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 301–400 of 869
IGUANe: A 3D generalizable CycleGAN for multicenter harmonization of brain MR images
Roca, V., Kuchcinski, G., Pruvo, J., Manouvriez, D., & Lopes, R. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103388 · Cited by 21
“Brain age prediction involves training a model to predict an individual’s age from brain MRI data and has been widely investigated with deep learning models (Cole et al., 2017; Gautherot et al., 2021; Jonsson et al., 2019).”
BackgroundMethodDeep transfer learning for cerebral cortex using area-preserving geometry mapping
Gao, K., Fan, Z., Su, J., Zeng, L., Shen, H., Zhu, J., & Hu, D. (2021) · Cerebral Cortex · doi:10.1093/cercor/bhab394 · Cited by 21
Contrastive Learning for Regression in Multi-Site Brain Age Prediction
Barbano, C. A., Dufumier, B., Duchesnay, É., Grangetto, M., & Gori, P. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230733 · Cited by 22
“While most DNN used to derive brain age gap are usually trained as standard regressors with the optimization of mean absolute error [5, 6], Ridge or cross-entropy loss [1] (if age is binarized), these frameworks do not pay particular care about site-related information during training to produce robust representations…”
The accuracy of T1-weighted voxel-wise and region-wise metrics for brain age estimation
Beheshti, I., Maikusa, N., & Matsuda, H. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106585 · Cited by 21
Attitudes to ageing, biomarkers of ageing and mortality: the Lothian Birth Cohort 1936
McLachlan, K., Cole, J. H., Harris, S. E., Marioni, R. E., Deary, I. J., & Galé, C. R. (2020) · Journal of Epidemiology & Community Health · doi:10.1136/jech-2019-213462 · Cited by 19
Self-citationNiu, X., Taylor, A., Shinohara, R. T., Kounios, J., & Zhang, F. (2021) · Cerebral Cortex · doi:10.1093/cercor/bhab530 · Cited by 20
Brain age gap in neuromyelitis optica spectrum disorders and multiple sclerosis
Wei, R., Xu, X., Duan, Y., Zhang, N., Sun, J., Li, H., Li, Y., Li, Y., Zeng, C., Han, X., et al. (2022) · Journal of Neurology Neurosurgery & Psychiatry · doi:10.1136/jnnp-2022-329680 · Cited by 20
“5,6 Previous studies have suggested that BAG is associated with various clinical risk factors and can be used for risk stratification of various neurological and psychiatric diseases including MS 7 .”
Self-citationA Skewed Loss Function for Correcting Predictive Bias in Brain Age Prediction
Wang, H., Treder, M. S., Marshall, D., Jones, D. K., & Li, Y. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3231730 · Cited by 21
“To measure this deviation, a metric known as brain age delta, defined as the difference between an individual’s estimated brain age and chronological age has been proposed [2].”
BackgroundMethodInfluentialForeman, B. P. (2020) · Neurotherapeutics · doi:10.1007/s13311-020-00846-1 · Cited by 20
Distinct brain age gradients across the adult lifespan reflect diverse neurobiological hierarchies
Riccardi, N., Teghipco, A., Newman-Norlund, S. E., Newman‐Norlund, R., Rangus, I., Rorden, C., Fridriksson, J., & Bonilha, L. (2025) · Communications Biology · doi:10.1038/s42003-025-08228-z · Cited by 18
“We investigated how these gradients are re fl ected in regional brain age patterns derived from deep learning 17 .”
Haugg, F., Lee, G. C., He, J., Johnson, J., Zapaishchykova, A., Bitterman, D. S., Kann, B. H., Aerts, H. J. W. L., & Mak, R. H. (2025) · The Lancet Healthy Longevity · doi:10.1016/j.lanhl.2025.100728 · Cited by 27
Delayed brain development of Rolandic epilepsy profiled by deep learning–based neuroanatomic imaging
Zhang, Q., He, Y., Qu, T., Yang, F., Lin, Y., Hu, Z., Li, X., Xu, Q., Xing, W., Gumenyuk, V., et al. (2021) · European Radiology · doi:10.1007/s00330-021-08048-9 · Cited by 19
“emerged as a popular trend in neuroscience [18, 19] and neurological fields [20].”
