Making group inferences using sparse representation of resting-state functional mRI data with application to sleep deprivation

Sleep deprivation changes frequency-specific functional organization of the resting human brain

Previous resting-state functional magnetic resonance imaging (rs-fMRI) studies have widely explored the temporal connection changes in the human brain following long-term sleep deprivation (SD). However, the frequency-specific topological properties of sleep-deprived functional networks remain virtually unclear. In this study, thirty-seven healthy male subjects underwent resting-state fMRI during rested wakefulness (RW) and after 36 hours of SD, and we examined frequency-specific spectral connection changes (0.01-0.08 Hz, interval = 0.01 Hz) caused by SD. First, we conducted a multivariate pattern analysis combining linear SVM classifiers with a robust feature selection algorithm, and the results revealed that accuracies of 74.29%-84.29% could be achieved in the classification between RW and SD states in leave-one-out cross-validation at different frequency bands, moreover, the spectral connection at the lowest and highest frequency bands exhibited higher discriminative power. Connection involving the cingulo-opercular network increased most, while connection involving the default-mode network decreased most following SD. Then we performed a graph-theoretic analysis and observed reduced low-frequency modularity and high-frequency global efficiency in the SD state. Moreover, hub regions, which were primarily situated in the cerebellum and the cingulo-opercular network after SD, exhibited high discriminative power in the aforementioned classification consistently. The findings may indicate the frequency-dependent effects of SD on the functional network topology and its efficiency of information exchange, providing new insights into the impact of SD on the human brain.

Mental fatigue assessment by an arbitrary channel EEG based on morphological features and LSTM-CNN

In order to achieve more sensitive mental fatigue assessment (MFA) based on an arbitrary channel EEG, this study proposed a series of feature extraction methods that combine mathematical morphology (MM), as well as an LSTM-CNN architecture. Firstly, 37 subjects had their resting-state EEGs collected at rested wakefulness (RW) and after 24 h of sleep deprivation (SD) using a 30-channel EEG acquisition device, the RW and SD groups were regarded as the negative and positive groups of mental fatigue, respectively, and the EEG collection were further categorized into two conditions: eye-opened state (EO) and eye-closed state (EC). Then, since MM can reflect the morphological characteristics of EEG rhythms and their potentials relatively independently of the time-frequency analysis and phase calculation, the MM methods were found to better reflect the mental fatigue after SD statistically, whether for single features (ANOVA: p<0.000001), multiple features (clustering by K-means, t-test: p<0.01), or time series feature spaces (calculating CD, t-test: p<0.01) of a single channel. Finally, the LSTM-CNN enhanced the generalization ability when dealing with different single-channel EEG by combining GRUs with convolutional layers: comparing the AUCs of different architectures for MFA based on an arbitrary channel, LSTM-CNN (0.992) > LSTM network (0.94) > CNN (0.831) > MLP (0.754). Moreover, the use of MM also improved the accuracy of analyzed architectures, and the true/false positive rate (TPR/FPR) of the LSTM-CNN architecture for MFA based on an arbitrary channel reached 97.024 %/3.497 %, which provided a feasible solution for the arbitrary channel EEG-based MFA.

Multi-head attention-based masked sequence model for mapping functional brain networks

The investigation of functional brain networks (FBNs) using task-based functional magnetic resonance imaging (tfMRI) has gained significant attention in the field of neuroimaging. Despite the availability of several methods for constructing FBNs, including traditional methods like GLM and deep learning methods such as spatiotemporal self-attention mechanism (STAAE), these methods have design and training limitations. Specifically, they do not consider the intrinsic characteristics of fMRI data, such as the possibility that the same signal value at different time points could represent different brain states and meanings. Furthermore, they overlook prior knowledge, such as task designs, during training. This study aims to overcome these limitations and develop a more efficient model by drawing inspiration from techniques in the field of natural language processing (NLP). The proposed model, called the Multi-head Attention-based Masked Sequence Model (MAMSM), uses a multi-headed attention mechanism and mask training approach to learn different states corresponding to the same voxel values. Additionally, it combines cosine similarity and task design curves to construct a novel loss function. The MAMSM was applied to seven task state datasets from the Human Connectome Project (HCP) tfMRI dataset. Experimental results showed that the features acquired by the MAMSM model exhibit a Pearson correlation coefficient with the task design curves above 0.95 on average. Moreover, the model can extract more meaningful networks beyond the known task-related brain networks. The experimental results demonstrated that MAMSM has great potential in advancing the understanding of functional brain networks.

