Spatio-temporal modeling of connectome-scale brain network interactions via time-evolving graphs

Mapping dynamic spatial patterns of brain function with spatial-wise attention

Objective: Using functional magnetic resonance imaging (fMRI) and deep learning to discover the spatial pattern of brain function, or functional brain networks (FBNs) has been attracted many reseachers. Most existing works focus on static FBNs or dynamic functional connectivity among fixed spatial network nodes, but ignore the potential dynamic/time-varying characteristics of the spatial networks themselves. And most of works based on the assumption of linearity and independence, that oversimplify the relationship between blood-oxygen level dependence signal changes and the heterogeneity of neuronal activity within voxels.Approach: To overcome these problems, we proposed a novel spatial-wise attention (SA) based method called Spatial and Channel-wise Attention Autoencoder (SCAAE) to discover the dynamic FBNs without the assumptions of linearity or independence. The core idea of SCAAE is to apply the SA to generate FBNs directly, relying solely on the spatial information present in fMRI volumes. Specifically, we trained the SCAAE in a self-supervised manner, using the autoencoder to guide the SA to focus on the activation regions. Experimental results show that the SA can generate multiple meaningful FBNs at each fMRI time point, which spatial similarity are close to the FBNs derived by known classical methods, such as independent component analysis.Main results: To validate the generalization of the method, we evaluate the approach on HCP-rest, HCP-task and ADHD-200 dataset. The results demonstrate that SA mechanism can be used to discover time-varying FBNs, and the identified dynamic FBNs over time clearly show the process of time-varying spatial patterns fading in and out.Significance: Thus we provide a novel method to understand human brain better. Code is available athttps://github.com/WhatAboutMyStar/SCAAE.

Spatial-temporal convolutional attention for discovering and characterizing functional brain networks in task fMRI

Functional brain networks (FBNs) are spatial patterns of brain function that play a critical role in understanding human brain function. There are many proposed methods for mapping the spatial patterns of brain function, however they oversimplify the underlying assumptions of brain function and have various limitations such as linearity and independence. Additionally, current methods fail to account for the dynamic nature of FBNs, which limits their effectiveness in accurately characterizing these networks. To address these limitations, we present a novel deep learning and spatial-wise attention based model called Spatial-Temporal Convolutional Attention (STCA) to accurately model dynamic FBNs. Specifically, we train STCA in a self-supervised manner by utilizing a Convolutional Autoencoder to guide the STCA module in assigning higher attention weights to regions of functional activity. To validate the reliability of the results, we evaluate our approach on the HCP-task motor behavior dataset, the experimental results demonstrate that the STCA derived FBNs have higher spatial similarity with the templates and that the spatial similarity between the templates and the FBNs derived by STCA fluctuates with the task design over time, suggesting that STCA can reflect the dynamic changes of brain function, providing a powerful tool to better understand human brain function. Code is available at https://github.com/SNNUBIAI/STCAE.

Probabilistically Weighted Multilayer Networks disclose the link between default mode network instability and psychosis-like experiences in healthy adults

The brain is a complex system in which the functional interactions among its subunits vary over time. The trajectories of this dynamic variation contribute to inter-individual behavioral differences and psychopathologic phenotypes. Despite many methodological advancements, the study of dynamic brain networks still relies on biased assumptions in the temporal domain. The current paper has two goals. First, we present a novel method to study multilayer networks: by modelling intra-nodal connections in a probabilistic, biologically driven way, we introduce a temporal resolution of the multilayer network based on signal similarity across time series. This new method is tested on synthetic networks by varying the number of modules and the sources of noise in the simulation. Secondly, we implement these probabilistically weighted (PW) multilayer networks to study the association between network dynamics and subclinical, psychosis-relevant personality traits in healthy adults. We show that the PW method for multilayer networks outperforms the standard procedure in modular detection and is less affected by increasing noise levels. Additionally, the PW method highlighted associations between the temporal instability of default mode network connections and psychosis-like experiences in healthy adults. PW multilayer networks allow an unbiased study of dynamic brain functioning and its behavioral correlates.

