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
Flagged first, then by citations
2 of the 72 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 401–500 of 869
Dissecting unique and common variance across body and brain health indicators using age prediction
Beck, D., de Lange, A. G., Gurholt, T. P., Voldsbekk, I., Maximov, I. I., Subramaniapillai, S., Schindler, L. S., Hindley, G., Leonardsen, E. H., Rahman, Z., et al. (2024) · Human Brain Mapping · doi:10.1002/hbm.26685 · Cited by 10
“…high accuracy based on brain white (WM) and gray matter (GM) characteristics derived from diffusion and T1-weighted MRI scans (Beck et al., 2021; Cole et al., 2017; Leonardsen et al., 2022), providing neuroanatomical markers of brain health and integrity (Cole & Franke, 2017; Franke et al.,…”
Background[18F]FDG PET integrated with structural MRI for accurate brain age prediction
Xue, L., Fu, Y., Gao, X., Feng, G., Qian, S., Wei, L., Li, L., Zhuo, C., Zhang, H., & Tian, M. (2024) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-024-06784-w · Cited by 11
“Previous studies on brain age estimation have predominantly focused on T1w images, which primarily capture structural or morphological brain changes [ 2– 5].”
Analysis of Brain Age Gap across Subject Cohorts and Prediction Model Architectures
Dular, L., Špiclin, Ž., Initiative, A. D. N., & Ageing, T. A. I. B. A. L. F. S. O. (2024) · Biomedicines · doi:10.3390/biomedicines12092139 · Cited by 11
Feng, L., Ye, Z., Du, Z., Pan, Y., Canida, T. A., Ke, H., Liu, S., Chen, S., Hong, L. E., Kochunov, P. V., et al. (2024) · American Journal of Epidemiology · doi:10.1093/aje/kwae396 · Cited by 11
Kojori, E. S., Bennett, I. J., Tomeldan, Z. A., Krawczyk, D. C., & Bart Rypma, A. (2021) · Brain Research · doi:10.1016/j.brainres.2021.147431 · Cited by 11
Connectome-based predictive models using resting-state fMRI for studying brain aging
Kim, E., Kim, S., Kim, Y., Cha, H., Lee, H. J., Lee, T., & Chang, Y. (2022) · Experimental Brain Research · doi:10.1007/s00221-022-06430-7 · Cited by 11
The value of arterial spin labelling perfusion MRI in brain age prediction
Dijsselhof, M. B. J., Barboure, M. C., Stritt, M., Nordhøy, W., Wink, A. M., Beck, D., Westlye, L. T., Cole, J. H., Barkhof, F., Mutsaerts, H. J. M. M., et al. (2023) · Human Brain Mapping · doi:10.1002/hbm.26242 · Cited by 11
“Contrary to these results, GPR combined with structural features performed well in previous applications to determine brain age, however, this has been performed on far larger data sets (n = 2001) (Cole et al., 2017).”
ResultSelf-citationBrain Age Estimation from MRI Using a Two-Stage Cascade Network with Ranking Loss
Liu, Z., Cheng, J., Zhu, H., Zhang, J., & Liu, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59728-3_20 · Cited by 11
Towards Self-explainable Classifiers and Regressors in Neuroimaging with Normalizing Flows
Wilms, M., Mouchès, P., Bannister, J. J., Rajashekar, D., Langner, S., & Forkert, N. D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87586-2_3 · Cited by 11
BrainAge of patients with severe late-life depression referred for electroconvulsive therapy
Wagenmakers, M. J., Oudega, M. L., Klaus, F., Wing, D., Orav, G., Han, L. K. M., Binnewies, J., Beekman, A. T. F., Veltman, D. J., Rhebergen, D., et al. (2023) · Journal of Affective Disorders · doi:10.1016/j.jad.2023.02.047 · Cited by 10
Valdes-Hernandez, P., Johnson, A. J., Montesino-Goicolea, S., Nodarse, C. L., Bashyam, V. M., Davatzikos, C., Fillingim, R., & Cruz-Almeida, Y. (2023) · Journal of Pain · doi:10.1016/j.jpain.2023.11.006 · Cited by 8
Deep learning-based, fully automated, pediatric brain segmentation
Kim, M., Hong, E., Yum, M., Lee, Y. J., Kim, J., & Ko, T. (2024) · Scientific Reports · doi:10.1038/s41598-024-54663-z · Cited by 11
Brain Age Prediction Using Multi-Hop Graph Attention Combined with Convolutional Neural Network
Lim, H., Joo, Y., Ha, E., Song, Y., Yoon, S. J., & Shin, T. (2024) · Bioengineering · doi:10.3390/bioengineering11030265 · Cited by 10
“Since the first CNN application to brain age prediction by Cole et al. [23], established CNN architectures verified on natural images or their variants have emerged, including VGG, ResNet, and DenseNet [5,24,25].”