BackgroundLower socioeconomic status is associated with premature brain aging
Busby, N., Newman-Norlund, S. E., Sayers, S., Newman‐Norlund, R., Wilmskoetter, J., Rorden, C., Nemati, S., Wilson, S. E., Riccardi, N., Roth, R., et al. (2023) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2023.06.012 · Cited by 19
Brain Age Estimation Using LSTM on Children's Brain MRI
He, S., Gollub, R. L., Murphy, S. N., Perez, J. D., Prabhu, S. P., Pienaar, R., Robertson, R. L., Grant, P. E., & Ou, Y. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098356 · Cited by 20
“The difference between the predicted and chronological age can be used to predict neurocognitive disorders [3] or brain anomaly caused by disease [2].”
BackgroundBrain age estimation using multi-feature-based networks
Liu, X., Beheshti, I., Zheng, W., Li, Y., Li, S., Zhao, Z., Yao, Z., & Hu, B. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105285 · Cited by 19
OMICmAge quantifies biological age by integrating multi-omics with electronic medical records
Chen, Q., Dwaraka, V. B., Carreras-Gallo, N., Armstrong, J., Sehgal, R., Argentieri, M. A., Richmond, A., Aparicio, A., Mendez, K. M., Chen, Y., et al. (2026) · Nature Aging · doi:10.1038/s43587-026-01073-7 · Cited by 21
“These biomarkers have been based on a variety of measures such as telomere length 3 , neuroimaging data 4–7 , immune cell counts 8 and large-scale omics including DNA methylation (DNAm) 2,9–11 , metabolomics 12 , gly-comics 13 and proteomics 14–17 .”
Robust Brain Age Estimation Based on sMRI via Nonlinear Age-Adaptive Ensemble Learning
Zhang, L., Jiang, R., Zhang, C., Williams, B. M., Jiang, Z., Li, C., Chazot, P. L., Pavese, N., Bouridane, A., & Beghdadi, A. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3190467 · Cited by 19
“For more details, please refer to [43].”
BackgroundMethodInfluentialPilli, R., Goel, T., Murugan, R., & Tanveer, M. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106596 · Cited by 19
CNN-assisted accurate smartphone testing of μPAD for pork sausage freshness
Liu, Y., Zhang, Y., Long, F., Bai, J., Huang, Y., & Gao, H. X. (2023) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2023.111772 · Cited by 18
Deep Learning and Geriatric Mental Health
Aizenstein, H. J., Moore, R. C., Vahia, I. V., & Ciarleglio, A. (2023) · American Journal of Geriatric Psychiatry · doi:10.1016/j.jagp.2023.11.008 · Cited by 22
Azzam, M., Xu, Z., Liu, R., Li, L., Soh, K. M., Challagundla, K. B., Wan, S., & Wang, J. (2024) · Briefings in Functional Genomics · doi:10.1093/bfgp/elae042 · Cited by 18
Analysis of brain NMR images for age estimation with deep learning
Rossi, A., Vannuccini, G., Andreini, P., Bonechi, S., Giacomini, G., Scarselli, F., & Bianchini, M. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.09.265 · Cited by 18
“Thus, it is easy to realize that the accurate prediction of the brain age can have a great clinical relevance [10].”
BackgroundMethodInfluentialVosylius, V., Wang, A. Y.-D., Waters, C., Zakharov, A., Ward, F. R., Folgoc, L. L., Cupitt, J., Makropoulos, A., Schuh, A., Rueckert, D., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60365-6_17 · Cited by 18
“ness (CT), sulcal depth (SD), curvature (C), and the myelin map (MM). All cortical features are extracted using the dHCP structural MRI processing pipeline [23]. 4.2 Implementation 3D CNN: Similar to [8], we rst segment the cortical gray matter from the 3D MRI scans. Our 3D CNN consists of 12 convolutional layers with…”
MethodInfluentialBrain-Age Prediction Using Shallow Machine Learning: Predictive Analytics Competition 2019
da Costa, P. F., Dafflon, J., & Pinaya, W. H. L. (2020) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2020.604478 · Cited by 18
“Although Relevance vector Regression (RVR), Support Vector Regression (SVR), Gaussian Process Regression are the most commonly used methods to predict brain age (8, 9, 13, 20), recently other methods such as Convolutional Neural Networks have gained popularity (13, 21).”
