Enhancing Neurodegenerative Disease Diagnosis through Confidence-Driven Dynamic Spatio-Temporal Convolutional Network.

Emotion affects human being's health to a great extent and it attracts lots of attention recently. Objective measurements are necessary for identifying various emotion states. As a powerful technique on high temporal resolution, Electroencephalogram (EEG) provides an effective way to quantify emotion impersonally, especially uncovering the dynamic characteristics. The implementation of time window length is one popular method for extracting dynamic interactions in the brain network. In this paper, the effect of time window length is revealed on dynamic brain network investigation. A quantitative pipeline is proposed based on brain network extraction and community mining in this paper. The EEG data of healthy subjects are recorded under sadness, happiness and neutral emotions that induced through video stimulation. Since beta (13-30Hz) band EEG signals are believed to play important role in cognitive processing, this paper focuses on the beta band EEG signals. Phase locking value (PLV) was adopted to calculate the functional interactions among brain areas. A nonoverlapping time window was taken in to produce dynamic connections. As a comparison, the dynamic brain networks were extracted by the length of 2s and 5S sliding time windows respectively. Later, the Louvain algorithm was used to detect the communities. As the member of community changes over time, the stationarity is quantified to measure the evolution of the varying communities in the brain network. The preliminary results illustrated that significant difference exists among communities from the beta band EEG networks that derived from 2s and 5s time windows separately. It is suggested that the choice of sliding time window will affect the stationarity quantification of the dynamic evolution of the brain network under various emotional conditions. It is necessary to pay attention to the choice of time length window when uncovering dynamic brain network changes in the future.

Background Autism spectrum disorder (ASD) is characterized by aberrant functional brain connectivity and deficits in network dynamics. Transcranial direct current stimulation (tDCS) has emerged as a promising intervention with potential therapeutic effects; however, its effects on both static and dynamic functional brain network organization remained insufficiently understood. Methods A total of 42 children with ASD aged 4–6 years were enrolled and randomly assigned to either active tDCS or sham stimulation groups. Resting-state electroencephalography (EEG) data were acquired before and after the intervention. Low-order functional connectivity (LOFC) and high-order functional connectivity (HOFC) networks were constructed, followed by graph-theoretical analyses to assess clustering coefficient, characteristic path length, global efficiency, and local efficiency. Furthermore, state entropy was employed to evaluate dynamic network transitions between integrated and segregated states. Results Active tDCS was associated with increased LOFC strength in the delta, alpha, and beta bands, and more widespread increases in HOFC across all examined frequency bands. Changes in network topology were primarily observed in HOFC, with reductions in characteristic path length and increases in global and local efficiency, particularly in the delta and theta bands. Dynamic network analysis indicated that tDCS modulated state entropy at specific time scales in both LOFC and HOFC networks. These findings suggest shifts in functional coordination and temporal variability among the recorded regions. Behavioral measures exhibited a trend toward improvement in the active group; however, these changes were not the focus of the present analysis, and their relationship to neural modulation remains to be clarified in future work. Conclusions tDCS modulated functional interaction patterns and dynamic state characteristics among the recorded brain regions in children with ASD. These results provide preliminary neurophysiological evidence regarding the influence of tDCS on both static and dynamic network organization and highlight potential network-based markers to guide future individualized neuromodulation research. Further studies with larger samples and longitudinal follow-ups are needed to clarify the functional and clinical significance of these network-level changes.

Extensive studies focus on analyzing human brain functional connectivity from a network perspective, in which each network contains complex graph structures. Based on resting-state functional MRI (rs-fMRI) data, graph convolutional networks (GCNs) enable comprehensive mapping of brain functional connectivity (FC) patterns to depict brain activities. However, existing studies usually characterize static properties of the FC patterns, ignoring the time-varying dynamic information. In addition, previous GCN methods generally use fixed group-level (e.g., patients or controls) representation of FC networks, and thus, cannot capture subject-level FC specificity. To this end, we propose a Temporal-Adaptive GCN (TAGCN) framework that can not only take advantage of both spatial and temporal information using resting-state FC patterns and time-series but also explicitly characterize subject-level specificity of FC patterns. Specifically, we first segment each ROI-based time-series into multiple overlapping windows, then employ an adaptive GCN to mine topological information. We further model the temporal patterns for each ROI along time to learn the periodic brain status changes. Experimental results on 533 major depressive disorder (MDD) and health control (HC) subjects demonstrate that the proposed TAGCN outperforms several state-of-the-art methods in MDD vs. HC classification, and also can be used to capture dynamic FC alterations and learn valid graph representations.

