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 601–700 of 869
Dörfel, R. P., Arenas‐Gomez, J. M., Svarer, C., Ganz, M., Knudsen, G. M., Svensson, J. E., & Plavén‐Sigray, P. (2024) · GeroScience · doi:10.1007/s11357-024-01148-6 · Cited by 3
“Machine learning (ML) allows for modeling the healthy aging brain by summarizing aging brain biology from neuroimages into one single variable, called “ brain age ” [25, 26].”
BackgroundBrain age estimation with a greedy dual-stream model for limited datasets
Kianian, I., & Sajedi, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127974 · Cited by 4
“As an earliest examples, Cole et al. [ 24 ] proposed a method which firstly gathered White Matter (WM) and Gray Matter (GM) of the brain using SPM12 toolbox and then trained a 3D CNN and demonstrated that GM is better than WM in the brain age estimation.”
MethodMapping brain development against neurological disorder using contrastive sharing
Hassan, M. A., Lin, J., Fateh, A. A., Zhuang, Y., Yun, G., Zeb, A., Xu, D. H., & Zeng, H. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124893 · Cited by 3
Pei, S., Li, Y., Gao, H., Liu, Y., Dai, E., Feng, F., & Lu, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-72047-1 · Cited by 3
Cardiovascular Risk Assessment via Sleep Patterns and ECG-Based Biological Age Estimation
Manimaran, G., Puthusserypady, S. K., Domínguez, H., & Bardram, J. E. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14103339 · Cited by 3
“Cole et al. [14] predicted biological age from brain magnetic resonance imaging (MRI) and showed that the deviations of predicted age are linked to cognitive impairment.”
Neurologic Diagnostics in 2035
Ciccarelli, O., & Pandolfo, M. (2021) · Neurology · doi:10.1212/wnl.0000000000012833 · Cited by 3
“A convolutional neural network, which is a DL algorithm, applied to a large database of conventionalMRI scans of healthy persons has detected different aspects of the ageing brain and identified healthy and unhealthy aging.(21) This approach can lead to recognition of early manifestations of neurologic diseases, which…”
MethodInferring the patient’s age from implicit age clues in health forum posts
Black, C. M., Meng, W., Yao, L., & Miled, Z. B. (2021) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103976 · Cited by 3
Jiang, D., Hu, Z., Zhao, C., Zhao, X., Yang, J., Zhu, Y., Liao, J., Liang, D., & Wang, H. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871037 · Cited by 3
“Recently, some studies have proposed that 3D CNNs can fully exploit the spatial features of MRI and achieve better performance [10].”
BackgroundCho, D., & Wallraven, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17976-1_2 · Cited by 3
“…of larger brain datasets also changed performance in this task: convolutional neural network architectures showed substantial improvement in age prediction over the past years - both in 2D (analyzing slices of brains, e.g. [13]) or 3D (analyzing the voxels directly, e.g. [3,5,12,18,25]).”
BackgroundMethodMachine Learning Driven Aid Classification for Sustainable Development
Lee, J.-H., Song, H., Lee, D., Kim, S., Sim, J., Cha, M., & Park, K. R. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/670 · Cited by 3
Levakov, G., Rosenthal, G., Shelef, I., Raviv, T. R., & Avidan, G. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/803742 · Cited by 3
“…results in serval neuroimaging tasks including cortical segmentation and tumor detection (Kamnitsas, Chen, & Ledig, 2015; Pereira, Pinto, Alves, & Silva, 2016) and were recently applied to age prediction from raw T1 magnetic resonance images (MRI) images (Cole, Poudel, et al., 2017).”
MethodGlobal-Local Transformer for Brain Age EstimationPreprint
He, S., Grant, P. E., & Ou, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01663 · Cited by 3
Mechanical Property Based Brain Age Prediction using Convolutional Neural NetworksPreprint
Clements, R. G., Claros-Olivares, C. C., McIlvain, G., Brockmeier, A. J., & Johnson, C. L. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.12.528186 · Cited by 3
“Imaging modalities including diffusion, functional, and structural MRI have already shown promising results for brain age prediction (Chen et al., 2020; Cole et al., 2017; Jiang et al., 2020; Lund et al., 2022).”