BackgroundMethodInfluentialTen years of image analysis and machine learning competitions in dementia
Bron, E. E., Klein, S., Reinke, A., Papma, J. M., Maier-Hein, L., Alexander, D. C., & Oxtoby, N. P. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119083 · Cited by 17
“Several approaches for biomarker-based screening have been proposed (Licher et al., 2019; Cole et al., 2017; Wang et al., 2019).”
Luckett, P. H., Paul, R. H., Navid, J., Cooley, S., Wisch, J. K., Boerwinkle, A. H., Tomov, D., & Ances, B. M. (2019) · JAIDS Journal of Acquired Immune Deficiency Syndromes · doi:10.1097/qai.0000000000002181 · Cited by 16
Transfer learning approach in deep neural networks for uterine fibroid detection
Sundar, S., & Subramanian, S. (2022) · International Journal of Computational Science and Engineering · doi:10.1504/ijcse.2022.120788 · Cited by 17
Accurate segmentation of neonatal brain MRI with deep learning
Richter, L., & Fetit, A. E. (2022) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2022.1006532 · Cited by 17
“3D CNNs have been successfully used for accurate prediction of brain age in adults based only on MRI scans (Cole et al., 2017; Jónsson et al., 2019; Peng et al., 2021).”
MethodFeng, L., Ye, Z., Mo, C., Wang, J., Liu, S., Gao, S., Ke, H., Canida, T. A., Pan, Y., van Greevenbroek, M. M. J., et al. (2023) · Journal of Hypertension · doi:10.1097/hjh.0000000000003553 · Cited by 17
“The scalar BAG measure has been widely used in the literature as an alternative to multivariate imaging models to yield more robust and interpretable results in brain aging studies [13,14].”
Increased MRI-based Brain Age in chronic migraine patients
González, R. N., García‐Azorín, D., Peral, Á. L. G., Planchuelo‐Gómez, Á., Aja‐Fernández, S., & de Luis-Garcı́a, R. (2023) · The Journal of Headache and Pain · doi:10.1186/s10194-023-01670-6 · Cited by 18
Nallapu, B. T., Initiative, T. A. D. N., Petersen, K. K., Lipton, R. B., Davatzikos, C. A., & Ezzati, A. (2024) · Journal of Alzheimer s Disease · doi:10.3233/jad-230620 · Cited by 17
Biological Age Estimated from Retinal Imaging: A Novel Biomarker of Aging
Liu, C., Wang, W., Li, Z., Jiang, Y., Han, X., Ha, J. J., Meng, W., & He, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32239-7_16 · Cited by 17
Brusini, I., MacNicol, E., Kim, E., Smedby, Ö., Wang, C., Westman, E., Veronese, M., Turkheimer, F., & Cash, D. (2021) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2021.10.004 · Cited by 17
Mattia, G. M., Sarton, B., Villain, E., Vinour, H., Ferré, F., Buffières, W., Lann, M. V. L., Franceries, X., Péran, P., & Silva, S. (2022) · Neurocritical Care · doi:10.1007/s12028-022-01525-z · Cited by 19
Deep learning to quantify the pace of brain aging in relation to neurocognitive changes
Yin, C., Imms, P., Chowdhury, N. F., Chaudhari, N. N., Ping, H., Wang, H., Bogdan, P., Irimia, A., Initiative, T. A. D. N., Weiner, M., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2413442122 · Cited by 18
Classification of Neurodevelopmental Age in Normal Infants Using 3D-CNN based on Brain MRI
Shabanian, M., Eckstein, E. C., Chen, H., & DeVincenzo, J. P. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983399 · Cited by 18
“From our review of the literature, 3D CNNs are appropriate deep methods for analyzing imaging data, a time-consuming process that currently requires expert analysis, especially for medical images such as Neuroimaging Informatics Technology Initiative (NIfTI) file formats of MRI [7, 8, 22, 23].”
BackgroundMethodMendes, S. L., Pinaya, W. H. L., Pan, P. M., & Sato, J. R. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5550914 · Cited by 16
“By training our model to predict the age of healthy individuals only (to be done), psychiatric conditions can be estimated by calculating the difference between the brain’s predicted age and the individual’s chronological age [46].”
BackgroundMethodInfluentialPeripheral inflammation levels associated with degree of advanced brain aging in schizophrenia
Klaus, F., Nguyen, T. T., Thomas, M. L., Liou, S. C., Soontornniyomkij, B., Mitchell, K. R., Daly, R., Sutherland, A. N., Jeste, D. V., & Eyler, L. T. (2022) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2022.966439 · Cited by 16
“Brain age calculations Brain-predicted age was calculated using “BrainAgeR” a validated predictive modeling approach based on Gaussian process regression applied to voxel-level raw T1-weighted MRI data (based on a training set of 3377 HC aged 18–92 years from seven publicly-available datasets) (45, 58).”
BackgroundMethodJha, M. K., Fatt, C. C., Minhajuddin, A., Mayes, T. L., Berry, J. D., & Trivedi, M. H. (2022) · Psychoneuroendocrinology · doi:10.1016/j.psyneuen.2022.105921 · Cited by 18
Mouchès, P., Wilms, M., Aulakh, A., Langner, S., & Forkert, N. D. (2022) · Frontiers in Neurology · doi:10.3389/fneur.2022.979774 · Cited by 16
“Past studies have proposed different types of CNN architectures with different levels of depth/number of layers and parameters (12, 13), types of convolutional layers [e.”
BackgroundResultInfluentialUnsupervised representation learning of spontaneous MEG data with nonlinear ICA
Zhu, Y., Parviainen, T. M., Heinilä, E., Parkkonen, L. T., & Hyvärinen, A. (2023) · NeuroImage · doi:10.1016/j.neuroimage.2023.120142 · Cited by 16
Valdes-Hernandez, P. A., Nodarse, C. L., Johnson, A. J., Montesino-Goicolea, S., Bashyam, V., Davatzikos, C. A., Peraza, J. A., Cole, J. H., Huo, Z., Fillingim, R. B., et al. (2023) · Pain · doi:10.1097/j.pain.0000000000002984 · Cited by 16
Self-citationD’Antonoli, T. A., Todea, R., Leu, N. H., Datta, A., Stieltjes, B., Prüfer, F., & Wasserthal, J. (2023) · Radiology Artificial Intelligence · doi:10.1148/ryai.220292 · Cited by 17
Analysing Race and Sex Bias in Brain Age Prediction
Piçarra, C., & Glocker, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-45249-9_19 · Cited by 17
Deep Learning for Perfusion Cerebral Blood Flow (CBF) and Volume (CBV) Predictions and Diagnostics
Talebi, S., Gai, S., Sossin, A., Zhu, V., Tong, E., & Mofrad, M. R. K. (2024) · Annals of Biomedical Engineering · doi:10.1007/s10439-024-03471-7 · Cited by 16
“Besides using DL for detection and segmentation intracranial abnormalities in brain images [25, 26], there are also DL models for predictions from input images [27, 28].”
MethodNeuroimaging Studies Illustrate the Commonalities Between Ageing and Brain Diseases
Cole, J. H. (2018) · BioEssays · doi:10.1002/bies.201700221 · Cited by 18
Self-citationNam, Y., Jang, J., Lee, H., Choi, Y., Shin, N. Y., Ryu, K., Kim, D. H., Jung, S. L., Ahn, K. J., & Kim, B. (2019) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2019.12.008 · Cited by 16
Transfer learning on T1-weighted images for brain age estimation
Jiang, H., Guo, J., Du, H., Xu, J., & Qiu, B. (2019) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2019218 · Cited by 16
Wankhede, N. L., Koppula, S., Umare, P. D., Umare, M. D., Lokhande, S. K., Taksande, B. G., Upaganlawar, A. B., Umekar, M. J., Kopalli, S. R., & Kale, M. B. (2025) · Brain Disorders · doi:10.1016/j.dscb.2025.100222 · Cited by 18
Jawinski, P., Forstbach, H., Kirsten, H., Beyer, F., Villringer, A., Witte, A. V., Scholz, M. R., Ripke, S., & Markett, S. A. (2025) · Nature Aging · doi:10.1038/s43587-025-00962-7 · Cited by 18
Wing, 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. (2022) · Neuroimage Reports · doi:10.1016/j.ynirp.2022.100146 · Cited by 16
“Further, outputs from these algorithms show high test/retest reliability (Cole et al., 2017) and correctly identify higher baseline brain age cross-sectionally and accelerated brain aging longitudinally in clinical populations manifesting symptoms of cognitive decline including development of…”
BackgroundWang, S., Zheng, K., Kong, W., Huang, R., Liu, L., Wen, G., & Yu, Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac515 · Cited by 15
Predicting future depressive episodes from resting-state fMRI with generative embedding
Galioulline, H., Frässle, S., Harrison, S. J., Pereira, I., Heinzle, J., & Stephan, K. E. (2023) · NeuroImage · doi:10.1016/j.neuroimage.2023.119986 · Cited by 17
Wilmskoetter, J., Busby, N., He, X., Caciagli, L., Roth, R., Kristinsson, S., Davis, K. A., Rorden, C., Bassett, D. S., Fridriksson, J., et al. (2023) · Communications Biology · doi:10.1038/s42003-023-05119-z · Cited by 15
“70, 84 , which is a freely available software Segmentation accuracy was veri fi ed through visual quality control.”