The multilayer dynamic network model has been proposed as an effective method to understand the brain function. In particular, derived from the definition of clustering coefficient in static networks, the temporal clustering coefficient provides a direct measure of the topological stability of dynamic brain networks and shows potential in predicting altered brain functions. However, test-retest reliability and demographic-related effects on this measure remain to be evaluated. Using a data set from the Human Connectome Project (157 male and 180 female healthy adults; 22-37 years old), the present study investigated: (1) the test-retest reliability of temporal clustering coefficient across four repeated resting-state functional magnetic resonance imaging scans as measured by intraclass correlation coefficient (ICC); and (2) sex- and age-related effects on temporal clustering coefficient. The results showed that (1) the temporal clustering coefficient had overall moderate test-retest reliability (ICC > 0.40 over a wide range of densities) at both global and subnetwork levels, (2) female subjects showed significantly higher temporal clustering coefficient than males at both global and subnetwork levels, particularly within the default-mode and subcortical regions, and (3) temporal clustering coefficient of the subcortical subnetwork was positively correlated with age in young adults. The results of sex effects were robustly replicated in an independent REST-meta-MDD data set, while the results of age effects were not. Our findings suggest that the temporal clustering coefficient is a relatively reliable and reproducible approach for identifying individual differences in brain function, and provide evidence for demographically related effects on the human brain dynamic connectomes.

Traffic forecasting is a challenging task due to complex spatial and temporal dependencies across sensor locations and time. Interest in solving this task has increased, but current research focuses on manually constructing neural network architectures without the aid of neural architecture search (NAS). In our work, we explore evolutionary neural architecture search (ENAS) by deploying a genetic algorithm (GA) to find optimal neural network architectures for predicting traffic conditions. The search space for the GA consists of arbitrary combinations of dilated convolutions and graph convolutions for modelling temporal and spatial dependencies respectively, limited in complexity only by technical constraints. Experimental results show that model architectures obtained via GA are able to match the current state-of-the-art on traffic prediction benchmarks.

Auditory-verbal hallucinations (AVH) are a key symptom of schizophrenia. Recent neuroimaging studies examining dynamic functional connectivity suggest that disrupted dynamic interactions between brain networks characterize complex symptoms in mental illness including schizophrenia. Studying dynamic connectivity may be especially relevant for hallucinations, given their fluctuating phenomenology. Indeed, it remains unknown whether AVH in schizophrenia are directly related to altered dynamic connectivity within and between key brain networks involved in auditory perception and language, emotion processing, and top-down control. In this study, we used dynamic connectivity approaches including sliding window and k-means to examine dynamic interactions among brain networks in schizophrenia patients with and without a recent history of AVH. Dynamic brain network analysis revealed that patients with AVH spent less time in a ‘network-antagonistic’ brain state where the default mode network (DMN) and the language network were anti-correlated, and had lower probability to switch into this brain state. Moreover, patients with AVH showed a lower connectivity within the language network and the auditory network, and lower connectivity was observed between the executive control and the language networks in certain dynamic states. Our study provides the first neuroimaging evidence of altered dynamic brain networks for understanding neural mechanisms of AVH in schizophrenia. The findings may inform and further strengthen cognitive models of AVH that aid the development of new coping strategies for patients.

