The DOI matches its Crossref record; 70 of the 72 references it cites were found in a registry or an index.
Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker
Open accessAbstract
&NA; Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people. Deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of ‘brain‐predicted age’ as a biomarker of individual differences in the brain ageing process, using a predictive modelling approach based on deep learning, and specifically convolutional neural networks (CNN), and applied to both pre‐processed and raw T1‐weighted MRI data. Firstly, we aimed to demonstrate the accuracy of CNN brain‐predicted age using a large dataset of healthy adults (N = 2001). Next, we sought to establish the heritability of brain‐predicted age using a sample of monozygotic and dizygotic female twins (N = 62). Thirdly, we examined the test‐retest and multi‐centre reliability of brain‐predicted age using two samples (within‐scanner N = 20; between‐scanner N = 11). CNN brain‐predicted ages were generated and compared to a Gaussian Process Regression (GPR) approach, on all datasets. Input data were grey matter (GM) or white matter (WM) volumetric maps generated by Statistical Parametric Mapping (SPM) or raw data. CNN accurately predicted chronological age using GM (correlation between brain‐predicted age and chronological age r = 0.96, mean absolute error [MAE] = 4.16 years) and raw (r = 0.94, MAE = 4.65 years) data. This was comparable to GPR brain‐predicted age using GM data (r = 0.95, MAE = 4.66 years). Brain‐predicted age was a heritable phenotype for all models and input data (h2 ≥ 0.5). Brain‐predicted age showed high test‐retest reliability (intraclass correlation coefficient [ICC] = 0.90–0.99). Multi‐centre reliability was more variable within high ICCs for GM (0.83–0.96) and poor‐moderate levels for WM and raw data (0.51–0.77). Brain‐predicted age represents an accurate, highly reliable and genetically‐influenced phenotype, that has potential to be used as a biomarker of brain ageing. Moreover, age predictions can be accurately generated on raw T1‐MRI data, substantially reducing computation time for novel data, bringing the process closer to giving real‐time information on brain health in clinical settings. HighlightsChronological age can be accurately predicted using convolutional neural networks.Age predicted is accurate even using raw structural neuroimaging data.Brain‐predicted age can be generated in a clinically applicable timeframe.Brain‐predicted age is significantly heritable.Brain‐predicted age is highly reliable, both within and between scanners.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879 · cited 1×
“In choosing between sub-models, variance components are excluded from the selection process if there is no significant deterioration in model fit after the component is dropped, as assessed by the Akaike Information Criterion (Akaike, 1974).”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“The architecture contains repeated 5 blocks of a (3 3 3) convolutional layer (with stride of 1), a rectified linear unit (ReLU), a (3 3 3) convolutional layer (with stride of 1), a 3D batch-normalization layer (Ioffe and Szegedy, 2015), a ReLU and finally a (2 2 2) max-pooling layer (with stride of 2).”
BackgroundIntraclass correlations: Uses in assessing rater reliability.
Shrout, P. E., & Fleiss, J. L. (1979) · Psychological Bulletin · doi:10.1037/0033-2909.86.2.420 · Cited by 24,532
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273
A fast diffeomorphic image registration algorithm
Ashburner, J. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.07.007 · Cited by 8,122
A global optimisation method for robust affine registration of brain images
Jenkinson, M., & Smith, S. M. (2001) · Medical Image Analysis · doi:10.1016/s1361-8415(01)00036-6 · Cited by 7,018 · cited 1×
“Raw Nifti files then underwent a rigid registration (i.e. six degrees-of-freedom) to MNI152 space, (FMRIB Software Library [FSL] FLIRT, Jenkinson and Smith, 2001) to ensure consistency of orientation (Right, Posterior, Inferior [RPI]).”
Method3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,313
Avants, B., Epstein, C. L., Grossman, M., & Gee, J. C. (2007) · Medical Image Analysis · doi:10.1016/j.media.2007.06.004 · Cited by 5,924
Cited by
Sorted by citations
Items 101–200 of 869
Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction
Lancaster, J., Lorenz, R., Leech, R., & Cole, J. H. (2018) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2018.00028 · Cited by 73
“In our previous work on brain-age prediction we used 1.5 mm 3 voxel dimensions and a 4 mm smoothing kernel (Cole et al., 2015, 2017a,b,c,d; Pardoe et al., 2017), which we subsequently refer to as ‘un-optimized’ pre-processing parameters.”
InfluentialSelf-citationUnbiased age-specific structural brain atlases for Chinese pediatric population
Zhao, T., Liao, X., Fonov, V., Wang, Q., Men, W., Wang, Y., Qin, S., Tan, S., Gao, J., Evans, A. C., et al. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.01.006 · Cited by 73
“Recently, an increasing number of pediatric studies have used the innovative concept of “brain age” to predict the extent of brain maturation (Ball et al., 2017; Brown et al., 2012; Cao et al., 2017; Cole et al., 2017; Dosenbach et al., 2010; Franke et al., 2012; Kwak et al., 2018; Madan and Kensinger, 2018; Zhao et a…”
Deep learning for biological age estimation
Rahman, S. A., Giacobbi, P. R., Pyles, L. A., Mullett, C. J., Doretto, G., & Adjeroh, D. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa021 · Cited by 75
“[9] studied a deep learning framework using 3D-CNN-based approach with raw MRI data.”