Machine Learning in Multiple Sclerosis
Jasperse, B., & Barkhof, F. (2023) · Neuromethods · doi:10.1007/978-1-0716-3195-9_28 · Cited by 17
Dufumier, B., Gori, P., Petiton, S., Louiset, R., Mangin, J., Grigis, A., & Duchesnay, É. (2024) · NeuroImage · doi:10.1016/j.neuroimage.2024.120665 · Cited by 18
“…2020; Glocker et al., 2019) showed that the prediction capacity of CNNs on images from never-seen sites is worse when using raw data than VBM as pre-processing for both age prediction (Cole et al., 2017; Hwang et al., 2021; Wachinger et al., 2021), Alzheimer’s diagnosis (Wen et al., 2020) and…”
BackgroundMethodResultInfluentialPrototype Learning for Explainable Brain Age Prediction
Hesse, L. S., Dinsdale, N. K., & Namburete, A. I. L. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00772 · Cited by 16
“Brain age prediction is an important medical imaging task: for adult MRI the difference between true and predicted age is a potential biomarker for disease [12,14]; during gestation the predicted brain age can be compared to true post-conceptual age to quantify fetal brain development [17,35].”
BackgroundZhang, X., Pan, Y., Wu, T., Zhao, W., Zhang, H., Ding, J., Ji, Q., Jia, X., Li, X., Lee, Z., et al. (2024) · NeuroImage · doi:10.1016/j.neuroimage.2024.120751 · Cited by 15
“The schematic illustration of the proposed 3D multi-feature-based CNN architecture was presented in Fig.”
BackgroundInfluentialDense-CAM: Visualize the Gender of Brains with MRI Images
Gao, K., Shen, H., Liu, Y., Zeng, L., & Hu, D. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852260 · Cited by 17
“proposed a 3D CNN to predict brain age [17].”
BackgroundFatt, C. C., Jha, M. K., Minhajuddin, A., Mayes, T. L., & Trivedi, M. H. (2020) · Psychoneuroendocrinology · doi:10.1016/j.psyneuen.2020.105059 · Cited by 15
Brain‐age estimation accuracy is significantly increased using multishell free‐water reconstruction
Nemmi, F., Levardon, M., & Péran, P. (2022) · Human Brain Mapping · doi:10.1002/hbm.25792 · Cited by 15
Machine Learning Quantifies Accelerated White-Matter Aging in Persons With HIV
Petersen, K. J., Strain, J. F., Cooley, S., Vaida, F., & Ances, B. M. (2022) · The Journal of Infectious Diseases · doi:10.1093/infdis/jiac156 · Cited by 15
EEG-Driven Age Prediction: Advancements in Machine Learning Models
Sakib, N., Saif, Z. B., Hasan, M. T., Adnan, M., Faisal, F., Nishat, M. M., Ali, S., & Shafiullah, A. (2023) · International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS) · doi:10.1109/ice3is59323.2023.10335221 · Cited by 15
“The findings indicate that EEG signals hold promise as a biomarker for age estimation, providing valuable insights into age-related variations in brain activity [61].”