Constrained CPD of Complex-Valued Multi-Subject fMRI Data via Alternating Rank-R and Rank-1 Least Squares

Complex-valued shift-invariant canonical polyadic decomposition (CPD) under a spatial phase sparsity constraint (pcsCPD) shows excellent separation performance when applied to band-pass filtered complex-valued multi-subject fMRI data. However, some useful information may also be eliminated when using a band-pass filter to suppress unwanted noise. As such, we propose an alternating rank- R and rank-1 least squares optimization to relax the CPD model. Based upon this optimization method, we present a novel constrained CPD algorithm with temporal shift-invariance and spatial sparsity and orthonormality constraints. More specifically, four steps are conducted until convergence for each iteration of the proposed algorithm: 1) use rank- R least-squares fit under spatial phase sparsity constraint to update shared spatial maps after phase de-ambiguity; 2) use orthonormality constraint to minimize the cross-talk between shared spatial maps; 3) update the aggregating mixing matrix using rank- R least-squares fit; 4) utilize shift-invariant rank-1 least-squares on a series of rank-1 matrices reconstructed by each column of the aggregating mixing matrix to update shared time courses, and subject-specific time delays and intensities. The experimental results of simulated and actual complex-valued fMRI data show that the proposed algorithm improves the estimates for task-related sensorimotor and auditory networks, compared to pcsCPD and tensorial spatial ICA. The proposed alternating rank- R and rank-1 least squares optimization is also flexible to improve CPD-related algorithm using alternating least squares.

Impact of spaceflight stressors on behavior and cognition: A molecular, neurochemical, and neurobiological perspective

The response of the human body to multiple spaceflight stressors is complex, but mounting evidence implicate risks to CNS functionality as significant, able to threaten metrics of mission success and longer-term behavioral and neurocognitive health. Prolonged exposure to microgravity, sleep disruption, social isolation, fluid shifts, and ionizing radiation have been shown to disrupt mechanisms of homeostasis and neurobiological well-being. The overarching goal of this review is to document the existing evidence of how the major spaceflight stressors, including radiation, microgravity, isolation/confinement, and sleep deprivation, alone or in combination alter molecular, neurochemical, neurobiological, and plasma metabolite/lipid signatures that may be linked to operationally-relevant behavioral and cognitive performance. While certain brain region-specific and/or systemic alterations titrated in part with neurobiological outcome, variations across model systems, study design, and the conspicuous absence of targeted studies implementing combinations of spaceflight stressors, confounded the identification of specific signatures having direct relevance to human activities in space. Summaries are provided for formulating new research directives and more predictive readouts of portending change in neurobiological function.

Discriminating mild traumatic brain injury using sparse dictionary learning of functional network dynamics