Connectivity-based Cortical Parcellation via Contrastive Learning on Spatial-Graph Convolution

Objective. Objective of this work is the development and evaluation of a cortical parcellation framework based on tractography-derived brain structural connectivity. Impact Statement. The proposed framework utilizes novel spatial-graph representation learning methods for solving the task of cortical parcellation, an important medical image analysis and neuroscientific problem. Introduction. The concept of "connectional fingerprint" has motivated many investigations on the connectivity-based cortical parcellation, especially with the technical advancement of diffusion imaging. Previous studies on multiple brain regions have been conducted with promising results. However, performance and applicability of these models are limited by the relatively simple computational scheme and the lack of effective representation of brain imaging data. Methods. We propose the Spatial-graph Convolution Parcellation (SGCP) framework, a two-stage deep learning-based modeling for the graph representation brain imaging. In the first stage, SGCP learns an effective embedding of the input data through a self-supervised contrastive learning scheme with the backbone encoder of a spatial-graph convolution network. In the second stage, SGCP learns a supervised classifier to perform voxel-wise classification for parcellating the desired brain region. Results. SGCP is evaluated on the parcellation task for 5 brain regions in a 15-subject DWI dataset. Performance comparisons between SGCP, traditional parcellation methods, and other deep learning-based methods show that SGCP can achieve superior performance in all the cases. Conclusion. Consistent good performance of the proposed SGCP framework indicates its potential to be used as a general solution for investigating the regional/subregional composition of human brain based on one or more connectivity measurements.

Control energy assessment of spatial interactions among macro‐scale brain networks

Many recent studies have revealed that spatial interactions of functional brain networks derived from fMRI data can well model functional connectomes of the human brain. However, it has been rarely explored what the energy consumption characteristics are for such spatial interactions of macro‐scale functional networks, which remains crucial for the understanding of brain organization, behavior, and dynamics. To explore this unanswered question, this article presents a novel framework for quantitative assessment of energy consumptions of macro‐scale functional brain network's spatial interactions via two main effective computational methodologies. First, we designed a novel scheme combining dictionary learning and hierarchical clustering to derive macro‐scale consistent brain network templates that can be used to define a common reference space for brain network interactions and energy assessments. Second, the control energy consumption for driving the brain networks during their spatial interactions is computed from the viewpoint of the linear network control theory. Especially, the energetically favorable brain networks were identified and their energy characteristics were comprehensively analyzed. Experimental results on the Human Connectome Project (HCP) task‐based fMRI (tfMRI) data showed that the proposed methods can reveal meaningful, diverse energy consumption patterns of macro‐scale network interactions. In particular, those networks present remarkable differences in energy consumption. The energetically least favorable brain networks are stable and consistent across HCP tasks such as motor, language, social, and working memory tasks. In general, our framework provides a new perspective to characterize human brain functional connectomes by quantitative assessment for the energy consumption of spatial interactions of macro‐scale brain networks.

Estimating Functional Connectivity by Integration of Inherent Brain Function Activity Pattern Priors

Brain functional connectivity (FC) has shown great potential in becoming biomarkers of brain status. However, the problem of accurately estimating FC from complex-noisy fMRI time series remains unsolved. Usually, a regularization function is more appropriate in fitting the real inherent properties of the brain function activity pattern, which can further limit noise interference to improve the accuracy of the estimated result. Recently, the neuroscientists widely suggested that the inherent brain function activity pattern indicates sparse, modular and overlapping topology. However, previous studies have never considered this factual characteristic. Thus, we propose a novel method by integration of these inherent brain function activity pattern priors to estimate FC. Extensive experiments on synthetic data demonstrate that our method can more accurately estimate the FC than previous. Then, we applied the estimated FC to predict the symptom severity of depressed patients, the symptom severity is related to subtle abnormal changes in the brain function activity, a more accurate FC can more effectively capture the subtle abnormal brain function activity changes. As results, our method better than others with a higher correlation coefficient of 0.4201. Moreover, the overlapping probability of each brain region can be further explored by the proposed method.

