Search

Introduction: Functional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable without task-specific contexts. Nonetheless, interconnections among ROIs provide essential insights into brain activity and exhibit unique characteristics across groups. Methods: To address these challenges, we propose an interpretable fusion analytic framework to identify and understand ROI connectivity differences between two groups, revealing their distinctive features. The framework involves three steps: first, constructing ROI-based Functional Connectivity Networks (FCNs) to manage resting-state fMRI data; second, employing a Self-Attention Deep Learning Model (Self-Attn) for binary classification to generate attention distributions encoding group-level differences; and third, utilizing a Latent Space Item-Response Model (LSIRM) to extract group-representative ROI features, visualized on group summary FCNs. Results: We applied our framework to analyze four types of cognitive impairments, demonstrating their effectiveness in identifying significant ROIs that contribute to the differences between the two disease groups. The results reveal distinct connectivity patterns and unique ROI features, which differentiate cognitive impairments. Specifically, our framework highlighted group-specific differences in functional connectivity, validating its capability to capture meaningful insights from high-dimensional fMRI data. Discussion: Our novel interpretable fusion analytic framework addresses the challenges of analyzing high-dimensional, resting-state fMRI data. By integrating FCNs, a Self-Attention Deep Learning Model, and LSIRM, the framework provides an innovative approach to discovering ROI connectivity disparities between groups. The attention distribution and group-representative ROI features offer interpretable insights into brain activity patterns and their variations among cognitive impairment groups. This methodology has significant potential to enhance our understanding of cognitive impairments, paving the way for more targeted therapeutic interventions. [ABSTRACT FROM AUTHOR]

Abstract Major Depressive Disorder (MDD) is a common mental disorder characterized by cognitive impairment, and its pathophysiology remains to be explored. In this study, we aimed to explore the efficacy of brain network topological properties (TPs) in identifying MDD patients, revealing variational brain regions with efficient TPs. Functional connectivity (FC) networks were constructed from resting-state functional magnetic resonance imaging (rs-fMRI). Small-worldness did not exhibit significant variations in MDD patients. Subsequently, two-sample t-tests were employed to screen FC and reconstruct the network. The discriminative ability of TPs between MDD patients and healthy controls was analyzed using receiver operating characteristic (ROC), ROC analysis showed the small-worldness of binary reconstructed FC network (p

IntroductionFunctional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable without task-specific contexts. Nonetheless, interconnections among ROIs provide essential insights into brain activity and exhibit unique characteristics across groups.MethodsTo address these challenges, we propose an interpretable fusion analytic framework to identify and understand ROI connectivity differences between two groups, revealing their distinctive features. The framework involves three steps: first, constructing ROI-based Functional Connectivity Networks (FCNs) to manage resting-state fMRI data; second, employing a Self-Attention Deep Learning Model (Self-Attn) for binary classification to generate attention distributions encoding group-level differences; and third, utilizing a Latent Space Item-Response Model (LSIRM) to extract group-representative ROI features, visualized on group summary FCNs.ResultsWe applied our framework to analyze four types of cognitive impairments, demonstrating their effectiveness in identifying significant ROIs that contribute to the differences between the two disease groups. The results reveal distinct connectivity patterns and unique ROI features, which differentiate cognitive impairments. Specifically, our framework highlighted group-specific differences in functional connectivity, validating its capability to capture meaningful insights from high-dimensional fMRI data.DiscussionOur novel interpretable fusion analytic framework addresses the challenges of analyzing high-dimensional, resting-state fMRI data. By integrating FCNs, a Self-Attention Deep Learning Model, and LSIRM, the framework provides an innovative approach to discovering ROI connectivity disparities between groups. The attention distribution and group-representative ROI features offer interpretable insights into brain activity patterns and their variations among cognitive impairment groups. This methodology has significant potential to enhance our understanding of cognitive impairments, paving the way for more targeted therapeutic interventions.

Objective: In this work, we propose a novel method for constructing wholebrain spatio-temporal multilayer functional connectivity networks (FCNs) and four innovative rich-club metrics. Methods: Spatio-temporal multilayer FCNs achieve a high-order representation of the spatio-temporal dynamic characteristics of brain networks by combining the sliding time window method with graph theory and hypergraph theory. The four proposed rich-club scales are based on the dynamic changes in rich-club node identity, providing a parameterized description of the topological dynamic characteristics of brain networks from both temporal and spatial perspectives. The proposed method was validated in three independent differential analysis experiments: male-female gender difference analysis, analysis of abnormality in patients with autism spectrum disorders (ASD), and individual difference analysis. Results: The proposed method yielded results consistent with previous relevant studies and revealed some innovative findings. For instance, the dynamic topological characteristics of specific white matter regions effectively reflected individual differences. The increased abnormality in internal functional connectivity within the basal ganglia may be a contributing factor to the occurrence of repetitive or restrictive behaviors in ASD patients. Conclusion: The proposed methodology provides an efficacious approach for constructing whole-brain spatio-temporal multilayer FCNs and conducting analysis of their dynamic topological structures. The dynamic topological characteristics of spatio-temporal multilayer FCNs may offer new insights into physiological variations and pathological abnormalities in neuroscience. [ABSTRACT FROM AUTHOR]

