Resting-state functional connectivity identifies individuals and predicts age in 8-to-26-month-olds

A Subset of Cortical Areas Exhibit Adult-like Functional Network Patterns in Early Childhood

The human cerebral cortex contains groups of areas that support sensory, motor, cognitive, and affective functions, often categorized into functional networks. These networks show stronger internal and weaker external functional connectivity (FC), with FC profiles more similar within the same network. Previous studies have shown these networks develop from nascent forms before birth to their mature, adult-like structures in childhood. However, these analyses often rely on adult functional network definitions. This study assesses the potential misidentification of infant functional networks when using adult models and explores the consequences and possible solutions to this problem. Our findings suggest that although adult networks only marginally describe infant FC organization better than chance, misidentification is primarily driven by specific areas. Restricting functional networks to areas with adult-like network clustering revealed consistent within-network FC across scans and throughout development. These areas are also near locations with low network identity variability. Our results highlight the implications of using adult networks for infants and offer guidance for selecting and utilizing functional network models based on research questions and scenarios.

The Lifespan Evolution of Individualized Neurophysiological Traits

How do neurophysiological traits that characterize individuals evolve across the lifespan? To address this question, we analyzed brief, task-free magnetoencephalographic recordings from over 1,000 individuals aged 4-89. We found that neurophysiological activity is significantly more similar between individuals in childhood than in adulthood, though periodic patterns of brain activity remain reliable markers of individuality across all ages. The cortical regions most critical for determining individuality shift across neurodevelopment and aging, with sensorimotor cortices becoming increasingly prominent in adulthood. These developmental changes in neurophysiology align closely with the expression of cortical genetic systems related to ion transport and neurotransmission, suggesting a growing influence of genetic factors on neurophysiological traits across the lifespan. Notably, this alignment peaks in late adolescence, a critical period when genetic factors significantly shape brain individuality. Overall, our findings highlight the role of sensorimotor regions in defining individual brain traits and reveal how genetic influences on these traits intensify with age. This study advances our understanding of the evolving biological foundations of inter-individual differences.

Lay summary

This study examines how brain activity reflects the development of individuality across a person's life. Using magnetoencephalography to capture brief recordings of spontaneous brain activity, the researchers distinguished between over 1,000 individuals, spanning ages 4 to 89. They found that the brain regions most associated with individuality change with age: sensory and motor regions become increasingly distinctive in early adulthood, highlighting their role in shaping a person's unique characteristics of brain activity. The study also revealed that changes in brain activity across different ages correspond to specific patterns of gene expression, shedding light on how genetics influence brain individuality. These findings deepen our understanding of the biological foundations of inter-individual differences and how it evolves over the lifespan.

Brain age prediction and deviations from normative trajectories in the neonatal connectome

Structural and functional connectomes undergo rapid changes during the third trimester and the first month of postnatal life. Despite progress, our understanding of the developmental trajectories of the connectome in the perinatal period remains incomplete. Brain age prediction uses machine learning to estimate the brain's maturity relative to normative data. The difference between the individual's predicted and chronological age-or brain age gap (BAG)-represents the deviation from these normative trajectories. Here, we assess brain age prediction and BAGs using structural and functional connectomes for infants in the first month of life. We use resting-state fMRI and DTI data from 611 infants (174 preterm; 437 term) from the Developing Human Connectome Project (dHCP) and connectome-based predictive modeling to predict postmenstrual age (PMA). Structural and functional connectomes accurately predict PMA for term and preterm infants. Predicted ages from each modality are correlated. At the network level, nearly all canonical brain networks-even putatively later developing ones-generate accurate PMA prediction. Additionally, BAGs are associated with perinatal exposures and toddler behavioral outcomes. Overall, our results underscore the importance of normative modeling and deviations from these models during the perinatal period.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Functional brain connectivity predictors of prospective substance use initiation and their environmental correlates

BACKGROUND

Early substance use initiation (SUI) places youth at substantially higher risk for later substance use disorders. Furthermore, adolescence is a critical period for the maturation of brain networks, the pace and magnitude of which are susceptible to environmental influences and may shape risk for SUI.

