Linking brain maturation and puberty during early adolescence using longitudinal brain age prediction in the ABCD cohort

Holm, Madelene; Leonardsen, Esten; Beck, Dani; Dahl, Andreas; Kjelkenes, Rikka; Lange, Ann-Marie G. de; Westlye, Lars T.

doi:10.1101/2022.05.16.22275146

Cited by 11 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond model building, we aimed at investigating whether the low dimensional embedding scores are sensitive to capture biologically meaningful variance in processes shaping the brain and thus may represent a useful imaging phenotype for (developmental) brain dynamics. Related to work suggesting a close link between pubertal dynamics and neurodevelopment e.g., 18,23 , we observed significant crosssectional associations between the predicted embedding scores and puberty measures for all models at all timepoints except for baseline data based on youth reports, which might have been biased by the difficulty to rate one´s own pubertal maturation at these early ages. Of note, all analyses were performed stratified for sex, because the embeddings span a sex-gradient, and pubertal timing and trajectories are known to vary between females and males 24 .…”

Section: Discussionsupporting

confidence: 61%

Traces of pubertal brain development and health revealed through domain adapted brain network fusion

Kraft

Alnæs

Kaufmann

2023

Preprint

View full text Add to dashboard Cite

Puberty demarks a period of profound brain dynamics that orchestrates changes to a multitude of neuroimaging-derived phenotypes. This poses a dimensionality problem when attempting to chart an individuals brain development on a single scale. Here, we illustrate shifts in subject similarity of imaging data that relate to pubertal maturation and altered mental health, suggesting that dimensional reference spaces of subject similarity render useful to chart brain dynamics in youths.

show abstract

Section: Discussionsupporting

confidence: 61%

Traces of pubertal brain development and health revealed through domain adapted brain network fusion

Kraft

Alnæs

Kaufmann

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The normative modeling framework is ideal for estimating age trajectories beyond adolescence, and future studies may benefit from including both a younger and older study population. Various environmental and genetic variables are likely to explain and modulate the associations between brain imaging, cognition, and psychopathology in youth, including sociodemographic variables such as poverty and quality of schooling, perinatal factors such as birth weight or premature birth (Alnaes et al, 2020;Modabbernia et al, 2021), and maturational processes including onset and rate of puberty (Holm et al, 2022). Future studies may be able to model the instantaneous influence of a range of modulating factors to increase the precision, relevance, and predictive value of the output from the normative modeling framework.…”

Section: Limitationsmentioning

confidence: 99%

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Kjelkenes¹,

Wolfers²,

Alnæs³

et al. 2022

Preprint

View full text Add to dashboard Cite

Combining imaging modalities and metrics that are sensitive to various aspects of brain structure and maturation may help identify individuals that show deviations in relation to same-aged peers, and thus benefit early-risk-assessment for mental disorders. We used one timepoint multimodal brain imaging, cognitive, and questionnaire data from 1280 8-21-year-olds from the Philadelphia Neurodevelopmental Cohort. We estimated age-related gray and white matter properties and estimated individual deviation scores using normative modeling. Next, we looked for associations between the estimated deviation scores, and with psychopathology domain scores and cognition. More negative deviations in DTI-based fractional anisotropy (FA) and the first principal eigenvalue of the diffusion tensor (L1) were associated with higher scores on psychosis positive and prodromal symptoms and a general psychopathology factor. A more negative deviation in cortical thickness (CT) was associated with a higher general psychopathology score. Negative deviations in global FA, surface area, L1 and CT were also associated with poorer cognitive performance. No robust associations were found between the deviation scores based on CT and DTI. The low correlations between the different multimodal MRI based deviation scores support that brain maturation is highly heterogenous and suggest that psychopathological burden in adolescence may map onto partly distinct neurobiological features.

show abstract

“…The prediction of biological age from healthy brain magnetic resonance imaging (MRI) scans (i.e. “ brain age ”) has the potential for wide-ranging medical and scientific applications 1,2 . Establishing reliable brain age prediction in large healthy-control populations would enable studying how various diseases, interventions, and socioeconomic factors influence brain development.…”

Section: Introductionmentioning

confidence: 99%

Diffusion Deep Learning for Brain Age Prediction and Longitudinal Tracking in Children Through Adulthood

Zapaishchykova,

Tak,

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning (DL)-based prediction of biological age in the developing human from a brain magnetic resonance image (MRI) (brain age) may have important diagnostic and therapeutic applications as a non-invasive biomarker of brain health, aging, and neurocognition. While previous deep learning tools for predicting brain age have shown promising capabilities using single-institution, cross-sectional datasets, our work aims to advance the field by leveraging multi-site, longitudinal data with externally validated and independently implementable code to facilitate clinical translation and utility. This builds on prior foundational efforts in brain age modeling to enable broader generalization and individual's longitudinal brain development. Here, we leveraged 32,851 T1-weighted MRI scans from healthy children and adolescents aged 3 to 30 from 16 multisite datasets to develop and evaluate several DL brain age frameworks, including a novel regression diffusion DL network (AgeDiffuse). In a multisite external validation (5 datasets), we found that AgeDiffuse outperformed conventional DL frameworks, with a mean absolute error (MAE) of 2.78 years (IQR:[1.2-3.9]). In a second, separate external validation (3 datasets), AgeDiffuse yielded an MAE of 1.97 years (IQR: [0.8-2.8]). We found that AgeDiffuse brain age predictions reflected age-related brain structure volume changes better than biological age (R2=0.48 vs R2=0.37). Finally, we found that longitudinal predicted brain age tracked closely with chronological age at the individual level. To enable independent validation and application, we made AgeDiffuse publicly available and usable for the research community.

show abstract

Linking brain maturation and puberty during early adolescence using longitudinal brain age prediction in the ABCD cohort

Cited by 11 publications

References 56 publications

Traces of pubertal brain development and health revealed through domain adapted brain network fusion

Traces of pubertal brain development and health revealed through domain adapted brain network fusion

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Diffusion Deep Learning for Brain Age Prediction and Longitudinal Tracking in Children Through Adulthood

Contact Info

Product

Resources

About