Mild traumatic brain injury (mTBI) is usually caused by a bump, blow, or jolt to the head or penetrating head injury, and carries the risk of inducing cognitive disorders. However, identifying the biomarkers for the diagnosis of mTBI is challenging as evident abnormalities in brain anatomy are rarely found in patients with mTBI. In this study, we tested whether the alteration of functional network dynamics could be used as potential biomarkers to better diagnose mTBI. We propose a sparse dictionary learning framework to delineate spontaneous fluctuation of functional connectivity into the subject-specific time-varying evolution of a set of overlapping group-level sparse connectivity components (SCCs) based on the resting-state functional magnetic resonance imaging (fMRI) data from 31 mTBI patients in the early acute phase (<3 days postinjury) and 31 healthy controls (HCs). The identified SCCs were consistently distributed in the cohort of subjects without significant inter-group differences in connectivity patterns. Nevertheless, subject-specific temporal expression of these SCCs could be used to discriminate patients with mTBI from HCs with a classification accuracy of 74.2% (specificity 64.5% and sensitivity 83.9%) using leave-one-out cross-validation. Taken together, our findings indicate neuroimaging biomarkers for mTBI individual diagnosis based on the temporal expression of SCCs underlying time-resolved functional connectivity.

Modeling and augmenting of fMRI data using deep recurrent variational auto-encoder

Objective. Recently, deep learning models have been successfully applied in functional magnetic resonance imaging (fMRI) modeling and associated applications. However, there still exist at least two challenges. Firstly, due to the lack of sufficient data, deep learning models tend to suffer from overfitting in the training process. Secondly, it is still challenging to model the temporal dynamics from fMRI, due to that the brain state is continuously changing over scan time. In addition, existing methods rarely studied and applied fMRI data augmentation.Approach. In this work, we construct a deep recurrent variational auto-encoder (DRVAE) that combined variational auto-encoder and recurrent neural network, aiming to address all of the above mentioned challenges. The encoder of DRVAE can extract more generalized temporal features from assumed Gaussian distribution of input data, and the decoder of DRVAE can generate new data to increase training samples and thus partially relieve the overfitting issue. The recurrent layers in DRVAE are designed to effectively model the temporal dynamics of functional brain activities. LASSO (least absolute shrinkage and selection operator) regression is applied on the temporal features and input fMRI data to estimate the corresponding spatial networks.Main results. Extensive experimental results on seven tasks from HCP dataset showed that the DRVAE and LASSO framework can learn meaningful temporal patterns and spatial networks from both real data and generated data. The results on group-wise data and single subject suggest that the brain activities may follow certain distribution. Moreover, we applied DRVAE on four resting state fMRI datasets from ADHD-200 for data augmentation, and the results showed that the classification performances on augmented datasets have been considerably improved.Significance. The proposed method can not only derive meaningful temporal features and spatial networks from fMRI, but also generate high-quality new data for fMRI data augmentation and associated applications.

Relation of Decreased Functional Connectivity Between Left Thalamus and Left Inferior Frontal Gyrus to Emotion Changes Following Acute Sleep Deprivation

Objective: The thalamus is a key node for sleep-wake pathway gate switching during acute sleep deprivation (ASD), and studies have shown that it plays a certain role in emotion changes. However, there are no studies on the association between the thalamus and emotion changes in ASD. In this study, we used resting-state functional magnetic resonance imaging (R-fMRI) to explore whether changes in the functional connections between the thalamus and other brain regions are related to emotion changes and further explored the function of the thalamus under total ASD conditions.

Method: Thirty healthy, right-handed adult men underwent emotional assessment according to the Profile of Mood States Scale and R-fMRI scans before and after ASD. The correlations between changes in functional connectivity between the thalamus and other brain regions and emotion changes were then studied.

Results: Positive emotions and psychomotor performance were reduced, and negative emotions were increased following ASD. The functional connections between the left thalamus and left middle temporal gyrus, left inferior frontal gyrus, right thalamus, right inferior temporal gyrus, left middle temporal pole gyrus, right calcarine, left cuneus, left rectus and left medial superior frontal gyrus were significantly altered. Decreased functional connectivity between left thalamus and left inferior frontal gyrus related to emotion changes following ASD.

Conclusion: This study finds that functional changes in the thalamus are associated with emotion changes during ASD, suggesting that the left thalamus probably plays an essential role in emotion changes under ASD conditions.