Objective: The coronavirus disease 2019 (COVID-19) is an acute respiratory infectious disease caused by the SARA-CoV-2, characterized by high infectivity and incidence. Clinical data indicates that COVID-19 significantly damages patients' perception, motor function, and cognitive function. However, the electrophysiological mechanism by which the disease affects the patient's nervous system is not yet clear. Our aim is to investigate the abnormal levels of brain activity and changes in brain functional connectivity network in patients with COVID-19. Methods: We compared and analyzed electroencephalography signal sample entropy, energy spectrum, and brain network characteristic parameters in the delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), and beta (13-30 Hz) bands of 15 patients with COVID-19 and 15 healthy controls at rest. Results: At rest, energy values of the four frequency bands in the frontal and temporal lobes of COVID-19 patients were significantly reduced. At the same time, the sample entropy value of the delta band in COVID-19 patients was significantly increased, while the value of the beta band was significantly decreased. However, the average value of the directed transfer function of patients did not show any abnormalities under the four frequency bands. Furthermore, node degree in the temporal lobe of patients was significantly increased, while the input degree of the frontal and temporal lobes was significantly decreased, and the output degree of the frontal and occipital lobes was significantly increased. Conclusion: The level of brain activity in COVID-19 patients at rest is reduced, and the brain functional network undergoes a rearrangement. These results preliminarily demonstrate that COVID-19 patients exhibit certain brain abnormalities during rest, it is feasible to explore the neurophysiological mechanism of COVID-19's impact on the nervous system by using EEG signals, which can provide a certain technical basis for the subsequent diagnosis and evaluation of COVID-19 using artificial intelligence and the prevention of brain nervous system diseases after COVID-19 infection. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to discover electrophysiologic markers correlated with clinical responses to vigabatrin-based treatment in infants with epileptic spasms (ES). Method: The study involved a descriptive analysis of ES patients from a single institution, as well as electroencephalogram (EEG) analyses of 40 samples and 20 age-matched healthy infants. EEG data were acquired during the interictal sleep state prior to the standard treatment. The weighted phase-lag index (wPLI) functional connectivity was explored across frequency and spatial domains, correlating these results with clinical features. Results: Infants with ES exhibited diffuse increases in delta and theta power, differing from healthy controls. For the wPLI analysis, ES subjects exhibited higher global connectivity compared to control subjects. Subjects who responded favorably to treatment were characterized by higher beta connectivity in the parieto-occipital regions, while those with poorer outcomes exhibited lower alpha connectivity in the frontal regions. Individuals with structural neuroimaging abnormalities exhibited correspondingly low functional connectivity, implying that ES patients who maintain adequate structural and functional integrity are more likely to respond favorably to vigabatrin-based treatments. Conclusion: This study highlights the potential utility of EEG functional connectivity analysis in predicting early response to treatments in infants with ES. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aims to provide computer-aided diagnosis and valuable biomarkers for autism spectrum disorders by leveraging functional connectivity networks (FCNs) from resting-state functional magnetic resonance imaging data. We propose a novel framework for multi-FCN fusion to adaptively learn the fusion weights of component FCNs during the classifer's learning process, guided by label information. It is simple and has better discriminability for autism spectrum disorder identification. Functional connectivity network (FCN) has become a popular tool to identify potential biomarkers for brain dysfunction, such as autism spectrum disorder (ASD). Due to its importance, researchers have proposed many methods to estimate FCNs from resting-state functional MRI (rs-fMRI) data. However, the existing FCN estimation methods usually only capture a single relationship between brain regions of interest (ROIs), e.g., linear correlation, nonlinear correlation, or higher-order correlation, thus failing to model the complex interaction among ROIs in the brain. Additionally, such traditional methods estimate FCNs in an unsupervised way, and the estimation process is independent of the downstream tasks, which makes it difficult to guarantee the optimal performance for ASD identification. To address these issues, in this paper, we propose a multi-FCN fusion framework for rs-fMRI-based ASD classification. Specifically, for each subject, we first estimate multiple FCNs using different methods to encode rich interactions among ROIs from different perspectives. Then, we use the label information (ASD vs. healthy control (HC)) to learn a set of fusion weights for measuring the importance/discrimination of those estimated FCNs. Finally, we apply the adaptively weighted fused FCN on the ABIDE dataset to identify subjects with ASD from HCs. The proposed FCN fusion framework is straightforward to implement and can significantly improve diagnostic accuracy compared to traditional and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Effective human-multiagent teams will incorporate the cognitive skills of the human with the autonomous capabilities of the multiagent group to maximize task performance. However, producing a seamless fusion requires a greater understanding of the human's cognitive state as it reacts to uncertainties in both the task environment and agent dynamics. This study examines external behaviors in concert with neurophysiological measures acquired via electroencephalography (EEG) to probe the interactions between cognitive processes, behaviors, and performance in a human-multiagent team task. We show that changes in the α (8–12 Hz) and θ (4–8 Hz) bands of EEG indicate a higher burden on the cognitive resources associated with visual-spatial reasoning required to estimate a more complex kinematic state of robotic agents. These results are reinforced by complementary behavioral shifts in gaze and pilot inputs. Additionally, higher-performing participants tend to engage more actively in the task by utilizing greater amounts of visual-spatial reasoning. Finally, we show that features based on EEG dynamic-network-metrics provide discriminative information that distinguishes gaze behaviors associated with the attention process. [ABSTRACT FROM AUTHOR]

Functional connectivity networks (FCN) analysis is instructive for the diagnosis of brain diseases, such as mild cognitive impairment (MCI) and major depressive disorder (MDD) at their early stages. As the critical step of FCN analysis, feature representation provides the basis for finding potential biomarkers of brain diseases. In previous studies, different node statistics (e.g. local efficiency and local clustering coefficients) are usually extracted from FCNs as features for the diagnosis/classification task, which can specifically locate disease-related regions on the node level, so as to help us understand the neurodevelopmental roots of brain disorders. However, each node statistic is proposed only considering a kind of specific network property, which has one-sidedness and limitations. As a result, it is incomplete to represent a node with only one statistic. To resolve this issue, we put forward a novel scheme to select multiple node statistics jointly from the estimated FCNs for automated classification, called multiple node statistics feature selection (MNSFS). Specifically, we first extract multiple statistics from the same nodes and assign each kind of statistic into a group. Then, sparse group least absolute shrinkage and selection operator (sgLASSO) is used to select groups (nodes) and statistics in the groups towards a better classification performance. Such a technique enables us to simultaneously locate the discriminative brain regions, as well as the specific statistics associated with these brain regions, making the classification results more interpretable. We conducted our scheme on two public databases for identifying subjects with MCI and MDD from normal controls. Experimental results show that the proposed scheme achieves superior classification accuracy and features interpreted on the benchmark datasets. [ABSTRACT FROM AUTHOR]

The functional connectivity network (FCN) has been used to achieve several remarkable advancements in the diagnosis of neuro-degenerative disorders. Therefore, it is imperative to accurately estimate biologically meaningful FCNs. Several efforts have been dedicated to this purpose by encoding biological priors. However, owing to the high complexity of the human brain, the estimation of an ’ideal' FCN remains an open problem. To the best of our knowledge, almost all existing studies lack the integration of domain expert knowledge, which limits their performance. In this study, we focused on incorporating domain expert knowledge into the FCN estimation from a modularity perspective. To achieve this, we presented a human-guided modular representation (MR) FCN estimation framework. Specifically, we designed an adversarial low-rank constraint to describe the module structure of FCNs under the guidance of domain expert knowledge (i.e., a predefined participant index). The chronic tinnitus (TIN) identification task based on the estimated FCNs was conducted to examine the proposed MR methods. Remarkably, MR significantly outperformed the baseline and state-of-the-art(SOTA) methods, achieving an accuracy of 92.11%. Moreover, post-hoc analysis revealed that the FCNs estimated by the proposed MR could highlight more biologically meaningful connections, which is beneficial for exploring the underlying mechanisms of TIN and diagnosing early TIN. [ABSTRACT FROM AUTHOR]

