4.7 Article

Multiscale functional connectivity patterns of the aging brain learned from harmonized rsfMRI data of the multi-cohort iSTAGING study

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Computing personalized brain functional networks from fMRI using self-supervised deep learning

Hongming Li et al.

Summary: A novel self-supervised DL method is developed to compute personalized brain functional networks based on fMRI. The DL model, trained without external supervision, optimizes functional homogeneity of personalized FNs using an end-to-end architecture. The identified personalized FNs are found to be informative for predicting individual differences in behavior, brain development, and schizophrenia status, demonstrating the effectiveness of this approach.

MEDICAL IMAGE ANALYSIS (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Generative Medical Image Harmonization for Improving Cross-Site Generalization in Deep Learning Predictors

Vishnu M. Bashyam et al.

Summary: In the medical imaging domain, deep learning methods have limited generalization performance across different imaging devices and acquisition protocols. However, using GAN-based image harmonization shows promise in improving cross-site generalization of deep learning age prediction.

JOURNAL OF MAGNETIC RESONANCE IMAGING (2022)

Article Neurosciences

Linking Individual Differences in Personalized Functional Network Topography to Psychopathology in Youth

Zaixu Cui et al.

Summary: The spatial layout of large-scale functional brain networks is related to major dimensions of psychopathology in youth, particularly to overall psychopathology. These findings highlight the importance of considering functional neuroanatomy for personalized diagnostics and therapeutics in psychiatry.

BIOLOGICAL PSYCHIATRY (2022)

Article Neurosciences

Mind the gap: Performance metric evaluation in brain-age prediction

Ann-Marie G. de Lange et al.

Summary: Estimating age based on neuroimaging-derived data is a popular approach, but there is significant variation in model accuracy across studies. This study found that performance metrics for age prediction models depend on cohort and study-specific data characteristics. Age range, sample size, and age-bias correction all have an impact on the accuracy of the models. Furthermore, evaluating prediction variance and age-bias provides important information about underlying model attributes.

HUMAN BRAIN MAPPING (2022)

Article Multidisciplinary Sciences

Reproducible brain-wide association studies require thousands of individuals

Scott Marek et al.

Summary: Magnetic resonance imaging (MRI) has greatly advanced our understanding of the human brain, but similar progress has not been made in mental health research. By analyzing three large neuroimaging datasets, researchers found that brain-wide association studies (BWAS) had smaller effect sizes than previously thought, leading to underpowered studies, inflated effect sizes, and replication failures. As sample sizes increased, replication rates improved and effect size inflation decreased. Functional MRI, cognitive tests, and multivariate methods showed more robust effects in BWAS. Smaller than expected brain-phenotype associations and population subsample variability explain the widespread replication failures in BWAS. Reproducibility in BWAS requires samples with thousands of individuals.

NATURE (2022)

Article Biochemical Research Methods

The normative modeling framework for computational psychiatry

Saige Rutherford et al.

Summary: Normative modeling is an innovative framework that maps individual differences to understand the relationship between biology and behavior. It allows for statistical inferences at the individual level and addresses the issue of biological heterogeneity in mental disorders.

NATURE PROTOCOLS (2022)

Article Multidisciplinary Sciences

Dissociable multi-scale patterns of development in personalized brain networks

Adam R. Pines et al.

Summary: The development of functional brain networks occurs at multiple scales and adheres to a hierarchy linked to cognition.

NATURE COMMUNICATIONS (2022)

Article Neurosciences

Harmonizing functional connectivity reduces scanner effects in community detection

Andrew A. Chen et al.

Summary: Community detection on graphs constructed from functional magnetic resonance imaging (fMRI) data has provided important insights into brain functional organization. However, differences in scanners can introduce variability into the results, known as scanner effects. In this study, new methodology for harmonizing functional connectivity is proposed to reduce these effects.

NEUROIMAGE (2022)

Article Neurosciences

Deep neural networks learn general and clinically relevant representations of the ageing brain

Esten H. Leonardsen et al.

Summary: The discrepancy between chronological age and brain age based on neuroimaging data has been established as a reliable marker of brain health. In this study, a large and diverse dataset of raw structural magnetic resonance images was compiled and convolutional neural networks were trained to predict age. The study achieved state-of-the-art performance in predicting age and showed associations between higher brain age delta and diabetes, alcohol intake, and smoking. Transfer learning was also utilized to predict common brain disorders with promising results.