Shift-Invariant Canonical Polyadic Decomposition of Complex-Valued Multi-Subject fMRI Data With a Phase Sparsity Constraint

Canonical polyadic decomposition (CPD) of multi-subject complex-valued fMRI data can be used to provide spatially and temporally shared components among groups with both magnitude and phase information. However, the CPD model is not well formulated due to the large subject variability in the spatial and temporal modalities, as well as the high noise level in complex-valued fMRI data. Considering that the shift-invariant CPD can model temporal variability across subjects, we propose to further impose a phase sparsity constraint on the shared spatial maps to denoise the complex-valued components and to model the inter-subject spatial variability as well. More precisely, subject-specific time delays are first estimated for the complex-valued shared time courses in the framework of real-valued shift-invariant CPD. Source phase sparsity is then imposed on the complex-valued shared spatial maps. A smoothed l₀ norm is specifically used to reduce voxels with large phase values after phase de-ambiguity based on the small phase characteristic of BOLD-related voxels. The results from both the simulated and experimental fMRI data demonstrate improvements of the proposed method over three complex-valued algorithms, namely, tensor-based spatial ICA, shift-invariant CPD and CPD without spatiotemporal constraints. When comparing with a real-valued algorithm combining shift-invariant CPD and ICA, the proposed method detects 178.7% more contiguous task-related activations.

Large-Scale Granger Causal Brain Network based on Resting-State fMRI data

The causal connections among small-scale regions based on resting-state fMRI data have been extensively studied and a lot of achievements have been demonstrated. However, the causal connection among large-scale regions was seldom discussed. In this paper, we applied global Granger causality analysis to construct the causal connections in the whole-brain network among 103 healthy subjects (33 M/66F, ages 20-23) based on a resting-state fMRI dataset. We further explored four large-scale cognitive networks which have been widely known: central executive network (CEN), default mode network (DMN), dorsal attention network (DAN) and salience network (SN). These four cognitive networks are particularly important for understanding higher cognitive functions and dysfunction. Based on the above research, Out-In degree were introduced to identify the driving and driven hubs. Studying the driving and driven hub of brain network is of great significance for assessing the functional mechanism of the brain network. There were 817 directed edges identified as significant among the 8010 possible causal connections; seven driving hubs and ten driven hubs were identified in the whole-brain network. In CEN, dorsolateral prefrontal cortex (DlPFC) and superior parietal cortex (SPC) were the driven and driving hubs, respectively; in DMN, they were posterior cingulate cortex (PCC) and medial prefrontal cortex (MPFC); in DAN, they were frontal eye fields (FEF) and intraparietal sulcus (IPS); and in SN, they were frontoinsular cortex (FIC) and medial frontal cortex (MFC). These findings may provide insights into our understanding of human brain function mechanisms and the diagnosis of brain diseases.

Manifold Learning of Dynamic Functional Connectivity Reliably Identifies Functionally Consistent Coupling Patterns in Human Brains

Most previous work on dynamic functional connectivity (dFC) has focused on analyzing temporal traits of functional connectivity (similar coupling patterns at different timepoints), dividing them into functional connectivity states and detecting their between-group differences. However, the coherent functional connectivity of brain activity among the temporal dynamics of functional connectivity remains unknown. In the study, we applied manifold learning of local linear embedding to explore the consistent coupling patterns (CCPs) that reflect functionally homogeneous regions underlying dFC throughout the entire scanning period. By embedding the whole-brain functional connectivity in a low-dimensional manifold space based on the Human Connectome Project (HCP) resting-state data, we identified ten stable patterns of functional coupling across regions that underpin the temporal evolution of dFC. Moreover, some of these CCPs exhibited significant neurophysiological meaning. Furthermore, we apply this method to HCP rsfMR and tfMRI data as well as sleep-deprivation data and found that the topological organization of these low-dimensional structures has high potential for predicting sleep-deprivation states (classification accuracy of 92.3%) and task types (100% identification for all seven tasks).In summary, this work provides a methodology for distilling coherent low-dimensional functional connectivity structures in complex brain dynamics that play an important role in performing tasks or characterizing specific states of the brain.