BackgroundMethodA deep neural network estimation of brain age is sensitive to cognitive impairment and declinePreprint
Yang, Y., Sathe, A., Schilling, K. G., Shashikumar, N., Moore, E. E., Dumitrescu, L. C., Pechman, K. R., Landman, B. A., Gifford, K. A., Hohman, T. J., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.10.552494 · Cited by 3
Imaging-Based Biomarkers in Neurological Diseases-A Critical ReviewPreprint
Kale, M. B., Wankhede, N. L., Taksande, B. G., Upaganlawar, A., Umekar, M. J., Koppula, S., & Kopalli, S. R. (2023) · Preprints.org · doi:10.20944/preprints202309.0536.v1 · Cited by 2
BrainAGE Estimation: Influence of Field Strength, Voxel Size, Race, and EthnicityPreprint
Dempsey, D. A., Deardorff, R. L., Wu, Y., Yu, M., Apostolova, L. G., Brosch, J. R., Clark, D. G., Farlow, M. R., Gao, S., Wang, S., et al. (2023) · medRxiv · doi:10.1101/2023.12.05.23299222 · Cited by 3
Brains Under Stress: Unravelling the Effects of the COVID-19 Pandemic on Brain AgeingPreprint
Mohammadi‐Nejad, A., Craig, M., Cox, E. F., Chen, X., Jenkins, G. R., Francis, S., Sotiropoulos, S. N., & Auer, D. P. (2024) · medRxiv · doi:10.1101/2024.07.22.24310790 · Cited by 3
Derboghossian, G., Pituch, K. A., Anthony, M., Salisbury, D. L., Lin, F. V., & Yu, F. (2025) · Journal of Alzheimer s Disease · doi:10.1177/13872877251333613 · Cited by 2
“21,33,34 Automated volumetric segmentation was performed with Freesurfer v7.”
Circulating Antioxidant Nutrients and Brain Age in Midlife Adults
Lower, M. J., DeCataldo, M. K., Kraynak, T. E., & Gianaros, P. J. (2025) · Psychosomatic Medicine · doi:10.1097/psy.0000000000001399 · Cited by 2
Skattebøl, L., Lundby, R., Øverås, M. H., Sowa, P., Celius, E. G., Harbo, H. F., Nordhøy, W., Høgestøl, E. A., & Nygaard, G. O. (2025) · Neuroimage Reports · doi:10.1016/j.ynirp.2025.100277 · Cited by 2
“To compute brain age, a convolutional neural network (CNN) can be used with structural or functional imaging data and chronological age as the baseline for any predicted deviations (Cole et al., 2017; Lundervold and Lundervold, 2019).”
Mateus, P., Garst, S. J. F., Yu, J., Cats, D., Harms, A. G. J., Birhanu, M. A., Beekman, M., Slagboom, P. E., Reinders, M. J. T., van der Grond, J., et al. (2025) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-025-00208-6 · Cited by 3
Pachter, D., Meir, A. Y., Kaplan, A., Tsaban, G., Zelicha, H., Rinott, E., Levakov, G., Finkelstein, O., Shelef, I., Salti, M., et al. (2025) · Clinical Nutrition · doi:10.1016/j.clnu.2025.08.021 · Cited by 2
“Brain age estimation is commonly performed by predicting age from neuroimaging data in a healthy reference population and applying the trained model to an independent, previously unseen subject [14].”
Fan, Y., Yang, P., Zhu, Y., Jing, W., Xu, Y., Xu, Y., Guo, J., Lu, F., Yang, M., Huang, W., et al. (2025) · Progress in Neuro-Psychopharmacology and Biological Psychiatry · doi:10.1016/j.pnpbp.2025.111498 · Cited by 2
Sihag, S., Mateos, G., & Ribeiro, A. (2025) · IEEE Signal Processing Magazine · doi:10.1109/msp.2025.3596731 · Cited by 2
“Some of the ML pipelines that are directly operated on the raw MRI scans are discussed in [S4]. where predicted brain age is the estimate of the biological age derived from neuroimaging data [9].”