Stroke is a chief cause of sudden brain damage that severely disrupts the whole-brain network. However, the potential mechanisms of motor recovery after stroke are uncertain and the prognosis of poststroke upper extremity recovery is still a challenge. This study investigated the global and local topological properties of the brain functional connectome in patients with subacute ischemic stroke and their associations with the clinical measurements. A total of 57 patients, consisting of 29 left-sided and 28 right-sided stroke patients, and 32 age- and gender-matched healthy controls (HCs) were recruited to undergo a resting-state functional magnetic resonance imaging (rs-fMRI) study; patients were also clinically evaluated with the Upper Extremity Fugl-Meyer Assessment (FMA_UE). The assessment was repeated at 15 weeks to assess upper extremity functional recovery for the patient remaining in the study (12 left- 20 right-sided stroke patients). Global graph topological disruption indices of stroke patients were significantly decreased compared with HCs but these indices were not significantly associated with FMA_UE. In addition, local brain network structure of stroke patients was altered, and the altered regions were dependent on the stroke site. Significant associations between local degree and motor performance and its recovery were observed in the right lateral occipital cortex (R LOC) in the right-sided stroke patients. Our findings suggested that brain functional topologies alterations in R LOC are promising as prognostic biomarkers for right-sided subacute stroke. This cortical area might be a potential target to be further validated for non-invasive brain stimulation treatment to improve poststroke upper extremity recovery. [ABSTRACT FROM AUTHOR]

Stroke is a chief cause of sudden brain damage that severely disrupts the whole-brain network. However, the potential mechanisms of motor recovery after stroke are uncertain and the prognosis of poststroke upper extremity recovery is still a challenge. This study investigated the global and local topological properties of the brain functional connectome in patients with subacute ischemic stroke and their associations with the clinical measurements. A total of 57 patients, consisting of 29 left-sided and 28 right-sided stroke patients, and 32 age- and gender-matched healthy controls (HCs) were recruited to undergo a resting-state functional magnetic resonance imaging (rs-fMRI) study; patients were also clinically evaluated with the Upper Extremity Fugl-Meyer Assessment (FMA_UE). The assessment was repeated at 15 weeks to assess upper extremity functional recovery for the patient remaining in the study (12 left- 20 right-sided stroke patients). Global graph topological disruption indices of stroke patients were significantly decreased compared with HCs but these indices were not significantly associated with FMA_UE. In addition, local brain network structure of stroke patients was altered, and the altered regions were dependent on the stroke site. Significant associations between local degree and motor performance and its recovery were observed in the right lateral occipital cortex (R LOC) in the right-sided stroke patients. Our findings suggested that brain functional topologies alterations in R LOC are promising as prognostic biomarkers for right-sided subacute stroke. This cortical area might be a potential target to be further validated for non-invasive brain stimulation treatment to improve poststroke upper extremity recovery.

Functional connectivity network (FCN) calculated by resting-state functional magnetic resonance imaging (rs-fMRI) plays an increasingly important role in the exploration of neurologic and mental diseases. Among the presented researches, the method of constructing FCN based on Matrix Variate Normal Distribution (MVND) theory provides a novel perspective, which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. However, when fitting MVND model, the dimension of the parameters (i.e., population mean and population covariance) to be estimated is too high, but the number of samples is relatively quite small, which is insufficient to achieve accurate fitting. To address the issue, we divide the brain network into several sub-networks, and then the MVND based FCN construction algorithm is implemented in each sub-network, thus the spatial dimension of MVND is reduced and more accurate estimates of low- and high-order FCNs is obtained. Furthermore, for making up the functional connectivity which is lost because of the sub-network division, the rs-fMRI mean series of all sub-networks are calculated, and the low- and high-order FCN across sub-networks are estimated with the MVND based FCN construction method. In order to prove the superiority and effectiveness of this method, we design and conduct classification experiments on ASD patients and normal controls. The experimental results show that the classification accuracy of “hierarchical sub-network method” is greatly improved, and the sub-network found most related to ASD in our experiment is consistent with other related medical researches.

Functional connectivity network (FCN) calculated by resting-state functional magnetic resonance imaging (rs-fMRI) plays an increasingly important role in the exploration of neurologic and mental diseases. Among the presented researches, the method of constructing FCN based on Matrix Variate Normal Distribution (MVND) theory provides a novel perspective, which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. However, when fitting MVND model, the dimension of the parameters (i.e., population mean and population covariance) to be estimated is too high, but the number of samples is relatively quite small, which is insufficient to achieve accurate fitting. To address the issue, we divide the brain network into several sub-networks, and then the MVND based FCN construction algorithm is implemented in each sub-network, thus the spatial dimension of MVND is reduced and more accurate estimates of low- and high-order FCNs is obtained. Furthermore, for making up the functional connectivity which is lost because of the sub-network division, the rs-fMRI mean series of all sub-networks are calculated, and the low- and high-order FCN across sub-networks are estimated with the MVND based FCN construction method. In order to prove the superiority and effectiveness of this method, we design and conduct classification experiments on ASD patients and normal controls. The experimental results show that the classification accuracy of "hierarchical sub-network method" is greatly improved, and the sub-network found most related to ASD in our experiment is consistent with other related medical researches. [ABSTRACT FROM AUTHOR]

The sliding-window-based dynamic functional connectivity networks (SW-D-FCN) derive from resting-state functional Magnetic Resonance Imaging has become an increasingly useful tool in the diagnosis of various neurodegenerative diseases. However, it is still challenging to learn how to extract and select the most discriminative features from SW-D-FCN. Conventionally, existing methods opt to select a single discriminative feature set or concatenate a few more from the SW-D-FCN. However, such reductionist strategies may fail to fully capture the personalized discriminative characteristics contained in each functional connectivity (FC) sequence of the SW-D-FCN. To address this issue, we propose a unit-based personalized fingerprint feature selection (UPFFS) strategy to better capture the most discriminative feature associated with a target disease for each unit. Specifically, we regard the FC sequence between any pair of brain regions of interest (ROIs) is regarded as a unit. For each unit, the most discriminative feature is identified by a specific feature evaluation method and all the most discriminative features are then concatenated together as a feature set for the subsequent classification task. In such a way, the personalized fingerprint feature derived from each FC sequence can be fully mined and utilized in classification decision. To illustrate the effectiveness of the proposed strategy, we conduct experiments to distinguish subjects diagnosed with autism spectrum disorder from normal controls. Experimental results show that the proposed strategy can select relevant discriminative features and achieve superior performance to benchmark methods.

The sliding-window-based dynamic functional connectivity networks (SW-D-FCN) derive from resting-state functional Magnetic Resonance Imaging has become an increasingly useful tool in the diagnosis of various neurodegenerative diseases. However, it is still challenging to learn how to extract and select the most discriminative features from SW-D-FCN. Conventionally, existing methods opt to select a single discriminative feature set or concatenate a few more from the SW-D-FCN. However, such reductionist strategies may fail to fully capture the personalized discriminative characteristics contained in each functional connectivity (FC) sequence of the SW-D-FCN. To address this issue, we propose a unit-based personalized fingerprint feature selection (UPFFS) strategy to better capture the most discriminative feature associated with a target disease for each unit. Specifically, we regard the FC sequence between any pair of brain regions of interest (ROIs) is regarded as a unit. For each unit, the most discriminative feature is identified by a specific feature evaluation method and all the most discriminative features are then concatenated together as a feature set for the subsequent classification task. In such a way, the personalized fingerprint feature derived from each FC sequence can be fully mined and utilized in classification decision. To illustrate the effectiveness of the proposed strategy, we conduct experiments to distinguish subjects diagnosed with autism spectrum disorder from normal controls. Experimental results show that the proposed strategy can select relevant discriminative features and achieve superior performance to benchmark methods. [ABSTRACT FROM AUTHOR]

Abstract Introduction Generalized tonic‐clonic seizure (GTCS) is a condition that is characterized by generalized spike‐wave discharge in bilateral cerebral hemispheres during the seizure. Although previous neuroimaging studies revealed functional abnormalities in the brain activities of children with GTCS, the topological alterations in whole‐brain networks remain poorly understood. Methods The present study used graph theory to investigate the topological organization of functional networks in 13 GTCS children and 30 age‐matched healthy controls. Results We found that both groups exhibited a small‐world topology of the functional network. However, children with GTCS showed a significant decrease in nodal local efficiency and clustering coefficient in some key nodes compared with the controls. The connections within the default mode network (DMN) were decreased significantly, and the internetwork connections were increased significantly. The altered topological properties may be an effect of chronic epilepsy. As a result, the optimal topological organization of the functional network was disrupted in the patient group. Notably, clustering coefficient and nodal local efficiency in the bilateral temporal pole of the middle temporal gyrus negatively correlated with the epilepsy duration. Conclusion These results suggest that the bilateral temporal pole plays an important role in reflecting the effect of chronic epilepsy on the topological properties in GTCS children. The present study demonstrated a disrupted topological organization in children with GTCS. These findings provide new insight into our understanding of this disorder.

Feature selection has been applied to the analysis of complex structured data, such as functional connectivity networks (FCNs) constructed on resting-state functional magnetic resonance imaging (rs-fMRI), for removing redundant/noisy information. Previous studies usually first extract topological measures (e.g., clustering coefficients) from FCNs as feature vectors, and then perform vector-based algorithms (e.g., t-test) for feature selection. However, due to the use of vector-based representations, these methods simply ignore important local-to-global structural information of connectivity networks, while such structural information could be used as prior knowledge of networks to improve the learning performance. To this end, we propose a graph kernel-based structured feature selection (gk-SFS) method for brain disease classification with connectivity networks. Different from previous studies, our proposed gk-SFS method uses the graph kernel technique to calculate the similarity of networks and thus can explicitly take advantage of the structural information of connectivity networks. Specifically, we first develop a new graph kernel-based Laplacian regularizer in our gk-SFS model to preserve the structural information of connectivity networks. We also employ an l1-norm based sparsity regularizer to select a small number of discriminative features for brain disease analysis (classification). The experimental results on both ADNI and ADHD-200 datasets with rs-fMRI data demonstrate that the proposed gk-SFS method can further improve the classification performance compared with the state-of-the-art methods.

Functional connectivity network (FCN) has become an increasingly important approach to gain a better understanding of the brain, as well as discover informative biomarkers for diagnosis of neurodegenerative diseases. Due to its importance, many FCN estimation methods have been developed in the past decades, including methods based on the classical Pearson's correlation, (regularized) partial correlation, and some higher-order variants. However, most of the existing methods estimate one FCN at a time, thus ignoring the possibly shared structure among FCNs from different subjects. Recently, researchers introduce group constraints (or population priors) into FCN estimation by assuming that FCNs are topologically identical across subjects. Obviously, such a constraint/prior is too strong to be satisfied in practice, especially when both patients and healthy subjects are involved simultaneously in the group. To address this problem, we propose a novel FCN estimation approach based on an assumption that the involved FCNs have similar but not necessarily identical topology. More specifically, we implement this idea under a two-step learning framework. First, we independently estimate FCNs based on traditional methods, such as Pearson's correltion and sparse representation, making sure that each FCN captures the specific properties of the corresponding subject. Then, we stack the estimated FCNs (in fact, their adjacency matrices) into a tensor, and refine the stacked FCNs via low-rank tensor approximation. Finally, we apply the improved FCNs to identify subjects with mild cognitive impairment (MCI) from healthy controls, and achieve a higher classification accuracy. [ABSTRACT FROM AUTHOR]

Decoding emotional neural representations from the electroencephalographic (EEG)-based functional connectivity network (FCN) is of great scientific importance for uncovering emotional cognition mechanisms and developing harmonious human–computer interactions. However, existing methods mainly rely on phase-based FCN measures (e.g., phase locking value [PLV]) to capture dynamic interactions between brain oscillations in emotional states, which fail to reflect the energy fluctuation of cortical oscillations over time. In this study, we initially examined the efficacy of amplitude-based functional networks (e.g., amplitude envelope correlation [AEC]) in representing emotional states. Subsequently, we proposed an efficient phase–amplitude fusion framework (PAF) to fuse PLV and AEC and used common spatial pattern (CSP) to extract fused spatial topological features from PAF for multi-class emotion recognition. We conducted extensive experiments on the DEAP and MAHNOB-HCI datasets. The results showed that: (1) AEC-derived discriminative spatial network topological features possess the ability to characterize emotional states, and the differential network patterns of AEC reflect dynamic interactions in brain regions associated with emotional cognition. (2) The proposed fusion features outperformed other state-of-the-art methods in terms of classification accuracy for both datasets. Moreover, the spatial filter learned from PAF is separable and interpretable, enabling a description of affective activation patterns from both phase and amplitude perspectives. [ABSTRACT FROM AUTHOR]