BackgroundHérent, P., Jégou, S., Wainrib, G., & Clozel, T. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/413302 · Cited by 16
Opel, N., Thalamuthu, A., Milaneschi, Y., Grotegerd, D., Flint, C., Leenings, R., Goltermann, J., Richter, M. F., Hahn, T., Woditsch, G., et al. (2021) · Molecular Psychiatry · doi:10.1038/s41380-021-01191-1 · Cited by 14
Characterising ongoing brain aging and baseline effects from cross-sectional data
Smith, S. M., Miller, K. L., & Nichols, T. E. (2025) · Imaging Neuroscience · doi:10.1162/imag.a.39 · Cited by 14
“Researchers have proposed the concept of “brain age” as a way of deriving markers of neurobiological aging, based, for example, on imaging data ( Cole & Franke, 2017; Cole et al., 2017; Franke et al., 2010).”
Accelerated brain ageing during the COVID-19 pandemic
Mohammadi‐Nejad, A., Craig, M., Cox, E. F., Chen, X., Jenkins, G. R., Francis, S., Sotiropoulos, S. N., & Auer, D. P. (2025) · Nature Communications · doi:10.1038/s41467-025-61033-4 · Cited by 20
Jha, M. K., Fatt, C. C., Minhajuddin, A., Mayes, T. L., & Trivedi, M. H. (2022) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2022.09.006 · Cited by 14
White matter hyperintensity load is associated with premature brain aging
Busby, N., Newman-Norlund, S. E., Sayers, S., Newman‐Norlund, R., Wilson, S. E., Nemati, S., Rorden, C., Wilmskoetter, J., Riccardi, N., Roth, R., et al. (2022) · Aging · doi:10.18632/aging.204397 · Cited by 14
Investigation of genetic variants and causal biomarkers associated with brain aging
Kim, J., Lee, J., Nam, K., & Lee, S. (2023) · Scientific Reports · doi:10.1038/s41598-023-27903-x · Cited by 14
“, for DNA methylation biomarkers, and (4) Pan-UK Biobank for the rest of the phenotypes26,50,51.”
BackgroundAge prediction from human blood plasma using proteomic and small RNA data: a comparative analysis
Salignon, J., Faridani, O. R., Miliotis, T., Janssens, G. E., Chen, P., Zarrouki, B., Sandberg, R., Davidsson, P., & Riedel, C. G. (2023) · Aging · doi:10.18632/aging.204787 · Cited by 17
MRI-based brain age prediction model for children under 3 years old using deep residual network
Hu, L., Wan, Q., Huang, L., Tang, J., Huang, S., Chen, X., Bai, X., Kong, L., Deng, J., Liang, H., et al. (2023) · Brain Structure and Function · doi:10.1007/s00429-023-02686-z · Cited by 14
Xiaoliang, G., Ding, Y., Xu, W., Wang, D., Yu, H., Lin, Y., Chang, S., Zhang, Q., & Zhang, Y. (2023) · Journal of Neuroradiology · doi:10.1016/j.neurad.2023.09.002 · Cited by 14
“Techniques such as Relevance Vector Machine (RVM), 23,24 Support Vector Machine (SVR), 25 Gaussian Regression, 15 and deep learning 11 have demonstrated signi fi cant utility in this context.”
Brain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection
Aghaei, A., Moghaddam, M. E., & Initiative, A. D. N. (2024) · Brain Informatics · doi:10.1186/s40708-024-00230-1 · Cited by 16
“In [7], a Convolutional Neural Network (CNN) was used to make predictions on brain age using both raw and pre-processed MRI data.”
BackgroundMethodJiang, J., Sheng, C., Chen, G., Liu, C., Jin, S., Li, L., Jiang, X., Han, Y., Initiative, A. D. N., Weiner, M. W., et al. (2022) · GeroScience · doi:10.1007/s11357-022-00588-2 · Cited by 14
“Currently, data-driven methods are usually applied to estimate brain ageing using chronological age as the training label [13–15].”
Ayu-Characterization of healthy aging from neuroimaging data with deep learning and rsfMRI
Borkar, K., Chaturvedi, A., Vinod, P. K. U., & Bapi, R. S. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.940922 · Cited by 14
“In recent years, sophisticated machine learning and deep learning methods have been used for brain age estimation and brain age classification (Cole et al., 2017; Lancaster et al., 2018).”