MethodBorrelli, S., Guisset, F., Bulcke, C. V., Stölting, A., Bugli, C., Lolli, V. E., Pasquier, R. D., Pesch, V. V., Absinta, M., Pasi, M., et al. (2024) · Multiple Sclerosis Journal · doi:10.1177/13524585241256881 · Cited by 11
Replication and Refinement of Brain Age Model for Adolescent Development
Ray, B., Chen, J., Fu, Z., Suresh, P., Thapaliya, B., Farahdel, B., Calhoun, V. D., & Liu, J. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635532 · Cited by 11
Brain age prediction via cross-stratified ensemble learning
Li, X., Hao, Z., Li, D., Jin, Q., Tang, Z., Yao, X., & Wu, T. (2024) · NeuroImage · doi:10.1016/j.neuroimage.2024.120825 · Cited by 10
“Thirdly, our proposed method was compared with the SOTA algorithms of 3D-CNN (Cole et al., 2017), SFCN (Peng et al., 2021), EfficientNet (Poloni and Ferrari, 2022), and an ensemble learning model (Levakov et al., 2020).”
Pilli, R., Goel, T., & Murugan, R. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108617 · Cited by 10
Assessing brain and biological aging trajectories associated with Alzheimer’s disease
Liang, W. S., Goetz, L. H., & Schork, N. J. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.1036102 · Cited by 12
“, 2018), and convolutional neural networks (Cole et al., 2017), which distinguished brain age gaps of early-onset (<65 years old) AD subjects from controls (Gautherot et al.”
Background3DCNN predicting brain age using diffusion tensor imaging
Wang, Y., Wen, J., Xin, J., Zhang, Y., Xie, H., & Tang, Y. (2023) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-023-02915-x · Cited by 10
“The sMRI provides detailed structural information about brain morphometry, such as the measurements of volumes, cortical thickness, surface area, and tissue compositions, which has been widely used to study (a)typical brain aging, and brain development [11, 16].”
Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections
Jönemo, J., Akbar, M. U., Kämpe, R., Hamilton, J. P., & Eklúnd, A. (2023) · Brain Sciences · doi:10.3390/brainsci13091329 · Cited by 10
Roca, V., Kuchcinski, G., Pruvo, J., Manouvriez, D., Leclerc, X., & Lopes, R. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e22647 · Cited by 13
“In the present study, we implemented an age prediction model similar to that described by Cole et al. [53]; the goal was to evaluate the harmonization approach’s ability to conserve or accentuate biological patterns.”
BackgroundMethodGemein, L. A. W., Schirrmeister, R. T., Boedecker, J., & Tonio Ball, A. (2024) · Imaging Neuroscience · doi:10.1162/imag_a_00210 · Cited by 9
Tensor Contraction & Regression Networks
Kossaifi, J., Lipton, Z. C., Khanna, A., Furlanello, T., & Anandkumar, A. (2018) · Cited by 15
Predicting Fluid Intelligence from Structural MRI Using Random Forest regression
Wlaszczyk, A., Kaminska, A., Pietraszek, A., Dąbrowski, J., Pawlak, M. A., & Nowicka, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31901-4_10 · Cited by 9
Decentralized Brain Age Estimation Using MRI Data
Basodi, S., Raja, R., Ray, B., Gazula, H., Sarwate, A. D., Plis, S., Liu, J., Verner, E., & Calhoun, V. D. (2022) · Neuroinformatics · doi:10.1007/s12021-022-09570-x · Cited by 10
“These and other studies (Cole et al., 2017; Yang et al., 2019; Franke & Gaser, 2019) suggest BAE may serve as an important bio-marker in understanding the aging process of the brain and its relationship to brain health and disorder.”
