Abstract
As individuals age, cortical alterations in brain structure contribute to cognitive decline. However, the specific patterns of age-related changes and their impact on cognition remain poorly understood. This study assessed the effects of aging on individual gray matter similarity networks and compared them to anatomical and functional connectivity networks derived from diffusion-weighted imaging and resting-state fMRI, respectively. Our results showed that gray matter similarity networks outperformed anatomical and functional connectivity in predicting age and cognition, showing the earliest age-related changes across the adult lifespan. These networks also demonstrated greater robustness to individual differences in cognition, behavior, and sex. Notably, age-related changes in gray matter similarity were associated with the brain’s underlying cytoarchitecture, being strongest in brain regions from cortical layers II and III. These findings provide a new biological insight into the neural mechanisms of cognitive aging and highlight the potential of individual morphological similarity for capturing complex brain changes across the lifespan.
Similar content being viewed by others
Data availability
This study utilized data from two publicly available sources: the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) cohort66 and the LEMON (Leipzig Mind-Brain-Body) cohort76,77 from the Max Planck Institute (as replication cohort). The Cam-CAN dataset, which includes both imaging and behavioral data, can be accessed at camcan-archive.mrccbu.cam.ac.uk/dataaccess/. Similarly, the LEMON dataset is available for public download via an Amazon Web Services S3 bucket at: fcp-indi/data/Projects/INDI/MPI-LEMON. Additional information about the cohorts can be found at and https://fcon_1000.projects.nitrc.org/indi/retro/MPI_LEMON.html.
References
Montine, T. J. et al. Concepts for brain aging: resistance, resilience, reserve, and compensation. Alzheimer’s. Res. Ther. 11, 1–3 (2019).
Stern, Y. et al. Whitepaper: defining and investigating cognitive reserve, brain reserve, and brain maintenance. Alzheimer’s. Dement. 16, 1305–1311 (2020).
Fornito, A., Zalesky, A. & Breakspear, M. The connectomics of brain disorders. Nat. Rev. Neurosci. 16, 159–172 (2015).
Zhang, F. et al. Quantitative mapping of the brain’s structural connectivity using diffusion MRI tractography: a review. Neuroimage 249, 118870 (2022).
Khanna, N. et al. Functional neuroimaging: fundamental principles and clinical applications. Neuroradiol. J. 28, 87–96 (2015).
Douaud, G. et al. A common brain network links development, aging, and vulnerability to disease. Proc. Natl. Acad. Sci. USA 111, 17648–17653 (2014).
Mijalkov, M. et al. Sex differences in multilayer functional network topology over the course of aging in 37543 UK Biobank participants. Netw. Neurosci. 7, 351–376 (2023).
Lin, L. et al. Predicting healthy older adult’s brain age based on structural connectivity networks using artificial neural networks. Comput. Methods Prog. Biomed. 125, 8–17 (2016).
Damoiseaux, J. S. Effects of aging on functional and structural brain connectivity. Neuroimage 160, 32–40 (2017).
Puxeddu, M. G. et al. The modular organization of brain cortical connectivity across the human lifespan. NeuroImage 218, 116974 (2020).
Ooi, L. Q. R. et al. Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI. NeuroImage 263, 119636 (2022).
Cabeza, R. et al. Maintenance, reserve and compensation: the cognitive neuroscience of healthy ageing. Nat. Rev. Neurosci. 19, 701–710 (2018).
Griffa, A. et al. Structural connectomics in brain diseases. Neuroimage 80, 515–526 (2013).
Sullivan, E. V., Adalsteinsson, E. & Pfefferbaum, A. Selective age-related degradation of anterior callosal fiber bundles quantified in vivo with fiber tracking. Cereb. Cortex 16, 1030–1039 (2006).
Salat, D. et al. Age-related alterations in white matter microstructure measured by diffusion tensor imaging. Neurobiol. aging 26, 1215–1227 (2005).
Fjell, A. M. et al. What is normal in normal aging? Effects of aging, amyloid and Alzheimer’s disease on the cerebral cortex and the hippocampus. Prog. Neurobiol. 117, 20–40 (2014).