BackgroundMethodAl-Asaly, M. S., Bencherif, M. A., Alsanad, A., & Hassan, M. M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06665-5 · Cited by 78
“In particular, deep learning has outperformed other machine learning methods and generated promising results in diverse fields, including computer vision [46–48], transfer learning [49, 50], image classification and object recognition [46, 51–54], speech recognition [55–57], natural language understanding [58, 59], tr…”
BackgroundClausen, A. N., Fercho, K. A., Monsour, M., Disner, S. G., Salminen, L. E., Haswell, C. C., Clarke‐Rubright, E. K., Watts, A. A., Buckley, M. N., Maron‐Katz, A., et al. (2021) · Brain and Behavior · doi:10.1002/brb3.2413 · Cited by 77
Self-citationA systematic review of object detection from images using deep learning
Kaur, J., & Singh, W. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15981-y · Cited by 78
Artificial intelligence in medicine: Technical basis and clinical applications
Erickson, B. J. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-821259-2.00002-8 · Cited by 71
Aging faster: worry and rumination in late life are associated with greater brain age
Karim, H. T., Ly, M. J., Yu, G. Z., Krafty, R. T., Tudorascu, D., Aizenstein, H. J., & Andreescu, C. (2021) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2021.01.009 · Cited by 76
“Past studies have shown that this generates reliable brain age estimates (Cole et al., 2017), but this may nonetheless affect the current results.”
Keding, T. J., Heyn, S. A., Russell, J. D., Zhu, X., Cisler, J. M., McLaughlin, K. A., & Herringa, R. J. (2021) · American Journal of Psychiatry · doi:10.1176/appi.ajp.2021.20081192 · Cited by 66
“BrainAGE has been shown to represent a biologically meaningful index that is reliable (17, 18), heritable (18), and associated with developmental neurophenotypes underlying illness (19, 20).”
BackgroundDomain- and task-specific transfer learning for medical segmentation tasks
Zoetmulder, R., Gavves, E., Caan, M. W. A., & Marquering, H. A. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106539 · Cited by 74
Self-citationApplication and Construction of Deep Learning Networks in Medical Imaging
Torres-Velázquez, M., Chen, W., Li, X., & McMillan, A. B. (2020) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2020.3030611 · Cited by 74
“Another study, successfully inputted gray and white matter volumetric maps and raw T1 MRI images to a 3-D CNN network to predict age [81].”
BackgroundOpenBHB: a Large-Scale Multi-Site Brain MRI Data-set for Age Prediction and Debiasing
Dufumier, B., Grigis, A., Victor, J., Ambroise, C., Frouin, V., & Duchesnay, É. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119637 · Cited by 78
“It has been shown Bashyam et al. (2020b) ; Cole and Franke (2017) ; Cole et al. (2017) ; Jonsson et al. (2019) ; Peng et al. (2021) that machine learning (ML) models can learn from neuroimaging data to accurately estimate chronological age from the healthy population, taking into account the…”
Predicting brain age with complex networks: From adolescence to adulthood
Bellantuono, L., Marzano, L., Rocca, M. L., Duncan, D., Lombardi, A., Maggipinto, T., Monaco, A., Tangaro, S., Amoroso, N., & Bellotti, R. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.117458 · Cited by 67
Cluceru, J. G., Interian, Y., Phillips, J. J., Molinaro, A. M., Luks, T. L., Leon, P. A., Olson, M. P., Nair, D., Lafontaine, M., Shai, A., et al. (2021) · Neuro-Oncology · doi:10.1093/neuonc/noab238 · Cited by 70
Review on Reliable Pattern Recognition with Machine Learning Techniques
Bhamare, D., & Suryawanshi, P. (2018) · Fuzzy Information and Engineering · doi:10.1080/16168658.2019.1611030 · Cited by 65
“In their proposed work age forecasts can be unequivocally delivered on crude T1-weighted information, altogether diminishing calculation time for novel information, conveying the procedure nearer to giving ongoing data on cerebrum wellbeing in clinical settings [23].”
BackgroundBrain Age Prediction of Children Using Routine Brain MR Images via Deep Learning
Hong, J., Feng, Z., Wang, S., Peet, A. C., Zhang, Y., Sun, Y., & Yang, M. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.584682 · Cited by 63
“…between adjacent slices is beneficial to the prediction accuracy of the model, and also shows the 3D CNN employing 3D kernels is a more reliable resolution that can take all full advantage of spatial contextual information of the 3D MR images for more accurate age prediction (16, 29, 52).”
