Brain Network Models Research Articles

Connectome-based Predictive Models of General and Specific Cognitive Control.

Cognitive control, the ability to adapt thoughts and actions to shifting contexts and goals, is composed primarily of three distinct yet interrelated components: Inhibition, Shifting, and Updating. While prior research has examined the nature of different cognitive components as well as their inter-relationships, fewer studies examined whole-brain connectivity to predict individual differences for the three cognitive components and associated tasks. Here, using the Connectome-based Predictive Modelling (CPM) approach and open-access data from the Human Connectome Project, we built brain network models to successfully predict individual performance differences on the Flanker task, the Dimensional Change Card Sort task, and the 2-Back task, each putatively corresponding to Inhibition, Shifting, and Updating. We focused on grayordinate fMRI data collected during the 2-Back tasks after confirming superior predictive performance over resting-state and volumetric data. High cross-task prediction accuracy as well as joint recruitment of canonical networks, such as the frontoparietal and default-mode networks, suggest the existence of a common cognitive control factor. To directly investigate the relationships among the three cognitive control components, we developed new measures to disentangle their shared and unique aspects. Our analysis confirmed that a shared control component can be well predicted from functional connectivity patterns densely located around the frontoparietal, default-mode and dorsal attention networks. In contrast, the Shifting-specific and Inhibition-specific components exhibited lower cross-prediction performance, indicating their distinct and specialized roles. Notably, the Updating-specific component showed significant cross-prediction with the general control factor, suggesting its central role in cognitive control. Given the limitation that individual behavioral measures do not purely reflect the intended cognitive constructs, our study demonstrates the need to distinguish between common and specific components of cognitive control.

White matter engagement in brain networks assessed by integration of functional and structural connectivity

Current models of brain networks may potentially be improved by integrating our knowledge of structural connections, within and between circuits, with metrics of functional interactions between network nodes. The former may be obtained from diffusion MRI of white matter (WM), while the latter may be derived by measuring correlations between resting state BOLD signals from pairs of gray matter (GM) regions. From inspection of diffusion MRI data, it is clear that each WM voxel within a 3D image array may be traversed by multiple WM structural tracts, each of which connects a pair of GM nodes. We hypothesized that by appropriately weighting and then integrating the functional connectivity of each such connected pair, the overall engagement of any WM voxel in brain functions could be evaluated. This model introduces a structural constraint to earlier studies of WM engagement and addresses some limitations of previous efforts to relate structure and function. Using concepts derived from graph theory, we obtained spatial maps of WM engagement which highlight WM regions critical for efficient communications across the brain. The distributions of WM engagement are highly reproducible across subjects and depict a notable interdependence between the distribution of GM activities and the detailed organization of WM. Additionally, we provide evidence that the engagement varies over time and shows significant differences between genders. These findings suggest the potential of WM engagement as a measure of the integrity of normal brain functions and as a biomarker for neurological and cognitive disorders.

A Brain Network Analysis Model for Motion Sickness in Electric Vehicles Based on EEG and fNIRS Signal Fusion

Motion sickness is a common issue in electric vehicles, significantly impacting passenger comfort. This study aims to develop a functional brain network analysis model by integrating electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals to evaluate motion sickness symptoms. During real-world testing with the Feifan F7 series of new energy-electric vehicles from SAIC Motor Corp, data were collected from 32 participants. The EEG signals were divided into four frequency bands: delta-range, theta-range, alpha-range, and beta-range, and brain oxygenation variation was calculated from the fNIRS signals. Functional connectivity between brain regions was measured to construct functional brain network models for motion sickness analysis. A motion sickness detection model was developed using a graph convolutional network (GCN) to integrate EEG and fNIRS data. Our results show significant differences in brain functional connectivity between participants in motion and non-motion sickness states. The model that combined fNIRS data with high-frequency EEG signals achieved the best performance, improving the F1 score by 11.4% compared to using EEG data alone and by 8.2% compared to using fNIRS data alone. These results highlight the effectiveness of integrating EEG and fNIRS signals using GCN for motion sickness detection. They demonstrate the model’s superiority over single-modality approaches, showcasing its potential for real-world applications in electric vehicles.

Aberrant Flexibility of Dynamic Brain Network in Patients with Autism Spectrum Disorder.