Exposure to mental stress for long period leads to serious accidents and health problems. To avoid negative consequences on health and safety, it is very important to detect mental stress at its early stages, i.e., when it is still limited to acute or episodic stress. In this study, we developed an experimental protocol to induce two different levels of stress by utilizing a mental arithmetic task with time pressure and negative feedback as the stressors. We assessed the levels of stress on 22 healthy subjects using frontal electroencephalogram (EEG) signals, salivary alpha-amylase level (AAL), and multiple machine learning (ML) classifiers. The EEG signals were analyzed using a fusion of functional connectivity networks estimated by the Phase Locking Value (PLV) and temporal and spectral domain features. A total of 210 different features were extracted from all domains. Only the optimum multi-domain features were used for classification. We then quantified stress levels using statistical analysis and seven ML classifiers. Our result showed that the AAL level was significantly increased (p < 0.01) under stress condition in all subjects. Likewise, the functional connectivity network demonstrated a significant decrease under stress, p < 0.05. Moreover, we achieved the highest stress classification accuracy of 93.2% using the Support Vector Machine (SVM) classifier. Other classifiers produced relatively similar results.

Pain experience increases individuals' perception and contagion of others' pain, but whether pain experience affects individuals' affiliative or antagonistic responses to others' pain is largely unknown. Additionally, the neural mechanisms underlying how pain experience modulates individuals' responses to others' pain remain unclear. In this study, we explored the effects of pain experience on individuals' responses to others' pain and the underlying neural mechanisms. By comparing locomotion, social, exploration, stereotyped, and anxiety-like behaviors of mice without any pain experience (naïve observers) and mice with a similar pain experience (experienced observers) when they observed the pain-free demonstrator with intraperitoneal injection of normal saline and the painful demonstrator with intraperitoneal injection of acetic acid, we found that pain experience of the observers led to decreased social avoidance to the painful demonstrator. Through whole-brain c-Fos quantification, we discovered that pain experience altered neuronal activity and enhanced functional connectivity in the mouse brain. The analysis of complex network and graph theory exhibited that functional connectivity networks and activated hub regions were altered by pain experience. Together, these findings reveal that neuronal activity and functional connectivity networks are involved in the modulation of individuals' responses to others' pain by pain experience., (© The Author(s) 2024. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

High-order correlation has recently been proposed to model brain functional connectivity network (FCN) for identifying neurological disorders, such as mild cognitive impairment (MCI) and autism spectrum disorder (ASD). In practice, the high-order FCN (HoFCN) can be derived from multiple low-order FCNs that are estimated separately in a series of sliding windows, and thus it in fact provides a way of integrating dynamic information encoded in a sequence of low-order FCNs. However, the estimation of low-order FCN may be unreliable due to the fact that the use of limited volumes/samples in a sliding window can significantly reduce the statistical power, which in turn affects the reliability of the resulted HoFCN. To address this issue, we propose to enhance HoFCN based on a regularized learning framework. More specifically, we first calculate an initial HoFCN using a recently developed method based on maximum likelihood estimation. Then, we learn an optimal neighborhood network of the initially estimated HoFCN with sparsity and modularity priors as regularizers. Finally, based on the improved HoFCNs, we conduct experiments to identify MCI and ASD patients from their corresponding normal controls. Experimental results show that the proposed methods outperform the baseline methods, and the improved HoFCNs with modularity prior consistently achieve the best performance.

Background/Aims: Brain functional connectivity networks constructed from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used for classifying Alzheimer's disease (AD) from normal controls (NC). However, conventional correlation analysis methods only capture the pairwise information, which may not be capable of revealing an adequate and accurate functional connectivity relationship among brain regions in the whole brain. Additionally, the non-sparse connectivity networks commonly contain a large number of spurious or insignificant connections, which are inconsistent with the sparse connectivity of actual brain networks in nature and may deteriorate the classification performance of Alzheimer's disease.Methods: To address these problems, in this paper, a new classification framework is proposed by combining the Group-constrained topology structure detection with sparse inverse covariance estimation (SICE) method to build the functional brain sub-network for each brain region. Particularly, to tune the sensitive analysis of the regularized parameters in the SICE method, a nested leave-one-out cross-validation (LOOCV) method is adopted. Sparse functional connectivity networks are thus effectively constructed by using the optimal regularized parameters. Finally, a decision classification tree (DCT) classifier is trained for classifying AD from NC based on these optimal functional brain sub-networks. The convergence performance of our proposed method is furthermore evaluated by the trend of coefficient variation.Results: Experiment results indicate that a LOOCV classification accuracy of 81.82% with a sensitivity of 80.00%, and a specificity of 83.33% can be obtained by using the proposed method for the classification AD from NC, and outperforms the most state-of-the-art methods in terms of the classification accuracy. Additionally, the experiment results of the convergence performance further suggest that our proposed scheme has a high rate of convergence. Particularly, the abnormal brain regions and functional connections identified by our proposed framework are highly associated with the underpinning pathological mechanism of the AD, which are consistent with previous studies.Conclusion: These results have demonstrated the effectiveness of the proposed Group- constrained SICE method, and are capable of clinical value to the diagnosis of Alzheimer's disease.

Functional connectivity network provides novel insights on how distributed brain regions are functionally integrated, and its deviations from healthy brain have recently been employed to identify biomarkers for neuropsychiatric disorders. However, most of brain network analysis methods utilized features extracted only from one functional connectivity network for brain disease detection and cannot provide a comprehensive representation on the subtle disruptions of brain functional organization induced by neuropsychiatric disorders. Inspired by the principles of multi‐view learning which utilizes information from multiple views to enhance object representation, we propose a novel multiple network based framework to enhance the representation of functional connectivity networks by fusing the common and complementary information conveyed in multiple networks. Specifically, four functional connectivity networks corresponding to the four adjacent values of regularization parameter are generated via a sparse regression model with group constraint (l2,1‐norm), to enhance the common intrinsic topological structure and limit the error rate caused by different views. To obtain a set of more meaningful and discriminative features, we propose using a modified version of weighted clustering coefficients to quantify the subtle differences of each group‐sparse network at local level. We then linearly fuse the selected features from each individual network via a multi‐kernel support vector machine for autism spectrum disorder (ASD) diagnosis. The proposed framework achieves an accuracy of 79.35%, outperforming all the compared single network methods for at least 7% improvement. Moreover, compared with other multiple network methods, our method also achieves the best performance, that is, with at least 11% improvement in accuracy. [ABSTRACT FROM AUTHOR]

Background/Aims: Brain functional connectivity networks constructed from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used for classifying Alzheimer's disease (AD) from normal controls (NC). However, conventional correlation analysis methods only capture the pairwise information, which may not be capable of revealing an adequate and accurate functional connectivity relationship among brain regions in the whole brain. Additionally, the non-sparse connectivity networks commonly contain a large number of spurious or insignificant connections, which are inconsistent with the sparse connectivity of actual brain networks in nature and may deteriorate the classification performance of Alzheimer's disease. Methods: To address these problems, in this paper, a new classification framework is proposed by combining the Group-constrained topology structure detection with sparse inverse covariance estimation (SICE) method to build the functional brain sub-network for each brain region. Particularly, to tune the sensitive analysis of the regularized parameters in the SICE method, a nested leave-one-out cross-validation (LOOCV) method is adopted. Sparse functional connectivity networks are thus effectively constructed by using the optimal regularized parameters. Finally, a decision classification tree (DCT) classifier is trained for classifying AD from NC based on these optimal functional brain sub-networks. The convergence performance of our proposed method is furthermore evaluated by the trend of coefficient variation. Results: Experiment results indicate that a LOOCV classification accuracy of 81.82% with a sensitivity of 80.00%, and a specificity of 83.33% can be obtained by using the proposed method for the classification AD from NC, and outperforms the most state-of-the-art methods in terms of the classification accuracy. Additionally, the experiment results of the convergence performance further suggest that our proposed scheme has a high rate of convergence. Particularly, the abnormal brain regions and functional connections identified by our proposed framework are highly associated with the underpinning pathological mechanism of the AD, which are consistent with previous studies. Conclusion: These results have demonstrated the effectiveness of the proposed Group- constrained SICE method, and are capable of clinical value to the diagnosis of Alzheimer's disease. [ABSTRACT FROM AUTHOR]

Functional connectivity networks (FCNs) using resting-state functional magnetic resonance imaging (rs-fMRI) have been applied to the analysis and diagnosis of brain disease, such as Alzheimer’s disease (AD) and its prodrome, i.e. , mild cognitive impairment (MCI). Different from conventional studies focusing on static descriptions on functional connectivity (FC) between brain regions in rs-fMRI, recent studies have resorted to dynamic connectivity networks (DCNs) to characterize the dynamic changes of FC, since dynamic changes of FC may indicate changes in macroscopic neural activity patterns in cognitive and behavioral aspects. However, most of the existing studies only investigate the temporal properties of DCNs ( e.g. , temporal variability of FC between specific brain regions), ignoring the important spatial properties of the network ( e.g. , spatial variability of FC associated with a specific brain region). Also, emerging evidence on FCNs has suggested that, besides temporal variability, there is significant spatial variability of activity foci over time. Hence, integrating both temporal and spatial properties of DCNs can intuitively promote the performance of connectivity-network-based learning methods. In this paper, we first define a new measure to characterize the spatial variability of DCNs, and then propose a novel learning framework to integrate both temporal and spatial variabilities of DCNs for automatic brain disease diagnosis. Specifically, we first construct DCNs from the rs-fMRI time series at successive non-overlapping time windows. Then, we characterize the spatial variability of a specific brain region by computing the correlation of functional sequences ( i.e. , the changing profile of FC between a pair of brain regions within all time windows) associated with this region. Furthermore, we extract both temporal variabilities and spatial variabilities from DCNs as features, and integrate them for classification by using manifold regularized multi-task feature learning and multi-kernel learning techniques. Results on 149 subjects with baseline rs-fMRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that our method can not only improve the classification performance in comparison with state-of-the-art methods, but also provide insights into the spatio-temporal interaction patterns of brain activity and their changes in brain disorders. [ABSTRACT FROM AUTHOR]

Local lesions caused by stroke may result in extensive structural and functional reorganization in the brain. Previous studies of this phenomenon have focused on specific brain networks. Here, we aimed to discover abnormalities in whole-brain networks and to explore the decoupling between structural and functional connectivity in patients with stroke. Fifteen ischemic stroke patients and 23 normal controls (NCs) were recruited in this study. A graph theoretical analysis was employed to investigate the abnormal topological properties of structural and functional brain networks in patients with stroke. Both patients with stroke and NCs exhibited small-world organization in brain networks. However, compared to NCs, patients with stroke exhibited abnormal global properties characterized by a higher characteristic path length and lower global efficiency. Furthermore, patients with stroke showed altered nodal characteristics, primarily in certain motor- and cognition-related regions. Positive correlations between the nodal degree of the inferior parietal lobule and the Fugl-Meyer Assessment (FMA) score and between the nodal betweenness centrality of the posterior cingulate gyrus (PCG) and immediate recall were observed in patients with stroke. Most importantly, the strength of the structural–functional connectivity network coupling was decreased, and the coupling degree was related to the FMA score of patients, suggesting that decoupling may provide a novel biomarker for the assessment of motor impairment in patients with stroke. Thus, the topological organization of brain networks is altered in patients with stroke, and our results provide insights into the structural and functional organization of the brain after stroke from the viewpoint of network topology. [ABSTRACT FROM AUTHOR]

The accurate estimation of functional brain networks is essential for comprehending the intricate relationships between different brain regions. Conventional methods such as Pearson Correlation and Sparse Representation often fail to uncover concealed information within diverse frequency bands. To address this limitation, we introduce a novel frequency-adaptive model based on wavelet transform, enabling selective capture of highly correlated frequency band sequences. Our approach involves decomposing the original time-domain signal from resting-state functional magnetic resonance imaging into distinct frequency domains, thus constructing an adjacency matrix that offers enhanced separation of features across brain regions. Comparative analysis demonstrates the superior performance of our proposed model over conventional techniques, showcasing improved clarity and distinctiveness. Notably, we achieved the highest accuracy rate of 89.01% using Sparse Representation based on Wavelet Transform, outperforming Pearson Correlation based on Wavelet Transform with an accuracy of 81.32%. Importantly, our method optimizes raw data without significantly altering feature topology, rendering it adaptable to various functional brain network estimation approaches. Overall, this innovation holds the potential to advance the understanding of brain function and furnish more accurate samples for future research and clinical applications., (© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

