Dataset Information

Morphological Brain Age Prediction using Multi-View Brain Networks Derived from Cortical Morphology in Healthy and Disordered Participants.

ABSTRACT: Brain development and aging are dynamic processes that unfold over years on multiple levels in both healthy and disordered individuals. Recent studies have revealed a disparity between the chronological brain age and the 'data-driven' brain age using functional MRI (fMRI) and diffusion MRI (dMRI). Particularly, predicting the 'brain age' from connectomic data might help identify relevant connectional biomarkers of neurological disorders that emerge early or late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional connectomic data, here we unprecedentedly propose to predict the morphological age of the brain by solely using morphological brain networks (derived from T1-weighted images) in both healthy and disordered populations. Besides, although T1-weighted MRI was widely used for brain age prediction, it was leveraged from an image-based analysis perspective not from a connectomic perspective. Our method includes the following steps: (i) building multi-view morphological brain networks (M-MBN), (ii) feature extraction and selection, (iii) training a machine-learning regression model to predict age from M-MBN data, and (iv) utilizing our model to identify connectional brain features related to age in both autistic and healthy populations. We demonstrate that our method significantly outperforms existing approaches and discovered brain connectional morphological features that fingerprint the age of brain cortical morphology in both autistic and healthy individuals. In particular, we discovered that the connectional cortical thickness best predicts the morphological age of the autistic brain.

SUBMITTER: Corps J

PROVIDER: S-EPMC6609705 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Morphological Brain Age Prediction using Multi-View Brain Networks Derived from Cortical Morphology in Healthy and Disordered Participants.

Corps Joshua J Rekik Islem I

Scientific reports 20190704 1

Brain development and aging are dynamic processes that unfold over years on multiple levels in both healthy and disordered individuals. Recent studies have revealed a disparity between the chronological brain age and the 'data-driven' brain age using functional MRI (fMRI) and diffusion MRI (dMRI). Particularly, predicting the 'brain age' from connectomic data might help identify relevant connectional biomarkers of neurological disorders that emerge early or late in the lifespan. While prior brai ...[more]

PMID: 31273275

Similar Datasets

Project description:During normal childhood development, functional brain networks evolve over time in parallel with changes in neuronal oscillations. Previous studies have demonstrated differences in network topology with age, particularly in neonates and in cohorts spanning from birth to early adulthood. Here, we evaluate the developmental changes in EEG functional connectivity with a specific focus on the first 2 years of life. Functional connectivity networks (FCNs) were calculated from the EEGs of 240 healthy infants aged 0-2 years during wakefulness and sleep using a cross-correlation-based measure and the weighted phase lag index. Topological features were assessed via network strength, global clustering coefficient, characteristic path length, and small world measures. We found that cross-correlation FCNs maintained a consistent small-world structure, and the connection strengths increased after the first 3 months of infancy. The strongest connections in these networks were consistently located in the frontal and occipital regions across age groups. In the delta and theta bands, weighted phase lag index networks decreased in strength after the first 3 months in both wakefulness and sleep, and a similar result was found in the alpha and beta bands during wakefulness. However, in the alpha band during sleep, FCNs exhibited a significant increase in strength with age, particularly in the 21-24 months age group. During this period, a majority of the strongest connections in the networks were located in frontocentral regions, and a qualitatively similar distribution was seen in the beta band during sleep for subjects older than 3 months. Graph theory analysis suggested a small world structure for weighted phase lag index networks, but to a lesser degree than those calculated using cross-correlation. In general, graph theory metrics showed little change over time, with no significant differences between age groups for the clustering coefficient (wakefulness and sleep), characteristics path length (sleep), and small world measure (sleep). These results suggest that infant FCNs evolve during the first 2 years with more significant changes to network strength than features of the network structure. This study quantifies normal brain networks during infant development and can serve as a baseline for future investigations in health and neurological disease.

Dataset Information

Morphological Brain Age Prediction using Multi-View Brain Networks Derived from Cortical Morphology in Healthy and Disordered Participants.

Publications

Morphological Brain Age Prediction using Multi-View Brain Networks Derived from Cortical Morphology in Healthy and Disordered Participants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets