001) · Medical Image Analysis · doi:10.1016/s1361-8415(01)00036-6 · Cited by 7,018 · cited 1×
“Raw Nifti files then underwent a rigid registration (i.e. six degrees-of-freedom) to MNI152 space, (FMRIB Software Library [FSL] FLIRT, Jenkinson and Smith, 2001) to ensure consistency of orientation (Right, Posterior, Inferior [RPI]).”
Method3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,313
Avants, B., Epstein, C. L., Grossman, M., & Gee, J. C. (2007) · Medical Image Analysis · doi:10.1016/j.media.2007.06.004 · Cited by 5,924
Cited by
Sorted by citations
An overview of deep learning in medical imaging focusing on MRI
Lundervold, A. S., & Lundervold, A. (2019) · Zeitschrift für Medizinische Physik · doi:10.1016/j.zemedi.2018.11.002 · Cited by 2,058
“Brain age [273] Chronological age prediction from raw brain T1-MRI data, also testing the heritability of brain-predicted age”
MethodZhou, S. K., Greenspan, H. K., Davatzikos, C. A., Duncan, J. S., van Ginneken, B., Madabhushi, A., Prince, J. L., Rueckert, D., & Summers, R. M. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3054390 · Cited by 1,373
“In recent years, a large amount of work has been published on deep learning based prediction tasks such as brain age prediction [124], [125], [126], Alzheimer’s disease classification and trajectory modeling [127], [128], [129], [130], and schizophrenia classification [131], [132].”
BackgroundAn overview of deep learning in medical imaging focusing on MRI
Lundervold, A. S., & Lundervold, A. (2018) · NORA - Norwegian Open Research Archives · Cited by 1,012
Predicting Age Using Neuroimaging: Innovative Brain Ageing Biomarkers
Cole, J. H., & Franke, K. (2017) · Trends in Neurosciences · doi:10.1016/j.tins.2017.10.001 · Cited by 939
“In particular, deep learning methods show [344_TD$DIFF]considerable promise [9].”
Self-citationHeterogeneous aging across multiple organ systems and prediction of chronic disease and mortality
Tian, Y. E., Cropley, V., Maier, A. B., Lautenschlager, N. T., Breakspear, M., & Zalesky, A. (2023) · Nature Medicine · doi:10.1038/s41591-023-02296-6 · Cited by 618
Metadata
- Authors
- Cole, J. H., Poudel, R. P. K., Tsagkrasoulis, D., Caan, M. W. A., Steves, C., Spector, T. D., & Montana, G.
- Affiliations
- Imperial College London (GB)
- King's College London (GB)
- Amsterdam UMC Location University of Amsterdam (NL)
- Corresponding author
- Montana, Giovanni
- Venue
- NeuroImage
- Publisher
- Elsevier BV
- Published
- 2017-12
- Volume
- 163
- Pages
- 115-124
- ISSN
- 1053-8119 (ISSN-L)
- OpenAlex
- W2579617530
- Semantic Scholar
- 5d71c918db224e21982d9eb5ab2359735466959b
- Cited by
- 872
- References
- 72
- Citations by year
- 2026: 91 · 2025: 116 · 2024: 99 · 2023: 106 · 2022: 113 · 2021: 122 · 2020: 92 · 2019: 87 · 2018: 39 · 2017: 6
- FWCI
- 49.85
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- NeuroImage (publishedVersion)
- PubMed (publishedVersion)
- UCL Discovery (University College London) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- Data Archiving and Networked Services (DANS) (submittedVersion)
- Research Portal (King's College London) (submittedVersion, cc-by-nc-nd)
- Pure Amsterdam UMC (submittedVersion)
- Spiral (Imperial College London) (submittedVersion, cc-by-nc-nd)
- Warwick Research Archive Portal (University of Warwick) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Wellcome Trust
- Medical Research Council
- European Commision’s Seventh Framework Program (FP7/2007-2013, 259749)
- National Institute for Health Research (NIHR)
- BioResource, Clinical Research Facility
- Biomedical Research Centre
- St Thomas' NHS Foundation Trust
- NIHR Biomedical Research Centre
- Imperial College London from the Medical Research Council (MR/L022141/1)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Keywords
- brain age prediction, brain aging, biomarkers, heritability, monozygotic and dizygotic twins, test-retest reliability, convolutional neural networks, gray matter volume, white matter volume, Gaussian process regression, healthy adults, cognitive impairment risk, neuroimaging
- MeSH terms
- Machine Learning, Adolescent, Adult, Aged, Aged, 80 and over, Aging, Brain, Female, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Male, Middle Aged, Phenotype, Neural Networks, Computer, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
