Mental disorders are among the leading causes of disability worldwide. The first step in treating these conditions is to obtain an accurate diagnosis, but the absence of established clinical tests makes this task challenging. Machine learning algorithms can provide a possible solution to this problem, as we describe in this work. We present a method for the automatic diagnosis of mental disorders based on the matrix of connections obtained from EEG time series and deep learning. We show that our approach can classify patients with Alzheimer's disease and schizophrenia with a high level of accuracy. The comparison with the traditional cases, that use raw EEG time series, shows that our method provides the highest precision. Therefore, the application of deep neural networks on data from brain connections is a very promising method to the diagnosis of neurological disorders.
Circadian rhythms synchronize a variety of physiological processes ranging from neural activity and hormone secretion to sleep cycles and feeding habits. Despite significant diurnal variation, time-of-day (TOD) is rarely recorded or analyzed in human brain research. Moreover, sleep-wake patterns, diurnal preferences, and daytime alertness vary across individuals, known as sleep chronotypes. Here, we performed graph-theory network analysis on resting-state functional MRI (rs-fMRI) data to explore topological differences in whole-brain functional networks between morning and evening sessions (TOD effect), and between extreme morning-type and evening-type chronotypes. To that end, 62 individuals (31 extreme morning, 31 evening-type) underwent two fMRI sessions: about 1 hour after the wake-up time (morning), and 10 hours thereafter, scheduled in accord with their declared habitual sleep-wake pattern. TOD significantly altered functional connectivity (FC) patterns, but there was no significant difference in chronotypic categories. Compared to the morning session, we found relatively increased small-worldness, modularity, assortativity, and synchronization in the evening session, indicating more efficient functional topology. Local measures were changed during the day predominantly across the areas involved in somatomotor, ventral attention, as well as default mode networks. Also, connectivity and hub analyses showed that the somatomotor, ventral attention, and visual networks are the most densely-connected brain areas in both sessions, respectively, with the first being more active in the evening session and the two latter in the morning session. Collectively, these findings suggest TOD can impact classic analyses used in human neuroimaging such as functional connectivity, and should be recorded and included in the analysis of functional neuroimaging data.
This bibliometric review summarised the research trends and analysed research areas in multiple sclerosis (MS) over the last decade. The documents containing the term "multiple sclerosis" in the article title were retrieved from the Scopus database. We found a total of 18003 articles published in journals in the English language between 2012 and 2021. The emerging keywords identified utilising the enhanced strategic diagram were "covid-19", "teriflunomide", "clinical trial", "microglia", "b cells", "myelin", "brain", "white matter", "functional connectivity", "pain", "employment", "health-related quality of life", "meta-analysis" and "comorbidity". In conclusion, this study demonstrates the tremendous growth of MS literature worldwide, which is expected to grow more than double during the next decade especially in the identified emerging topics.
The study of functional brain connectivity (FC) is important for understanding the underlying mechanisms of many psychiatric disorders. Many recent analyses adopt graph convolutional networks, to study non-linear interactions between functionally-correlated states. However, although patterns of brain activation are known to be hierarchically organised in both space and time, many methods have failed to extract powerful spatio-temporal features. To overcome those challenges, and improve understanding of long-range functional dynamics, we translate an approach, from the domain of skeleton-based action recognition, designed to model interactions across space and time. We evaluate this approach using the Human Connectome Project (HCP) dataset on sex classification and fluid intelligence prediction. To account for subject topographic variability of functional organisation, we modelled functional connectomes using multi-resolution dual-regressed (subject-specific) ICA nodes. Results show a prediction accuracy of 94.4% for sex classification (an increase of 6.2% compared to other methods), and an improvement of correlation with fluid intelligence of 0.325 vs 0.144, relative to a baseline model that encodes space and time separately. Results suggest that explicit encoding of spatio-temporal dynamics of brain functional activity may improve the precision with which behavioural and cognitive phenotypes may be predicted in the future.