MethodResultNeuroCrypt: Machine Learning Over Encrypted Distributed Neuroimaging Data
Senanayake, N., Podschwadt, R., Takabi, D., Calhoun, V. D., & Plis, S. (2021) · Neuroinformatics · doi:10.1007/s12021-021-09525-8 · Cited by 10
“…Greenspan et al. 2016; Pizarro et al. 2019); specifically in the image preprocessing, diagnostic classification, regression, disease characterization, and disease prediction domains (Mahmood et al. 2020; Plis et al. 2014; Oh et al. 2019; Cole et al. 2017; Fedorov et al. 2019; Abrol et al. 2019).”
BackgroundFinkelstein, O., Levakov, G., Kaplan, A., Zelicha, H., Meir, A. Y., Rinott, E., Tsaban, G., Witte, A. V., Blüher, M., Stümvoll, M., et al. (2024) · Human Brain Mapping · doi:10.1002/hbm.26595 · Cited by 8
“Once trained, at the inference phase, the networks can predict brain age based only on the imaging data, which can be either structural as done in the current study (Cole et al., 2017; Franke et al., 2012) or functional (Levakov et al., 2023; Lund et al., 2022).”
MethodKounios, J., Fleck, J. I., Zhang, F., & Oh, Y. (2024) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2024.1340732 · Cited by 10
Zhou, J., Chen, Y., Jin, X., Mao, W., Xiao, Z., Zhang, S., Zhang, T., Liu, T., Kendrick, K. M., & Jiang, X. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106592 · Cited by 9
Zabihi, M., Kia, S. M., Wolfers, T., de Boer, A. A. A., Fraza, C., Soheili‐Nezhad, S., Llera, A., Bzdok, D., Beckmann, C. F., Beckmann, C. F., et al. (2024) · PLoS ONE · doi:10.1371/journal.pone.0308329 · Cited by 19
Hofmann, S., Goltermann, O., Scherf, N., Müller, K., Loeffler, M., Villringer, A., Gaebler, M., Witte, A. V., & Beyer, F. (2025) · Imaging Neuroscience · doi:10.1162/imag_a_00497 · Cited by 9
“…Vieira et al., 2017; Zhang et al., 2018) and the estimation of continuous variables such as brain age (BA; Ball et al., 2021; Bashyam et al., 2020; Cole et al., 2017; Dinsdale et al., 2021; Feng et al., 2020; Peng et al., 2021) from minimally processed magnetic resonance images (MRIs), avoiding a…”
Do Transformers and CNNs Learn Different Concepts of Brain Age?
Siegel, N. T., Kainmueller, D., Deniz, F., Ritter, K., & Schulz, M.-A. (2025) · Human Brain Mapping · doi:10.1002/hbm.70243 · Cited by 12
Data augmentation for medical image analysis
Zhao, H., Li, H., & Li, C. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824349-7.00021-9 · Cited by 9
Interpretation for Individual Brain Age Prediction Based on Gray Matter Volume
Sun, J., Tu, Z., Meng, D., Gong, Y., Zhang, M., & Xu, J. (2022) · Brain Sciences · doi:10.3390/brainsci12111517 · Cited by 9
“found that both deep learning and Gaussian process regression (GPR) methods were able to achieve age prediction accurately for a given pre-processed data [14].”
BackgroundMendes, S. L., Pinaya, W. H. L., Pan, P. M., Jackowski, A. P., Bressan, R. A., & Sato, J. R. (2023) · Scientific Reports · doi:10.1038/s41598-023-33920-7 · Cited by 9
Multimodal Brain Age Estimation Using Interpretable Adaptive Population-Graph Learning
Bintsi, K.-M., Baltatzis, V., Potamias, R. A., Hammers, A., & Rueckert, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43993-3_19 · Cited by 9
Estimating Biological Age from Physical Activity using Deep Learning with 3D CNN
Rahman, S. A., & Adjeroh, D. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983251 · Cited by 9
A High-Powered Brain Age Prediction Model Based on Convolutional Neural Network
Rao, G., Li, A., Liu, Y., & Liu, B. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098376 · Cited by 9
“To verify the superiority of our new model, we compared our method with other deep learning models proposed recently, including multichannel 3D-CNN + full connect layer [12], cascading 3D-CNN + full connect layer [13], multiplex network [14].”
MethodLarge-Scale Inference of Liver Fat with Neural Networks on UK Biobank Body MRI
Langner, T., Strand, R., Ahlström, H. K., & Kullberg, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59713-9_58 · Cited by 9
“Similar strategies have been previously applied to a range of medical imaging modalities including MRI, with the goal of quantifying properties such as age [2][4][10] and structures of the heart [17], but also blood pressure and smoking status [12].”
