Multi-dynamic Modelling Reveals Strongly Time-varying Resting fMRI Correlations

Abstract

The activity of functional brain networks is responsible for the emergence of time-varying cognition and behaviour. Accordingly, time-varying correlations (Functional Connectivity) in resting fMRI have been shown to be predictive of behavioural traits, and psychiatric and neurological conditions. Typically, methods that measure time-varying Functional Connectivity (FC), such as sliding windows approaches, do not separately model when changes occur in the mean activity levels from when changes occur in the FC, therefore conflating these two distinct types of modulation. We show that this can bias the estimation of time-varying FC to appear more stable over time than it actually is. Here, we propose an alternative approach that models changes in the mean brain activity and in the FC as being able to occur at different times to each other. We refer to this method as the Multi-dynamic Adversarial Generator Encoder (MAGE) model, which includes a model of the network dynamics that captures long-range time dependencies, and is estimated on fMRI data using principles of Generative Adversarial Networks. We evaluated the approach across several simulation studies and resting fMRI data from the Human Connectome Project (1003 subjects), as well as from UK Biobank (13301 subjects). Importantly, we find that separating fluctuations in the mean activity levels from those in the FC reveals much stronger changes in FC over time, and is a better predictor of individual behavioural variability

Generative AI for brain image computing and brain network computing: a review

“… Model categorization map under different brain image analysis tasks. Coregistration: CAE-GAN (Yang et al, 2020 ), RegGAN (Kong et al, 2021 ), cGAN (Sundar et al, 2021 ), AC-flow (Wang B. et al, 2022 ), DiffuseMorph (Kim et al, 2022 ); Enhancement: α-GAN (Kwon et al, 2019 ), AR-GAN (Luo et al, 2022 ), Multi-stream GAN (Yurt et al, 2021 ), Intro VAE (Hirte et al, 2021 ), MBTI (Rouzrokh et al, 2022 ); Segmentation: ToStaGAN (Ding et al, 2021 ), CPGAN (Wang S. et al, 2022 ), SD-GAN (Wu et al, 2021 ), DAE (Bangalore Yogananda et al, 2022 ), MedSegDiff (Wu et al, 2022 ), PD-DDPM (Guo et al, 2022 ); Super-resolution: Flow Enhancer (Dong et al, 2022 ), Dual GANs (Song et al, 2020 ), FP-GAN (You et al, 2022 ); Cross-modality: UCAN (Zhou et al, 2021 ), MouseGAN (Yu et al, 2021c ), BMGAN (Hu et al, 2021 ), D2FE-GAN (Zhan et al, 2022 ), SynDiff (Özbey et al, 2022 ), UMM-CSGM (Meng et al, 2022 ); Classification: CN-StyleGAN (Lee et al, 2022 ), THS-GAN (Yu et al, 2021a ), Smile-GAN (Yang Z. et al, 2021 ), VAEGAN-QC (Mostapha et al, 2019 ); Brain network analysis: LG-DADA (Bessadok et al, 2021 ), AGSR-Net (Isallari and Rekik, 2021 ), GSDAE (Qiao et al, 2021 ), GATE (Liu M. et al, 2021 ), MAGE (Pervaiz et al, 2021 ); Brain decode: D-VAE (Ren et al, 2021 ), DMACN (Lu et al, 2021 ), DGNN (VanRullen and Reddy, 2019 ), Untrained DNN (Baek et al, 2021 ), MinD-Vis (Chen et al, 2022 ). …”

Mixtures of large-scale dynamic functional brain network modes

“…This facilitates the use of more sophisticated and non-linear observation models and opens up a range of future modelling opportunities. This includes the use of an autoregressive model capable of learning temporal correlations in the observed data; the hierarchical modelling of inter-subject variability and the inclusion of dynamics at multiple time scales, similar to the approach used in [45].…”

“…True brain dynamics might be better modelled by patterns that can flexibly combine and mix over time. The mutual exclusivity constraint was found to lead to errors in inferred functional brain network metrics in [43].…”

Time-varying hierarchical core voxels disclosed by k-core percolation on dynamic inter-voxel connectivity resting-state fMRI

“…Even though voxels are considered as the unit entities of brain function, current mm 3 resolution of fMRI yield a voxel consisting of mixture of neurons of 10 5 ( 20 ). Dynamic binning of time down to 1-min also let us to assume stationarity of neuronal interaction within this voxel ( 21, 22 ). Keeping in mind the heterogeneity of composition of voxels and unproven stationarity of time bins, we can move on to look for the hierarchical structures of voxels from both correlated and anti-correlated relations between voxels, along the pre-determined time bins with stationarity assumption.…”

“…Static functional connectivity studies used long-time bins of 7 to 15 minutes with stationarity assumption. Now dynamic studies can be done using 1-min time bins to disclose whether the static and the minute time-bin dynamic analysis of rsfMRI would represent the state progress or transition of individuals’ mental states at rest ( 7, 21, 22 ).…”