To identify subgroups of people with internet gaming disorder (IGD) based on addiction-related resting-state functional connectivity and how these subgroups show different clinical correlates and responses to treatment. Secondary analysis of two functional magnetic resonance imaging (fMRI) data sets. Zhejiang province and Beijing, China. One hundred and sixty-nine IGD and 147 control subjects. k-Means algorithmic and support-vector machine-learning approaches were used to identify subgroups of IGD subjects. These groups were examined with respect to assessments of craving, behavioral activation and inhibition, emotional regulation, cue-reactivity and guessing-related measures. Two groups of subjects with IGD were identified and defined by distinct patterns of connectivity in brain networks previously implicated in addictions: subgroup 1 ('craving-related subgroup') and subgroup 2 ('mixed psychological subgroup'). Clustering IGD on this basis enabled the development of diagnostic classifiers with high sensitivity and specificity for IGD subgroups in 10-fold validation (n = 218) and out-of-sample replication (n = 98) data sets. Subgroup 1 is characterized by high craving scores, cue-reactivity during fMRI and responsiveness to a craving behavioral intervention therapy. Subgroup 2 is characterized by high craving, behavioral inhibition and activations scores, non-adaptive emotion-regulation strategies and guessing-task fMRI measures. Subgroups 1 and 2 showed largely opposite functional-connectivity patterns in overlapping networks. There appear to be two subgroups of people with internet gaming disorder, each associated with differing patterns of brain functional connectivity and distinct clinical symptom profiles and gender compositions.

BackgroundEmerging research suggests that patterns of brain functional connectivity can be used to predict clinical features and disease states. Individuals across the Alzheimer’s Continuum exhibit alterations in connectivity across various brain networks (Contreras et al., 2019). However, less is known about functional changes during the preclinical stage and whether those changes are associated with cognitive test performance. This study sought to identify functional connectivity characteristics that track with episodic memory, one of the earliest cognitive changes observed in the disease course (Mortamais et al., 2017), among cognitively unimpaired older adults with and without brain amyloid deposition.Method n = 51) and ‐negative group (AB‐, n = 89). Resting‐state data were submitted to a pipeline for creating individual‐specific functional parcellations that account for variability in brain topology (Wang et al., 2015). Functional connectivity was used to predict demographically‐adjusted memory factor scores (Besser et al., 2018; Kiselica et al., 2020) in each group. Predictive models were generated using ridge regression and 50 iterations of 10‐fold cross‐validation. Prediction accuracies (i.e., Spearman rank correlations between predicted and observed scores) from the median performing models are reported.ResultMedian prediction accuracy was r s = 0.40 (IQR = .063) in the AB+ group and r s = 0.11 (IQR = .059) in the AB‐ group. Although the two groups did not differ on memory scores, the resulting networks were topologically distinct (Fig. 1). Qualitative visual review showed that the AB+ networks were predominantly comprised of inter‐network connections, whereas the networks in the AB‐ group appeared more circumscribed. In the AB+ group, the majority of connections predicting better memory were frontoparietal inter‐network connections, a pattern suggestive of compensatory hyper‐connectivity.ConclusionIndividual‐specific patterns of resting‐state functional connectivity can be used to predict episodic memory in the preclinical stages of the Alzheimer’s Continuum. These results suggest that the presence of beta‐amyloid is associated with less network segregation, potentially reflecting early disease‐related network disruption even prior to the emergence of clinical symptoms.

Low back pain (LBP) is a prevalent pain condition whose persistence can lead to changes in the brain regions responsible for sensory, cognitive, attentional, and emotional processing. Previous neuroimaging studies have identified various structural and functional abnormalities in patients with LBP; however, how the static and dynamic large-scale functional network connectivity (FNC) of the brain is affected in these patients remains unclear. Forty-one patients with chronic low back pain (cLBP) and 42 healthy controls underwent resting-state functional MRI scanning. The independent component analysis method was employed to extract the resting-state networks. Subsequently, we calculate and compare between groups for static intra- and inter-network functional connectivity. In addition, we investigated the differences between dynamic functional network connectivity and dynamic temporal metrics between cLBP patients and healthy controls. Finally, we tried to distinguish cLBP patients from healthy controls by support vector machine method. The results showed that significant reductions in functional connectivity within the network were found within the DMN,DAN, and ECN in cLBP patients. Significant between-group differences were also found in static FNC and in each state of dynamic FNC. In addition, in terms of dynamic temporal metrics, fraction time and mean dwell time were significantly altered in cLBP patients. In conclusion, our study suggests the existence of static and dynamic large-scale brain network alterations in patients with cLBP. The findings provide insights into the neural mechanisms underlying various brain function abnormalities and altered pain experiences in patients with cLBP.