NEUROIMAGE (2022)

Article Multidisciplinary Sciences

Sex differences in the functional topography of association networks in youth

Sheila Shanmugan et al.

Summary: Prior work has shown substantial interindividual variation in the spatial distribution of functional networks across the cerebral cortex, but it remains unknown whether there are sex differences in the topography of individualized networks in youth. In this study, researchers leveraged advanced machine learning to define individualized functional networks in youth and found that there are sex-related spatial patterns in functional topography. These patterns showed high accuracy in classifying participant sex based on functional topography. Additionally, the study revealed that the sex differences in functional topography were correlated with gene expression on the X chromosome.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2022)

Article Neurosciences

A comparison of methods to harmonize cortical thickness measurements across scanners and sites

Delin Sun et al.

Summary: This study compared the impact of different data harmonization methods on cortical thickness data analysis results, finding that ComBat-GAM was more sensitive than other methods in detecting differences between cases and controls.

NEUROIMAGE (2022)

Review Clinical Neurology

Site effects how-to and when: An overview of retrospective techniques to accommodate site effects in multi-site neuroimaging analyses

Johanna M. M. Bayer et al.

Summary: In this paper, we provide an overview of different statistical and machine learning methods developed to remove unwanted site effects from independently collected neuroimaging samples. We discuss the statistical foundation, strengths, weaknesses, and conditions of use for each method, and provide information on software availability and ease of use. We also provide guidance on when to use each method based on context and research questions.

FRONTIERS IN NEUROLOGY (2022)

Article Clinical Neurology

Neural alterations in opioid-exposed infants revealed by edge-centric brain functional networks

Weixiong Jiang et al.

Summary: This study found that dynamic functional connectivity (dFC) can distinguish infants exposed to opioids from the control group. Prenatal opioid exposure mainly affects the inter-network connections related to visual, subcortical, and default mode networks. These findings help understand the neural basis of adverse effects observed in multiple neurodevelopmental domains in infants exposed to opioids and suggest that edge-centric networks could be a promising tool for investigating the effects of prenatal opioid exposure on neurodevelopment.

BRAIN COMMUNICATIONS (2022)

Article Neuroimaging

Brain-predicted age difference score is related to specific cognitive functions: a multi-site replication analysis

Rory Boyle et al.

Summary: By applying machine learning to predict the relationship between chronological age and grey matter data based on MRI scans, and then applying this model to independent datasets, it was found that increased brain-predicted age differences were significantly negatively correlated with reduced cognitive function in certain domains. This suggests a strong connection between accelerated ageing as predicted by brain age and cognitive decline in specific areas.

BRAIN IMAGING AND BEHAVIOR (2021)

Article Clinical Neurology

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

Mohamad Habes et al.

Summary: The relationship between white matter hyperintensities and various factors such as brain aging, AD neuropathology, cognitive decline, and Aβ positivity after age 65 have been observed in a large MRI database. The Brain Chart established can quantify brain-aging trajectories and provide systematic evaluation of brain-aging patterns relative to a large consortium. Brain aging, AD-like atrophy, and WMHs were shown to be better predictors of cognition than chronological age in MCI/AD subjects.

ALZHEIMERS & DEMENTIA (2021)

Article Computer Science, Artificial Intelligence

Accurate brain age prediction with lightweight deep neural networks

Han Peng et al.

Summary: This study proposed a deep convolutional neural network model, SFCN, for accurate prediction of brain age, which achieved state-of-the-art performance through the combination of various performance-boosting techniques.

MEDICAL IMAGE ANALYSIS (2021)

Article Neurosciences

Re-visiting Riemannian geometry of symmetric positive definite matrices for the analysis of functional connectivity

Kisung You et al.

Summary: Functional networks are commonly represented using symmetric positive definite matrices on the Riemannian manifold, considering all pairwise interactions. Despite the geometric properties of the SPD manifold, there are limited studies focusing on connectivity analysis.

NEUROIMAGE (2021)

Article Neurosciences

Learning patterns of the ageing brain in MRI using deep convolutional networks

Nicola K. Dinsdale et al.