Clinical pain increased with older brain age, yet placebo effects were preserved
Cundiff-O’Sullivan, R. L., Wang, Y., Michailidis, V., Latypov, T. H., Chen, S., Hodaie, M., & Colloca, L. (2026) · Pain · doi:10.1097/j.pain.0000000000003901 · Cited by 3
Pallapothu, R., Kudaravalli, S., Newman‐Norlund, R., Pallapothu, S., Kannan, P. R., Kummari, S. K., Absher, J. R., & Rorden, C. (2026) · GeroScience · doi:10.1007/s11357-026-02218-7 · Cited by 2
Monaghan, P. G., Takla, T. N., Cole, J. H., & Fritz, N. E. (2026) · Sensors · doi:10.3390/s26082442 · Cited by 2
Self-citationThe contributions of brain structural and functional variance in predicting age, sex and treatment
Chen, N.-X., Fu, G. C., Chen, X., Li, L., Milham, M. P., Lui, S., & Yan, C. (2021) · Neuroimage Reports · doi:10.1016/j.ynirp.2021.100024 · Cited by 2
“Other machine learning methods have also been used for prediction studies (Schulz et al., 2020), such as to predict age (Cole et al., 2017), sex (Anderson et al., 2019) and schizophrenia subtypes (Chand et al., 2020).”
Estimating Brain Age with Global and Local Dependencies
Yang, Y., Guo, X., Chang, Z., Ye, C., Xiang, Y., Lv, H., & Ma, T. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897454 · Cited by 2
“Recently, researches have demonstrated that MRIs could be used to predict chronological age and show that the brain age, derived purely from neuroimaging data is vital to help improve detection of early-age neurodegeneration and predict age-related cognitive decline [3].”
BackgroundMethodData Augmentation via Partial Nonlinear Registration for Brain-Age Prediction
Schulz, M.-A., Koch, A. W., Guarino, V. E., Kainmueller, D., & Ritter, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17899-3_17 · Cited by 2
Sarada, J., & Lakshmi, N. V. M. (2022) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v10i2s.5917 · Cited by 2
Brain Structural Saliency over the Ages
Taylor, D. J., Shock, J. P., Moodley, D., Ipser, J., & Treder, M. S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25891-6_40 · Cited by 2
“Many factors can contribute to accelerated BA (positive BAG), such as the presence of neurodegenerative disease, type 2 diabetes or HIV, and past physical activity [5].”
Kuka, M. (2023) · American Journal Of Applied Science And Technology · doi:10.37547/ajast/volume03issue05-11 · Cited by 2
Robust Brain Age Estimation via Regression Models and MRI-Derived Features
Ahmed, M., Sardar, U., Ali, S., Alam, S., Patterson, M., & Khan, I. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-41774-0_52 · Cited by 2
Modeling Life-Span Brain Age from Large-Scale Dataset Based on Multi-level Information Fusion
Zhao, N., Pan, Y., Sun, K., Gu, Y., Liu, M., Xue, Z., Zhang, H., Yang, Q., Gao, F., Shi, F., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-45676-3_9 · Cited by 2
Using a deep generation network reveals neuroanatomical specificity in hemispheres
Wang, G., Jiang, N., Ma, Y., Suo, D., Liu, T., Funahashi, S., & Yan, T. (2024) · Patterns · doi:10.1016/j.patter.2024.100930 · Cited by 1
“11 Brain aging is generally associated with a loss of GM tissue so GM can be used to 250 accurately predict chronological age [32].”