Coelho, A. et al. Signatures of white-matter microstructure degradation during aging and its association with cognitive status. Sci. Rep. 11, 4517 (2021).
Brown, C. A. et al. Distinct patterns of default mode and executive control network circuitry contribute to present and future executive function in older adults. NeuroImage 195, 320–332 (2019).
Fjell, A. M. et al. The disconnected brain and executive function decline in aging. Cereb. Cortex 27, 2303–2317 (2017).
Gong, G. et al. Age-and gender-related differences in the cortical anatomical network. J. Neurosci. 29, 15684–15693 (2009).
Zhao, T. et al. Age-related changes in the topological organization of the white matter structural connectome across the human lifespan. Hum. Brain Mapp. 36, 3777–3792 (2015).
Sebenius, I. et al. Structural MRI of brain similarity networks. Nat. Rev. Neurosci. 26, 42–59 (2025).
Forkel, S. J. et al. White matter variability, cognition, and disorders: a systematic review. Brain Struct. Funct. 227, 529–544 (2022).
Salama, G. R. et al. Diffusion weighted/tensor imaging, functional MRI and perfusion weighted imaging in glioblastoma—foundations and future. Front. Neurol. 8, 660 (2018).
Molloy, E. K., Meyerand, M. E. & Birn, R. M. The influence of spatial resolution and smoothing on the detectability of resting-state and task fMRI. Neuroimage 86, 221–230 (2014).
Zaitsev, M., Maclaren, J. & Herbst, M. Motion artifacts in MRI: a complex problem with many partial solutions. J. Magn. Reson. Imaging 42, 887–901 (2015).
Le Bihan, D. et al. Artifacts and pitfalls in diffusion MRI. J. Magn. Reson. Imaging 24, 478–488 (2006).
Cai, M. et al. Individual-level brain morphological similarity networks: Current methodologies and applications. CNS Neurosci. Ther. 29, 3713–3724 (2023).
Seidlitz, J. et al. Morphometric similarity networks detect microscale cortical organization and predict inter-individual cognitive variation. Neuron 97, 231–247.e7 (2018).
Wang, Y. et al. Age-related differences of cortical topology across the adult lifespan: Evidence from a multisite MRI study with 1427 individuals. J. Magn. Reson. Imaging 57, 434–443 (2023).
Li, J. et al. Tracking age-related topological changes in individual brain morphological networks across the human lifespan. J. Magn. Reson. Imaging 59, 1841–1851 (2024).
Kong, X. -z. et al. Mapping individual brain networks using statistical similarity in regional morphology from MRI. PloS ONE 10, e0141840 (2015).
Mertens, N. et al. The effect of aging on brain glucose metabolic connectivity revealed by [18F] FDG PET-MR and individual brain networks. Front. Aging Neurosci. 13, 798410 (2022).
Ruan, J. et al. Single-subject cortical morphological brain networks across the adult lifespan. Hum. Brain Mapp. 44, 5429–5449 (2023).
Sebenius, I. et al. Robust estimation of cortical similarity networks from brain MRI. Nat. Neurosci. 26, 1461–1471 (2023).
Li, W. et al. Construction of individual morphological brain networks with multiple morphometric features. Front. Neuroanat. 11, 34 (2017).
Yao, G. et al. Transcriptional patterns of the cortical Morphometric Inverse Divergence in first-episode, treatment-naïve early-onset schizophrenia. NeuroImage 285, 120493 (2024).
Liu, Z. et al. Resolving heterogeneity in schizophrenia through a novel systems approach to brain structure: individualized structural covariance network analysis. Mol. Psychiatry 26, 7719–7731 (2021).
Ge, R. et al. Normative modelling of brain morphometry across the lifespan with CentileBrain: algorithm benchmarking and model optimisation. Lancet Digit. Health 6, e211–e221 (2024).
Wang, P. Y. et al. Generalizable machine learning in neuroscience using graph neural networks. Front. Artif. Intell. 4, 618372 (2021).
Bessadok, A., Mahjoub, M. A. & Rekik, I. Graph neural networks in network neuroscience. IEEE Trans. Pattern Anal. Mach. Intell. 45, 5833–5848 (2022).
Farahani, F. V., Karwowski, W. & Lighthall, N. R. Application of graph theory for identifying connectivity patterns in human brain networks: a systematic review. Front. Neurosci. 13, 585 (2019).
Fjell, A. M. et al. Critical ages in the life course of the adult brain: nonlinear subcortical aging. Neurobiol. Aging 34, 2239–2247 (2013).
Ziegler, G. et al. Models of the aging brain structure and individual decline. Front. Neuroinformatics 6, 3 (2012).
Aboud, K. S. et al. Structural covariance across the lifespan: brain development and aging through the lens of inter-network relationships. Hum. Brain Mapp. 40, 125–136 (2019).
Bethlehem, R. A. et al. Brain charts for the human lifespan. Nature 604, 525–533 (2022).
Sun, L. et al. Human lifespan changes in the brain’s functional connectome. Nat. Neurosci. 28, 891–901 (2025).
Niu, J. et al. Age-associated cortical similarity networks correlate with cell type-specific transcriptional signatures. Cereb. Cortex 34, bhad454 (2024).
Liang, X. et al. Dissecting human cortical similarity networks across the lifespan. Neuron 113, 3275–3295.e11 (2025).
Habes, M. et al. White matter hyperintensities and imaging patterns of brain ageing in the general population. Brain 139, 1164–1179 (2016).
Chong, I.-G. & Jun, C.-H. Performance of some variable selection methods when multicollinearity is present. Chemom. Intell. Lab. Syst. 78, 103–112 (2005).
Mechelli, A. et al. Structural covariance in the human cortex. J. Neurosci. 25, 8303–8310 (2005).
Saberi, A. et al. The regional variation of laminar thickness in the human isocortex is related to cortical hierarchy and interregional connectivity. PLoS Biol. 21, e3002365 (2023).
von Economo, C. F. & Koskinas, G. N. Die Cytoarchitektonik der Hirnrinde des erwachsenen Menschen. Arch. NeurPsych. 16, 816 (1926).
Vértes, P. E. et al. Gene transcription profiles associated with inter-modular hubs and connection distance in human functional magnetic resonance imaging networks. Philos. Trans. R. Soc. B Biol. Sci. 371, 20150362 (2016).
Jiang, Q. et al. Antiageing strategy for neurodegenerative diseases: from mechanisms to clinical advances. Signal Transduct. Target. Ther. 10, 76 (2025).
Perovnik, M. et al. Functional brain networks in the evaluation of patients with neurodegenerative disorders. Nat. Rev. Neurol. 19, 73–90 (2023).
Kelly, C. et al. A convergent functional architecture of the insula emerges across imaging modalities. Neuroimage 61, 1129–1142 (2012).
Seeley, W. W. et al. Neurodegenerative diseases target large-scale human brain networks. Neuron 62, 42–52 (2009).
Ouyang, M. et al. Short-range connections in the developmental connectome during typical and atypical brain maturation. Neurosci. Biobehav. Rev. 83, 109–122 (2017).
Honey, C. J. et al. Predicting human resting-state functional connectivity from structural connectivity. Proc. Natl. Acad. Sci. USA 106, 2035–2040 (2009).
Damoiseaux, J. S. & Greicius, M. D. Greater than the sum of its parts: a review of studies combining structural connectivity and resting-state functional connectivity. Brain Struct. Funct. 213, 525–533 (2009).
Alexander-Bloch, A., Giedd, J. N. & Bullmore, E. Imaging structural co-variance between human brain regions. Nat. Rev. Neurosci. 14, 322–336 (2013).
Solari, S. V. H. & Stoner, R. M. Cognitive consilience: primate non-primary neuroanatomical circuits underlying cognition. Front. Neuroanat. 5, 65 (2011).
Morrison, J. H. & Hof, P. R. Life and death of neurons in the aging cerebral cortex. Int. Rev. Neurobiol. 81, 41–57 (2007).
Shafto, M. A. et al. The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) study protocol: a cross-sectional, lifespan, multidisciplinary examination of healthy cognitive ageing. BMC Neurol. 14, 204 (2014).
Cattell, R. B. & Cattell, A. K. Measuring Intelligence With the Culture Fair Tests. (Institute for Personality and Ability Testing, 1960).