METHODS

We examined whether patterns of functional brain connectivity during rest (rsFC), measured longitudinally in pre-and-early adolescence, can predict future SUI. Next, in an independent sub-sample, we tested whether these patterns are associated with earlier environmental exposures, specifically neighborhood pollution and socioeconomic dimensions. We utilized data from the Adolescent Brain Cognitive Development (ABCD) Study®. SUI was defined as first-time use of at least one full dose of alcohol, nicotine, cannabis, or other drugs. We created a control group (N = 228) of participants without SUI who were matched with the SUI group (N = 233) on age, sex, race/ethnicity, and parental income and education.

RESULTS

Multivariate analysis showed that whole-brain rsFC from 9-10 to 11-12 years of age (prior to SUI) prospectively differentiated the SUI and control groups. The SUI-related rsFC pattern was also related to aging in both groups, suggesting a pattern of accelerated maturation in the years prior to SUI. This same pattern of rsFC was predicted by higher pollution, but not neighborhood disadvantage (adjusted for family socioeconomic factors) in an independent sub-sample (N = 2,854).

CONCLUSION

Brain functional connectivity patterns in early adolescence that are linked to accelerated maturation can predict SUI in youth and are associated with exposure to pollution.

White matter functional networks in the developing brain

Background

Functional magnetic resonance imaging (fMRI) is widely used to depict neural activity and understand human brain function. Studies show that functional networks in gray matter undergo complex transformations from neonatal age to childhood, supporting rapid cognitive development. However, white matter functional networks, given the much weaker fMRI signal, have not been characterized until recently, and changes in white matter functional networks in the developing brain remain unclear.

Purpose

Aims to examine and compare white matter functional networks in neonates and 8-year-old children.

Methods

We acquired resting-state fMRI data on 69 full-term healthy neonates and 38 healthy 8-year-old children using a same imaging protocol and studied their brain white matter functional networks using a similar pipeline. First, we utilized the ICA method to extract white matter functional networks. Next, we analyzed the characteristics of the white matter functional networks from both time-domain and frequency-domain perspectives, specifically, intra-network functional connectivity (intra-network FC), inter-network functional connectivity (inter-network FC), and fractional amplitude of low-frequency fluctuation (fALFF). Finally, the differences in the above functional networks' characteristics between the two groups were evaluated. As a supplemental measure and to confirm with literature findings on gray matter functional network changes in the developing brain, we also studied and reported functional networks in gray matter.

Results

White matter functional networks in the developing brain can be depicted for both the neonates and the 8-year-old children. White matter intra-network FC within the optic radiations, corticospinal tract, and anterior corona radiata was lower in 8-year-old children compared to neonates (p < 0.05). Inter-network FC between cerebral peduncle (CP) and anterior corona radiation (ACR) was higher in 8-year-olds (p < 0.05). Additionally, 8-year-olds showed a greater distribution of brain activity energy in the high-frequency range of 0.01-0.15 Hz. Significant developmental differences in brain white matter functional networks exist between the two group, characterized by increased inter-network FC, decreased intra-network FC, and higher high-frequency energy distribution. Similar findings were also observed in gray matter functional networks.

Conclusion

White matter functional networks can be reliably measured in the developing brain, and the differences in these networks reflect functional differentiation and integration in brain development.

BIBSNet: A Deep Learning Baby Image Brain Segmentation Network for MRI Scans

Objectives

Brain segmentation of infant magnetic resonance (MR) images is vitally important in studying developmental mental health and disease. The infant brain undergoes many changes throughout the first years of postnatal life, making tissue segmentation difficult for most existing algorithms. Here, we introduce a deep neural network BIBSNet (Baby and Infant Brain Segmentation Neural Network), an open-source, community-driven model that relies on data augmentation and a large sample size of manually annotated images to facilitate the production of robust and generalizable brain segmentations.