Wu, Y., Chen, Y., Yang, Y., Lin, C., Su, S., Zhao, J., Wu, S., Wu, G., Liu, H., Liu, X., et al. (2024) · Cerebral Cortex · doi:10.1093/cercor/bhae030 · Cited by 2
Brain identification of IBS patients based on GBDT and multiple imaging techniques
Han, L., Xu, Q., Meng, P., Xu, R., & Nan, J. (2024) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-024-01394-0 · Cited by 2
Attention over vulnerable brain regions associating cerebral palsy disorder and biological markers
Hassan, M. H. U. H., Lin, J., Fateh, A. A., Pang, W., Zhang, L., Wang, D., Yun, G., & Zeng, H. (2024) · Journal of Advanced Research · doi:10.1016/j.jare.2024.11.015 · Cited by 2
“I Traditional ways rely on the extracted features from brain MRIs [23]; however, they lack suffi-cient visual explanations of BTs association in healthy and CP.”
InfluentialFletcher, E. M., Gavett, B. E., Farias, S. T., Widaman, K. F., Whitmer, R. A., Fan, A. P., Corrada, M. M., DeCarli, C. S., & Mungas, D. (2024) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.70026 · Cited by 2
Multi-Volumetric Feature-Based Brain Age Prediction Using sMRI and Graph Neural Networks
Kumar, S., & Gupta, C. N. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831639 · Cited by 2
“The aim of this article is to develop GNN-based brain age prediction models to predict brain age at the ROI level utilizing sMRI and multi-volumetric features, including grey and white matter [14], [16].”
Aim-based choice of strategy for MEG-based brain state classification
Saranskaia, I., Gutkin, B. S., & Геннадьевич, З. Д. (2025) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-025-01587-y · Cited by 2
Wu, W. E., Wei, Q., Zhou, Z., Ring, H. Z., Islam, M. T., & Xing, L. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110534 · Cited by 3
Kumar, S. R., Hazarika, S., & Gupta, C. N. (2025) · Brain Sciences · doi:10.3390/brainsci15070752 · Cited by 2
“Brain age, on the other hand, is determined by considering the structural and functional characteristics of the brain, which is also known as biological age [7,8].”
Regulatory Genomic Circuitry of Brain Age by Integrative Functional Genomic Analyses
Zhao, X., Yang, A., Ding, J., Yang, Y., & Zhao, X. (2025) · Genomics Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf064 · Cited by 2
“…resonance imaging (MRI) has proven to be a valuable technology for quantitatively assessing the aging status of the brain [4], while machine learning and deep learning methodologies have been utilized to predict “brain age” by extracting aging-related features from structured MRI images [5–7].”
Rosemann, S., & Thiel, C. M. (2021) · Neuroimage Reports · doi:10.1016/j.ynirp.2021.100020 · Cited by 2
“In this model, the brain age of participants is predicted by using magnetic resonance imaging (MRI) estimates of grey and white matter and a machine-learning framework, which is based on data from over 3000 healthy adults (Cole et al., 2017, 2018).”
InfluentialBrain Age Estimation from MRI Images using 2D-CNN instead of 3D-CNN
Darıcı, M. B., Yıldırım, Ş., & Gezer, M. (2021) · Acta Infologica · doi:10.26650/acin.911202 · Cited by 2
Artificial neural networks for non-linear age correction of diffusion metrics in the brain
Kocar, T. D., Behler, A., Leinert, C., Denkinger, M. D., Ludolph, A. C., Müller, H., & Kassubek, J. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.999787 · Cited by 2
“This may become important in terms of a general application of the model since many brain age algorithms are sensitive to field strength or scanner type (Cole et al., 2017; Baecker et al., 2021).”
BackgroundA Review of Challenges of Block Chain with COVID-19: A Review Paper
Alarjani, M., Alhaider, M., & Ahmad, H. F. (2023) · European Journal of Health Sciences · doi:10.47672/ejhs.1384 · Cited by 2
“Numerous researchers throughout the world are striving to identify ways to employ BC technology to tackle COVID-19, although some proposed BC-based techniques, such as GlobeChain [24], BiiMED [28], Bychain [34], MedBlock [40], and BCovX [41], have been simulated.”