MethodAge Prediction based on Brain MRI Images using Extreme Learning Machine
Afshar, L. K., & Sajedi, H. (2019) · Iranian Joint Congress on Fuzzy and Intelligent Systems · doi:10.1109/cfis.2019.8692156 · Cited by 14
He, T., Kong, R., Holmes, A. J., Nguyen, M., Sabuncu, M. R., Eickhoff, S. B., Bzdok, D., Feng, J., & Yeo, B. T. T. (2018) · doi:10.1101/473603 · Cited by 16
Chmiel, J., & Malinowska, A. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14155357 · Cited by 14
“These techniques are already being used in other domains of neuroscience (e.g., brain age estimation, ADHD classification) and could be extended to burnout detection once large enough datasets become available [203,204].”
Hellstrøm, T., Anđelić, N., de Lange, A. G., Helseth, E., Eiklid, K. L., & Westlye, L. T. (2021) · Journal of Clinical Medicine · doi:10.3390/jcm10030418 · Cited by 13
Ze-fang, L., Wu, X., Yan, Z., Cui, Y., Liu, Y., Cui, S., Wang, Y., & Liu, T. (2024) · Archives of Gerontology and Geriatrics · doi:10.1016/j.archger.2024.105412 · Cited by 15
Clinical and multimodal imaging features of adult-onset neuronal intranuclear inclusion disease
Zhu, R., Qu, J., Xu, G., Wu, Y., Xin, J., & Wang, D. (2024) · Neurological Sciences · doi:10.1007/s10072-024-07699-y · Cited by 13
Estimated Brain Age in Healthy Aging and Across Multiple Neurological Disorders
Chai, L., Sun, J., Zhuo, Z., Wei, R., Xu, X., Duan, Y., Tian, D., Bai, Y., Zhang, N., Li, H., et al. (2024) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.29667 · Cited by 13
“12 A negative BAG indicates that the brain appears younger than expected, suggesting delayed brain aging, while a positive BAG indicates a brain age that is older than expected for the chronological age.”
Self-citationBrain age in genetic and idiopathic Parkinson's disease
Teipel, S. J., Hoffmann, H., Storch, A., Hermann, A., Dyrba, M., & Schumacher, J. (2024) · Brain Communications · doi:10.1093/braincomms/fcae382 · Cited by 13
Grey Matter Age Prediction as a Biomarker for Risk of Dementia: A Population-based StudyPreprint
Wang, J. Z., Knol, M. J., Tiulpin, A., Dubost, F., de Bruijne, M., Vernooij, M. W., Adams, H. H. H., Ikram, M. A., Niessen, W. J., & Roshchupkin, G. V. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/518506 · Cited by 13
Lam, P., Zhu, A. H., Gari, I. B., Jahanshad, N., & Thompson, P. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09115 · Cited by 13
“More recently, deep learning methods such as convolutional neural networks (CNN) have been applied to preprocessed and raw T1-weighted MRI data [5], and adapted to accommodate multiple datasets using transfer learning [6].”
MethodBrain age in multiple sclerosis: a study with deep learning and traditional machine learning
Skattebøl, L., Nygaard, G. O., Leonardsen, E. H., Kaufmann, T., Moridi, T., Stawiarz, L., Ouellette, R., Ineichen, B. V., Ferreira, D., Muehlboeck, J., et al. (2025) · Brain Communications · doi:10.1093/braincomms/fcaf152 · Cited by 12
“19,23 These challenges are exacerbated by the opacity in deep models, where the large parameter space and complex paths for information flow make it difficult to pinpoint which features contribute to predictions.”