Revealing the Relevant Spatiotemporal Scale Underlying Whole-Brain Dynamics

The brain rapidly processes and adapts to new information by dynamically transitioning between whole-brain functional networks. In this whole-brain modeling study we investigate the relevance of spatiotemporal scale in whole-brain functional networks. This is achieved through estimating brain parcellations at different spatial scales (100-900 regions) and time series at different temporal scales (from milliseconds to seconds) generated by a whole-brain model fitted to fMRI data. We quantify the richness of the dynamic repertoire at each spatiotemporal scale by computing the entropy of transitions between whole-brain functional networks. The results show that the optimal relevant spatial scale is around 300 regions and a temporal scale of around 150 ms. Overall, this study provides much needed evidence for the relevant spatiotemporal scales and recommendations for analyses of brain dynamics.

Fundamental functional differences between gyri and sulci: implications for brain function, cognition, and behavior

Folding of the cerebral cortex is a prominent characteristic of mammalian brains. Alterations or deficits in cortical folding are strongly correlated with abnormal brain function, cognition, and behavior. Therefore, a precise mapping between the anatomy and function of the brain is critical to our understanding of the mechanisms of brain structural architecture in both health and diseases. Gyri and sulci, the standard nomenclature for cortical anatomy, serve as building blocks to make up complex folding patterns, providing a window to decipher cortical anatomy and its relation with brain functions. Huge efforts have been devoted to this research topic from a variety of disciplines including genetics, cell biology, anatomy, neuroimaging, and neurology, as well as involving computational approaches based on machine learning and artificial intelligence algorithms. However, despite increasing progress, our understanding of the functional anatomy of gyro-sulcal patterns is still in its infancy. In this review, we present the current state of this field and provide our perspectives of the methodologies and conclusions concerning functional differentiation between gyri and sulci, as well as the supporting information from genetic, cell biology, and brain structure research. In particular, we will further present a proposed framework for attempting to interpret the dynamic mechanisms of the functional interplay between gyri and sulci. Hopefully, this review will provide a comprehensive summary of anatomo-functional relationships in the cortical gyro-sulcal system together with a consideration of how these contribute to brain function, cognition, and behavior, as well as to mental disorders.

Differentiable neural architecture search for optimal spatial/temporal brain function network decomposition

It has been a key topic to decompose the brain's spatial/temporal function networks from 4D functional magnetic resonance imaging (fMRI) data. With the advantages of robust and meaningful brain pattern extraction, deep neural networks have been shown to be more powerful and flexible in fMRI data modeling than other traditional methods. However, the challenge of designing neural network architecture for high-dimensional and complex fMRI data has also been realized recently. In this paper, we propose a new spatial/temporal differentiable neural architecture search algorithm (ST-DARTS) for optimal brain network decomposition. The core idea of ST-DARTS is to optimize the inner cell structure of the vanilla recurrent neural network (RNN) in order to effectively decompose spatial/temporal brain function networks from fMRI data. Based on the evaluations on all seven fMRI tasks in human connectome project (HCP) dataset, the ST-DARTS model is shown to perform promisingly, both spatially (i.e., it can recognize the most stimuli-correlated spatial brain network activation that is very similar to the benchmark) and temporally (i.e., its temporal activity is highly positively correlated with the task-design). To further improve the efficiency of ST-DARTS model, we introduce a flexible early-stopping mechanism, named as ST-DARTS+, which further improves experimental results significantly. To our best knowledge, the proposed ST-DARTS and ST-DARTS+ models are among the early efforts in optimally decomposing spatial/temporal brain function networks from fMRI data with neural architecture search strategy and they demonstrate great promise.