BackgroundMethodInfluentialQuantification of the Biological Age of the Brain Using Neuroimaging
Cole, J. H., Franke, K., & Cherbuin, N. (2019) · Healthy ageing and longevity · doi:10.1007/978-3-030-24970-0_19 · Cited by 65
Self-citationPromises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
Eitel, F., Schulz, M.-A., Seiler, M., Walter, H., & Ritter, K. (2021) · Experimental Neurology · doi:10.1016/j.expneurol.2021.113608 · Cited by 73
A review on brain age prediction models
Kumari, L. K. S., & Sundarrajan, R. (2023) · Brain Research · doi:10.1016/j.brainres.2023.148668 · Cited by 64
Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders
Kolbeinsson, A., Filippi, S., Panagakis, Y., Matthews, P. M., Elliott, P., Dehghan, A., & Tzoulaki, I. (2020) · Scientific Reports · doi:10.1038/s41598-020-76518-z · Cited by 65
Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets
Bento, M., Fantini, I., Park, J., Rittner, L., & Frayne, R. (2022) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2021.805669 · Cited by 72
“By analyzing and modeling image data variability, these approaches tend to provide more reliable results because their outputs are related to the underlying research question ( i.e. , pathology of interest) and are not influenced by batch effects (Cole et al., 2017).”
BackgroundCumplido‐Mayoral, I., García-Prat, M., Operto, G., Falcón, C., Shekari, M., Cacciaglia, R., Milà‐Alomà, M., Lorenzini, L., Ingala, S., Wink, A. M., et al. (2023) · eLife · doi:10.7554/elife.81067 · Cited by 74
Bonifazi, P., Erramuzpe, A., Diez, I. P., Gabilondo, I., Boisgontier, M. P., Pauwels, L., Stramaglia, S., Swinnen, S. P., & Cortés, J. M. (2018) · Human Brain Mapping · doi:10.1002/hbm.24312 · Cited by 60
“It is important to remark that the value of MAE of BCA equal to 5.89 years is no better than the performance of some other prediction models using merely volumetric data (Cole, Poudel, et al., 2017; Franke et al., 2010; Mwangi et al., 2015).”
ResultInfluentialThe Speed of Development of Adolescent Brain Age Depends on Sex and Is Genetically Determined
Brouwer, R. M., Schutte, J., Janssen, R. J., Boomsma, D. I., Pol, H. E. H., & Schnack, H. G. (2020) · Cerebral Cortex · doi:10.1093/cercor/bhaa296 · Cited by 63
“Brain age itself has been found to be a heritable phenotype in a small sample of adult females (Cole et al. 2017).”
Association of Sleep Electroencephalography-Based Brain Age Index With Dementia
Ye, E. M., Sun, H., Leone, M. J., Paixão, L., THOMAS, R. J., Lam, A. D., & Westover, M. B. (2020) · JAMA Network Open · doi:10.1001/jamanetworkopen.2020.17357 · Cited by 61
Hofmann, S., Beyer, F., Lapuschkin, S., Goltermann, O., Loeffler, M., Müller, K., Villringer, A., Samek, W., & Witte, A. V. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119504 · Cited by 67
A perspective on brain-age estimation and its clinical promise
Gaser, C., Kalc, P., & Cole, J. H. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00659-8 · Cited by 65
“Various models, such as convolutional neural networks 44 , ResNet 45 and simple fully convolutional network 46 , have been developed to predict the brain age.”
MethodSelf-citationChen, C., Hsu, Y., Yang, L., Tung, Y.-H., Luo, W., Liu, C., Hwang, T., Hwu, H., & Tseng, W. I. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.116831 · Cited by 63
Hu, Z., Liu, G., Dong, Q., & Niu, H. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00476 · Cited by 64
“The quickly accumulating neurological data from this technique combined with the emerging deep learning technology (Hennrich et al., 2015; Marblestone et al., 2016; Cole et al., 2017; Shen et al., 2017; Vieira et al., 2017; Zhou et al., 2018) could help to diagnose neurological diseases precisely.”
BackgroundBrain age prediction in schizophrenia: Does the choice of machine learning algorithm matter?
Lee, W. H., Antoniades, M., Schnack, H. G., Kahn, R. S., & Frangou, S. (2021) · Psychiatry Research Neuroimaging · doi:10.1016/j.pscychresns.2021.111270 · Cited by 58
Xifra‐Porxas, A., Ghosh, A., Mitsis, G. D., & Boudrias, M. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.117822 · Cited by 60
Mouchès, P., Wilms, M., Rajashekar, D., Langner, S., & Forkert, N. D. (2022) · Human Brain Mapping · doi:10.1002/hbm.25805 · Cited by 59
Holm, M. C., Leonardsen, E. H., Beck, D., Dahl, A., Kjelkenes, R., de Lange, A. G., & Westlye, L. T. (2023) · Developmental Cognitive Neuroscience · doi:10.1016/j.dcn.2023.101220 · Cited by 59
“In adults, the difference between brain age and chronological age has been shown to represent a heritable trait (Cole et al., 2017; Kaufmann et al., 2019) and a range of clinically relevant characteristics and conditions have been associated with higher brain age (Tønnesen et al.”