Introduction: It is unknown the alterations in the dynamic networks of the brain and the underlying molecular pathological mechanism of Alzheimer's disease (AD) spectrum. Here, we aim to explore the association between alterations in the dynamic brain networks' trajectory and cognitive decline in the AD spectrum. Methods: One hundred sixty subjects were recruited from the ADNI database, including 49 early mild cognitive impairment, 28 late mild cognitive impairment, 24 AD patients, and 59 cognitively normal. All participants completed the resting-state functional magnetic resonance imaging scan and neuropsychological tests. We integrated a new method combining large-scale network analysis and canonical correlation analysis to explore the dynamic spatiotemporal patterns within- and between resting-state networks (RSNs) and their significance in the AD spectrum. Results: All RSNs represented an increase in connectivity within networks by enhancing inner cohesive ability, while 7 out of 10 RSNs were characterized by a decrease in connectivity between networks, which indicated a weakened connector among networks from the early stage to dementia. This dichotomous mode presenting large-scale dynamic network abnormality was significantly correlated with the levels of molecular biomarkers of AD, and cognitive performance, as well as with the accumulating effects of 10 identified AD-related genetic risk factors. Discussion: These findings deepen our understanding of the associated mechanism underlying large-scale network disruption, linking known molecular biomarkers and phenotypic variations in the AD spectrum.

The human brain is a complex system able to continuously adapt. How and where brain activity is modulated by behavior can be studied with functional magnetic resonance imaging (fMRI), a non-invasive neuroimaging technique with excellent spatial resolution and whole-brain coverage. FMRI scans of healthy adults completing a variety of behavioral tasks have greatly contributed to our understanding of the functional role of individual brain regions. However, by statistically analyzing each region independently, these studies ignore that brain regions act in concert rather than in unison. Thus, many studies since have instead examined how brain regions interact. Surprisingly, structured interactions between distinct brain regions not only occur during behavioral tasks but also while a subject rests quietly in the MRI scanner. Multiple groups of regions interact very strongly with each other and not only do these groups bear a striking resemblance to the sets of regions co-activated in tasks, but many of these interactions are also progressively disrupted in neurological diseases. This suggests that spontaneous fluctuations in activity can provide novel insights into fundamental organizing principles of the human brain in health and disease. Many techniques to date have segregated regions into spatially distinct networks, which ignores that any brain region can take part in multiple networks across time. A more natural view is to estimate dynamic brain networks that allow flexible functional interactions (or connectivity) over time. The estimation and analysis of such dynamic functional interactions is the subject of this dissertation. We take the perspective that dynamic brain networks evolve in a low-dimensional space and can be described by a small number of characteristic spatiotemporal patterns. Our proposed approaches are based on well-established statistical methods, such as principal component analysis (PCA), sparse matrix decompositions, temporal clustering, as well as a multiscale analysis by novel graph wavelet designs. We adapt and extend these methods to the analysis of dynamic brain networks. We show that PCA and its higher-order equivalent can identify co-varying functional interactions, which reveal disturbed dynamic properties in multiple sclerosis and which are related to the timing of stimuli for task studies, respectively. Further we show that sparse matrix decompositions provide a valid alternative approach to PCA and improve interpretability of the identified patterns. Finally, assuming an even simpler low-dimensional space and the exclusive temporal expression of individual patterns, we show that specific transient interactions of the medial prefrontal cortex are disturbed in aging and relate to impaired memory.

Major depressive disorder (MDD) is a common and intractable mood disorder. Electroconvulsive therapy (ECT) is a common means of brain electrical stimulation for the treatment of MDD, but the neurobiological mechanism of its clinical symptom relief effect is still to be explored. This study aims to explore how ECT plays a role in depression remissions by investigating the changes of static and dynamic brain network characteristics in MDD patients before and after ECT. Resting-state functional magnetic resonance imaging (fMRI) scans were obtained from nine MDD patients twice before and after a full course of ECT, all of whom responded to ECT as defined by at least a 50% reduction from baseline Hamilton Depression Scale (HAMD) scores. Both static and dynamic characteristics of the functional brain network were compared between the pre- and post-ECT scans for all participants, and the correlations between changes in clinical symptoms and altered network metrics were also investigated. The clustering coefficient and local efficiency in static brain networks were increased significantly, while the global flexibility of dynamic brain networks was decreased significantly after ECT. Several regions of interest (ROIs) that changed significantly at the local level were also identified, which involved regions of the cerebellum, hippocampus as well as frontal and temporal cortices. Although not significant, the decrease of HAMD scores were associated with trends of changed network metrics after ECT. Our results suggest that ECT may alleviate the depressive symptoms of MDD by decreasing the randomness of the brain network as reflected by changes in both static and dynamic network properties and that the temporal gyrus, frontal gyrus, hippocampus, and cerebellar regions may play key roles in such mechanisms. These findings have important implications for our understandings of ECT and depression. However, this study is limited by a relatively small sample size and the results should be confirmed in larger samples.