BackgroundMethodInfluentialHydranet: Data Augmentation for Regression Neural Networks
Dubost, F., Bortsova, G., Adams, H. H. H., Ikram, M. A., Niessen, W. J., Vernooij, M. W., & de Bruijne, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32251-9_48 · Cited by 2
Using Brain MRI Images to Predict Memory, BMI & Age
Yadav, C., & Razavian, N. (2019) · doi:10.1109/hcc46620.2019.00026 · Cited by 2
Uncertainty-Based Biological Age Estimation of Brain MRI Scans
Armanious, K., Abdulatif, S., Shi, W., Hepp, T., Gatidis, S., & Yang, B. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414112 · Cited by 2
“Recent advances have attempted the use of relatively shallow 3D CNN architectures to incorporate the spatial information between slices in the brain age estimation procedure [33, 34].”
BackgroundThe New Landscape of Diagnostic Imaging with the Incorporation of Computer Vision
Cossio, M. (2023) · Artificial intelligence · doi:10.5772/intechopen.110133 · Cited by 3
Interpreting Deep Learning Models for Multi-modal Neuroimaging
Müller, K. R., & Hofmann, S. (2023) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci57258.2023.10078502 · Cited by 2
Epidemiology, Genetics and Epigenetics of Biological Aging: One or More Aging Systems?
Gialluisi, A., Izzi, B., de Gaetano, G., & Iacoviello, L. (2023) · Healthy ageing and longevity · doi:10.1007/978-3-031-35176-1_6 · Cited by 1
Machine learning for human biological age estimation based on clinical blood analysis
Slipchenko, V. H., Полягушко, Л. Г., Shatylo, V., & Rudyk, V. K. (2023) · Applied Aspects of Information Technology · doi:10.15276/aait.06.2023.29 · Cited by 2
FORCASTING ACADMIC PERFORMANCE IN COMPUTER SCIENCE STUDENTS BASEDON FUTURE ANALYSIS METHOD
KUMAR, N. K., KRANTHI, L. B., HARSHITHA, B. G., KRISHNA, B. H., & KRISHNAKANTH, N. V. (2024) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.61841/turcomat.v15i1.14558 · Cited by 2
Understanding the interplay of sleep and aging: Methodological challengesPreprint
Muehlroth, B. E., & Werkle-Bergner, M. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/713552 · Cited by 2
“, 2018; Habib and Nyberg, 2007; Lindenberger, 2014), particularly in old age, chronological age can deviate greatly from an individual’s physiological age (Cole et al., 2017; MacDonald et al., 2011; Steffener et al., 2016).”
BackgroundDafflon, J., Pinaya, W. H. L., Turkheimer, F., Cole, J. H., Leech, R., Harris, M. A., Cox, S. R., Whalley, H. C., McIntosh, A. M., & Hellyer, P. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.03349 · Cited by 2
Self-citationStudying the interplay of sleep and aging: Methodological challengesPreprint
Muehlroth, B. E., & Werkle‐Bergner, M. (2019) · MPG.PuRe (Max Planck Society) · Cited by 3
Reviews: Topological Distances and Losses for Brain NetworksPreprint
Chung, M. K., Smith, A. D. S., & Shiu, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08623 · Cited by 2
“…mean absolute error (MAE), which is L 2 -norm: The MAE was successfully used in clustering (Jain et al., 1999), tumor segmentation in MRI (Blessy and Sulochana, 2015), age prediction in deep learning (Cole et al., 2017) and the conversion of MRI to CT through deep learning (Wolterink et al., 2017).”
MethodMultimodal image fusion via deep generative modelsPreprint
Dimitri, G. M., Spasov, S., Duggento, A., Passamonti, L., Lió, P., & Toschi, N. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.03.08.434427 · Cited by 2
Cordero‐Grande, L., Ortuño, J. E., Uus, A. U., Deprez, M., Santos, A., Hajnal, J. V., & Ledesma‐Carbayo, M. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00102 · Cited by 2
“Finally, our GA estimation pipeline permits a straightforward application to brain age prediction in adults (Cole et al., 2017), particularly if volumetrically encoded sequences are available.”