Biomarkers of ageing: Current state‐of‐art, challenges, and opportunities
Chen, R., Wang, Y., Zhang, S., Bulloch, G., Zhang, J., Liao, H., Shang, X., Clark, M., Peng, Q., Ge, Z., et al. (2023) · MedComm – Future Medicine · doi:10.1002/mef2.50 · Cited by 63
“26 192 Recent studies demonstrated the utility of multimodality neuroimaging data in terms of age prediction.”
BackgroundDeep Learning and Multiplex Networks for Accurate Modeling of Brain Age
Amoroso, N., Rocca, M. L., Bellantuono, L., Diacono, D., Fanizzi, A., Lella, E., Lombardi, A., Maggipinto, T., Monaco, A., Tangaro, S., et al. (2019) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2019.00115 · Cited by 59
“A not secondary aspect to consider is age distribution: in this work we have analyzed a roughly uniform cohort, which is not the case, e.g., in Cole et al. (2017a).”
BackgroundResultIndividual variation underlying brain age estimates in typical development
Ball, G., Kelly, C. E., Beare, R. J., & Seal, M. L. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118036 · Cited by 62
Kim, H., Lee, Y. I., Kim, Y., Lim, Y., Lee, J. S., Woo, J., Jang, S.-K., Oh, Y. J., Kim, H. W., Lee, E., et al. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.599042 · Cited by 60
“Additionally, although most imaging studies have used 2D CNNs as their model architecture, some recent studies have proposed the use of 3D CNNs to fully utilize the spatial features of MRI and achieve better performance (27–30).”
Age-Related Alterations in DTI Metrics in the Human Brain—Consequences for Age Correction
Behler, A., Kassubek, J., & Müller, H. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.682109 · Cited by 56
“The so-called “brain age” of a subject, estimated by structural properties, often differs from the actual chronological age (Franke et al., 2010; Cole et al., 2017; Smith et al., 2019).”
BackgroundGialluisi, A., Castelnuovo, A. F. D., Costanzo, S., Bonaccio, M., Persichillo, M., Magnacca, S., Curtis, A. D., Cerletti, C., Donati, M. B., de Gaetano, G., et al. (2021) · European Journal of Epidemiology · doi:10.1007/s10654-021-00797-7 · Cited by 56
AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction
Gao, F., Yoon, H., Xu, Y., Goradia, D., Luo, J., Wu, T., & Su, Y. (2020) · NeuroImage: Clinical · doi:10.1016/j.nicl.2020.102290 · Cited by 64
“H. et al., 2017). In Cole, J. H. et al., (2017), the researchers trained a deep learning model on MRI neuroimages from cognitively normal subjects to predict each subject’s biological age (B-Age).”
BackgroundAge-Net: An MRI-Based Iterative Framework for Brain Biological Age Estimation
Armanious, K., Abdulatif, S., Shi, W., Salian, S., Küstner, T., Weiskopf, D., Hepp, T., Gatidis, S., & Yang, B. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3066857 · Cited by 59
Accelerated brain aging predicts impulsivity and symptom severity in depression
Dunlop, K., Victoria, L. W., Downar, J. H., Gunning, F. M., & Liston, C. M. (2021) · Neuropsychopharmacology · doi:10.1038/s41386-021-00967-x · Cited by 56
Accelerated aging in the brain, epigenetic aging in blood, and polygenic risk for schizophrenia
Teeuw, J., Ori, A. P. S., Brouwer, R. M., de Zwarte, S. M. C., Schnack, H. G., Pol, H. E. H., & Ophoff, R. A. (2021) · Schizophrenia Research · doi:10.1016/j.schres.2021.04.005 · Cited by 55
A deep ensemble hippocampal CNN model for brain age estimation applied to Alzheimer’s diagnosis
Poloni, K. M., & Ferrari, R. J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116622 · Cited by 55
Deep Relation Learning for Regression and Its Application to Brain Age Estimation
He, S., Feng, Y., Grant, P. E., & Ou, Y. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3161739 · Cited by 59
Macdonald-Dunlop, E., Taba, N., Klarić, L., Frkatović-Hodžić, A., Walker, R. M., Hayward, C., Esko, T., Haley, C., Fischer, K., Wilson, J. F., et al. (2022) · Aging · doi:10.18632/aging.203847 · Cited by 60
Age-level bias correction in brain age prediction
Zhang, B., Zhang, S., Feng, J., & Zhang, S. (2023) · NeuroImage Clinical · doi:10.1016/j.nicl.2023.103319 · Cited by 62
“For example, those genome-wide association studies (GWAS) of PAD may yield misleading sequence variants [11, 12].”