Autism spectrum disorder (ASD) is a collection of neurodevelopmental disorders whose pathobiology remains elusive. This study aimed to investigate the possible neural mechanisms underlying ASD using a dynamic brain network model and a relatively large-sample, multi-site dataset. Resting-state functional magnetic resonance imaging data were acquired from 208 ASD patients and 227 typical development (TD) controls, who were drawn from the multi-site Autism Brain Imaging Data Exchange (ABIDE) database. Brain network flexibilities were estimated and compared between the ASD and TD groups at both global and local levels, after adjusting for sex, age, head motion, and site effects. The results revealed significantly increased brain network flexibilities (indicating a decreased stability) at the global level, as well as at the local level within the default mode and sensorimotor areas in ASD patients than TD participants. Additionally, significant ASD-related decreases in flexibilities were also observed in several occipital regions at the nodal level. Most of these changes were significantly correlated with the Autism Diagnostic Observation Schedule (ADOS) total score in the entire sample. These results suggested that ASD is characterized by significant changes in temporal stabilities of the functional brain network, which can further strengthen our understanding of the pathobiology of ASD.

Abnormal Dynamic Reconstruction of Overlapping Communities in Schizophrenia Patients.

This study aims to explore the changes in dynamic overlapping communities in the brains of schizophrenia (SZ) patients and further investigate the dynamic restructuring patterns of overlapping communities in SZ patients. A total of 43 SZ patients and 49 normal controls (NC) were selected for resting-state functional MRI (rs-fMRI) scans. Dynamic functional connectivity analysis was conducted separately on SZ patients and NC using rs-fMRI and Jackknife Correlation techniques to construct dynamic brain network models. Based on these models, a dynamic overlapping community detection method was utilized to explore the abnormal overlapping community structure in SZ patients using evaluation metrics such as the structural stability of overlapping communities, nodes' functional diversity, and activity level of overlapping communities. The stability of communities in SZ patients showed a decreasing trend. The changes in the overlapping community structure of SZ patients may be related to a decrease in the diversity of overlapping node functions. Additionally, compared to the NC group, the activity level of overlapping communities of SZ patients was significantly reduced. The structure or organization of the brain functional network in SZ patients is abnormal or disrupted, and the activity of the brain network in information processing and transmission is weakened in SZ patients.

Propagation of transient explosive synchronization in a mesoscale mouse brain network model of epilepsy.

Generalized epileptic attacks, which exhibit widespread disruption of brain activity, are characterized by recurrent, spontaneous, and synchronized bursts of neural activity that self-initiate and self-terminate through critical transitions. Here we utilize the general framework of explosive synchronization (ES) from complex systems science to study the role of network structure and resource dynamics in the generation and propagation of seizures. We show that a combination of resource constraint and adaptive coupling in a Kuramoto network oscillator model can reliably generate seizure-like synchronization activity across different network topologies, including a biologically derived mesoscale mouse brain network. The model, coupled with a novel algorithm for tracking seizure propagation, provides mechanistic insight into the dynamics of transition to the synchronized state and its dependence on resources; and identifies key brain areas that may be involved in the initiation and spatial propagation of the seizure. The model, though minimal, efficiently recapitulates several experimental and theoretical predictions from more complex models and makes novel experimentally testable predictions.

Contrastive voxel clustering for multiscale modeling of brain network

Resting-state functional magnetic resonance imaging (fMRI) provides an efficient way to analyze the functional connectivity between brain regions. A comprehensive understanding of brain functionality requires a unified description of multi-scale layers of neural structure. However, existing brain network modeling methods often simplify this property by averaging Blood oxygen level dependent (BOLD) signals at the brain region level for fMRI-based analysis with the assumption that BOLD signals are homogeneous within each brain region, which ignores the heterogeneity of voxels within each Region of Interest (ROI). This study introduces a novel multi-stage self-supervised learning framework for multiscale brain network analysis, which effectively delineates brain functionality from voxel to ROIs and up to sample level. A Contrastive Voxel Clustering (CVC) module is proposed to simultaneously learn the voxel-level features and clustering assignments, which ensures the retention of informative clustering features at the finest voxel-level and concurrently preserves functional connectivity characteristics. Additionally, based on the extracted features and clustering assignments at the voxel level by CVC, a Brain ROI-based Graph Neural Network (BR-GNN) is built to extract functional connectivity features at the brain ROI-level and used for sample-level prediction, which integrates the functional clustering maps with the pre-established structural ROI maps and creates a more comprehensive and effective analytical tool. Experiments are performed on two datasets, which illustrate the effectiveness and generalization ability of the proposed method by analyzing voxel-level clustering results and brain ROIs-level functional characteristics. The proposed method provides a multiscale modeling framework for brain functional connectivity analysis, which will be further used for other brain disease identification. Code is available at https://github.com/yanliugroup/fmri-cvc.