Sleep stage classification is essential for sleep assessment and disease diagnosis. Although previous attempts to classify sleep stages have achieved high classification performance, several challenges remain open: 1) How to effectively utilize time-varying spatial and temporal features from multi-channel brain signals remains challenging. Prior works have not been able to fully utilize the spatial topological information among brain regions. 2) Due to the many differences found in individual biological signals, how to overcome the differences of subjects and improve the generalization of deep neural networks is important. 3) Most deep learning methods ignore the interpretability of the model to the brain. To address the above challenges, we propose a multi-view spatial-temporal graph convolutional networks (MSTGCN) with domain generalization for sleep stage classification. Specifically, we construct two brain view graphs for MSTGCN based on the functional connectivity and physical distance proximity of the brain regions. The MSTGCN consists of graph convolutions for extracting spatial features and temporal convolutions for capturing the transition rules among sleep stages. In addition, attention mechanism is employed for capturing the most relevant spatial-temporal information for sleep stage classification. Finally, domain generalization and MSTGCN are integrated into a unified framework to extract subject-invariant sleep features. Experiments on two public datasets demonstrate that the proposed model outperforms the state-of-the-art baselines.
A large body of literature has shown the substantial inter-regional functional connectivity in the mammal brain. One important property remaining un-studied is the cross-time interareal connection. This paper serves to provide a tool to characterize the cross-time functional connectivity. The method is extended from the temporal embedding based brain temporal coherence analysis. Both synthetic data and in-vivo data were used to evaluate the various properties of the cross-time functional connectivity matrix, which is also called the cross-regional temporal coherence matrix.
Emerging evidence showed that major depressive disorder (MDD) is associated with disruptions of brain structural and functional networks, rather than impairment of isolated brain region. Thus, connectome-based models capable of predicting the depression severity at the individual level can be clinically useful. Here, we applied a machine-learning approach to predict the severity of depression using resting-state networks derived from source-reconstructed Electroencephalography (EEG) signals. Using regression models and three independent EEG datasets (N=328), we tested whether resting state functional connectivity could predict individual depression score. On the first dataset, results showed that individuals scores could be reasonably predicted (r=0.61, p=4 x 10-18) using intrinsic functional connectivity in the EEG alpha band (8-13 Hz). In particular, the brain regions which contributed the most to the predictive network belong to the default mode network. We further tested the predictive potential of the established model by conducting two external validations on (N1=53, N2=154). Results showed high significant correlations between the predicted and the measured depression scale scores (r1= 0.49, r2=0.37, p<0.001). These findings lay the foundation for developing a generalizable and scientifically interpretable EEG network-based markers that can ultimately support clinicians in a biologically-based characterization of MDD.
Propofol, when administered for general anesthesia, induces oscillatory dynamic brain states that are thought to underlie the drug's pharmacological effects. Despite the elucidation of propofol's mechanisms of action at the molecular level, its effects on neural circuits and overall cortical functioning, which eventually lead to unconsciousness, are still unclear. To identify possible mechanisms, the spatial-temporal patterns of functional connectivity established among specialized cortical areas in anesthetized subjects need to be described. Within this context, the present research involved the analysis of dense sub-dural ECoG electrode array recordings from macaques under propofol anesthetic induction. Granger causality methodology was used to infer functional connectivity interactions in five physiological frequency bands serially over time, every five seconds throughout the experiment. The time-resolved networks obtained permitted us to observe the unfolding of the anesthetic induction and compare the networks obtained under different experimental conditions. About one minute after administering propofol, functional connectivity started to increase for 4-5 minutes, then decreased until the LOC was achieved. A predominant Granger causality flow from the occipital and temporal areas towards the frontal and parietal regions was also evidenced during the transition. During general anesthesia, the local connectivity of the occipital lobe increased, as did the interactions between the occipital and temporal lobes. Conversely, the functional connectivity from the frontal and parietal lobes toward the temporal and occipital regions was mainly impaired. The research is one of the first studies to describe the dynamics of the functional connectivity during the transitional state that precedes the LOC.