BackgroundMethodInfluentialAttention-guided deep learning for gestational age prediction using fetal brain MRI
Shen, L., Zheng, J., Lee, E. H., Shpanskaya, K. S., McKenna, E. S., Atluri, M. G., Plasto, D., Mitchell, C., Lai, L. M., Guimaraes, C. V. A., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-05468-5 · Cited by 54
Risk of Training Diagnostic Algorithms on Data with Demographic Bias
Abbasi-Sureshjani, S., Raumanns, R., Michels, B. E. J., Schouten, G., & Cheplygina, V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61166-8_20 · Cited by 54
“rform poorly on under-represented groups [5]. In medical imaging, similar factors might in uence the data, thus have an impact on the incidence of disease too, as shown in some studies. For instance, [8,21] show that signs of brain aging as a biomarker of aging can be predicted from brain and retinal images; or the wo…”
BackgroundMulti-Center Brain Imaging Classification Using a Novel 3D CNN Approach
Yuan, L., Wei, X., Shen, H., Zeng, L., & Hu, D. (2018) · IEEE Access · doi:10.1109/access.2018.2868813 · Cited by 55
Deep learning in systems medicine
Wang, H., Pujos‐Guillot, E., Comte, B., de Miranda, J. L., Spiwok, V., Chorbev, I., Castiglione, F., Tieri, P., Watterson, S., McAllister, R., et al. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa237 · Cited by 54
“an accurate biomarker of chronological age using eye cornea images [107] and also applied in neuroimaging to identify biomarkers of brain aging using CNNs [108].”
MethodInfluentialLong-term Anabolic–Androgenic Steroid Use Is Associated With Deviant Brain Aging
Bjørnebekk, A., Kaufmann, T., Hauger, L. E., Klonteig, S., Hullstein, I. R., & Westlye, L. T. (2021) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2021.01.001 · Cited by 52
“The difference between the predicted and chronological age, termed the brain age gap (BAG), serves as a surrogate marker of individual brain health and individual differences in brain maturation and aging (49, 50).”
Brain structure ages—A new biomarker for multi‐disease classification
Nguyen, H., Clément, M., Mansencal, B., & Coupé, P. (2024) · Human Brain Mapping · doi:10.1002/hbm.26558 · Cited by 53
“Recent studies show the capacity of deep learning algorithms in the brain age estimation task based on sMRI with an MAE ranging from 1.96 to 4.16 years (Armanious et al., 2021; Bermudez et al., 2019; Bintsi et al., 2020; Cole et al., 2017; Jonsson et al., 2019).”
BackgroundMethodInfluentialGialluisi, A., Castelnuovo, A. F. D., Donati, M. B., de Gaetano, G., Iacoviello, L., & the Moli-sani Study Investigators (2019) · Frontiers in Medicine · doi:10.3389/fmed.2019.00146 · Cited by 50
“Here, we will focus on the most recent and accurate developments, which use structural Magnetic Resonance Imaging (MRI) data (5, 6, 23, 27, 28, 31, 32).”
BackgroundMethodInfluentialBeck, D., de Lange, A. G., Alnæs, D., Maximov, I. I., Pedersen, M. L., Leinhard, O. D., Linge, J., Simon, R. A., Richard, G., Ulrichsen, K. M., et al. (2022) · NeuroImage Clinical · doi:10.1016/j.nicl.2022.102949 · Cited by 49
Wagen, A. Z., Coath, W., Keshavan, A., James, S., Parker, T. D., Lane, C., Buchanan, S. M., Keuss, S. E., Storey, M., Lu, K., et al. (2022) · The Lancet Healthy Longevity · doi:10.1016/s2666-7568(22)00167-2 · Cited by 49
“37 Moreover, since T1-weighted MRI has been validated far more extensively, 9 our results can be readily compared with most of the brain age literature.”
Self-citation“Brain age” predicts disability accumulation in multiple sclerosis
Brier, M. R., Li, Z., Ly, M. J., Karim, H. T., Liang, L., Du, W., McCarthy, J. E., Cross, A. H., Benzinger, T. L. S., Naismith, R. T., et al. (2023) · Annals of Clinical and Translational Neurology · doi:10.1002/acn3.51782 · Cited by 49
Genetic architecture of brain age and its causal relations with brain and mental disorders
Leonardsen, E. H., Dídac Vidal-piñeiro, A., Roe, J. M., Frei, O., Shadrin, A. A., Iakunchykova, O. P., de Lange, A. G., Kaufmann, T., Taschler, B., Smith, S. M., et al. (2023) · Molecular Psychiatry · doi:10.1038/s41380-023-02087-y · Cited by 48
“Twin-based heritability for BAG has been estimated to be as high as 0.66 [17], and single nucleotide polymorphism (SNP)-based heritability estimates are also relatively high — around 0.2 [6, 18].”