MethodJawinski, P., Forstbach, H., Kirsten, H., Beyer, F., Villringer, A., Witte, A. V., Scholz, M. R., Ripke, S., & Markett, S. A. (2023) · medRxiv · doi:10.1101/2023.12.26.23300533 · Cited by 2
Pontillo, G., Prados, F., Colman, J., Kanber, B., Abdel‐Mannan, O., Al‐Araji, S., Bellenberg, B., Bianchi, A., Bisecco, A., Brownlee, W. J., et al. (2024) · medRxiv · doi:10.1101/2024.01.02.23300497 · Cited by 2
“…the MS-age model was highly accurate, nearly approaching the performance of state-of-the-art deep learning models of healthy brain ageing 14,26–28 , but the corresponding gap measure was highly correlated with BAG, suggesting a greater degree of residual dependence from healthy brain ageing…”
Self-citationAccelerated brain age in young to early middle-aged adults after mild to moderate COVID-19 infectionPreprint
Kesler, S. R., Franco‐Rocha, O. Y., Schutz, A. D. L. T., Lewis, K., Aziz, R., Brode, W. M., & Melamed, E. (2024) · medRxiv · doi:10.1101/2024.03.05.24303816 · Cited by 2
“The algorithm implements a Gaussian Processes regression model to predict brain age from segmented brain volumes [34,35] .”
MethodMulholland, M. M., Stuifbergen, A. M., Schutz, A. D. L. T., Franco‐Rocha, O. Y., Blayney, D. W., & Kesler, S. R. (2024) · medRxiv · doi:10.1101/2024.04.22.24306190 · Cited by 2
Whitman, E. T., Elliott, M. L., Knodt, A. R., Abraham, W. C., Anderson, T., Cutfield, N. J., Hogan, S., Ireland, D. R., Melzer, T. R., Ramrakha, S., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.19.608305 · Cited by 2
“Current neuroimaging-based approaches to measure aging, akin to first-generation epigenetic clocks, involve training models to predict chronological age from variability in MRI measures of brain structure in large multi-age samples 26–30 .”
Texture Analysis of Brain MR Images for Age Detection
Al-Hazzouri, F., Bazzi, F., & Diab, A. (2021) · International Conference on Advances in Biomedical Engineering (ICABME) · doi:10.1109/icabme53305.2021.9604841 · Cited by 1
User-Centric Democratization towards Social Value Aligned Medical AI Services
Zhang, L., & Jiang, R. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/702 · Cited by 1
Estimation of the Biological Age of the Human Brain Using Multitask Self-Supervised Learning
Sajjadi, Z., Hamzebeigi, S., & Soryani, M. (2024) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/mvip62238.2024.10491175 · Cited by 1
“In 2017, Cole et al. [4] were among the first to utilize deep learning for predicting brain age.”
BackgroundWu, Y., Lu, C., Li, M., Li, B., Shang, X., Jian, G., Zhang, Q., Chen, X., Cao, X., He, B., et al. (2025) · Autism Research · doi:10.1002/aur.70008 · Cited by 1
“Resting-state functional magnetic resonance imaging (resting-state fMRI) has frequently appeared in studies using the brain-AGE method (Cole et al. 2017; Lund et al. 2022; Li et al. 2018).”
Busby, N., Rangus, I., Riccardi, N., Newman‐Norlund, R., Rorden, C., Fridriksson, J., & Bonilha, L. (2025) · Aging Brain · doi:10.1016/j.nbas.2025.100150 · Cited by 1
“The BrainAgeR pipeline was applied using the default protocol [25,40].”
Patel, B., Wilson, T., Stephen, J., Calhoun, V., & Wang, Y.-P. (2025) · IEEE Access · doi:10.1109/access.2025.3601649 · Cited by 1
“An example of this is Cole et al. [15], where the authors propose a novel method that employs multimodal multiple regression analysis using various MRI modalities from a group of healthy subjects.”