Experimental Design

Included in model training and testing were MR brain images on 84 participants with an age range of 0-8 months (median postmenstrual ages of 13.57 months). Using manually annotated real and synthetic segmentation images, the model was trained using a 10-fold cross-validation procedure. Testing occurred on MRI data processed with the DCAN labs infant-ABCD-BIDS processing pipeline using segmentations produced from gold standard manual annotation, joint-label fusion (JLF), and BIBSNet to assess model performance.

Principal Observations

Using group analyses, results suggest that cortical metrics produced using BIBSNet segmentations outperforms JLF segmentations. Additionally, when analyzing individual differences, BIBSNet segmentations perform even better.

Conclusions

BIBSNet segmentation shows marked improvement over JLF segmentations across all age groups analyzed. The BIBSNet model is 600x faster compared to JLF and can be easily included in other processing pipelines.

Separating group- and individual-level brain signatures in the newborn functional connectome: A deep learning approach

Recent studies indicate that differences in cognition among individuals may be partially attributed to unique brain wiring patterns. While functional connectivity (FC)-based fingerprinting has demonstrated high accuracy in identifying adults, early studies on neonates suggest that individualized FC signatures are absent. We posit that individual uniqueness is present in neonatal FC data and that conventional linear models fail to capture the rapid developmental trajectories characteristic of newborn brains. To explore this hypothesis, we employed a deep generative model, known as a variational autoencoder (VAE), leveraging two extensive public datasets: one comprising resting-state functional MRI (rs-fMRI) scans from 100 adults and the other from 464 neonates. VAE models trained on rs-fMRI from both adults and newborns produced superior age prediction performance (with r between predicted- and actual age ∼ 0.7) and individual identification accuracy (∼45 %) compared to models trained solely on adult or neonatal data. The VAE model also showed significantly higher individual identification accuracy than linear models (=10∼30 %). Importantly, the VAE differentiated connections reflecting age-related changes from those indicative of individual uniqueness, a distinction not possible with linear models. Moreover, we derived 20 latent variables, each corresponding to distinct patterns of cortical functional network (CFNs). These CFNs varied in their representation of brain maturation and individual signatures; notably, certain CFNs that failed to capture neurodevelopmental traits, in fact, exhibited individual signatures. CFNs associated with neonatal neurodevelopment predominantly encompassed unimodal regions such as visual and sensorimotor areas, whereas those linked to individual uniqueness spanned multimodal and transmodal brain regions. The VAE's capacity to extract features from rs-fMRI data beyond the capabilities of linear models positions it as a valuable tool for delineating cognitive traits inherent in rs-fMRI and exploring individualized imaging phenotypes.

Network-level enrichment provides a framework for biological interpretation of machine learning results

Machine learning algorithms are increasingly being utilized to identify brain connectivity biomarkers linked to behavioral and clinical outcomes. However, research often prioritizes prediction accuracy at the expense of biological interpretability, and inconsistent implementation of ML methods may hinder model accuracy. To address this, our paper introduces a network-level enrichment approach, which integrates brain system organization in the context of connectome-wide statistical analysis to reveal network-level links between brain connectivity and behavior. To demonstrate the efficacy of this approach, we used linear support vector regression (LSVR) models to examine the relationship between resting-state functional connectivity networks and chronological age. We compared network-level associations based on raw LSVR weights to those produced from the forward and inverse models. Results indicated that not accounting for shared family variance inflated prediction performance, the k-best feature selection via Pearson correlation reduced accuracy and reliability, and raw LSVR model weights produced network-level associations that deviated from the significant brain systems identified by forward and inverse models. Our findings offer crucial insights for applying machine learning to neuroimaging data, emphasizing the value of network enrichment for biological interpretation.