BackgroundInfluentialExcess brain age in the sleep electroencephalogram predicts reduced life expectancy
Paixão, L., Sikka, P., Sun, H., Jain, A., Hogan, J. S., THOMAS, R. J., & Westover, M. B. (2019) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2019.12.015 · Cited by 49
“Cole (2017) and Cole et al. (2017b) further found that raw T1-weighted MRI data using machine learning methods can function as a brain aging biomarker.”
BackgroundTunç, B., Yankowitz, L., Parker, D., Alappatt, J. A., Pandey, J., Schultz, R., & Verma, R. (2019) · Molecular Autism · doi:10.1186/s13229-019-0301-5 · Cited by 47
“Brain age models, while limiting region-specific interpretations, use multivariate machine learning techniques to better capture complex interactions between brain regions during development [42, 43], as well as the interplay between different modalities such as anatomical and diffusion metrics.”
BackgroundPopulation modeling with machine learning can enhance measures of mental health
Dadi, K., Varoquaux, G. P., Houenou, J., Bzdok, D., Thirion, B., & Engemann, D. A. (2021) · GigaScience · doi:10.1093/gigascience/giab071 · Cited by 54
“Learning curves documented that the training split was sufficiently large for constructing stable prediction models Figure 1 – Figure supplement 1 with profiles of performance similar to latest benchmarks on model complexity in the UK Biobank [71].”
InfluentialYu, X. (2018) · Data Archiving and Networked Services (DANS) · doi:10.17632/ffkv2xj2m7.1 · Cited by 48
“…machine learning research (LeCun et al., 2015), which has a deep structure of arti fi cial neural networks with capable of processing very large-scale data, and has dramatically improved the modeling performance in many data analysis tasks (Zhao and Du, 2016; Farias et al., 2016; Cole et al., 2017).”
BackgroundAn automated machine learning approach to predict brain age from cortical anatomical measures
Dafflon, 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. (2020) · Human Brain Mapping · doi:10.1002/hbm.25028 · Cited by 48
“A similar problem has been described and extensively studied in motion correction in resting state fMRI.”
MethodInfluentialSelf-citationHepp, T., Blum, D., Armanious, K., Schölkopf, B., Štern, D., Yang, B., & Gatidis, S. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101967 · Cited by 49
Investigating the impact of motion in the scanner on brain age predictions
Moqadam, R., Dadar, M., & Zeighami, Y. (2024) · Imaging Neuroscience · doi:10.1162/imag_a_00079 · Cited by 50
Lv, H., Zeng, N., Li, M., Sun, J., Wu, N., Xu, M., Chen, Q., Zhao, X., Chen, S., Liu, W., et al. (2024) · Health Data Science · doi:10.34133/hds.0087 · Cited by 46
Petersen, K. J., Metcalf, N. V., Cooley, S., Tomov, D., Vaida, F., Paul, R. H., & Ances, B. M. (2021) · Clinical Infectious Diseases · doi:10.1093/cid/ciab169 · Cited by 46
“Brain Aging in HIV • cid 2021:73 (15 November) • 1819 predictive accuracy in training and testing [34].”
BackgroundUsman, O. L., & Muniyandi, R. C. (2020) · Symmetry · doi:10.3390/sym12050836 · Cited by 50
“Additionally, at the end, CNN usually has fully connected layers that compute the final output [44].”
BackgroundA deep learning model for brain age prediction using minimally preprocessed T1w images as input
Dartora, C. M., Marseglia, A., Mårtensson, G., Rukh, G., Dang, J., Muehlboeck, J., Wahlund, L., Moreno, R., Barroso, J., Ferreira, D., et al. (2024) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2023.1303036 · Cited by 46
Anatomical context improves deep learning on the brain age estimation task
Bermudez, C. L., Plassard, A. J., Chaganti, S., Huo, Y., Aboud, K. S., Cutting, L. E., Resnick, S. M., & Landman, B. A. (2019) · Magnetic Resonance Imaging · doi:10.1016/j.mri.2019.06.018 · Cited by 45
“Cole et. al proposed a convolutional deep neural network technique on raw T1w MRI images which showed an mean absolute error of 4.65 years in 2,001 healthy adults ages 18 to 90 years (13).”
BackgroundMethodInfluentialImproving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework
Kuo, C.-Y., Tai, T., Lee, P., Tseng, C.-W., Chen, C.-Y., Chen, L., Lee, C.-K., Chou, K., See, S. C. W., & Lin, C. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.626677 · Cited by 46
“Several DL-based studies have demonstrated the superior predictive performance of this approach using single imaging modalities as the input feature set for estimating individual brain age with minimal image preprocessing procedures and feature extraction steps (19, 21, 22).”
BackgroundMethodRadiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke
Bretzner, M., Bonkhoff, A. K., Schirmer, M. D., Hong, S., Dalca, A. V., Donahue, K., Giese, A., Etherton, M. R., Rist, P. M., Nardin, M., et al. (2022) · Neurology · doi:10.1212/wnl.0000000000201596 · Cited by 44
Self-citationHong, G.-S., Jang, M., Kyung, S., Cho, K., Jeong, J., Lee, G. Y., Shin, K., Kim, K., Ryu, S. M., Seo, J. B., et al. (2023) · Korean Journal of Radiology · doi:10.3348/kjr.2023.0393 · Cited by 46
“The disparities between predicted and chronological ages may be attributed to the accumulation of age-related alterations in pathological circumstances [185-187] or protective factors in brain aging [188,189].”
BackgroundWeakly supervised object detection with 2D and 3D regression neural networks
Dubost, F., Adams, H. H. H., Yilmaz, P., Bortsova, G., van Tulder, G., Ikram, M. A., Niessen, W. J., Vernooij, M. W., & de Bruijne, M. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101767 · Cited by 45
Dunås, T., Wåhlin, A., Nyberg, L. H., & Boraxbekk, C. (2021) · Cerebral Cortex · doi:10.1093/cercor/bhab019 · Cited by 45
Geometric deep learning on brain shape predicts sex and age
Besson, P., Parrish, T. B., Katsaggelos, A. K., & Bandt, S. K. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101939 · Cited by 43
Couvy‐Duchesne, B., Faouzi, J., Martin, B., Thibeau–Sutre, E., Wild, A., Ansart, M., Durrleman, S., Dormont, D., Burgos, N., & Olivier Colliot, A. (2020) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2020.593336 · Cited by 47
“In addition, brain age (and PAD) has been shown to be heritable (17, 18), and recent genome-wide association studies (GWASs) have started shedding light on some of themolecular mechanisms responsible for brain aging (19, 20).”
BackgroundVoldsbekk, I., Barth, C., Maximov, I. I., Kaufmann, T., Beck, D., Richard, G., Moberget, T., Westlye, L. T., & de Lange, A. G. (2021) · Human Brain Mapping · doi:10.1002/hbm.25553 · Cited by 45
Drobinin, V., Gestel, H. V., Helmick, C. A., Schmidt, M. H., Bowen, C. V., & Uher, R. (2021) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2021.09.004 · Cited by 47
Korbmacher, M., de Lange, A. G., van der Meer, D., Beck, D., Eikefjord, E., Lundervold, A., Andreassen, O. A., Westlye, L. T., & Maximov, I. I. (2023) · Human Brain Mapping · doi:10.1002/hbm.26333 · Cited by 43
“The disparity between chronological age and predicted age, the so-called brain age gap (BAG), can be used as an indicator of various disorders and potentially general health status (Beck et al., 2022; Cole et al., 2017; Franke & Ten Gaser, 2019; Kaufmann et al., 2019; Leonardsen et al., 2021).”
BackgroundMethodPredicting Brain Age Based on Spatial and Temporal Features of Human Brain Functional Networks
Zhai, J., & Li, K. (2019) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2019.00062 · Cited by 40
Gong, W., Beckmann, C. F., Vedaldi, A., Smith, S. M., & Peng, H. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.627996 · Cited by 43
Stripelis, D., Thompson, P. M., & Ambite, J. L. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3524885 · Cited by 57
“We evaluate the protocols on the CIFAR-10, CIFAR-100, and ExtendedMNIST By Class [9, 13] benchmark datasets with a federation consisting of 10 learners as well as on the BrainAge prediction task [14, 22, 28, 52, 66] with a federation of eight learners.”
MethodNeuroimaging-Based Brain Age Estimation: A Promising Personalized Biomarker in Neuropsychiatry
Sone, D., & Beheshti, I. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12111850 · Cited by 41
“In 2017, James Cole and his peers developed the first deep learning-based brain-age estimation framework, with a 3D convolutional neural network (CNN) that uses 3D gray matter and 3D white matter intensity maps as the input data [11].”
BackgroundMethodInfluentialJoo, Y., Namgung, E., Jeong, H. S., Kang, I., Kim, J., Oh, S., Lyoo, I. K., Yoon, S. J., & Hwang, J. (2023) · Scientific Reports · doi:10.1038/s41598-023-49514-2 · Cited by 43
“While their study 15 did not specify the exact training duration, the application of Gaussian process regression (GPR) is known to reduce computational time compared to certain other deep learning algorithms with a similar level of performance.”
BackgroundMethodResultInfluentialImproved Brain Age Estimation With Slice-Based Set Networks
Gupta, U., Lam, P., Steeg, G. V., & Thompson, P. M. (2021) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9434081 · Cited by 41
“3D-CNN: Most conventional deep learning approaches for BrainAGE estimation use 3D-CNNs [4, 5].”