Molecular pathways and biomarkers associated with age-related cognitive decline
Mitra, S., Pandey, S., Gill, A., Roy, A., Dutta, S., Kumar, A., Ali, M., & Chawla, G. (2025) · Academia Biology · doi:10.20935/acadbiol7909 · Cited by 2
Xu, G., Wu, Y., Zhu, R., Qu, J., Xu, W., Xin, J., & Wang, D. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1629870 · Cited by 1
Brain aging among individuals with trigeminal neuralgia
Cruz‐Almeida, Y., Valdes-Hernandez, P. A., Liang, Y., Ding, M., & Neubert, J. K. (2025) · Neurobiology of Pain · doi:10.1016/j.ynpai.2025.100201 · Cited by 1
“The first one was BrainageR, a machine learning pipeline that applies Gaussian Process Regression (GPR) to structural MRI data (Cole et al., 2017).”
Neural Network Analysis of Psychological Data: A Step-by-Step Guide
Tong, L., & Zhang, Z. (2025) · Multivariate Behavioral Research · doi:10.1080/00273171.2025.2587379 · Cited by 1
“They have also applied in neuroimaging, such as predicting brain age from raw MRI data (Cole et al., 2017), identifying biomarkers for conditions traditionally diagnosed through behavioral observation.”
Association between 24‐h time‐use composition and brain age: The IGNITE study
Collins, A. M., Mellow, M. L., Wan, L., Smith, A. E., Oberlin, L. E., Sewell, K. R., Gothe, N. P., Fanning, J. T., Migueles, J. H., Dumuid, D., et al. (2025) · Alzheimer s & Dementia Translational Research & Clinical Interventions · doi:10.1002/trc2.70187 · Cited by 1
“31,33 This pretrained model was applied to the preprocessed imagingdatatoestimatebrainageforeachparticipant.”
Hunt, J. R., Buchholz, E. J., Franz, C. E., Reynolds, C. A., Panizzon, M. S., Williams, M. E., Bell, T. R., Tang, R., Hagler, D. J., Gillespie, N. A., et al. (2025) · The Journals of Gerontology Series A · doi:10.1093/gerona/glaf283 · Cited by 1
Fang, C., Jin, J., Shi, W., Xu, X., Li, H., Duan, Q., Yu, X., Wu, S., Lu, T., Hu, F., et al. (2026) · BMC Medicine · doi:10.1186/s12916-026-04631-3 · Cited by 1
“Convolutional neural networks (CNNs) have been widely used in developing brain-age models due to their capacity to extract age-related features from high-dimensional magnetic resonance imaging (MRI) data [18, 19].”
Payas, A., Seber, T., Çiçek, F., Kocaman, H., Yıldırım, H., BUDAK, M., & Uçar, İ. (2026) · Brain Mechanisms · doi:10.1016/j.bramec.2026.202543 · Cited by 1
Kim, H. E., Kim, B.-H., Cho, Y., Ko, Y., & Kim, J.-J. (2026) · Computers in Human Behavior · doi:10.1016/j.chb.2026.108976 · Cited by 1
Lee, S., Lee, M., Kim, Y. M., & Yang, H.-J. (2026) · Applied Sciences · doi:10.3390/app16063004 · Cited by 1
Aging beyond diagnosis: the MRI brain age gap across disorders
Mhanna, H. Y. A., Oestreich, L., Vashistha, R., Wang, Y., & Vegh, V. (2026) · GeroScience · doi:10.1007/s11357-026-02315-7 · Cited by 4
Ito, K. (2021) · Springer eBooks · doi:10.1007/978-981-16-4325-5_19 · Cited by 1
Deep Learning for Diagnosis of Alzheimer’s Disease with FDG-PET Neuroimaging
Bastos, J. M., da Silva, F. M. T. P., & Georgieva, P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-04881-4_8 · Cited by 2
Artificial intelligence applications of fetal brain and cardiac MRI
Ren, J., Zhu, M., & Dong, S. (2022) · Chinese Journal of Academic Radiology · doi:10.1007/s42058-022-00108-3 · Cited by 1
Influence of endogenous estrogen on a network model of female brain integrity
Foret, J. T., Caillaud, M. L., Gourley, D., Dekhtyar, M., Tanaka, H., & Haley, A. P. (2022) · Aging Brain · doi:10.1016/j.nbas.2022.100053 · Cited by 1
“’s [12,14] machine-learning framework (Gaussian Process), trained on data available via public repositories from 2001 healthy individuals ages 18–90.”