BackgroundAI-based investigation of molecular biomarkers of longevity
Kendiukhov, I. (2020) · Biogerontology · doi:10.1007/s10522-020-09890-y · Cited by 16
High-accuracy Decoding of Complex Visual Scenes from Neuronal Calcium ResponsesPreprint
Ellis, R. J., & Michaelides, M. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/271296 · Cited by 8
de Lange, A. G., Barth, C., Kaufmann, T., Maximov, I. I., van der Meer, D., Agartz, I., & Westlye, L. T. (2019) · MPG.PuRe (Max Planck Society) · Cited by 11
Constantinides, C., Baltramonaityte, V., Caramaschi, D., Han, L. K. M., Lancaster, T. M., Zammit, S., Freeman, T. P., & Walton, E. (2023) · Cortex · doi:10.1016/j.cortex.2023.11.015 · Cited by 8
Brusaferri, L., Alshelh, Z., Schnieders, J. H., Sandström, A., Mohammadian, M., Morrissey, E. J., Kim, M., Chane, C. A., Grmek, G., Murphy, J. P., et al. (2023) · Brain Behavior and Immunity · doi:10.1016/j.bbi.2023.12.016 · Cited by 8
Artificial Intelligence Diagnosis of Parkinson's Disease From MRI Scans
Reddy, S., Giri, D., & Patel, R. (2024) · Cureus · doi:10.7759/cureus.58841 · Cited by 12
“In neurology, artificial intelligence (AI) has rapidly emerged as a transformative tool with diverse applications across various domains, revolutionizing the landscape of disease diagnosis, prognosis, and treatment [12].”
BackgroundA voxel-level approach to brain age prediction: A method to assess regional brain aging
Gianchandani, N., Dibaji, M., Ospel, J. M., Vega, F., Bento, M., MacDonald, M. E., & de Souza, R. M. (2024) · The Journal of Machine Learning for Biomedical Imaging · doi:10.59275/j.melba.2024-4dg2 · Cited by 11
“An effective biomarker of neurological disorders is increased brain age (Cole et al., 2017, 2018; Huang et al., 2017).”
BackgroundMethodMFCA: Collaborative prediction algorithm of brain age based on multimodal fuzzy feature fusion
Ding, W., Wang, J., Huang, J., Cheng, C., & Jiang, S. (2024) · Information Sciences · doi:10.1016/j.ins.2024.121376 · Cited by 8
Epilepsy is associated with the accelerated aging of brain activity in sleep
Hadar, P., Westmeijer, M., Sun, H., Meulenbrugge, E., Jin, J., Paixao, L., Tesh, R. A., Cardoso, M. D. S., Arnal, P. J., Au, R., et al. (2024) · Frontiers in Physiology · doi:10.3389/fphys.2024.1458592 · Cited by 8
Brain Age as a New Measure of Disease Stratification in Huntington's Disease
Abeyasinghe, P. M., Cole, J. H., Razi, A., Poudel, G. R., Paulsen, J. S., Tabrizi, S. J., Long, J. D., & Georgiou‐Karistianis, N. (2025) · Movement Disorders · doi:10.1002/mds.30109 · Cited by 8
“26 As a result, a separate data harmonization method was deemed unnecessary when combining data from various sites and scanners.”
Self-citationDisparities in accelerated brain aging in recent-onset and chronic schizophrenia
Joo, S. W., Lee, J., Han, J., Kim, M., Kim, Y., Lee, H., Jo, Y. T., Shin, J., Lee, J. S., & Lee, W. H. (2025) · Psychological Medicine · doi:10.1017/s0033291725000285 · Cited by 8
“Multiple studies have demonstrated that smaller datasets significantly impact model performance, highlighting the critical need for larger datasets to enhance prediction accuracy and generalizability (Cole et al., 2017).”
Network Occlusion Sensitivity Analysis Identifies Regional Contributions to Brain Age Prediction
He, L., Wang, S., Chen, C., Wang, Y., Fan, Q., Chu, C., Fan, L., & Xu, J. (2025) · Human Brain Mapping · doi:10.1002/hbm.70239 · Cited by 9
“By predicting the difference between individual brain age and chronological age, we can infer the risk of neuro-degenerative diseases and even mortality (Cole et al. 2018; Elliott et al. 2021; Jawinski et al. 2022).”