MethodSex differences in predictors and regional patterns of brain age gap estimates
Sanford, N., Ge, R., Antoniades, M., Modabbernia, A., Haas, S. S., Whalley, H. C., Galea, L. A. M., Popescu, S. G., Cole, J. H., & Frangou, S. (2022) · Human Brain Mapping · doi:10.1002/hbm.25983 · Cited by 42
“G-brainAGE is a global index of age-related changes across the brain (Cole et al., 2017; Cole & Franke, 2017; Franke et al., 2010) while L-brainAGE informs about regional age-related brain changes (Popescu et al., 2021).”
Self-citationAnatomical context protects deep learning from adversarial perturbations in medical imaging
Li, Y., Zhang, H., Bermudez, C. L., Chen, Y., Landman, B. A., & Vorobeychik, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.085 · Cited by 41
“…photographs with great accuracy, while Bejnordi et al. [3] were able to accurately detect lymph node metastasis in patients with breast cancer, and Cole et al. [4] used deep learning to produce a more accurate brain age prediction, which has been shown to correlate with neurodegenerative diseases.”
Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction
Treder, M. S., Shock, J. P., Stein, D. J., du Plessis, S. S., Seedat, S., & Tsvetanov, K. A. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.615754 · Cited by 41
“Neuroimaging Data Neuroimaging data supplied within the Predictive Analytics Competition were fully pre-processed T1-weighted MRI scans from 2,640 training set and 660 validation set subjects as described previously (2).”
BackgroundMethodInfluentialAssociations between alcohol use and accelerated biological ageing
Bøstrand, S. M. K., Vaher, K., de Nooij, L., Harris, M. A., Cole, J. H., Cox, S. R., Marioni, R. E., McCartney, D. L., Walker, R. M., McIntosh, A. M., et al. (2021) · Addiction Biology · doi:10.1111/adb.13100 · Cited by 45
“This could account for some of the variation in susceptibility to age-related disease and suggests that measures of biological ageing may be more clinically relevant than chronological age (10,11).”
Self-citationMultimodal and multicontrast image fusion via deep generative models
Dimitri, G. M., Spasov, S., Duggento, A., Passamonti, L., Lió, P., & Toschi, N. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.07.017 · Cited by 41
EEG-based image classification via a region-level stacked bi-directional deep learning framework
Fares, A. H., Zhong, S.-H., & Jiang, J. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0967-9 · Cited by 38
MRI-based biomarkers of accelerated aging and dementia risk in midlife: how close are we?
Elliott, M. L. (2020) · Ageing Research Reviews · doi:10.1016/j.arr.2020.101075 · Cited by 39
Deep learning model for predicting gestational age after the first trimester using fetal MRI
Kojita, Y., Matsuo, H., Kanda, T., Nishio, M., Sofue, K., Nogami, M., Kono, A. K., Hori, M., & Murakami, T. (2021) · European Radiology · doi:10.1007/s00330-021-07915-9 · Cited by 39
“CNNs have been shown to be able to accurately predict the age of adult subjects from brain MRI [13, 14].”
BackgroundSullivan, E. V., & Adolf Pfefferbaum, A. (2022) · Alcohol · doi:10.1016/j.alcohol.2022.06.002 · Cited by 44
Identification of Tumor-Specific MRI Biomarkers Using Machine Learning (ML)
Hajjo, R., Sabbah, D. A., Bardaweel, S. K., & Tropsha, A. (2021) · Diagnostics · doi:10.3390/diagnostics11050742 · Cited by 38
“Exploiting quantitative data embedded in images along with demanding protocols for accession and scoring linked with machine learning algorithms have been applied in neurodegenerative disease and treatment protocol [174,175].”
Vasta, R., Cerasa, A., Sarica, A., Bartolini, E., Martino, I., Mari, F., Metitieri, T. T., Quattrone, A., Gambardella, A., Guerrini, R., et al. (2018) · Epilepsy & Behavior · doi:10.1016/j.yebeh.2018.09.008 · Cited by 38
Ning, K., Duffy, B. A., Franklin, M., Matloff, W. J., Zhao, L., Arzouni, N., Sun, F., & Toga, A. W. (2021) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2021.03.014 · Cited by 38
Brain age estimation reveals older adults’ accelerated senescence after traumatic brain injury
Amgalan, A., Maher, A. S., Ghosh, S., Chui, H. C., Bogdan, P., & Andrei Irimia, A. (2022) · GeroScience · doi:10.1007/s11357-022-00597-1 · Cited by 38
“BA estimation procedures [10], and (C) the ability to predict mortality from BA estimates [7].”
MethodIs musical engagement enough to keep the brain young?
Matziorinis, A. M., Gaser, C., & Koelsch, S. (2022) · Brain Structure and Function · doi:10.1007/s00429-022-02602-x · Cited by 38
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