Proceedings of the 18th Python in Science Conference
(2019) · Proceedings of the Python in Science Conferences · doi:10.25080/majora-7ddc1dd1-026 · Cited by 1
Main Existing Datasets for Open Brain Research on Humans
Couvy‐Duchesne, B., Bottani, S., Camenen, E., Fang, F., Fikere, M., Gonzalez-Astudillo, J., Harvey, J., Hassanaly, R., Kassam, I., Lind, P. A., et al. (2023) · Neuromethods · doi:10.1007/978-1-0716-3195-9_24 · Cited by 2
Bintsi, K.-M., Mueller, T. T., Starck, S., Baltatzis, V., Hammers, A., & Rueckert, D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-55088-1_6 · Cited by 1
McAvoy, E., Wilms, M., & Forkert, N. D. (2024) · SPIE Medical Imaging: Imaging Informatics for Healthcare, Research, and Applications · doi:10.1117/12.3006650 · Cited by 1
Brain reserve in midlife is associated with executive function changes across 12 years
Gustavson, D. E., Elman, J. A., Reynolds, C. A., Eyler, L. T., Fennema‐Notestine, C., Puckett, O. K., Panizzon, M. S., Gillespie, N. A., Neale, M. C., Lyons, M. J., et al. (2024) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2024.05.001 · Cited by 1
Machine learning and neuroimaging: Understanding the human brain in health and disease
Gu, Z., Jamison, K. W., Sabuncu, M. R., & Kuceyeski, A. F. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13480-7.00010-7 · Cited by 1
Prediction of gender from structural MRI images using Multiscale ShuffleNet Extreme Learning Machine
Stanley, B. F., Kumar, R. J. R., Gnanaprakash, V., Palas, P. B., Patturose, J. G. B., & Daniel, D. J. J. D. (2024) · International Conference on Artificial Intelligence for Internet of Things (AIIoT) · doi:10.1109/aiiot58432.2024.10574550 · Cited by 1
“While not directly related to gender prediction, Cole et al. [5] demonstrated the utility of deep learning models in predicting brain age from MRI scans, providing valuable insights into the potential of advanced computational techniques in neuroimaging analysis.”
BackgroundDefining, Re-defining, and Understanding the Brain and Mental Health During Ageing
Kaur, G., & Rattan, S. I. S. (2024) · Healthy ageing and longevity · doi:10.1007/978-3-031-68513-2_1 · Cited by 2
Epigenetic age across development in children and adolescents with ADHD
Wrigglesworth, J., Fransquet, P., Ryabinin, P., Mooney, M. A., Craig, J. M., & Silk, T. (2025) · Psychiatry Research · doi:10.1016/j.psychres.2025.116373 · Cited by 2
“Alternative biomarkers of aging like ‘Brain Age ’ (Cole et al., 2017, Franke et al., 2020) in ADHD have demonstrated comparable brain age (Kaufmann et al., 2019) or suggest possible accelerated biological aging (Amen et al., 2018; Hu et al., 2023), however these findings are currently limited to cross-sectional studie…”
Structured regularization with object size selection using mathematical morphology
Lin, D., Hägg, L., Wadbro, E., Berggren, M., & Löfstedt, T. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01444-7 · Cited by 1
“The images were preprocessed using SPM12, 5 following the pipeline outlined by Cole et al. [35 ].”
Fong, M. C., Liu, J. C. H., Ma, M. K.-H., Ng, X. S.-W., Hui, C. L. L., Waye, M. M. Y., Chien, W. T., & Wang, W. Y. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10981090 · Cited by 1
“Specifically, after using the Cole’s method [3] to correct for the “regression to the mean” problem, the MAE reduced from its single-channel value (T1: 3.978; T2: 3.539) to 3.327, when both T1 and T2 were used as the input; similar conclusions can be drawn for the rest of metrics (e.g., the…”
Influential
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