Summary: The study explores predicting brain age using convolutional neural networks and the UK Biobank dataset, showing competitive performance with significant correlations between CNN prediction errors and clinical measurements from the UK Biobank. Additionally, the use of nonlinearly registered images in training CNNs may limit clinical relevance by potentially missing subtle indicators of ageing, highlighting the need for further exploration in longitudinal health outcomes prediction.

NEUROIMAGE (2021)

Article Neurosciences

Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory

Lianrui Zuo et al.

Summary: CALAMITI is an unsupervised MR image harmonization approach that learns a globally disentangled latent space to alleviate contrast variations across different sites. The method achieves superior performance compared to other harmonization approaches.

NEUROIMAGE (2021)

Article Neurosciences

Machine learning prediction of cognition from functional connectivity: Are feature weights reliable?

Ye Tian et al.

Summary: The study found that the reliability of feature weights in predictive models of cognitive performance based on resting-state functional connectivity networks is generally poor, but some methods in feature selection and feature space can marginally improve reliability. Due to a tradeoff between feature weight reliability and prediction accuracy, univariate statistics are slightly more reliable in terms of reliability compared to feature weights.

NEUROIMAGE (2021)

Article Neurosciences

Individual variation underlying brain age estimates in typical development

Gareth Ball et al.

Summary: This study investigates the use of machine learning algorithms to model brain development trajectories and found consistent patterns in brain age prediction and cortical feature explanation across different model types. While overall brain age estimates based on cortical development are robust and consistent, there is significant variability in the features explaining erroneous predictions on an individual level.

NEUROIMAGE (2021)

Article Computer Science, Information Systems

Hierarchical Rough-to-Fine Model for Infant Age Prediction Based on Cortical Features

Dan Hu et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Article Neurosciences

A toolbox for brain network construction and classification (BrainNetClass)

Zhen Zhou et al.

HUMAN BRAIN MAPPING (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Scanner invariant representations for diffusion MRI harmonization

Daniel Moyer et al.

MAGNETIC RESONANCE IN MEDICINE (2020)

Article Neurosciences

Optimising network modelling methods for fMRI

Usama Pervaiz et al.

NEUROIMAGE (2020)

Article Neurosciences

Sampling Rate Effects on Resting State fMRI Metrics

Niko Huotari et al.

FRONTIERS IN NEUROSCIENCE (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

DeepHarmony: A deep learning approach to contrast harmonization across scanner changes

Blake E. Dewey et al.

MAGNETIC RESONANCE IMAGING (2019)

Article Neurosciences

Estimation of brain age delta from brain imaging

Stephen M. Smith et al.

NEUROIMAGE (2019)

Article Multidisciplinary Sciences

Brain age prediction using deep learning uncovers associated sequence variants

B. A. Jonsson et al.

NATURE COMMUNICATIONS (2019)

Article Biochemical Research Methods

Advantages of short repetition time resting-state functional MRI enabled by simultaneous multi-slice imaging

Hesamoddin Jahanian et al.

JOURNAL OF NEUROSCIENCE METHODS (2019)

Article Neurosciences

Evaluation of non-negative matrix factorization of grey matter in age prediction

Deepthi P. Varikuti et al.

NEUROIMAGE (2018)

Article Neurosciences

Harmonization of cortical thickness measurements across scanners and sites

Jean-Philippe Fortin et al.

NEUROIMAGE (2018)

Review Neurosciences

Imaging-based parcellations of the human brain

Simon B. Eickhoff et al.

NATURE REVIEWS NEUROSCIENCE (2018)

Review Neurosciences

Gray Matter Asymmetries in Aging and Neurodegeneration: A Review and Meta-Analysis

Lora Minkova et al.

HUMAN BRAIN MAPPING (2017)

Review Engineering, Biomedical

Riemannian Approaches in Brain-Computer Interfaces: A Review

Florian Yger et al.

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING (2017)

Article Neurosciences

Large-scale sparse functional networks from resting state fMRI

Hongming Li et al.

NEUROIMAGE (2017)

Article Neurosciences

Multi-scale brain networks

Richard F. Betzel et al.

NEUROIMAGE (2017)

Article Neurosciences

Harmonization of multi-site diffusion tensor imaging data

Jean-Philippe Fortin et al.

