Multiscale functional connectivity patterns of the aging brain learned from rsfMRI data of 4,259 individuals of the multi-cohort iSTAGING study

To learn multiscale functional connectivity patterns of the aging brain, we built a brain age prediction model of functional connectivity measures at seven scales on a large fMRI dataset, consisting of resting-state fMRI scans of 4259 individuals with a wide age range (22 to 97 years, with an average of 63) from five cohorts. We computed multiscale functional connectivity measures of individual subjects using a personalized functional network computational method, harmonized the functional connectivity measures of subjects from multiple datasets in order to build a functional brain age model, and finally evaluated how functional brain age gap correlated with cognitive measures of individual subjects. Our study has revealed that functional connectivity measures at multiple scales were more informative than those at any single scale for the brain age prediction, the data harmonization significantly improved the brain age prediction performance, and harmonization in the tangent space worked better than in the original space. Moreover, brain age gap scores of individual subjects derived from the brain age prediction model were significantly correlated with clinical and cognitive measures. Overall, these results demonstrated that multiscale functional connectivity patterns learned from a large-scale multi-site rsfMRI dataset were informative for characterizing the aging brain and the derived brain age gap was associated with cognitive and clinical measures.

[1]  Maxwell A. Bertolero,et al.  Sex differences in the functional topography of association networks in youth , 2022, Proceedings of the National Academy of Sciences of the United States of America.

[2]  C. Davatzikos,et al.  Harmonization of multi-site functional connectivity measures in tangent space improves brain age prediction , 2022, Medical Imaging.

[3]  Timothy O. Laumann,et al.  Reproducible brain-wide association studies require thousands of individuals , 2022, Nature.

[4]  D. Bassett,et al.  Harmonizing functional connectivity reduces scanner effects in community detection , 2021, NeuroImage.

[5]  Evan M. Gordon,et al.  A comparison of methods to harmonize cortical thickness measurements across scanners and sites , 2021, NeuroImage.

[6]  A. Marquand,et al.  Accommodating Site Variation In Neuroimaging Data Using Normative And Hierarchical Bayesian Models , 2021, NeuroImage.

[7]  Fanny Orlhac,et al.  A Guide to ComBat Harmonization of Imaging Biomarkers in Multicenter Studies , 2021, The Journal of Nuclear Medicine.

[8]  Jerry L Prince,et al.  Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory , 2021, NeuroImage.

[9]  S. Rutherford,et al.  The Normative Modeling Framework for Computational Psychiatry , 2021, Nature Protocols.

[10]  Maxwell A. Bertolero,et al.  Dissociable multi-scale patterns of development in personalized brain networks , 2021, Nature Communications.

[11]  A. Zalesky,et al.  Machine learning prediction of cognition from functional connectivity: Are feature weights reliable? , 2021, NeuroImage.

[12]  Maxwell A. Bertolero,et al.  Linking Individual Differences in Personalized Functional Network Topography to Psychopathology in Youth , 2021, Biological Psychiatry.

[13]  N. Jahanshad,et al.  Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization , 2021, bioRxiv.

[14]  A. Belger,et al.  Multi-spatial-scale dynamic interactions between functional sources reveal sex-specific changes in schizophrenia , 2021, bioRxiv.

[15]  Hae-Jeong Park,et al.  Re-visiting Riemannian geometry of symmetric positive definite matrices for the analysis of functional connectivity , 2020, NeuroImage.

[16]  Mark Jenkinson,et al.  Learning patterns of the ageing brain in MRI using deep convolutional networks , 2020, NeuroImage.

[17]  Dinggang Shen,et al.  Building Dynamic Hierarchical Brain Networks and Capturing Transient Meta-states for Early Mild Cognitive Impairment Diagnosis , 2021, MICCAI.

[18]  Kuncheng Li,et al.  Increased functional connectivity of anterior insula to anterior cingulate cortex in amnestic mild cognitive impairment: A longitudinal resting‐state fMRI study , 2020 .

[19]  Sterling C. Johnson,et al.  The Brain Chart of Aging: Machine‐learning analytics reveals links between brain aging, white matter disease, amyloid burden, and cognition in the iSTAGING consortium of 10,216 harmonized MR scans , 2020, Alzheimer's & dementia : the journal of the Alzheimer's Association.

[20]  Christos Davatzikos,et al.  MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide. , 2020, Brain : a journal of neurology.

[21]  Lars T. Westlye,et al.  Hierarchical Bayesian Regression for Multi-Site Normative Modeling of Neuroimaging Data , 2020, MICCAI.