Synaptic plasticity and neuron cross-talk are some of the important key mechanisms underlying formation of dynamic clusters of active neurons. The essence of this study is to model and decipher the mechanism of emergence of a task-specific functional connectivity among a population of neurons. We have used our proposed neuron activity pattern (NAP) model to define an assorted range of interactions and simulated across a 2D lattice with two-state (firing/non-firing) neurons. We observed the emergence of scale-free, hierarchically organized ordered patterns of active neurons, that we call as functional cortical patterns (FCPs), only at the near-critical phase transition. We have done extensive topological characterization of FCPs and tested its congruency with the functional brain networks obtained from the empirical electrophysiological data of a visual stimulus task. Our results of network theory attributes, fractal analysis and functional cartography have confirmed the transitioning effect while generation of FCPs. This gives us strong implication that the functional neuronal system supports far-from-equilibrium dynamics upon receiving a stimulus. Our investigation for the long, critical and short-ranged interactions has lead to an interpretation that near-critical transition phase is a spectrum of critical temperatures (coupling strengths) being affected by the distance between the neurons. The range of interaction among neurons plays an important role in defining the functional severity of the neuronal circuitry. We propose that interaction range as a function of coupling strength drives connectivity in an augmenting fashion as we observed an increase in coupling strength from short to long-range interactions, among the population of neurons. This gives us insight towards the intensity of cognitive behaviour, which is attained by multiple stimulus attempts.
Brain functional connectivity (FC) reveals biomarkers for identification of various neuropsychiatric disorders. Recent application of deep neural networks (DNNs) to connectome-based classification mostly relies on traditional convolutional neural networks using input connectivity matrices on a regular Euclidean grid. We propose a graph deep learning framework to incorporate the non-Euclidean information about graph structure for classifying functional magnetic resonance imaging (fMRI)-derived brain networks in major depressive disorder (MDD). We design a novel graph autoencoder (GAE) architecture based on the graph convolutional networks (GCNs) to embed the topological structure and node content of large-sized fMRI networks into low-dimensional latent representations. In network construction, we employ the Ledoit-Wolf (LDW) shrinkage method to estimate the high-dimensional FC metrics efficiently from fMRI data. We consider both supervised and unsupervised approaches for the graph embedding learning. The learned embeddings are then used as feature inputs for a deep fully-connected neural network (FCNN) to discriminate MDD from healthy controls. Evaluated on two resting-state fMRI (rs-fMRI) MDD datasets, results show that the proposed GAE-FCNN model significantly outperforms several state-of-the-art methods for brain connectome classification, achieving the best accuracy using the LDW-FC edges as node features. The graph embeddings of fMRI FC networks learned by the GAE also reveal apparent group differences between MDD and HC. Our new framework demonstrates feasibility of learning graph embeddings on brain networks to provide discriminative information for diagnosis of brain disorders.
We address a biophysical network dynamical model to study how the modulation of dopamine (DA) activity and related N-methyl-d-aspartate (NMDA) glutamate receptor activity as well as the emerging Pre-Frontal Cortex (PFC) functional connectivity network (FCN) affect inhibitory cognitive function in schizophrenia in an antisaccade task. The values of the model parameters and the topology of the PFC-FCN were estimated by minimizing the differences between simulations and the observed distributions of reaction times (RT) during the performance of the antisaccade task in 30 patients with schizophrenia and 30 healthy controls. We show that the proposed model approximates remarkably well the predicted prefrontal cortical DA hypo-activity and the related NMDA receptor hypo-function as well as the FCN dysconnection pattern that are considered as the major etio-pathological hypotheses to explain cognitive deficits in schizophrenia.