Kamei, T., Miyake, M., Sado, K., Morino, K., Mori, Y., Tabara, Y., Matsuda, F., Tamura, H., & Tsujikawa, A. (2025) · Japanese Journal of Ophthalmology · doi:10.1007/s10384-025-01205-3 · Cited by 12
Fitness and exercise effects on brain age: A randomized clinical trial
Wan, L., Molina‐Hidalgo, C., Crisafio, M. E., Grove, G., Leckie, R. L., Kamarck, T. W., Kang, C., DeCataldo, M. K., Marsland, A. L., Muldoon, M. F., et al. (2025) · Journal of sport and health science/Journal of Sport and Health Science · doi:10.1016/j.jshs.2025.101079 · Cited by 13
Moon, H. S., Mahzarnia, A., Stout, J. A., Anderson, R. J., Han, Z. Y., Tremblay, J. T., Badea, C. T., & Badea, A. (2024) · Imaging Neuroscience · doi:10.1162/imag_a_00245 · Cited by 14
“…have contributed to an accelerated development of image-based models to classify subjects in disease groups, predict age ( Antipov et al., 2017; Cole et al., 2017; Jonsson et al., 2019; Peng et al., 2021; J. Wang et al., 2019), segment lesions ( Moon et al., 2022), etc. Brain age prediction…”
InfluentialGenomic determinants of biological age estimated by deep learning applied to retinal images
Huang, Y., Syed, M. G., Chen, R., Li, C., Shang, X., Wang, W., Zhang, X., Zhang, X., Tang, S., Liu, J., et al. (2025) · GeroScience · doi:10.1007/s11357-024-01481-w · Cited by 10
“…of deep learning (DL) techniques, there has been growing interest in the use of this approach to determine BA from latent information contained in medical images, for example, BA derived from brain magnetic resonance images (MRI) [6, 7], from liver and pancreas MRI [8], and chest radiographs [9].”
Human Age and Gender Prediction Using Deep Multi-Task Convolutional Neural Network
Al-Azzawi, D. S. (2019) · Journal of Southwest Jiaotong University · doi:10.35741/issn.0258-2724.54.4.11 · Cited by 12
“Figure 2 presents the extraction patterns of the key points from the human face whereby the cheeks and surrounding areas are given labels and then trained for the predictive discovery [5, 6].”
BackgroundPatch‐wise brain age longitudinal reliability
Beheshti, I., Potvin, O., & Duchesne, S. (2020) · Human Brain Mapping · doi:10.1002/hbm.25253 · Cited by 12
Brain-Predicted Age Difference Moderates the Association Between Muscle Strength and Mobility
Vaughan, B. A., Simon, J. E., Grooms, D. R., Clark, L. A., Wages, N. P., & Clark, B. C. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.808022 · Cited by 12
Ceolini, E., Brunner, I. C., Bunschoten, J. W., Majoie, M., Thijs, R. D., & Ghosh, A. (2022) · iScience · doi:10.1016/j.isci.2022.104792 · Cited by 12
Brain status modeling with non-negative projective dictionary learning
Zhang, M., Desrosiers, C., Guo, Y., Khundrakpam, B. S., Al‐Sharif, N., Kiar, G., Valdes-Sosa, P. A., Poline, J., & Evans, A. C. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.116226 · Cited by 12
“…features such as cortical surface measures for analyzing brain development and brain maturity (Cole and Franke, 2017; Ball et al., 2017; Brown et al., 2012; Becker et al., 2018; Varikuti et al., 2018; Franke et al., 2018; Pardoe and Kuzniecky, 2018; Cole, 2017; Yamaguchi and Honma, 2012).”
Gómez‐Ramírez, J., Fernández‐Blázquez, M. A., & González-Rosa, J. J. (2022) · Brain Sciences · doi:10.3390/brainsci12050579 · Cited by 13
“Nevertheless, characteristics of the sample data used to train the models can lead to different estimates of the mean absolute error in age predictions [76], with some studies having a wide range of ages [66,77,78] while others concentrating on a limited range [68].”
BackgroundNeuroimaging-Derived Predicted Brain Age and Alcohol Use Among Community-Dwelling Older Adults
Funk‐White, M., Wing, D., Eyler, L. T., Moore, A. A., Reas, E. T., & McEvoy, L. K. (2023) · American Journal of Geriatric Psychiatry · doi:10.1016/j.jagp.2023.02.043 · Cited by 11
Brain Age Prediction Based on Quantitative Susceptibility Mapping Using the Segmentation Transformer
Chen, M., Wang, Y., Shi, Y., Feng, J., Feng, R., Guan, X., Xu, X., Zhang, Y., Jin, C., & Wei, H. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3341629 · Cited by 11
Ordinal Classification with Distance Regularization for Robust Brain Age Prediction
Shah, J., Siddiquee, M. M. R., Su, Y., Wu, T., & Li, B. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00770 · Cited by 12
“Our method’s performance is also significantly better than MAE reported by prior studies using regression analysis [21, 23, 9], however, on different cohorts.”
BackgroundMethodResultInfluential
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