NEUROIMAGE (2017)

Article Neurosciences

Effects of aging on functional and structural brain connectivity

Jessica S. Damoiseaux

NEUROIMAGE (2017)

Review Neurosciences

Predicting Age Using Neuroimaging: Innovative Brain Ageing Biomarkers

James H. Cole et al.

TRENDS IN NEUROSCIENCES (2017)

Article Clinical Neurology

Volumetric Analysis from a Harmonized Multisite Brain MRI Study of a Single Subject with Multiple Sclerosis

R. T. Shinohara et al.

AMERICAN JOURNAL OF NEURORADIOLOGY (2017)

Review Clinical Neurology

White matter hyperintensities, cognitive impairment and dementia: an update

Niels D. Prins et al.

NATURE REVIEWS NEUROLOGY (2015)

Article Neurosciences

Imaging Patterns of Brain Development and their Relationship to Cognition

Guray Erus et al.

CEREBRAL CORTEX (2015)

Article Psychiatry

Study protocol: the Whitehall II imaging sub-study

Nicola Filippini et al.

BMC PSYCHIATRY (2014)

Article Biochemical Research Methods

Exploration of scanning effects in multi-site structural MRI studies

Jiayu Chen et al.

JOURNAL OF NEUROSCIENCE METHODS (2014)

Review Neurosciences

Unraveling the Miswired Connectome: A Developmental Perspective

Adriana Di Martino et al.

NEURON (2014)

Review Psychology, Clinical

Functional Brain Connectivity Using fMRI in Aging and Alzheimer's Disease

Emily L. Dennis et al.

NEUROPSYCHOLOGY REVIEW (2014)

Article Multidisciplinary Sciences

A common brain network links development, aging, and vulnerability to disease

Gwenaelle Douaud et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2014)

Article Multidisciplinary Sciences

Decreased segregation of brain systems across the healthy adult lifespan

Micaela Y. Chan et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2014)

Article Geriatrics & Gerontology

Resting-state functional connectivity in anterior cingulate cortex in normal aging

Weifang Cao et al.

FRONTIERS IN AGING NEUROSCIENCE (2014)

Article Psychology, Multidisciplinary

What do verbal fluency tasks measure? Predictors of verbal fluency performance in older adults

Zeshu Shao et al.

FRONTIERS IN PSYCHOLOGY (2014)

Review Behavioral Sciences

Resting-state functional connectivity in normal brain aging

Luiz Kobuti Ferreira et al.

NEUROSCIENCE AND BIOBEHAVIORAL REVIEWS (2013)

Article Neurosciences

A whole brain fMRI atlas generated via spatially constrained spectral clustering

R. Cameron Craddock et al.

HUMAN BRAIN MAPPING (2012)

Review Neurosciences

FSL

Mark Jenkinson et al.

NEUROIMAGE (2012)

Article Psychology, Clinical

The use of the Digit Span Test in screening for cognitive impairment in acute medical inpatients

Jess L. M. Leung et al.

INTERNATIONAL PSYCHOGERIATRICS (2011)

Article Neurosciences

Multi-site voxel-based morphometry - Not quite there yet

N. K. Focke et al.

NEUROIMAGE (2011)

Article Multidisciplinary Sciences

Prediction of Individual Brain Maturity Using fMRI

Nico U. F. Dosenbach et al.

SCIENCE (2010)

Article Clinical Neurology

Construct validity of the Trail Making Test: Role of task-switching, working memory, inhibition/interference control, and visuomotor abilities

I. Sanchez-Cubillo et al.

JOURNAL OF THE INTERNATIONAL NEUROPSYCHOLOGICAL SOCIETY (2009)

Article Multidisciplinary Sciences

The maturing architecture of the brain's default network

Damien A. Fair et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2008)

Article Geriatrics & Gerontology

The montreal cognitive assessment, MoCA:: A brief screening tool for mild cognitive impairment

ZS Nasreddine et al.

JOURNAL OF THE AMERICAN GERIATRICS SOCIETY (2005)

Article Computer Science, Interdisciplinary Applications

Principal geodesic analysis for the study of nonlinear statistics of shape

PT Fletcher et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2004)