Hierarchical modelling of functional brain networks in population and individuals from big fMRI data.

A major goal of large-scale brain imaging datasets is to provide resources for investigating heterogeneous populations. Characterisation of functional brain networks for individual subjects from these datasets will have an enormous potential for prediction of cognitive or clinical traits. We propose for the first time a technique, Stochastic Probabilistic Functional Modes (sPROFUMO), that is scalable to UK Biobank (UKB) with expected 100,000 participants, and hierarchically estimates functional brain networks in individuals and the population, while allowing for bidirectional flow of information between the two. Using simulations, we show the model's utility, especially in scenarios that involve significant cross-subject variability, or require delineation of fine-grained differences between the networks. Subsequently, by applying the model to resting-state fMRI from 4999 UKB subjects, we mapped resting state networks (RSNs) in single subjects with greater detail than has been possible previously in UKB (>100 RSNs), and demonstrate that these RSNs can predict a range of sensorimotor and higher-level cognitive functions. Furthermore, we demonstrate several advantages of the model over independent component analysis combined with dual-regression (ICA-DR), particularly with respect to the estimation of the spatial configuration of the RSNs and the predictive power for cognitive traits. The proposed model and results can open a new door for future investigations into individualised profiles of brain function from big data.

Functional connectome fingerprinting: Identifying individuals and predicting cognitive functions via autoencoder.

Functional network connectivity has been widely acknowledged to characterize brain functions, which can be regarded as "brain fingerprinting" to identify an individual from a pool of subjects. Both common and unique information has been shown to exist in the connectomes across individuals. However, very little is known about whether and how this information can be used to predict the individual variability of the brain. In this paper, we propose to enhance the uniqueness of individual connectome based on an autoencoder network. Specifically, we hypothesize that the common neural activities shared across individuals may reduce the individual identification. By removing contributions from shared activities, inter-subject variability can be enhanced. Our experimental results on HCP data show that the refined connectomes obtained by utilizing autoencoder with sparse dictionary learning can distinguish an individual from the remaining participants with high accuracy (up to 99.5% for the rest-rest pair). Furthermore, high-level cognitive behaviors (e.g., fluid intelligence, executive function, and language comprehension) can also be better predicted with the obtained refined connectomes. We also find that high-order association cortices contribute more to both individual discrimination and behavior prediction. In summary, our proposed framework provides a promising way to leverage functional connectivity networks for cognition and behavior study, in addition to a better understanding of brain functions.

The prediction of later neurodevelopmental status of preterm infants at ages 7 to 10 years using the Bayley Infant Neurodevelopmental Screener.

The aim of this study was to see whether the scores of the Bayley Infant Neurodevelopmental Screener of 45 high-risk preterm infants (gestational age 26-37 wk) between the ages of 3 and 24 months predicted neurodevelopmental status at 7 to 10 years of age. Neurodevelopmental status of 45/122 preterm infants, grouped according to their gestational ages of 26 to 29, 30 to 32, and 33 to 37 weeks, were previously evaluated by Bayley Infant Neurodevelopmental Screener. The scores were categorized as low or high-moderate. Verbal and performance scores of Wechsler Intelligence Scale for Children-Revised (WISC-R) of those patients were assessed between 7 and 10 years. The patients with high-moderate-risk scores of Bayley Infant Neurodevelopmental Screener at all times, regardless of their gestational age, had lower performance, verbal, and total scores of WISC-R than those of who had low Bayley Infant Neurodevelopmental Screener risk scores. High-moderate risk score of Bayley Infant Neurodevelopmental Screener at 7 to 10, and 16 to 20 months, of all patients especially showed good prediction for identifying lower verbal and performance scales. For 7 to 10 months, verbal scale: positive predictive value = 92.3%, negative predictive value = 44.4%, sensitivity = 70.58%, and specificity = 80%; performance scale: positive predictive value = 100%, negative predictive value = 30%, sensitivity = 68.18%, and specificity = 100%. For 16 to 20 months, verbal scale: positive predictive value = 90%, negative predictive value = 37.5%, sensitivity = 64.3%, and specificity = 80%; performance scale: positive predictive value = 90%, negative predictive value = 12.5%, sensitivity = 56.3%, and specificity = 50%. Bayley Infant Neurodevelopmental Screener shows good prediction of later verbal and performance scores of Wechsler Intelligence Scale-Revised for Children as early as 7 to 10 months, which gives us the opportunity to start early intervention.