Network Modeling Sex Differences in Brain Integrity and Metabolic Health
Foret, J. T., Dekhtyar, M., Cole, J. H., Gourley, D., Caillaud, M. L., Tanaka, H., & Haley, A. P. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.691691 · Cited by 8
“Brain-predicted age was estimated using themachine-learning framework (Gaussian Process) devised by Cole (2017) and Cole et al. (2017) and trained on data available via public repositories from 2001 healthy individuals ages 18–90. brainPAD was calculated by subtracting chronological age from…”
MethodSelf-citationDeep learning prediction of stroke thrombus red blood cell content from multiparametric MRI
Christiansen, S. D., Liu, J., Bullrich, M. B., Sharma, M., Boulton, M., Pandey, S. K., Sposato, L. A., & Drangova, M. (2022) · Interventional Neuroradiology · doi:10.1177/15910199221140962 · Cited by 8
“20,21 CNNs have also demonstrated utility related to AIS, in areas such as predicting ischemic tissue fate and thrombus detection.”
A ResNet mini architecture for brain age prediction
Zhang, X., Duan, S., Wang, S., Chen, Y., Lai, S., Zou, J.-S., Cheng, Y., Guan, J.-T., Wu, R., & Zhang, X. (2024) · Scientific Reports · doi:10.1038/s41598-024-61915-5 · Cited by 8
Network and state specificity in connectivity‐based predictions of individual behavior
Kraljević, N., Langner, R., Küppers, V., Raimondo, F., Patil, K. R., Eickhoff, S. B., & Müller, V. I. (2024) · Human Brain Mapping · doi:10.1002/hbm.26753 · Cited by 8
“A number of studies in this area have shown that, for example, regional gray-matter volume and structural connectivity significantly predict age (Cole et al., 2017; Franke et al., 2012; More et al., 2023), reading comprehension (Cui et al.”
BackgroundSun, J., Han, J. J., & Chen, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-78712-9 · Cited by 8
Dragendorf, E., Bültmann, E., & Wolff, D. (2024) · Frontiers Neuroinformatics · doi:10.3389/fninf.2024.1496143 · Cited by 7
Gu, Y., Wong, N. M. L., Chan, C. C. H., Wu, J., & Lee, T. M. C. (2025) · GeroScience · doi:10.1007/s11357-025-01515-x · Cited by 8
“The brain-age gap is a widely used index indicating a potential difference between an individual’s predicted brain age and chronological age, offering insights into the senescence process [71].”
Mind the Gap: Does Brain Age Improve Alzheimer’s Disease Prediction?
Tan, T. W. K., Nguyen, K., Zhang, C., Kong, R., Cheng, S. F., Ji, F., Chong, J. S. X., Chong, E. J. Y., Venketasubramanian, N., Orbán, C., et al. (2025) · Human Brain Mapping · doi:10.1002/hbm.70276 · Cited by 10
“In the case of brain age, this involves training a machine learning model to predict chronological age from brain imaging data of healthy individuals (Cole et al. 2017; Dosenbach et al. 2010; Franke et al. 2010).”
Organ-Based Chronological Age Estimation Based on 3D MRI Scans
Armanious, K., Abdulatif, S., Bhaktharaguttu, A. R., Küstner, T., Hepp, T., Gatidis, S., & Yang, B. (2020) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco47968.2020.9287398 · Cited by 8
“More notably, shallow 3D CNN architecture were used to predict the brain age using T1-weighted MRI volumes [16], [17].”
MethodRisk score-embedded deep learning for biological age estimation: Development and validation
Kim, S., Kim, H., Lee, E.-S., Lim, C., & Lee, J. (2021) · Information Sciences · doi:10.1016/j.ins.2021.12.015 · Cited by 8
Federation of Brain Age Estimation in Structural Neuroimaging Data
Basodi, S., Raja, R., Ray, B., Gazula, H., Liu, J., Verner, E., & Calhoun, V. D. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9629865 · Cited by 8
“Authors of [10] compute BAE using both raw MR images and preprocessed MR images with deep learning models, and both showed consistent results.”
ResultGuo, Y., Yang, X. C., Yuan, Z., Qiu, J., & Lu, W. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac4bfe · Cited by 8
“8 between brainpredicted age and chronological age [9, 10].”