Incorporating slow NMDA-type receptors with nonlinear voltage-dependent magnesium block in a next generation neural mass model: derivation and dynamics

We derive a next generation neural mass model of a population of quadratic-integrate-and-fire neurons, with slow adaptation, and conductance-based AMPAR, GABAR and nonlinear NMDAR synapses. We show that the Lorentzian ansatz assumption can be satisfied by introducing a piece-wise polynomial approximation of the nonlinear voltage-dependent magnesium block of NMDAR current. We study the dynamics of the resulting system for two example cases of excitatory cortical neurons and inhibitory striatal neurons. Bifurcation diagrams are presented comparing the different dynamical regimes as compared to the case of linear NMDAR currents, along with sample comparison simulation time series demonstrating different possible oscillatory solutions. The omission of the nonlinearity of NMDAR currents results in a shift in the range (and possible disappearance) of the constant high firing rate regime, along with a modulation in the amplitude and frequency power spectrum of oscillations. Moreover, nonlinear NMDAR action is seen to be state-dependent and can have opposite effects depending on the type of neurons involved and the level of input firing rate received. The presented model can serve as a computationally efficient building block in whole brain network models for investigating the differential modulation of different types of synapses under neuromodulatory influence or receptor specific malfunction.

A lesion‐aware automated processing framework for clinical stroke magnetic resonance imaging

AbstractMagnetic resonance imaging (MRI) and MRI based computational modelling studies provide insights into severity and recovery of ischemic stroke patients. The presence of brain lesions, however, can heavily distort and impair state‐of‐the‐art processing frameworks due to abnormal intensity values and tissue distortions. In this study, we introduce and validate the novel “Lesion Aware automated Processing Pipeline (LeAPP).” LeAPP automatically processes clinical stroke MRI data while significantly reducing the impact of pathological artefacts on processing outputs such as structural and functional connectomes (SC, FC). This helps to advance the identification of biomarkers for recovery and mechanism‐based intervention planning using MRI as well as computational approaches. We extended existing frameworks, such as the Human Connectome Project (HCP) minimal processing pipeline, introducing correction steps, and implementing and modifying functional and diffusion processing to cope with MRI acquisition protocols more typical for the clinical context. A total of 51 participants (36 patients, 15 age‐matched controls) were processed across four time points for patients (3–5, 30–40, 85–95, 340–380 days after stroke onset) and one time point for controls. We validated performance using artificial lesioned brains (N = 81), derived from healthy brains and informed by real stroke lesions. The quality of reconstructing the ground truth was quantified on whole brain level and for lesion affected and unaffected regions‐of‐interest (ROIs) for brain parcellations and for SCs. Volume based agreement was evaluated using metrics such as dice coefficient, volume difference or ROI center‐of‐gravity distance while SC based agreement was defined as the difference in network metrics (e.g., node strength, clustering coefficient, or centrality). The observed deviations in reconstructed ground truth brain parcellations and structural connectomes from lesioned brains were significantly reduced for LeAPP, compared to the performance of existing pipelines such as HCP minimal processing pipeline. For instance, in the case of lesion affected ROIS we achieved a mean dice coefficient (where a value of one represents total agreement as defined by an exact overlap of both ROIs) of 0.81 with LeAPP, compared to 0.75 for HCP (p < .0001*). Additionally, the average measured ROI distance (where a value of zero represents no difference) for lesion ROIs was 0.87 for LeAPP in contrast to 1.7 for HCP (p < .0001*), indicating an overall superior performance of LeAPP. The pipeline generates standardized output files ready for brain network modelling for instance with The Virtual Brain software. This novel open‐source automated processing framework contributes to reproducible research and provides a robust framework for automated processing of clinical stroke MRI data, supporting the identification of brain network‐based biomarkers of stroke recovery.

Interplay of synchronization and cortical input in models of brain networks

It is well known that synchronization patterns and coherence have a major role in the functioning of brain networks, both in pathological and in healthy states. In particular, in the perception of sound, one can observe an increase in coherence between the global dynamics in the network and the auditory input. In this perspective article, we show that synchronization scenarios are determined by a fine interplay between network topology, the location of the input, and frequencies of these cortical input signals. To this end, we analyze the influence of an external stimulation in a network of FitzHugh-Nagumo oscillators with empirically measured structural connectivity, and discuss different areas of cortical stimulation, including the auditory cortex.

A Multiscale Closed-Loop Neurotoxicity Model of Alzheimer's Disease Progression Explains Functional Connectivity Alterations.

The accumulation of amyloid-β (Aβ) and hyperphosphorylated-tau (hp-tau) are two classical histopathological biomarkers in Alzheimer's disease (AD). However, their detailed interactions with the electrophysiological changes at the meso- and macroscale are not yet fully understood. We developed a mechanistic multiscale model of AD progression, linking proteinopathy to its effects on neural activity and vice-versa. We integrated a heterodimer model of prion-like protein propagation and a brain network model of Jansen-Rit neural masses derived from human neuroimaging data whose parameters varied due to neurotoxicity. Results showed that changes in inhibition guided the electrophysiological alterations found in AD, and these changes were mainly attributed to Aβ effects. Additionally, we found a causal disconnection between cellular hyperactivity and interregional hypersynchrony contrary to previous beliefs. Finally, we demonstrated that early Aβ and hp-tau depositions' location determine the spatiotemporal profile of the proteinopathy. The presented model combines the molecular effects of both Aβ and hp-tau together with a mechanistic protein propagation model and network effects within a closed-loop model. This holds the potential to enlighten the interplay between AD mechanisms on various scales, aiming to develop and test novel hypotheses on the contribution of different AD-related variables to the disease evolution.

Bridging the Semantic Latent Space between Brain and Machine: Similarity Is All You Need

How our brain encodes complex concepts has been a longstanding mystery in neuroscience. The answer to this problem can lead to new understandings about how the brain retrieves information in large-scale data with high efficiency and robustness. Neuroscience studies suggest the brain represents concepts in a locality-sensitive hashing (LSH) strategy, i.e., similar concepts will be represented by similar responses. This finding has inspired the design of similarity-based algorithms, especially in contrastive learning. Here, we hypothesize that the brain and large neural network models, both using similarity-based learning rules, could contain a similar semantic embedding space. To verify that, this paper proposes a functional Magnetic Resonance Imaging (fMRI) semantic learning network named BrainSem, aimed at seeking a joint semantic latent space that bridges the brain and a Contrastive Language-Image Pre-training (CLIP) model. Given that our perception is inherently cross-modal, we introduce a fuzzy (one-to-many) matching loss function to encourage the models to extract high-level semantic components from neural signals. Our results claimed that using only a small set of fMRI recordings for semantic space alignment, we could obtain shared embedding valid for unseen categories out of the training set, which provided potential evidence for the semantic representation similarity between the brain and large neural networks. In a zero-shot classification task, our BrainSem achieves an 11.6% improvement over the state-of-the-art.

Inferring brain causal and temporal-lag networks for recognizing abnormal patterns of dementia

Brain functional network analysis has become a popular method to explore the laws of brain organization and identify biomarkers of neurological diseases. However, it is still a challenging task to construct an ideal brain network due to the limited understanding of the human brain. Existing methods often ignore the impact of temporal-lag on the results of brain network modeling, which may lead to some unreliable conclusions. To overcome this issue, we propose a novel brain functional network estimation method, which can simultaneously infer the causal mechanisms and temporal-lag values among brain regions. Specifically, our method converts the lag learning into an instantaneous effect estimation problem, and further embeds the search objectives into a deep neural network model as parameters to be learned. To verify the effectiveness of the proposed estimation method, we perform experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database by comparing the proposed model with several existing methods, including correlation-based and causality-based methods. The experimental results show that our brain networks constructed by the proposed estimation method can not only achieve promising classification performance, but also exhibit some characteristics of physiological mechanisms. Our approach provides a new perspective for understanding the pathogenesis of brain diseases. The source code is released at https://github.com/NJUSTxiazw/CTLN.

Dynamic Organization of Large-scale Functional Brain Networks Supports Interactions Between Emotion and Executive Control.

Emotion and executive control are often conceptualized as two distinct modes of human brain functioning. Little, however, is known about how the dynamic organization of large-scale functional brain networks that support flexible emotion processing and executive control, especially their interactions. The amygdala and prefrontal systems have long been thought to play crucial roles in these processes. Recent advances in human neuroimaging studies have begun to delineate functional organization principles among the large-scale brain networks underlying emotion, executive control, and their interactions. Here, we propose a dynamic brain network model to account for interactive competition between emotion and executive control by reviewing recent resting-state and task-related neuroimaging studies using network-based approaches. In this model, dynamic interactions among the executive control network, the salience network, the default mode network, and sensorimotor networks enable dynamic processes of emotion and support flexible executive control of multiple processes; neural oscillations across multiple frequency bands and the locus coeruleus-norepinephrine pathway serve as communicational mechanisms underlying dynamic synergy among large-scale functional brain networks. This model has important implications for understanding how the dynamic organization of complex brain systems and networks empowers flexible cognitive and affective functions.

Modeling default mode network patterns via a universal spatio-temporal brain attention skip network

Designing a comprehensive four-dimensional resting-state functional magnetic resonance imaging (4D Rs-fMRI) based default mode network (DMN) modeling methodology to reveal the spatio-temporal patterns of individual DMN, is crucial for understanding the cognitive mechanisms of the brain and the pathogenesis of psychiatric disorders. However, there are still two limitations of existing approaches for DMN modeling. The approaches either (1) simply split the spatio-temporal components and ignore the overall character of the spatio-temporal patterns or (2) are biased in the process of feature extraction for DMN modeling, and their spatio-temporal accuracy is thus not warranted. To this end, we propose a novel Spatio-Temporal Brain Attention Skip Network (STBAS-Net) to model the personalized spatio-temporal patterns of the DMN. STBAS-Net consists of spatial and temporal components, where the multi-head attention skip connection block in the spatial component achieves detailed feature extraction and enhancement in the shallow stage. Under the guidance of spatial information, we technically fuse multiple spatio-temporal information in the temporal component, which dexterously exploits the overall spatio-temporal features and achieves mutual constraints of spatio-temporal patterns to characterize the spatio-temporal patterns of the DMN. We verify the proposed STBAS-Net on a publicly released 4D Rs-fMRI dataset and an EMCI dataset. The experimental results show that compared with existing advanced methods, the proposed network can more accurately model the personalized spatio-temporal patterns of the human brain DMN and successfully identify abnormal spatio-temporal patterns in EMCI patients. This study provides a potential tool for revealing the spatio-temporal patterns of the human brain DMN and is expected to provide an effective methodological framework for future exploration of abnormal brain spatio-temporal patterns and modeling of other functional brain networks.

Virtual neural network-guided optimization of non-invasive brain stimulation in Alzheimer's disease.

Transcranial direct current stimulation (tDCS) is a non-invasive brain stimulation technique with potential for counteracting disrupted brain network activity in Alzheimer's disease (AD) to improve cognition. However, the results of tDCS studies in AD have been variable due to different methodological choices such as electrode placement. To address this, a virtual brain network model of AD was used to explore tDCS optimization. We compared a large, representative set of virtual tDCS intervention setups, to identify the theoretically optimized tDCS electrode positions for restoring functional network features disrupted in AD. We simulated 20 tDCS setups using a computational dynamic network model of 78 neural masses coupled according to human structural topology. AD network damage was simulated using an activity-dependent degeneration algorithm. Current flow modeling was used to estimate tDCS-targeted cortical regions for different electrode positions, and excitability of the pyramidal neurons of the corresponding neural masses was modulated to simulate tDCS. Outcome measures were relative power spectral density (alpha bands, 8-10 Hz and 10-13 Hz), total spectral power, posterior alpha peak frequency, and connectivity measures phase lag index (PLI) and amplitude envelope correlation (AEC). Virtual tDCS performance varied, with optimized strategies improving all outcome measures, while others caused further deterioration. The best performing setup involved right parietal anodal stimulation, with a contralateral supraorbital cathode. A clear correlation between the network role of stimulated regions and tDCS success was not observed. This modeling-informed approach can guide and perhaps accelerate tDCS therapy development and enhance our understanding of tDCS effects. Follow-up studies will compare the general predictions to personalized virtual models and validate them with tDCS-magnetoencephalography (MEG) in a clinical AD patient cohort.

Recent Progress in Brain Network Models for Medical Applications: A Review.

Importance: Pathological perturbations of the brain often spread via connectome to fundamentally alter functional consequences. By integrating multimodal neuroimaging data with mathematical neural mass modeling, brain network models (BNMs) enable to quantitatively characterize aberrant network dynamics underlying multiple neurological and psychiatric disorders. We delved into the advancements of BNM-based medical applications, discussed the prevalent challenges within this field, and provided possible solutions and future directions. Highlights: This paper reviewed the theoretical foundations and current medical applications of computational BNMs. Composed of neural mass models, the BNM framework allows to investigate large-scale brain dynamics behind brain diseases by linking the simulated functional signals to the empirical neurophysiological data, and has shown promise in exploring neuropathological mechanisms, elucidating therapeutic effects, and predicting disease outcome. Despite that several limitations existed, one promising trend of this research field is to precisely guide clinical neuromodulation treatment based on individual BNM simulation. Conclusion: BNM carries the potential to help understand the mechanism underlying how neuropathology affects brain network dynamics, further contributing to decision-making in clinical diagnosis and treatment. Several constraints must be addressed and surmounted to pave the way for its utilization in the clinic.

S-TBN: A New Neural Decoding Model to Identify Stimulus Categories From Brain Activity Patterns.

Neural decoding is still a challenging and a hot topic in neurocomputing science. Recently, many studies have shown that brain network patterns containing rich spatiotemporal structural information represent the brain's activation information under external stimuli. In the traditional method, brain network features are directly obtained using the standard machine learning method and provide to a classifier, subsequently decoding external stimuli. However, this method cannot effectively extract the multidimensional structural information hidden in the brain network. Furthermore, studies on tensors have show that the tensor decomposition model can fully mine unique spatiotemporal structural characteristics of a spatiotemporal structure in data with a multidimensional structure. This research proposed a stimulus-constrained Tensor Brain Network (s-TBN) model that involves the tensor decomposition and stimulus category-constraint information. The model was verified on real neuroimaging data obtained via magnetoencephalograph and functional mangetic resonance imaging). Experimental results show that the s-TBN model achieve accuracy matrices of greater than 11.06% and 18.46% on the accuracy matrix compared with other methods on two modal datasets. These results prove the superiority of extracting discriminative characteristics using the STN model, especially for decoding object stimuli with semantic information.

UCLN: Toward the Causal Understanding of Brain Disorders With Temporal Lag Dynamics.

Resting-state functional magnetic resonance imaging (rs-fMRI) has emerged as a powerful tool for exploring interactions among brain regions. A growing body of research is actively investigating various computational approaches for estimating causal effects among brain regions. Compared to traditional methods, causal relationship reveals the causal influences among distinct brain regions, offering a deeper understanding of brain network dynamics. However, existing methods either neglect the concept of temporal lag across brain regions or set the temporal lag value to a fixed value. To address this limitation, we propose a Unified Causal and Temporal Lag Network (termed UCLN) that jointly learns the causal effects and temporal lag values among brain regions. Our method effectively captures variations in temporal lag between distant brain regions by avoiding the predefined lag value across the entire brain. The brain networks obtained are directed and weighted graphs, enabling a more comprehensive disentanglement of complex interactions. In addition, we also introduce three guiding mechanisms for efficient brain network modeling. The proposed method outperforms state-of-the-art approaches in classification accuracy on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our findings indicate that the method not only achieves superior classification but also successfully identifies crucial neuroimaging biomarkers associated with the disease.

Extraction of brain function pattern with visual-capture-task fMRI using dynamic time-window method in ADHD children

Attention deficit/Hyperactivity disorder (ADHD) has a great impact on children's development. This paper uses a novel adaptive brain state extraction algorithm to construct a dynamic time-window brain network, which captures the brain function pattern characteristics of ADHD children with higher temporal resolution. The test data were acquired by functional magnetic resonance imaging (fMRI) obtained from 23 children with ADHD during the visual-capture-task [age: (8.27 ± 2.77)]. A spatial standard deviation method is used after the initial data processing, to extract the brain activity pattern state; An improved clustering algorithm is constructed to verify the changes made to the dynamic time-window brain network model. There can be seen clear differences between each state within 0.05 s after the test. The results show that our improved new framework can effectively obtain the characteristics of dynamic brain functional connection strength changes during the task. In addition, the new algorithm is able to capture the dynamic changes of the brain network, with an 80 % improvement compared to traditional methods for the average modularity value Q. This work demonstrates a novel approach to find out the pattern changes between dynamic brain function connections, which can be of great significance for the adjuvant treatment of children with ADHD.