We consider the problem of interpretable network representation learning for samples of network-valued data. We propose the Principal Component Analysis for Networks (PCAN) algorithm to identify statistically meaningful low-dimensional representations of a network sample via subgraph count statistics. The PCAN procedure provides an interpretable framework for which one can readily visualize, explore, and formulate predictive models for network samples. We furthermore introduce a fast sampling-based algorithm, sPCAN, which is significantly more computationally efficient than its counterpart, but still enjoys advantages of interpretability. We investigate the relationship between these two methods and analyze their large-sample properties under the common regime where the sample of networks is a collection of kernel-based random graphs. We show that under this regime, the embeddings of the sPCAN method enjoy a central limit theorem and moreover that the population level embeddings of PCAN and sPCAN are equivalent. We assess PCAN's ability to visualize, cluster, and classify observations in network samples arising in nature, including functional connectivity network samples and dynamic networks describing the political co-voting habits of the U.S. Senate. Our analyses reveal that our proposed algorithm provides informative and discriminatory features describing the networks in each sample. The PCAN and sPCAN methods build on the current literature of network representation learning and set the stage for a new line of research in interpretable learning on network-valued data. Publicly available software for the PCAN and sPCAN methods are available at https://www.github.com/jihuilee/.
Edge time series are increasingly used in brain functional imaging to study the node functional connectivity (nFC) dynamics at the finest temporal resolution while avoiding sliding windows. Here, we lay the mathematical foundations for the edge-centric analysis of neuroimaging time series, explaining why a few high-amplitude cofluctuations drive the nFC across datasets. Our exposition also constitutes a critique of the existing edge-centric studies, showing that their main findings can be derived from the nFC under a static null hypothesis that disregards temporal correlations. Testing the analytic predictions on functional MRI data from the Human Connectome Project confirms that the nFC can explain most variation in the edge FC matrix, the edge communities, the large cofluctuations, and the corresponding spatial patterns. We encourage the use of dynamic measures in future research, which exploit the temporal structure of the edge time series and cannot be replicated by static null models.
The objective of this study is to derive functional networks for the autism spectrum disorder (ASD) population using the group ICA and dictionary learning model together and to classify ASD and typically developing (TD) participants using the functional connectivity calculated from the derived functional networks. In our experiments, the ASD functional networks were derived from resting-state functional magnetic resonance imaging (rs-fMRI) data. We downloaded a total of 120 training samples, including 58 ASD and 62 TD participants, which were obtained from the public repository: Autism Brain Imaging Data Exchange I (ABIDE I). Our methodology and results have five main parts. First, we utilize a group ICA model to extract functional networks from the ASD group and rank the top 20 regions of interest (ROIs). Second, we utilize a dictionary learning model to extract functional networks from the ASD group and rank the top 20 ROIs. Third, we merged the 40 selected ROIs from the two models together as the ASD functional networks. Fourth, we generate three corresponding masks based on the 20 selected ROIs from group ICA, the 20 ROIs selected from dictionary learning, and the 40 combined ROIs selected from both. Finally, we extract ROIs for all training samples using the above three masks, and the calculated functional connectivity was used as features for ASD and TD classification. The classification results showed that the functional networks derived from ICA and dictionary learning together outperform those derived from a single ICA model or a single dictionary learning model.
Individual grip force profiling of bimanual simulator task performance of experts and novices using a robotic control device designed for endoscopic surgery permits defining benchmark criteria that tell true expert task skills from the skills of novices or trainee surgeons. Grip force variability in a true expert and a complete novice executing a robot assisted surgical simulator task reveal statistically significant differences as a function of task expertise. Here we show that the skill specific differences in local grip forces are predicted by the output metric of a Self Organizing neural network Map (SOM) with a bio inspired functional architecture that maps the functional connectivity of somatosensory neural networks in the primate brain.