The Impact of Genes and Environment on Brain Ageing in Males Aged 51 to 72 Years
Gillespie, N. A., Hatton, S. N., Hagler, D. J., Dale, A. M., Elman, J. A., McEvoy, L. K., Eyler, L. T., Fennema‐Notestine, C., Logue, M. W., McKenzie, R. E., et al. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.831002 · Cited by 8
Giannakopoulos, P., Montandon, M., Herrmann, F. R., Hedderich, D. M., Christian Gaser, B., Kellner, E., Rodriguez, C. K., & Haller, S. (2022) · European Radiology · doi:10.1007/s00330-022-08798-0 · Cited by 8
“It was shown to be altered in various neuropsychiatric conditions, most prominently in age-associated disorders such as Alzheimer’s disease (AD) [27].”
BackgroundGao, X., & Pang, Y. (2022) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/iwecai55315.2022.00101 · Cited by 8
Zhang, S., Wang, R., Wang, J., He, Z., Wu, J., Kang, Y., Zhang, Y., Gao, H. B., Hu, X., & Zhang, T. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.951508 · Cited by 8
“Thus, the advanced learning algorithms are preferred to be adopted into the study of differentiating and characterizing brain diseases and biomarkers (Cole et al., 2017; Mehdipour Ghazi et al., 2019).”
BackgroundAssociations between polygenic risk scores and accelerated brain ageing in smokers
Yang, Z., Zhao, W. D., Linli, Z., Guo, S., & Feng, J. (2023) · Psychological Medicine · doi:10.1017/s0033291723001812 · Cited by 8
“In addition, BAG has been confirmed to be heritable (Cole et al., 2017) and has polygenic overlaps with brain disorders such as schizophrenia (SCZ), bipolar disorder, multiple sclerosis, and Alzheimer ’ s disease with BAG (Luders, Cherbuin, & Gaser, 2016).”
BackgroundAssociation of brain age with smoking, alcohol consumption, and genetic variantsPreprint
Ning, K., Zhao, L., Matloff, W. J., Sun, F., & Toga, A. W. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/469924 · Cited by 8
“PBA has been derived and used in several studies, where the mean absolute error between PBA and CA was less than 5 years in adults (Cole and Franke, 2017; Cole et al., 2017b; Franke et al., 2010).”
BackgroundMethodResultInfluentialDufumier, B., Gori, P., Battaglia, I., Victor, J., Grigis, A., & Duchesnay, É. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01132 · Cited by 22
“As we shall demonstrate, this over-fitting effect can be largely attributed to the bias towards the acquisition sites (in line with [36]), which explains why it has not been systematically reported [12, 80].”
BackgroundMethodInfluentialBiological age and brain age in midlife: relationship to multimorbidity and mental health
Zhang, F., Chang, H., Schaefer, S. M., & Gou, J. (2023) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2023.09.003 · Cited by 7
Feng, L., Milleson, H. S., Ye, Z., Canida, T. A., Ke, H., Liang, M., Gao, S., Chen, S., Hong, L. E., Kochunov, P., et al. (2024) · Genes · doi:10.3390/genes15101285 · Cited by 7
“The scaler BAG is a robust, easily interpretable metric that simplifies complex multivariate analyses [20,21,28], making it ideal for XWAS analysis of brain aging.”
BackgroundBrain Age Prediction Using a Lightweight Convolutional Neural Network
Eltashani, F., Parreno-Centeno, M., Cole, J. H., Papa, J. P., & Costen, F. (2025) · IEEE Access · doi:10.1109/access.2025.3526520 · Cited by 7
“They are widely utilised to predict brain age based on MR images either using two-[11], [12] or three-dimensional [13], [14] CNN backbones.”
Self-citationInvestigating dynamic brain functional redundancy as a mechanism of cognitive reserve
Schwarz, J., Zistler, F., Usheva, A., Fix, A., Zinn, S., Zimmermann, J., Knolle, F., Schneider, G. H., & Nuttall, R. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1535657 · Cited by 8
Kim, H., Karaman, B. K., Zhao, Q., Wang, A. Q., Sabuncu, M. R., Initiative, A. D. N., Weiner, M. W., Aisen, P. S. S., Petersen, R. C., Jack, C. R., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2411492122 · Cited by 8
Hoogen, H., Vieira, B. H., & Langer, N. (2025) · European Journal of Neuroscience · doi:10.1111/ejn.70085 · Cited by 11
“A smaller MAE indicates a better accuracy of the model (Cole et al. 2017).”