Dissociating individual connectome traits using low-rank learning

Intrinsic functional connectivity (FC) exhibits high variability across individuals, which may account for the diversity of cognitive and behavioural ability. This variability in connectivity could be attributed to individual-specific trait and inter-session state differences (intra-subject differences), as well as a small amount of noise. However, it is still a challenge to perform accurate identification of connectivity traits from FC. Here, we introduced a novel low-rank learning model to solve this problem with a new constraint item that could reduce intra-subject differences. The model could dissociate FC into a substrate (substrate) that delineates functional characteristics common across the population and connectivity traits that are expected to account for individual behavioural differences. Subsequently, we performed a sparse dictionary learning algorithm on the extracted connectivity traits and obtained a dictionary matrix, named connectivity dictionary. We could then predict cognitive behaviours, including fluid intelligence, oral reading recognition, grip strength and anger-aggression, more accurately using the connectivity dictionary than the original FC. The results reflect that we captured individual connectivity traits that more effectively represent cognitive behaviour. Moreover, we found that the functional substrate is significantly correlated with large-scale anatomical brain architecture, and individual differences in connectivity traits are constrained by the connectivity substrate. Our findings may advance our understanding of the relationships among anatomy, function, and behaviour.

Quantifying the Variability in Resting-State Networks

Recent precision functional mapping of individual human brains has shown that individual brain organization is qualitatively different from group average estimates and that individuals exhibit distinct brain network topologies. How this variability affects the connectivity within individual resting-state networks remains an open question. This is particularly important since certain resting-state networks such as the default mode network (DMN) and the fronto-parietal network (FPN) play an important role in the early detection of neurophysiological diseases like Alzheimer’s, Parkinson’s, and attention deficit hyperactivity disorder. Using different types of similarity measures including conditional mutual information, we show here that the backbone of the functional connectivity and the direct connectivity within both the DMN and the FPN does not vary significantly between healthy individuals for the AAL brain atlas. Weaker connections do vary however, having a particularly pronounced effect on the cross-connections between DMN and FPN. Our findings suggest that the link topology of single resting-state networks is quite robust if a fixed brain atlas is used and the recordings are sufficiently long—even if the whole brain network topology between different individuals is variable.

Structured Sparse Principal Components Analysis With the TV-Elastic Net Penalty

Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover the dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, PCA's interpretability remains limited. Indeed, the components produced by PCA are often noisy or exhibit no visually meaningful patterns. Furthermore, the fact that the components are usually non-sparse may also impede interpretation, unless arbitrary thresholding is applied. However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population. Recently, some alternatives to the standard PCA approach, such as sparse PCA (SPCA), have been proposed, their aim being to limit the density of the components. Nonetheless, sparsity alone does not entirely solve the interpretability problem in neuroimaging, since it may yield scattered and unstable components. We hypothesized that the incorporation of prior information regarding the structure of the data may lead to improved relevance and interpretability of brain patterns. We therefore present a simple extension of the popular PCA framework that adds structured sparsity penalties on the loading vectors in order to identify the few stable regions in the brain images that capture most of the variability. Such structured sparsity can be obtained by combining, e.g., and total variation (TV) penalties, where the TV regularization encodes information on the underlying structure of the data. This paper presents the structured SPCA (denoted SPCA-TV) optimization framework and its resolution. We demonstrate SPCA-TV's effectiveness and versatility on three different data sets. It can be applied to any kind of structured data, such as, e.g., -dimensional array images or meshes of cortical surfaces. The gains of SPCA-TV over unstructured approaches (such as SPCA and ElasticNet PCA) or structured approach (such as GraphNet PCA) are significant, since SPCA-TV reveals the variability within a data set in the form of intelligible brain patterns that are easier to interpret and more stable across different samples.