Assessing neurocognitive maturation in early adolescence based on baby and adult functional brain landscapes

Adolescence is a period of growth in cognitive performance and functioning. Recently, data-driven measures of brain-age gap, which can index cognitive decline in older populations, have been utilized in adolescent data with mixed findings. Instead of using a data-driven approach, here we assess the maturation status of the brain functional landscape in early adolescence by directly comparing an individual's resting-state functional connectivity (rsFC) to the canonical early-life and adulthood communities. Specifically, we hypothesized that the degree to which a youth's connectome is better captured by adult networks compared to infant/toddler networks is predictive of their cognitive development. To test this hypothesis across individuals and longitudinally, we utilized the Adolescent Brain Cognitive Development (ABCD) Study at baseline (9-10 years; n = 6,489) and 2-year-follow-up (Y2: 11-12 years; n = 5,089). Adjusted for demographic factors, our anchored rsFC score (AFC) was associated with better task performance both across and within participants. AFC was related to age and aging across youth, and change in AFC statistically mediated the age-related change in task performance. In conclusion, we showed that a model-fitting-free index of the brain at rest that is anchored to both adult and baby connectivity landscapes predicts cognitive performance and development in youth.

Early Life Neuroimaging: The Generalizability of Cortical Area Parcellations Across Development

The cerebral cortex comprises discrete cortical areas that form during development. Accurate area parcellation in neuroimaging studies enhances statistical power and comparability across studies. The formation of cortical areas is influenced by intrinsic embryonic patterning as well as extrinsic inputs, particularly through postnatal exposure. Given the substantial changes in brain volume, microstructure, and functional connectivity during the first years of life, we hypothesized that cortical areas in 1-to-3-year-olds would exhibit major differences from those in neonates and progressively resemble adults as development progresses. Here, we parcellated the cerebral cortex into putative areas using local functional connectivity gradients in 92 toddlers at 2 years old. We demonstrated high reproducibility of these cortical regions across 1-to-3-year-olds in two independent datasets. The area boundaries in 1-to-3-year-olds were more similar to adults than neonates. While the age-specific group parcellation fitted better to the underlying functional connectivity in individuals during the first 3 years, adult area parcellations might still have some utility in developmental studies, especially in children older than 6 years. Additionally, we provided connectivity-based community assignments of the parcels, showing fragmented anterior and posterior components based on the strongest connectivity, yet alignment with adult systems when weaker connectivity was included.

Flexible parametrization of graph-theoretical features from individual-specific networks for prediction

Statistical techniques are needed to analyze data structures with complex dependencies such that clinically useful information can be extracted. Individual-specific networks, which capture dependencies in complex biological systems, are often summarized by graph-theoretical features. These features, which lend themselves to outcome modeling, can be subject to high variability due to arbitrary decisions in network inference and noise. Correlation-based adjacency matrices often need to be sparsified before meaningful graph-theoretical features can be extracted, requiring the data analysts to determine an optimal threshold. To address this issue, we propose to incorporate a flexible weighting function over the full range of possible thresholds to capture the variability of graph-theoretical features over the threshold domain. The potential of this approach, which extends concepts from functional data analysis to a graph-theoretical setting, is explored in a plasmode simulation study using real functional magnetic resonance imaging (fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE) Preprocessed initiative. The simulations show that our modeling approach yields accurate estimates of the functional form of the weight function, improves inference efficiency, and achieves a comparable or reduced root mean square prediction error compared to competitor modeling approaches. This assertion holds true in settings where both complex functional forms underlie the outcome-generating process and a universal threshold value is employed. We demonstrate the practical utility of our approach by using resting-state fMRI data to predict biological age in children. Our study establishes the flexible modeling approach as a statistically principled, serious competitor to ad-hoc methods with superior performance.

Functional brain connectivity predictors of prospective substance use initiation and their environmental correlates

Background

Early substance use initiation (SUI) places youth at substantially higher risk for later substance use disorders. Furthermore, adolescence is a critical period for the maturation of brain networks, the pace and magnitude of which are susceptible to environmental influences and may shape risk for SUI.