The normative modelling framework for traumatic brain injury
Mitchell, J. E., McDonald, S. J., Sharp, D. J., Gan, G., Ponsford, J. L., Marquand, A. F., Wellington, C. L., Law, M., Shultz, S. R., & Spitz, G. (2025) · Brain · doi:10.1093/brain/awaf296 · Cited by 9
Kaczmarek, E., Szeto, J., Nichyporuk, B., & Arbel, T. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00141 · Cited by 7
“In recent years, there has been significant success using deep learning to analyze brain structural MRI for a wide variety of individual tasks [7, 10, 15, 23].”
Multimodal Brain Age Prediction with Feature Selection and Comparison
Ray, B., Duan, K., Chen, J., Fu, Z., Suresh, P., Johnson, S., Calhoun, V., & Liu, J.-Y. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc46164.2021.9631007 · Cited by 7
“brain development [1,8], abnormal aging process [4], and early clinical indicators of neuropsychiatric problems [5,911].”
BackgroundDeeper Architecture for Brain Age Prediction Based on MRI Images Using Transfer Learning Technique
Wormi, N. M., Ya’u, B. I., Boukari, S., Musa, M. A., Shittu, F., & Lawal, M. A. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.11.028 · Cited by 7
Weissman, D. G., Baum, G. L., Sanders, A., Rosen, M. L., Barch, D. M., McLaughlin, K. A., & Somerville, L. H. (2023) · Imaging Neuroscience · doi:10.1162/imag_a_00021 · Cited by 7
“…about developmental processes, statistical methods that characterize age-related patterns based on multivariate patterns (e.g., “Brain age”) can be useful in making neurodevelopmental inferences with considerable predictive accuracy (Cole et al., 2017; Dosenbach et al., 2010; Franke et al., 2010).”
BackgroundWing, D., Eyler, L. T., Lenze, E. J., Wetherell, J. L., Nichols, J. F., MEEUSEN, R. R., Godino, J., Shimony, J. S., Snyder, A. Z., Nishino, T., et al. (2023) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0000000000003337 · Cited by 8
“In addition, these algorithms show very good test/retest reliability (23) and have correctly identified larger BrainPAD (i.e., higher values/older brains) in populations with expected negative changes in brain structure and/or with evident cognitive decline including multiple sclerosis (24), stroke…”
BackgroundThe role of cortical structural variance in deep learning-based prediction of fetal brain age
Kwon, H., You, S., Yun, H. J., Jeong, S., Barba, A. P. D. L., Aguilar, M. E. L., Vergara, P., Davila, S. U., Grant, P. E., Lee, J., et al. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1411334 · Cited by 7
Al-Asaly, M. S., Hassan, M. M., & Alsanad, A. (2019) · Soft Computing · doi:10.1007/s00500-019-04061-9 · Cited by 8
“…recognition (Mikolov et al. 2011; Hinton et al. 2012; Sainath et al. 2013), natural language understanding (Collobert et al. 2011), traffic flow prediction (Lv et al. 2015), industry (Solar Radiation prediction (Dey et al. 2017), medical (predicting brain age) (Cole et al. 2017) and many other fields.”
BackgroundSex Differences in Predicting Fluid Intelligence of Adolescent Brain from T1-Weighted MRIs
Ranjbar, S., Singleton, K., Curtin, L. A., Massey, S. C., Hawkins-Daarud, A. J., Jackson, P., & Swanson, K. R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31901-4_18 · Cited by 6
“r further understanding the neural underpinnings of cognitive development. Recently deep learning models trained on brain MRI data have shown promising results in the diagnosis of Alzheimer’s disease [10], prediction of age [11, 12] and classification of overall survival in brain tumor patients [8]. In this work we co…”
ResultDeep Integrated Biomarkers of Aging
Mamoshina, P., & Zhavoronkov, A. A. (2019) · Healthy ageing and longevity · doi:10.1007/978-3-030-24970-0_18 · Cited by 8
Applications of Convolutional Neural Networks in neurodegeneration and physiological aging
Chriskos, P., Frantzidιs, C. A., Papanastasiou, E., & Bamidis, P. D. (2020) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2020.08.015 · Cited by 7
Patch individual filter layers in CNNs to harness the spatial homogeneity of neuroimaging data
Eitel, F., Albrecht, J. P., Weygandt, M., Paul, F., & Ritter, K. (2021) · Scientific Reports · doi:10.1038/s41598-021-03785-9 · Cited by 7
“For the PIF architecture, we performed only translation and not (3) (xov , yov) = (xo + sx”
MethodMcEvoy, L. K., Bergstrom, J., Hagler, D. J., Wing, D., & Reas, E. T. (2023) · Journal of Alzheimer s Disease · doi:10.3233/jad-230767 · Cited by 7
Brain Age Estimation using Brain MRI and 3D Convolutional Neural Network
Pardakhti, N., & Sajedi, H. (2019) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke48569.2019.8964975 · Cited by 7
“Fortunately, there are some accurate ML implementations of the BAE system such as what are discussed in [12] and [13].”
