Abstract
A resting-state functional connectivity (rsFC)-constructed functional network (FN) derived from functional magnetic resonance imaging (fMRI) data can effectively mine alterations in brain function during aging due to the non-invasive and effective advantages of fMRI. With global health research focusing on aging, several open fMRI datasets have been made available that combine deep learning with big data and are a new, promising trend and open issue for brain information detection in fMRI studies of brain aging. In this study, we proposed a new method based on deep learning from the perspective of big data, named Deep neural network (DNN) with Autoencoder (AE) pretrained Functional connectivity Analysis (DAFA), to deeply mine the important functional connectivity changes in fMRI during brain aging. First, using resting-state fMRI data from 421 subjects from the CamCAN dataset, functional connectivities were calculated using sliding window method, and the complex functional patterns were mined by an AE. Then, to increase the statistical power and reliability of the results, we used an AE-pretrained DNN to relabel the functional connectivities of each subject to classify them as belonging to the attributes of young or old individuals. A method called search-back analysis was performed to find alterations in brain function during aging according to the relabeled functional connectivities. Finally, behavioral data regarding fluid intelligence and response time were used to verify the revealed functional changes. Compared to traditional methods, DAFA revealed additional, important aged-related changes in FC patterns [e.g., FC connections within the default mode (DMN) and the sensorimotor and cingulo-opercular networks, as well as connections between the frontoparietal and cingulo-opercular networks, between the DMN and the frontoparietal/cingulo-opercular/sensorimotor/occipital/cerebellum networks, and between the sensorimotor and frontoparietal/cingulo-opercular networks], which were correlated to behavioral data. These findings demonstrated that the proposed DAFA method was superior to traditional FC-determining methods in discovering changes in brain functional connectivity during aging. In addition, it may be a promising method for exploring important information in other fMRI studies.
Highlights
Functional networks (FNs) constructed by resting-state functional connectivity analysis using data from blood oxygen level dependence (BOLD)-based functional magnetic resonance imaging have greatly deepened our understanding of the functioning of the human brain
In this work, using deep learning from a big-data perspective, we proposed a new analysis method, named Deep neural network (DNN) with AE pretrained Functional connectivity Analysis (DAFA), to deeply mine the important functional connectivity changes in functional magnetic resonance imaging (fMRI) during brain aging
DAFA revealed additional significant, altered FC patterns between the young and old groups, which were ignored by the static method, and these changes were correlated with behavior scores (Cattell score, M-Reaction Time (RT), and SD-RT), which might be indicative of cognitive decline during aging
Summary
Functional networks (FNs) constructed by resting-state functional connectivity (rSFC) analysis using data from blood oxygen level dependence (BOLD)-based functional magnetic resonance imaging (fMRI) have greatly deepened our understanding of the functioning of the human brain. Researchers have found that increased FC involving the frontal, parietal networks and motor, subcortical networks was related to aging, which may reflect the compensatory responses to the decreased strength of FC during aging (Biswal et al, 2010; Tomasi and Volkow, 2012; Ferreira and Busatto, 2013) These results have greatly enhanced our understanding of aging in the brain; functional connectivity analysis is expected to be a valuable tool for objectively evaluating the health status of the brain in the function and cognition of elderly individuals and may benefit the clinical diagnosis and intervention of brain aging-related diseases (Geerligs et al, 2017; de Vos et al, 2018). Most of the present studies primarily rely on traditional, relatively small samples (from 10 to a few 100 samples) based on statistical analyses (e.g., two-sample t-test and multiple linear regression), which may result in insufficient analysis of resting-state FCs during brain aging, ignoring some important underlying information regarding FN alterations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