[22]  Katrin Amunts,et al.  Functional network reorganization in older adults: Graph-theoretical analyses of age, cognition and sex , 2020, NeuroImage.

[23]  Dan Hu,et al.  A toolbox for brain network construction and classification (BrainNetClass) , 2019, Human brain mapping.

[24]  Christos Davatzikos,et al.  Individual Variation in Functional Topography of Association Networks in Youth , 2020, Neuron.

[25]  Lars T. Westlye,et al.  Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study , 2020, NeuroImage.

[26]  R. Gur,et al.  A Multidimensional Neural Maturation Index Reveals Reproducible Developmental Patterns in Children and Adolescents , 2020, The Journal of Neuroscience.

[27]  Christos Davatzikos,et al.  Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan , 2019, NeuroImage.

[28]  M. Mallar Chakravarty,et al.  Investigating microstructural variation in the human hippocampus using non-negative matrix factorization , 2019, NeuroImage.

[29]  Mark W. Woolrich,et al.  Optimising network modelling methods for fMRI , 2019, NeuroImage.

[30]  Paul M. Thompson,et al.  Scanner invariant representations for diffusion MRI harmonization , 2019, Magnetic resonance in medicine.

[31]  Zhi-Hua Zhou,et al.  Learning With Interpretable Structure From Gated RNN , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Aaron Carass,et al.  DeepHarmony: A deep learning approach to contrast harmonization across scanner changes. , 2019, Magnetic resonance imaging.

[33]  Olivier Potvin,et al.  Bias-adjustment in neuroimaging-based brain age frameworks: A robust scheme , 2019, NeuroImage: Clinical.

[34]  Lloyd T. Elliott,et al.  Brain aging comprises many modes of structural and functional change with distinct genetic and biophysical associations , 2019, bioRxiv.

[35]  Anders M. Dale,et al.  Common brain disorders are associated with heritable patterns of apparent aging of the brain , 2019, Nature Neuroscience.

[36]  Hualou Liang,et al.  Investigating systematic bias in brain age estimation with application to post‐traumatic stress disorders , 2019, Human brain mapping.

[37]  Y. Stern,et al.  Brain-predicted age difference score is related to specific cognitive functions: a multi-site replication analysis , 2019, Brain Imaging and Behavior.

[38]  Wiro J. Niessen,et al.  Patterns of functional connectivity in an aging population: The Rotterdam Study , 2019, NeuroImage.

[39]  Stephen M. Smith,et al.  Estimation of brain age delta from brain imaging , 2019, NeuroImage.

[40]  Simon B Eickhoff,et al.  Imaging-based parcellations of the human brain , 2018, Nature Reviews Neuroscience.

[41]  Xiaofeng Zhu,et al.  Identification of Multi-scale Hierarchical Brain Functional Networks Using Deep Matrix Factorization , 2018, MICCAI.

[42]  M. Weissman,et al.  Statistical harmonization corrects site effects in functional connectivity measurements from multi‐site fMRI data , 2018, Human brain mapping.

[43]  Zaixu Cui,et al.  Individualized Prediction of Reading Comprehension Ability Using Gray Matter Volume , 2018, Cerebral cortex.

[44]  Christos Davatzikos,et al.  Evaluation of non-negative matrix factorization of grey matter in age prediction , 2018, NeuroImage.

[45]  Yong Fan,et al.  Brain age prediction based on resting-state functional connectivity patterns using convolutional neural networks , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[46]  Russell T. Shinohara,et al.  Harmonization of cortical thickness measurements across scanners and sites , 2017, NeuroImage.

[47]  Ludovica Griffanti,et al.  Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank , 2017, NeuroImage.

[48]  Daniel Rueckert,et al.  Human brain mapping: A systematic comparison of parcellation methods for the human cerebral cortex , 2017, NeuroImage.

[49]  Agnieszka Tymula,et al.  The Reduction of Ventrolateral Prefrontal Cortex Gray Matter Volume Correlates with Loss of Economic Rationality in Aging , 2017, The Journal of Neuroscience.

[50]  J. Cole,et al.  Predicting Age Using Neuroimaging: Innovative Brain Ageing Biomarkers , 2017, Trends in Neurosciences.

[51]  Jessica S. Damoiseaux,et al.  Effects of aging on functional and structural brain connectivity , 2017, NeuroImage.