Intrinsic, dynamic and effective connectivity among large-scale brain networks modulated by oxytocin

The neuropeptide oxytocin is a key modulator of social-emotional behavior and its intranasal administration can influence the functional connectivity of brain networks involved in the control of attention, emotion and reward reported in humans. However, no studies have systematically investigated the effects of oxytocin on dynamic or directional aspects of functional connectivity. The present study employed a novel computational framework to investigate these latter aspects in 15 oxytocin-sensitive regions using data from randomized placebo-controlled between-subject resting state functional MRI studies incorporating 200 healthy subjects. In order to characterize the temporal dynamics, the 'temporal state' was defined as a temporal segment of the whole functional MRI signal which exhibited a similar functional interaction pattern among brain regions of interest. Results showed that while no significant effects of oxytocin were found on brain temporal state related characteristics (including temporal state switching frequency, probability of transitions between neighboring states, and averaged dwell time on each state) oxytocin extensively (n = 54 links) modulated effective connectivity among the 15 regions. The effects of oxytocin were primarily characterized by increased effective connectivity both between and within emotion, reward, salience, attention and social cognition processing networks and their interactions with the default mode network. Top-down control over emotional processing regions such as the amygdala was particularly affected. Oxytocin also increased effective homotopic interhemispheric connectivity in almost all these regions. Additionally, the effects of oxytocin on effective connectivity were sex-dependent, being more extensive in males. Overall, these findings suggest that modulatory effects of oxytocin on both within- and between-network interactions may underlie its functional influence on social-emotional behaviors, although in a sex-dependent manner. These findings may be of particular relevance to potential therapeutic use of oxytocin in psychiatric disorders associated with social dysfunction, such as autism spectrum disorder and schizophrenia, where directionality of treatment effects on causal interactions between networks may be of key importance .

Target controllability with minimal mediators in complex biological networks

Controllability of a complex network system is related to finding a set of minimum number of nodes, known as drivers, controlling which allows having a full control on the dynamics of the network. For some applications, only a portion of the network is required to be controlled, for which target control has been proposed. Often, along the controlling route from driver nodes to target nodes, some mediators (intermediate nodes) are also unwillingly controlled, which might cause various side effects. In controlling cancerous cells, unwillingly controlling healthy cells, might result in weakening them, thus affecting the immune system against cancer. This manuscript proposes a suitable candidate solution to the problem of finding minimum number of driver nodes under minimal mediators. Although many others have attempted to develop algorithms to find minimum number of drivers for target control, the newly proposed algorithm is the first one that is capable of achieving this goal and at the same time, keeping the number of the mediators to a minimum. The proposed controllability condition, based on path lengths between node pairs, meets Kalman's controllability rank condition and can be applied on directed networks. Our results show that the path length is a major determinant of in properties of the target control under minimal mediators. As the average path length becomes larger, the ratio of drivers to target nodes decreases and the ratio of mediators to targets increases. The proposed methodology has potential applications in biological networks. The source code of the algorithm and the networks that have been used are available from the following link: https://github.com/LBBSoft/Target-Control-with-Minimal-Mediators.git.

A Deep Network Model on Dynamic Functional Connectivity With Applications to Gender Classification and Intelligence Prediction

Increasing evidence has suggested that the dynamic properties of functional brain networks are related to individual behaviors and cognition traits. However, current fMRI-based approaches mostly focus on statistical characteristics of the windowed correlation time course, potentially overlooking subtle time-varying patterns in dynamic functional connectivity (dFC). Here, we proposed the use of an end-to-end deep learning model that combines the convolutional neural network (CNN) and long short-term memory (LSTM) network to capture temporal and spatial features of functional connectivity sequences simultaneously. The results on a large cohort (Human Connectome Project, n = 1,050) demonstrated that our model could achieve a high classification accuracy of about 93% in a gender classification task and prediction accuracies of 0.31 and 0.49 (Pearson's correlation coefficient) in fluid and crystallized intelligence prediction tasks, significantly outperforming previously reported models. Furthermore, we demonstrated that our model could effectively learn spatiotemporal dynamics underlying dFC with high statistical significance based on the null hypothesis estimated using surrogate data. Overall, this study suggests the advantages of a deep learning model in making full use of dynamic information in resting-state functional connectivity, and highlights the potential of time-varying connectivity patterns in improving the prediction of individualized characterization of demographics and cognition traits.

Disrupted brain network dynamics and cognitive functions in methamphetamine use disorder: insights from EEG microstates

BACKGROUND

Dysfunction in brain network dynamics has been found to correlate with many psychiatric disorders. However, there is limited research regarding resting electroencephalogram (EEG) brain network and its association with cognitive process for patients with methamphetamine use disorder (MUD). This study aimed at using EEG microstate analysis to determine whether brain network dynamics in patients with MUD differ from those of healthy controls (HC).