BackgroundMethodPredicting Brain Age Using Structural Neuroimaging and Deep LearningPreprint
Varatharajah, Y., Baradwaj, S., Kiraly, A. P., Ardila, D., Iyer, R. K., Shetty, S., & Kohlhoff, K. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/497925 · Cited by 7
“Prior studies [2, 3] have proposed machinelearning-based approaches that use a Gaussian process regression to predict brain age from SMRI images.”
BackgroundPopulation modeling with machine learning can enhance measures of mental healthPreprint
Dadi, K., Varoquaux, G. P., Houenou, J., Bzdok, D., Thirion, B., & Engemann, D. A. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.08.25.266536 · Cited by 7
Fisch, L., Ernsting, J., Winter, N. R., Holstein, V., Leenings, R., Beisemann, M., Sarink, K., Emden, D., Opel, N., Redlich, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11695 · Cited by 10
“…Neural Networks (CNNs) (LeCun et al., 1998) – which already constitute the state-of-the-art in neighboring fields including computer vision – have received increased attention in the brain-age community (Bashyam et al., 2020; Cole et al., 2017; Dinsdale et al., 2021; Hong et al., 2020).”
BackgroundExplanatory latent representation of heterogeneous spatial maps of task-fMRI in large-scale datasetsPreprint
Zabihi, M., Kia, S. M., Wolfers, T., de Boer, A. A. A., Fraza, C., Soheili‐Nezhad, S., Dinga, R., Llera, A., Bzdok, D., Beckmann, C. F., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.10.434856 · Cited by 7
Low-Rank Tensor Fusion for Enhanced Deep Learning-Based Multimodal Brain Age Estimation
Liu, X., Zheng, G., Beheshti, I., Ji, S., Gou, Z., & Cui, W.-K. (2024) · Brain Sciences · doi:10.3390/brainsci14121252 · Cited by 7
Epigenetic age acceleration in peripheral blood correlates with brain-MRI age acceleration
Ferreira, P. S. B., van Dongen, J., den Braber, A., Boomsma, D. I., de Geus, E. J. C., & Ent, D. V. ‘. (2025) · Brain · doi:10.1093/brain/awaf069 · Cited by 8
“26 Thus, the associations between age acceleration at the epigenome level and age acceleration at the brain level may be explained by genetic and environmental factors that influence both ageing-related processes.”
Wang, Z., Liu, J., Chen, F., Wang, W. K., Xu, Y., Lu, F., Li, Y., & Gao, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107926 · Cited by 7
A systematic review: Brain age gap as a promising early diagnostic biomarker for Alzheimer's disease
Liu, S., Xu, L., Xu, G., Wang, Y., Zhang, G., & He, L. (2025) · Journal of the Neurological Sciences · doi:10.1016/j.jns.2025.123563 · Cited by 7
Brain Aging in Patients With Cardiovascular Disease From the UK Biobank
Mcavoy, E., Stanley, E. A. M., Winder, A. J., Wilms, M., & Forkert, N. D. (2025) · Human Brain Mapping · doi:10.1002/hbm.70252 · Cited by 6
“The BAG is defined by the difference be-tween a machine learning-predicted biological brain age and the chronological age of an individual (Cole et al. 2017), wherein a positive BAG suggests that the brain of an individual appears older than the chronological age of the patient.”
Advanced brain aging, selective vulnerability in gray matter, and cognition in Parkinson’s disease
Cai, M., He, C., Li, H., Yang, R., Rong, S., Gao, Z., Luo, Q., Li, Z., Li, Y., Liu, Z., et al. (2025) · The Journals of Gerontology Series A · doi:10.1093/gerona/glaf124 · Cited by 6
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