[52]  F. Yger,et al.  Riemannian Approaches in Brain-Computer Interfaces: A Review , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[53]  S. Eickhoff,et al.  Gray matter asymmetries in aging and neurodegeneration: A review and meta‐analysis , 2017, Human brain mapping.

[54]  Yong Fan,et al.  Large-scale sparse functional networks from resting state fMRI , 2017, NeuroImage.

[55]  D. Reich,et al.  Volumetric Analysis from a Harmonized Multisite Brain MRI Study of a Single Subject with Multiple Sclerosis , 2017, American Journal of Neuroradiology.

[56]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[57]  Ragini Verma,et al.  Harmonization of multi-site diffusion tensor imaging data , 2017, NeuroImage.

[58]  Giovanni Montana,et al.  Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker , 2016, NeuroImage.

[59]  Danielle S. Bassett,et al.  Multi-scale brain networks , 2016, NeuroImage.

[60]  C. Grady,et al.  Age differences in the functional interactions among the default, frontoparietal control, and dorsal attention networks , 2016, Neurobiology of Aging.

[61]  Christos Davatzikos,et al.  White matter hyperintensities and imaging patterns of brain ageing in the general population. , 2016, Brain : a journal of neurology.

[62]  Christos Davatzikos,et al.  Imaging patterns of brain development and their relationship to cognition. , 2015, Cerebral cortex.

[63]  Lutz Jäncke,et al.  Associations between age, motor function, and resting state sensorimotor network connectivity in healthy older adults , 2015, NeuroImage.

[64]  P. Scheltens,et al.  White matter hyperintensities, cognitive impairment and dementia: an update , 2015, Nature Reviews Neurology.

[65]  P. Matthews,et al.  A common brain network links development, aging, and vulnerability to disease , 2014, Proceedings of the National Academy of Sciences.

[66]  Mary E. Meyerand,et al.  Age-Related Reorganizational Changes in Modularity and Functional Connectivity of Human Brain Networks , 2014, Brain Connect..

[67]  Denise C. Park,et al.  Decreased segregation of brain systems across the healthy adult lifespan , 2014, Proceedings of the National Academy of Sciences.

[68]  Cheng Luo,et al.  Resting-state functional connectivity in anterior cingulate cortex in normal aging , 2014, Front. Aging Neurosci..

[69]  B. Leventhal,et al.  Unraveling the Miswired Connectome: A Developmental Perspective , 2014, Neuron.

[70]  Jean-Baptiste Poline,et al.  Transport on Riemannian Manifold for Functional Connectivity-Based Classification , 2014, MICCAI.

[71]  Steen Moeller,et al.  ICA-based artefact removal and accelerated fMRI acquisition for improved resting state network imaging , 2014, NeuroImage.

[72]  Jessica A. Turner,et al.  Exploration of scanning effects in multi-site structural MRI studies , 2014, Journal of Neuroscience Methods.

[73]  Klaus P. Ebmeier,et al.  Study protocol: the Whitehall II imaging sub-study , 2014, BMC Psychiatry.

[74]  Ludovica Griffanti,et al.  Automatic denoising of functional MRI data: Combining independent component analysis and hierarchical fusion of classifiers , 2014, NeuroImage.

[75]  Emily L. Dennis,et al.  Functional Brain Connectivity Using fMRI in Aging and Alzheimer’s Disease , 2014, Neuropsychology Review.

[76]  G. Busatto,et al.  Resting-state functional connectivity in normal brain aging , 2013, Neuroscience & Biobehavioral Reviews.

[77]  R Cameron Craddock,et al.  A whole brain fMRI atlas generated via spatially constrained spectral clustering , 2012, Human brain mapping.

[78]  N. K. Focke,et al.  Multi-site voxel-based morphometry — Not quite there yet , 2011, NeuroImage.

[79]  Jonathan D. Power,et al.  Prediction of Individual Brain Maturity Using fMRI , 2010, Science.

[80]  S. Petersen,et al.  The maturing architecture of the brain's default network , 2008, Proceedings of the National Academy of Sciences.

[81]  Cheng Li,et al.  Adjusting batch effects in microarray expression data using empirical Bayes methods. , 2007, Biostatistics.

[82]  Janaina Mourão Miranda,et al.  Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI data , 2005, NeuroImage.

[83]  Sayan Mukherjee,et al.  Permutation Tests for Classification , 2005, COLT.

[84]  P. Thomas Fletcher,et al.  Principal geodesic analysis for the study of nonlinear statistics of shape , 2004, IEEE Transactions on Medical Imaging.