METHODS

A total of 55 MUD patients and 27 matched healthy controls were included for analysis. The resting brain activity was recorded by 64-channel electroencephalography. EEG microstate parameters and intracerebral current sources of each EEG microstate were compared between the two groups. Generalized linear regression model was used to explore the correlation between significant microstates with drug history and cognitive functions.

RESULTS

MUD patients showed lower mean durations of the microstate classes A and B, and a higher global explained variance of the microstate class C. Besides, MUD patients presented with different current density power in microstates A, B, and C relative to the HC. The generalized linear model showed that MA use frequency is negatively correlated with the MMD of class A. Further, the generalized linear model showed that MA use frequency, scores of Two-back task, and the error rate of MA word are correlated with the MMD and GEV of class B, respectively.

CONCLUSIONS

Intracranial current source densities of resting EEG microstates are disrupted in MUD patients, hence causing temporal changes in microstate topographies, which are correlated with attention bias and history of drug use.

Functional Neuroimaging in the New Era of Big Data

The field of functional neuroimaging has substantially advanced as a big data science in the past decade, thanks to international collaborative projects and community efforts. Here we conducted a literature review on functional neuroimaging, with focus on three general challenges in big data tasks: data collection and sharing, data infrastructure construction, and data analysis methods. The review covers a wide range of literature types including perspectives, database descriptions, methodology developments, and technical details. We show how each of the challenges was proposed and addressed, and how these solutions formed the three core foundations for the functional neuroimaging as a big data science and helped to build the current data-rich and data-driven community. Furthermore, based on our review of recent literature on the upcoming challenges and opportunities toward future scientific discoveries, we envisioned that the functional neuroimaging community needs to advance from the current foundations to better data integration infrastructure, methodology development toward improved learning capability, and multi-discipline translational research framework for this new era of big data.

Temporal Variability of Cortical Gyral-Sulcal Resting State Functional Activity Correlates With Fluid Intelligence

The human cerebral cortex is highly convoluted as convex gyri and concave sulci. In the past decades, extensive studies have consistently revealed substantial differences between gyri and sulci in terms of genetics, anatomy, morphology, axonal fiber connections, and function. Although interesting findings have been reported to date to elucidate the functional difference between gyri and sulci, the temporal variability of functional activity, which could explain individual differences in learning and higher-order cognitive functions, and as well as differences in gyri and sulci, remains to be explored. The present study explored the temporal variability of cortical gyral-sulcal resting state functional activity and its association with fluid intelligence measures on the Human Connectome Project dataset. We found that the temporal variance of resting state fMRI BOLD signal was significantly larger in gyri than in sulci. We also found that the temporal variability of certain regions including middle frontal cortex, inferior parietal lobe and visual cortex was positively associated with fluid intelligence. Moreover, those regions were predominately located in gyri rather than in sulci. This study reports initial evidence for temporal variability difference of functional activity between gyri and sulci, and its association with fluid intelligence measures, and thus provides novel insights to understand the mechanism and functional relevance of gyri and sulci.

Discovering and characterizing dynamic functional brain networks in task FMRI

Many existing studies for the mapping of function brain networks impose an implicit assumption that the networks' spatial distributions are constant over time. However, the latest research reports reveal that functional brain networks are dynamical and have time-varying spatial patterns. Furthermore, how these functional networks evolve over time has not been elaborated and explained in sufficient details yet. In this paper, we aim to discover and characterize the dynamics of functional brain networks via a windowed group-wise dictionary learning and sparse coding approach. First, we aggregated the sampled subjects' fMRI signals into one big data matrix, and learned a common dictionary for all individuals via a group-wise dictionary learning step. Second, we obtained the dynamic time-varying functional networks by using the windowed time-varying sparse coding approach. Experimental results demonstrated that our windowed group-wise dictionary learning and sparse coding method can effectively detect the task-evoked networks and also characterize how these networks evolve over time. This work sheds novel insights on the dynamics mechanism of functional brain networks.