Kievit, R. A. et al. Distinct aspects of frontal lobe structure mediate age-related differences in fluid intelligence and multitasking. Nat. Commun. 5, 5658 (2014).
Mather, M. & Carstensen, L. L. Aging and motivated cognition: the positivity effect in attention and memory. Trends Cogn. Sci. 9, 496–502 (2005).
Dalgleish, T. The emotional brain. Nat. Rev. Neurosci. 5, 583–589 (2004).
Mather, M. The emotion paradox in the aging brain. Ann. N. Y. Acad. Sci. 1251, 33–49 (2012).
Taylor, J. R. et al. The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) data repository: Structural and functional MRI, MEG, and cognitive data from a cross-sectional adult lifespan sample. Neuroimage 144, 262–269 (2017).
Shallice, T. & Burgess, P. W. Deficits in strategy application following frontal lobe damage in man. Brain 114, 727–741 (1991).
Zigmond, A. S. & Snaith, R. P. The hospital anxiety and depression scale. Acta Psychiatr. Scand. 67, 361–370 (1983).
Buysse, D. J. et al. The Pittsburgh Sleep Quality Index: a new instrument for psychiatric practice and research. Psychiatry Res. 28, 193–213 (1989).
Babayan, A. et al. A mind-brain-body dataset of MRI, EEG, cognition, emotion, and peripheral physiology in young and old adults. Sci. Data 6, 1–21 (2019).
Mendes, N. et al. A functional connectome phenotyping dataset including cognitive state and personality measures. Sci. Data 6, 1–19 (2019).
Marques, J. P. et al. MP2RAGE, a self bias-field corrected sequence for improved segmentation and T1-mapping at high field. Neuroimage 49, 1271–1281 (2010).
Andersson, J. L. R. & Sotiropoulos, S. N. An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging. Neuroimage 125, 1063–1078 (2016).
Friston, K. J. et al. Movement-related effects in fMRI time-series. Magn. Reson. Med. 35, 346–355 (1996).
Laso, P., et al. Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI. in 2024 IEEE International Symposium on Biomedical Imaging (ISBI). 2024. IEEE.
Ding, H. et al. Topological properties of individual gray matter morphological networks in identifying the preclinical stages of Alzheimer’s disease: a preliminary study. Quant. Imaging Med. Surg. 13, 5258 (2023).
Yu, K. et al. Individual morphological brain network construction based on multivariate euclidean distances between brain regions. Front. Hum. Neurosci. 12, 204 (2018).
Li, W. et al. Alterations of graphic properties and related cognitive functioning changes in mild Alzheimer’s disease revealed by individual morphological brain network. Front. Neurosci. 12, 927 (2018).
Liu, X. et al. Personalized characterization of diseases using sample-specific networks. Nucleic Acids Res. 44, e164 (2016).
Chang, Y.-W. et al. BRAPH 2: a flexible, open-source, reproducible, community-oriented, easy-to-use framework for network analyses in neurosciences. Preprint at bioRxiv, https://doi.org/10.1101/2025.04.11.648455 (2025).
Mijalkov, M. et al. BRAPH: a graph theory software for the analysis of brain connectivity. PloS ONE 12, e0178798 (2017).
Wang, M. et al. Individual brain metabolic connectome indicator based on Kullback-Leibler Divergence Similarity Estimation predicts progression from mild cognitive impairment to Alzheimer’s dementia. Eur. J. Nucl. Med. Mol. Imaging 47, 2753–2764 (2020).
Wang, L. et al. A metabolism-functional connectome sparse coupling method to reveal imaging markers for Alzheimer’s disease based on simultaneous PET/MRI scans. Hum. Brain Mapp. 44, 6020–6030 (2023).
Xu, X. et al. Morphological, structural, and functional networks highlight the role of the cortical-subcortical circuit in individuals with subjective cognitive decline. Front. Aging Neurosci. 13, 688113 (2021).
Chen, H. et al. Alzheimer’s disease clinical scores prediction based on the label distribution learning using brain structural MRI. In Proc. 2022 International Joint Conference on Neural Networks (IJCNN) (IEEE, 2022).