An imbalance in neural activity within large-scale networks appears to be an important pathophysiological aspect of depression. Yet, there is little consensus regarding the abnormality within the default mode network (DMN) in major depressive disorder (MDD). In the present study, 16 first-episode, medication-naïve patients with MDD and 16 matched healthy controls underwent functional magnetic resonance imaging (fMRI) at rest. With the precuneus (a central node of the DMN) as a seed region, functional connectivity (FC) was measured across the entire brain. The association between the FC of the precuneus and overall symptom severity was assessed using the Hamilton Depression Rating Scale. Patients with MDD exhibited a more negative relationship between the precuneus and the non-DMN regions, including the sensory processing regions (fusiform gyrus, postcentral gyrus) and the secondary motor cortex (supplementary motor area and precentral gyrus). Moreover, greater severity of depression was associated with greater anti-correlation between the precuneus and the temporo-parietal junction as well as stronger positive connectivity between the precuneus and the dorsomedial prefrontal cortex. These results indicate that dissociated large-scale networks of the precuneus may contribute to the clinical expression of depression in MDD. [ABSTRACT FROM AUTHOR]

Mild cognitive impairment (MCI) has been considered as a transition phase to Alzheimer's disease (AD), and the diagnosis of MCI may help patients to carry out appropriate treatments to delay or even prevent AD. Recent advanced network analysis techniques utilizing resting-state functional Magnetic Resonance Imaging (rs-fMRI) has been widely used to get more comprehensive understanding of neurological disorders at a whole-brain connectivity level. However, how to explore effective brain functional connectivity from fMRI data is still a challenge especially when the ultimate goal is to train classifiers for discriminating patients effectively. In our research, we studied the functional connectivity of the whole brain by calculating Pearson's correlation coefficients based on rs-fMRI data, and proposed a set of novel features by applying Two Sample T-Test on the correlation coefficients matrix to identify the most discriminative correlation coefficients. We trained a L2-regularized Logistic Regression classifier based on the five novel features for the first time and evaluated the classification performance via leave-one-out cross validation. We also iterated 10-fold cross validation ten times in order to evaluate the statistical significance of our method. The experiment result demonstrates that classification accuracy and the area under receiver operating characteristic (ROC) curve in our method are 87.5% and 0.929 respectively, and the statistical results prove that our method is statistically significant better than other three algorithms, which means our method could be meaningful to assist physicians efficiently in “real-world” diagnostic situations. [ABSTRACT FROM PUBLISHER]

Recently, brain connectivity networks have been used for classification of Alzheimer's disease and mild cognitive impairment (MCI) from normal controls (NC). In typical connectivity-networks-based classification approaches, local measures of connectivity networks are first extracted from each region-of-interest as network features, which are then concatenated into a vector for subsequent feature selection and classification. However, some useful structural information of network, especially global topological information, may be lost in this type of approaches. To address this issue, in this article, we propose a connectivity-networks-based classification framework to identify accurately the MCI patients from NC. The core of the proposed method involves the use of a new graph-kernel-based approach to measure directly the topological similarity between connectivity networks. We evaluate our method on functional connectivity networks of 12 MCI and 25 NC subjects. The experimental results show that our proposed method achieves a classification accuracy of 91.9%, a sensitivity of 100.0%, a balanced accuracy of 94.0%, and an area under receiver operating characteristic curve of 0.94, demonstrating a great potential in MCI classification, based on connectivity networks. Further connectivity analysis indicates that the connectivity of the selected brain regions is different between MCI patients and NC, that is, MCI patients show reduced functional connectivity compared with NC, in line with the findings reported in the existing studies. Hum Brain Mapp 35:2876-2897, 2014. © 2013 Wiley Periodicals, Inc. [ABSTRACT FROM AUTHOR]

Abstract: The functional architecture of the human brain has been extensively described in terms of functional connectivity networks, detected from the low-frequency coherent neuronal fluctuations during a resting state condition. Accumulating evidence suggests that the overall organization of functional connectivity networks is associated with individual differences in cognitive performance and prior experience. Such an association raises the question of how cognitive expertise exerts an influence on the topological properties of large-scale functional networks. To address this question, we examined the overall organization of brain functional networks in 20 grandmaster and master level Chinese-chess players (GM/M) and twenty novice players, by means of resting-state functional connectivity and graph theoretical analyses. We found that, relative to novices, functional connectivity was increased in GM/Ms between basal ganglia, thalamus, hippocampus, and several parietal and temporal areas, suggesting the influence of cognitive expertise on intrinsic connectivity networks associated with learning and memory. Furthermore, we observed economical small-world topology in the whole-brain functional connectivity networks in both groups, but GM/Ms exhibited significantly increased values of normalized clustering coefficient which resulted in increased small-world topology. These findings suggest an association between the functional organization of brain networks and individual differences in cognitive expertise, which might provide further evidence of the mechanisms underlying expert behavior. [Copyright &y& Elsevier]

Subcortical ischemic vascular disease could induce subcortical vascular cognitive impairments (SVCIs), such as amnestic mild cognitive impairment (aMCI) and non-amnestic MCI (naMCI), or sometimes no cognitive impairment (NCI). Previous SVCI studies focused on focal structural lesions such as lacunes and microbleeds, while the functional connectivity networks (FCNs) from functional magnetic resonance imaging are drawing increasing attentions. Considering remarkable variations in structural lesion sizes, we expect that seeking abnormalities in the multiscale hierarchy of brain FCNs could be more informative to differentiate SVCI patients with varied outcomes (NCI, aMCI, and naMCI). Driven by this hypothesis, we first build FCNs based on the atlases at multiple spatial scales for group comparisons and found distributed FCN differences across different spatial scales. We then verify that combining multiscale features in a prediction model could improve differentiation accuracy among NCI, aMCI, and naMCI. Furthermore, we propose a graph convolutional network to integrate the naturally emerged multiscale features based on the brain network hierarchy, which significantly outperforms all other competing methods. In addition, the predictive features derived from our method consistently emphasize the limbic network in identifying aMCI across the different scales. The proposed analysis provides a better understanding of SVCI and may benefit its clinical diagnosis., (© The Author(s) 2022. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permission@oup.com.)