Methods

We examined whether patterns of functional brain connectivity during rest (rsFC), measured longitudinally in pre-and-early adolescence, can predict future SUI. In an independent sub-sample, we also tested whether these patterns are associated with key environmental factors, specifically neighborhood pollution and socioeconomic dimensions. We utilized data from the Adolescent Brain Cognitive Development (ABCD) Study®. SUI was defined as first-time use of at least one full dose of alcohol, nicotine, cannabis, or other drugs. We created a control group (N = 228) of participants without SUI who were matched with the SUI group (N = 233) on age, sex, race/ethnicity, and parental income and education.

Results

Multivariate analysis showed that whole-brain rsFC prior to SUI during 9-10 and 11-12 years of age successfully differentiated the prospective SUI and control groups. This rsFC signature was expressed more at older ages in both groups, suggesting a pattern of accelerated maturation in the SUI group in the years prior to SUI. In an independent sub-sample (N = 2,854) and adjusted for family socioeconomic factors, expression of this rsFC pattern was associated with higher pollution, but not neighborhood disadvantage.

Conclusion

Brain functional connectivity patterns in early adolescence that are linked to accelerated maturation and environmental exposures can predict future SUI in youth.

Brain age prediction and deviations from normative trajectories in the neonatal connectome

Structural and functional connectomes undergo rapid changes during the third trimester and the first month of postnatal life. Despite progress, our understanding of the developmental trajectories of the connectome in the perinatal period remains incomplete. Brain age prediction uses machine learning to estimate the brain's maturity relative to normative data. The difference between the individual's predicted and chronological age-or brain age gap (BAG)-represents the deviation from these normative trajectories. Here, we assess brain age prediction and BAGs using structural and functional connectomes for infants in the first month of life. We used resting-state fMRI and DTI data from 611 infants (174 preterm; 437 term) from the Developing Human Connectome Project (dHCP) and connectome-based predictive modeling to predict postmenstrual age (PMA). Structural and functional connectomes accurately predicted PMA for term and preterm infants. Predicted ages from each modality were correlated. At the network level, nearly all canonical brain networks-even putatively later developing ones-generated accurate PMA prediction. Additionally, BAGs were associated with perinatal exposures and toddler behavioral outcomes. Overall, our results underscore the importance of normative modeling and deviations from these models during the perinatal period.

Data leakage inflates prediction performance in connectome-based machine learning models

Predictive modeling is a central technique in neuroimaging to identify brain-behavior relationships and test their generalizability to unseen data. However, data leakage undermines the validity of predictive models by breaching the separation between training and test data. Leakage is always an incorrect practice but still pervasive in machine learning. Understanding its effects on neuroimaging predictive models can inform how leakage affects existing literature. Here, we investigate the effects of five forms of leakage-involving feature selection, covariate correction, and dependence between subjects-on functional and structural connectome-based machine learning models across four datasets and three phenotypes. Leakage via feature selection and repeated subjects drastically inflates prediction performance, whereas other forms of leakage have minor effects. Furthermore, small datasets exacerbate the effects of leakage. Overall, our results illustrate the variable effects of leakage and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.