Abstract. The objective of the article is to systematize the dynamic and especially static entrepreneurial networks as they look, appear, and act in a country with so-called emerging markets. This is accomplished on the example of Russia. Special attention is paid to relevant business goals and patterns to typical members of such networks, to why, when and how one passes from outsourcing in dynamic networks to static networking.The article contains a field research based on (1) access to public databases like Spark-Interfax in Russia, with updated information on registered firms (their founders, affiliated companies, businesses) and (2) interviews with businessmen who agreed to comment on the problems under discussion.As regards the results of the research, two points seem to be especially important. First, when, according to legislation, information on registered firms and their statistical reports is public, it is not too problematic to find out and monitor the activities of practically all types of business static networks in all industries. Second, when the business environment becomes more competitive, dynamic networks tend to be transformed into static ones not only due to considerable contract risks, but also because one needs to select from wider samples of possible suppliers the most competitive and those who are ready to invest into the technological innovations.The general conclusion is that in countries with a dynamic economic growth and increasing competitiveness of the business environment, like in Russia, this advantage of static networking might prevail, especially if static networks appear as a result of selecting business partners from the firm’s experience in outsourcing.Key words: static and dynamic networks, outsourcing, information networking, affiliated companiesp>

Dynamic gesture recognition based on skeletal data has garnered significant attention with the rise of graph convolutional networks (GCNs). Existing methods typically calculate dependencies between joints and utilize spatio-temporal attention features. However, they often rely on joint topological features of limited spatial extent and short-time features, making it challenging to extract intra-frame spatial features and long-term inter-frame temporal features. To address this, we propose a new GCN architecture for dynamic hand gesture recognition, called a spatio-temporal dynamic attention graph convolutional network (STDA-GCN). This model employs dynamic attention spatial graph convolution, enhancing spatial feature extraction capabilities while reducing computational complexity through improved cross-channel information interaction. Additionally, a salient location channel attention mechanism is integrated between spatio-temporal convolutions to extract useful spatial features and avoid redundancy. Finally, dynamic multi-scale temporal convolution is used to extract richer inter-frame gesture features, effectively capturing information across various time scales. Evaluations on the SHREC’17 Track and DHG-14/28 benchmark datasets show that our model achieves 97.14% and 95.84% accuracy, respectively. These results demonstrate the superior performance of STDA-GCN in dynamic gesture recognition tasks.

The rapid accumulation of large-scale, long-term meteorological data presents unprecedented opportunities for data-driven weather modeling and high-resolution numerical weather prediction. While various deep learning techniques—such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and Graph Neural Networks (GNNs)—have been explored for weather forecasting, the complex spatial dependencies within historical meteorological data, particularly dynamic spatial correlations, remain insufficiently addressed. To tackle this challenge, we propose a Dynamic Spatio-Temporal Fusion Graph Network (DSTFGN), a novel module that integrates multivariate time-series analysis with graph-based causal inference to capture intricate and time-varying interdependencies among weather variables. The DSTFGN module fuses real-time inputs (e.g., sensor data, live weather feeds, external events) with historical records to model the propagation of disruptions—such as accidents or road closures—through the meteorological network. By effectively capturing dynamic spatial-temporal interactions, our approach significantly enhances forecasting accuracy and supports adaptive weather management strategies. Experimental evaluations on two real-world datasets demonstrate that DSTFGN consistently outperforms existing baseline models across short, medium, and long-term forecasting horizons.