Wang, H. et al. Single-subject morphological brain networks: connectivity mapping, topological characterization and test–retest reliability. Brain Behav. 6, e00448 (2016).
Xu, X. et al. Altered pattern analysis and identification of subjective cognitive decline based on morphological brain network. Front. Aging Neurosci. 14, 965923 (2022).
Peng, L. et al. Rich-Club organization disturbances of the individual morphological network in subjective cognitive decline. Front. Aging Neurosci. 14, 834145 (2022).
Li, Y. et al. Surface-based single-subject morphological brain networks: effects of morphological index, brain parcellation and similarity measure, sample size-varying stability and test-retest reliability. NeuroImage 235, 118018 (2021).
Lin, J. Divergence measures based on the Shannon entropy. IEEE Trans. Inf. theory 37, 145–151 (1991).
Abadi, M. et al. {TensorFlow}: a system for {Large-Scale} machine learning. in Proc. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) (USENIX Association, 2016).
Fornito, A. & Bullmore, E. T. Connectomics: a new paradigm for understanding brain disease. Eur. Neuropsychopharmacol. 25, 733–748 (2015).
Pineda, J. et al. Geometric deep learning reveals the spatiotemporal features of microscopic motion. Nat. Mach. Intell. 5, 71–82 (2023).
Midtvedt, B. et al. Deep Learning Crash Course (No Starch Press, 2025).
Velickovic, P. et al. Graph attention networks. stat 1050, 10–48550 (2017).
Abdi, H. & Williams, L. J. Partial least squares methods: partial least squares correlation and partial least square regression. Comput. Toxicol. II, 549–579 (2013).
de Lange, A. M. G. et al. Mind the gap: performance metric evaluation in brain-age prediction. Hum. Brain Mapp. 43, 3113–3129 (2022).
Beheshti, I. et al. Bias-adjustment in neuroimaging-based brain age frameworks: a robust scheme. NeuroImage Clin. 24, 102063 (2019).
Cole, J. H. Multimodality neuroimaging brain-age in UK biobank: relationship to biomedical, lifestyle, and cognitive factors. Neurobiol. Aging 92, 34–42 (2020).
Xiong, M. et al. Comparison of machine learning models for brain age prediction using six imaging modalities on middle-aged and older adults. Sensors 23, 3622 (2023).
More, S. et al. Brain-age prediction: a systematic comparison of machine learning workflows. NeuroImage 270, 119947 (2023).
Acknowledgements
This research was supported by several funding bodies, including the Swedish Research Council (grant no. 2022-01108), the Alzheimer Foundation, and the Brain Foundation (grant no. 2022-014). Additional support was provided by the European Union–NextGenerationEU and the Romanian Government through Romania’s National Recovery and Resilience Plan (contract no. 760250/28.12.2023, code PNRR-C9-I8-CF109/31.07.2023), administered by the Romanian Ministry of Research, Innovation and Digitalization under Component 9, Investment I8. Further funding was received from the KI Consolidator Grant, KID funding, the King Gustaf V and Queen Victoria’s Foundation, the Foundation for Geriatric Diseases at Karolinska Institutet, Gamla Tjänarinnor, the Stohnes Foundation, and the Lars Hierta Memorial Foundation (awarded to J.B.P.). The data analysis was enabled by resources provided by the National Academic Infrastructure for Supercomputing in Sweden (NAISS), partially funded by the Swedish Research Council through grant agreement no. 2022-06725.
Funding
Open access funding provided by Karolinska Institute.
Author information
Authors and Affiliations
Contributions
B.Z. carried out the main analyses, wrote the main manuscript and prepared the figures and tables. J.S. built the individual gray matter similarity networks. J.P. contributed to the development of the architecture of the Graph Neural Networks. G.V. contributed to the design of the methodology to train the deep learning models. M.M contributed to the development and analysis using Parial Least Squares (PLS) models.J.B.P supervised and designed the whole project. All authors reviewed the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Zufiria-Gerbolés, B., Sun, J., Pineda, J. et al. Similar minds age alike: an MRI similarity approach for predicting age-related cognitive decline. npj Aging (2026). https://doi.org/10.1038/s41514-026-00345-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41514-026-00345-1