The effects of data leakage on connectome-based machine learning models

Predictive modeling has now become a central technique in neuroimaging to identify complex brain-behavior relationships and test their generalizability to unseen data. However, data leakage, which unintentionally breaches the separation between data used to train and test the model, undermines the validity of predictive models. Previous literature suggests that leakage is generally pervasive in machine learning, but few studies have empirically evaluated the effects of leakage in neuroimaging data. Although leakage is always an incorrect practice, understanding the effects of leakage on neuroimaging predictive models provides insight into the extent to which leakage may affect the literature. Here, we investigated the effects of leakage on machine learning models in two common neuroimaging modalities, functional and structural connectomes. Using over 400 different pipelines spanning four large datasets and three phenotypes, we evaluated five forms of leakage fitting into three broad categories: feature selection, covariate correction, and lack of independence between subjects. As expected, leakage via feature selection and repeated subjects drastically inflated prediction performance. Notably, other forms of leakage had only minor effects (e.g., leaky site correction) or even decreased prediction performance (e.g., leaky covariate regression). In some cases, leakage affected not only prediction performance, but also model coefficients, and thus neurobiological interpretations. Finally, we found that predictive models using small datasets were more sensitive to leakage. Overall, our results illustrate the variable effects of leakage on prediction pipelines and underscore the importance of avoiding data leakage to improve the validity and reproducibility of predictive modeling.

Functional networks in the infant brain during sleep and wake states

Functional brain networks are assessed differently earlier versus later in development: infants are almost universally scanned asleep, whereas adults are typically scanned awake. Observed differences between infant and adult functional networks may thus reflect differing states of consciousness rather than or in addition to developmental changes. We explore this question by comparing functional networks in functional magnetic resonance imaging (fMRI) scans of infants during natural sleep and awake movie-watching. As a reference, we also scanned adults during awake rest and movie-watching. Whole-brain functional connectivity was more similar within the same state (sleep and movie in infants; rest and movie in adults) compared with across states. Indeed, a classifier trained on patterns of functional connectivity robustly decoded infant state and even generalized to adults; interestingly, a classifier trained on adult state did not generalize as well to infants. Moreover, overall similarity between infant and adult functional connectivity was modulated by adult state (stronger for movie than rest) but not infant state (same for sleep and movie). Nevertheless, the connections that drove this similarity, particularly in the frontoparietal control network, were modulated by infant state. In sum, infant functional connectivity differs between sleep and movie states, highlighting the value of awake fMRI for studying functional networks over development.

Baby Brains at Work: How Task-Based Functional Magnetic Resonance Imaging Can Illuminate the Early Emergence of Psychiatric Risk

Psychiatric disorders are complex, often emerging from multiple atypical processes within specified domains over the course of development. Characterizing the development of the neural circuits supporting these domains may help break down the components of complex disorders and reveal variations in functioning associated with psychiatric risk. This review highlights the current and potential role of infant task-based functional magnetic resonance imaging (fMRI) in elucidating the developmental neurobiology of psychiatric disorders. Task-fMRI measures evoked brain activity in response to specific stimuli through changes in the blood oxygen level-dependent signal. First, we review extant studies using task fMRI from birth through the first few years of life and synthesize current evidence for when, where, and how different neural computations are performed across the infant brain. Neural circuits for sensory perception, the perception of abstract categories, and the detection of statistical regularities have been characterized with task fMRI in infants, providing developmental context for identifying and interpreting variation in the functioning of neural circuits related to psychiatric risk. Next, we discuss studies that specifically examine variation in the functioning of these neural circuits during infancy in relation to risk for psychiatric disorders. These studies reveal when maturation of specific neural circuits diverges, the influence of environmental risk factors, and the potential utility for task fMRI to facilitate early treatment or prevention of later psychiatric problems. Finally, we provide considerations for future infant task-fMRI studies with the potential to advance understanding of both functioning of neural circuits during infancy and subsequent risk for psychiatric disorders.

Down and up! Does the mu rhythm index a gating mechanism in the developing motor system?

Developmental research on action processing in the motor cortex relies on a key neural marker - a decrease in 6-12 Hz activity (coined mu suppression). However, recent evidence points towards an increase in mu power, specific for the observation of others' actions. Complementing the findings on mu suppression, this raises the critical question for the functional role of the mu rhythm in the developing motor system. We here discuss a potential solution to this seeming controversy by suggesting a gating function of the mu rhythm: A decrease in mu power may index the facilitation, while an increase may index the inhibition of motor processes, which are critical during action observation. This account may advance our conception of action understanding in early brain development and points towards critical directions for future research.