Brain network constraints and recurrent neural networks reproduce unique trajectories and state transitions seen over the span of minutes in resting-state fMRI

A deep learning approach to estimating initial conditions of Brain Network Models in reference to measured fMRI data

Introduction

Brain Network Models (BNMs) are mathematical models that simulate the activity of the entire brain. These models use neural mass models to represent local activity in different brain regions that interact with each other via a global structural network. Researchers have been interested in using these models to explain measured brain activity, particularly resting state functional magnetic resonance imaging (rs-fMRI). BNMs have shown to produce similar properties as measured data computed over longer periods of time such as average functional connectivity (FC), but it is unclear how well simulated trajectories compare to empirical trajectories on a timepoint-by-timepoint basis. During task fMRI, the relevant processes pertaining to task occur over the time frame of the hemodynamic response function, and thus it is important to understand how BNMs capture these dynamics over these short periods.

Methods

To test the nature of BNMs' short-term trajectories, we used a deep learning technique called Neural ODE to simulate short trajectories from estimated initial conditions based on observed fMRI measurements. To compare to previous methods, we solved for the parameterization of a specific BNM, the Firing Rate Model, using these short-term trajectories as a metric.

Results

Our results show an agreement between parameterization of using previous long-term metrics with the novel short term metrics exists if also considering other factors such as the sensitivity in accuracy with relative to changes in structural connectivity, and the presence of noise.

Discussion

Therefore, we conclude that there is evidence that by using Neural ODE, BNMs can be simulated in a meaningful way when comparing against measured data trajectories, although future studies are necessary to establish how BNM activity relate to behavioral variables or to faster neural processes during this time period.

Representation learning of resting state fMRI with variational autoencoder

Resting state functional magnetic resonance imaging (rsfMRI) data exhibits complex but structured patterns. However, the underlying origins are unclear and entangled in rsfMRI data. Here we establish a variational auto-encoder, as a generative model trainable with unsupervised learning, to disentangle the unknown sources of rsfMRI activity. After being trained with large data from the Human Connectome Project, the model has learned to represent and generate patterns of cortical activity and connectivity using latent variables. The latent representation and its trajectory represent the spatiotemporal characteristics of rsfMRI activity. The latent variables reflect the principal gradients of the latent trajectory and drive activity changes in cortical networks. Representational geometry captured as covariance or correlation between latent variables, rather than cortical connectivity, can be used as a more reliable feature to accurately identify subjects from a large group, even if only a short period of data is available in each subject. Our results demonstrate that VAE is a valuable addition to existing tools, particularly suited for unsupervised representation learning of resting state fMRI activity.

Contribution of animal models toward understanding resting state functional connectivity

Functional connectivity, which reflects the spatial and temporal organization of intrinsic activity throughout the brain, is one of the most studied measures in human neuroimaging research. The noninvasive acquisition of resting state functional magnetic resonance imaging (rs-fMRI) allows the characterization of features designated as functional networks, functional connectivity gradients, and time-varying activity patterns that provide insight into the intrinsic functional organization of the brain and potential alterations related to brain dysfunction. Functional connectivity, hence, captures dimensions of the brain's activity that have enormous potential for both clinical and preclinical research. However, the mechanisms underlying functional connectivity have yet to be fully characterized, hindering interpretation of rs-fMRI studies. As in other branches of neuroscience, the identification of the neurophysiological processes that contribute to functional connectivity largely depends on research conducted on laboratory animals, which provide a platform where specific, multi-dimensional investigations that involve invasive measurements can be carried out. These highly controlled experiments facilitate the interpretation of the temporal correlations observed across the brain. Indeed, information obtained from animal experimentation to date is the basis for our current understanding of the underlying basis for functional brain connectivity. This review presents a compendium of some of the most critical advances in the field based on the efforts made by the animal neuroimaging community.