The human brain is a large-scale integrated network in the functional and structural domain. Graph theoretical analysis provides a novel framework for analysing such complex networks. While previous neuroimaging studies have uncovered abnormalities in several specific brain networks in patients with idiopathic generalized epilepsy characterized by tonic–clonic seizures, little is known about changes in whole-brain functional and structural connectivity networks. Regarding functional and structural connectivity, networks are intimately related and share common small-world topological features. We predict that patients with idiopathic generalized epilepsy would exhibit a decoupling between functional and structural networks. In this study, 26 patients with idiopathic generalized epilepsy characterized by tonic–clonic seizures and 26 age- and sex-matched healthy controls were recruited. Resting-state functional magnetic resonance imaging signal correlations and diffusion tensor image tractography were used to generate functional and structural connectivity networks. Graph theoretical analysis revealed that the patients lost optimal topological organization in both functional and structural connectivity networks. Moreover, the patients showed significant increases in nodal topological characteristics in several cortical and subcortical regions, including mesial frontal cortex, putamen, thalamus and amygdala relative to controls, supporting the hypothesis that regions playing important roles in the pathogenesis of epilepsy may display abnormal hub properties in network analysis. Relative to controls, patients showed further decreases in nodal topological characteristics in areas of the default mode network, such as the posterior cingulate gyrus and inferior temporal gyrus. Most importantly, the degree of coupling between functional and structural connectivity networks was decreased, and exhibited a negative correlation with epilepsy duration in patients. Our findings suggest that the decoupling of functional and structural connectivity may reflect the progress of long-term impairment in idiopathic generalized epilepsy, and may be used as a potential biomarker to detect subtle brain abnormalities in epilepsy. Overall, our results demonstrate for the first time that idiopathic generalized epilepsy is reflected in a disrupted topological organization in large-scale brain functional and structural networks, thus providing valuable information for better understanding the pathophysiological mechanisms of generalized tonic–clonic seizures. [ABSTRACT FROM PUBLISHER]

Exposure to mental stress for long period leads to serious accidents and health problems. To avoid negative consequences on health and safety, it is very important to detect mental stress at its early stages, i.e., when it is still limited to acute or episodic stress. In this study, we developed an experimental protocol to induce two different levels of stress by utilizing a mental arithmetic task with time pressure and negative feedback as the stressors. We assessed the levels of stress on 22 healthy subjects using frontal electroencephalogram (EEG) signals, salivary alpha-amylase level (AAL), and multiple machine learning (ML) classifiers. The EEG signals were analyzed using a fusion of functional connectivity networks estimated by the Phase Locking Value (PLV) and temporal and spectral domain features. A total of 210 different features were extracted from all domains. Only the optimum multi-domain features were used for classification. We then quantified stress levels using statistical analysis and seven ML classifiers. Our result showed that the AAL level was significantly increased (p < 0.01) under stress condition in all subjects. Likewise, the functional connectivity network demonstrated a significant decrease under stress, p < 0.05. Moreover, we achieved the highest stress classification accuracy of 93.2% using the Support Vector Machine (SVM) classifier. Other classifiers produced relatively similar results. [ABSTRACT FROM AUTHOR]

Background: The purpose of this study was to analyze "small world" characteristics in glioma patients in order to understand the relationship between cognitive dysfunction and brain functional connectivity network in the resting state. Methods: Resting-state magnetoencephalography was performed in 20 patients with glioma and 20 healthy subjects. The clustering coefficient of the resting functional connectivity network in the brain, average path length, and "small world" index (SWI) were calculated. Cognitive function was estimated by testing of attention, verbal fluency, memory, athletic ability, visual-spatial ability, and intelligence. Results: Compared with healthy controls, patients with glioma showed decreased cognitive function, and diminished low and high gamma band "small world" characteristics in the resting functional connectivity network. Conclusion: The SWI is associated with cognitive function and is diminished in patients with glioma, and is therefore correlated with cognition dysfunction. [ABSTRACT FROM AUTHOR]

Functional connectivity networks (FCNs) provide a potential way for understanding the brain organizational patterns and diagnosing neurological diseases. Currently, researchers have proposed many methods for FCN construction, among which the most classic example is Pearson's correlation (PC). Despite its simplicity and popularity, PC always results in dense FCNs, and thus a thresholding strategy is usually needed in practice to sparsify the estimated FCNs prior to the network analysis, which undoubtedly causes the problem of threshold parameter selection. As an alternative to PC, sparse representation (SR) can directly generate sparse FCNs due to the l1 regularizer in the estimation model. However, similar to the thresholding scheme used in PC, it is also challenging to determine suitable values for the regularization parameter in SR. To circumvent the difficulty of parameter selection involved in these traditional methods, we propose a hyperparameter-free method for FCN construction based on the global representation among fMRI time courses. Interestingly, the proposed method can automatically generate sparse FCNs, without any thresholding or regularization parameters. To verify the effectiveness of the proposed method, we conduct experiments to identify subjects with mild cognitive impairment (MCI) and Autism spectrum disorder (ASD) from normal controls (NCs) based on the estimated FCNs. Experimental results on two benchmark databases demonstrate that the achieved classification performance of our proposed scheme is comparable to four conventional methods. [ABSTRACT FROM AUTHOR]

• A new wc-kernel to measure the correlation of brain regions, with weights learned in a data-driven manner to characterize specific contributions of different time points, is proposed. • A unified wc-kernel-based CNN framework to define functional connectivity networks and extract hierarchical connectivities for disease diagnosis is developed. • Achieving an accuracy of 84.6%, 88.0% and 57.0 for eMCI (early MCI) vs. HC (healthy control), AD vs. HC, and AD vs. lMCI (later MCI) vs. eMCI vs. HC classifications, respectively. Functional connectivity networks (FCNs) based on functional magnetic resonance imaging (fMRI) have been widely applied to analyzing and diagnosing brain diseases, such as Alzheimer's disease (AD) and its prodrome stage, i.e. , mild cognitive impairment (MCI). Existing studies usually use Pearson correlation coefficient (PCC) method to construct FCNs, and then extract network measures (e.g. , clustering coefficients) as features to learn a diagnostic model. However, the valuable observation information in network construction (e.g. , specific contributions of different time points), as well as high-level and high-order network features are neglected in these studies. In this paper, we first define a novel weighted correlation kernel (called wc-kernel) to measure the correlation of brain regions, by which weighting factors are learned in a data-driven manner to characterize the contributions of different time points, thus conveying the richer interaction information among brain regions compared with the PCC method. Furthermore, we build a wc-kernel based convolutional neural network (CNN) (called wck-CNN) framework for learning the hierarchical (i.e. , from local to global and also from low-level to high-level) features for disease diagnosis, by using fMRI data. Specifically, we first define a layer to build dynamic FCNs using our proposed wc-kernels. Then, we define another three layers to sequentially extract local (brain region specific), global (brain network specific) and temporal features from the constructed dynamic FCNs for classification. Experimental results on 174 subjects (a total of 563 scans) with rest-state fMRI (rs-fMRI) data from ADNI database demonstrate the efficacy of our proposed method. [ABSTRACT FROM AUTHOR]