Mild cognitive impairment (MCI) is a high-risk dementia condition which progresses to probable Alzheimer's disease (AD) at approximately 10% to 15% per year. Characterization of group-level differences between two subtypes of MCI - stable MCI (sMCI) and progressive MCI (pMCI) is the key step to understand the mechanisms of MCI progression and enable possible delay of transition from MCI to AD. Functional connectivity (FC) is considered as a promising way to study MCI progression since which may show alterations even in preclinical stages and provide substrates for AD progression. However, the representative FC patterns during AD development for different clinical groups, especially for sMCI and pMCI, have been understudied. In this work, we integrated autoencoder and multi-class classification into a single deep model and successfully learned a set of clinical group related feature vectors. Specifically, we trained two non-linear mappings which realized the mutual transformations between original FC space and the feature space. By mapping the learned clinical group related feature vectors to the original FC space, representative FCs were constructed for each group. Moreover, based on these feature vectors, our model achieves a high classification accuracy - 68% for multi-class classification (NC vs SMC vs sMCI vs pMCI vs AD).
Functional connectivity (FC) between regions of the brain can be assessed by the degree of temporal correlation measured with functional neuroimaging modalities. Based on the fact that these connectivities build a network, graph-based approaches for analyzing the brain connectome have provided insights into the functions of the human brain. The development of graph neural networks (GNNs) capable of learning representation from graph structured data has led to increased interest in learning the graph representation of the brain connectome. Although recent attempts to apply GNN to the FC network have shown promising results, there is still a common limitation that they usually do not incorporate the dynamic characteristics of the FC network which fluctuates over time. In addition, a few studies that have attempted to use dynamic FC as an input for the GNN reported a reduction in performance compared to static FC methods, and did not provide temporal explainability. Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention. Specifically, a temporal sequence of brain graphs is input to the STAGIN to obtain the dynamic graph representation, while novel READOUT functions and the Transformer encoder provide spatial and temporal explainability with attention, respectively. Experiments on the HCP-Rest and the HCP-Task datasets demonstrate exceptional performance of our proposed method. Analysis of the spatio-temporal attention also provide concurrent interpretation with the neuroscientific knowledge, which further validates our method. Code is available at https://github.com/egyptdj/stagin
With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.
Targeted electrical stimulation of the brain perturbs neural networks and modulates their rhythmic activity both at the site of stimulation and at remote brain regions. Understanding, or even predicting, this neuromodulatory effect is crucial for any therapeutic use of brain stimulation. To this end, we analyzed the stimulation responses in 131 stimulation sessions across 66 patients with focal epilepsy recorded through intracranial EEG (iEEG). We considered functional and structural connectivity features as predictors of the response at every iEEG contact. Taking advantage of multiple recordings over days, we also investigated how slow changes in interictal functional connectivity (FC) ahead of the stimulation relate to stimulation responses. The results reveal that, indeed, this long-term variability of FC exhibits strong association with the stimulation-induced increases in delta and theta band power. Furthermore, we show through cross-validation that long-term variability of FC improves prediction of responses above the performance of spatial predictors alone. These findings can enhance the patient-specific design of effective neuromodulatory protocols for therapeutic interventions.
Song appreciation involves a broad range of mental processes, and different neural networks may be activated by different song types. The aim of the present study was to show differential functional connectivity of the prefrontal cortices while listening to breakup and rebellious songs. Breakup songs describe romance and longing, whereas rebellious songs convey criticism of conventional ideas or socio-cultural norms. We hypothesized that the medial and lateral prefrontal cortices may interact with different brain regions in response to these two song types. Functional magnetic resonance imaging data of fifteen participants were collected while they were listening to two complete breakup songs and two complete rebellious songs currently popular in Taiwan. The results showed that listening to the breakup songs, compared to the rebellious songs, enhanced the coupling between the medial prefrontal cortex and several emotion-related regions, including the thalamus, caudate, amygdala, hippocampus, middle orbitofrontal cortex, and right inferior frontal gyrus. This coupling may reflect the neural processes of pain empathy, reward processing, compassion, and reappraisal in response to longing and sorrow expressed by the breakup songs. Compared to the breakup songs, listening to the rebellious songs was associated with enhanced coupling between subregions in the prefrontal and orbitofrontal cortices. These areas might work in concert to support re-evaluation of conventional ideas or socio-cultural norms as suggested by the rebellious songs. This study advanced our understanding of the integration of brain functions while processing complex information.