Functional Connectivity Features Research Articles

A sex-dependent functional-effective connectivity model for diagnostic classification of Autism Spectrum Disorder using resting-state fMRI

Autism spectrum disorder (ASD) is a neurodevelopmental disorder associated with deficits in social interactions. Currently, its diagnosis is done by behavioral tests. Previous studies have shown that connections between brain regions can be a suitable biomarker for the diagnosis of ASD from normal control (NC). Also, differences in the connections of the brain regions of ASD individuals have been shown between male and female groups. This study, proposed a sex-dependent functional-effective connectivity model for the diagnostic classification of ASD using resting-state fMRI (rs-fMRI).After preprocessing, dual regression independent component analysis (ICA) was applied to obtain the time course of each resting state network (RSN) for each subject. To investigate the role of sex, two male and female groups were considered. Functional connectivity (FC) between time series of RSNs were extracted using full and partial correlation. Also, effective connectivity (EC) was extracted using bivariate granger causality. Two feature selection approacheswere proposedbased on different modes of combining FC and EC features. Finally, the classification accuracy was obtained using thirteen different classifiers for each sex group.The highest classification accuracy of 96.6% in the male group was achieved by using the combination of partial correlation (FC) and granger causality (EC) features, while in the female group, the highest classification accuracy of 93.3% was obtained by all the combinations that used full correlation (FC) features.The results have shown the combination of features obtained from FC and EC can lead to improved classification accuracy in male and female groups.

Tracking functional network connectivity dynamics in the elderly.

Functional magnetic resonance imaging (fMRI) has shown that aging disturbs healthy brain organization and functional connectivity. However, how this age-induced alteration impacts dynamic brain function interaction has not yet been fully investigated. Dynamic function network connectivity (DFNC) analysis can produce a brain representation based on the time-varying network connectivity changes, which can be further used to study the brain aging mechanism for people at different age stages. This presented investigation examined the dynamic functional connectivity representation and its relationship with brain age for people at an elderly stage as well as in early adulthood. Specifically, the resting-state fMRI data from the University of North Carolina cohort of 34 young adults and 28 elderly participants were fed into a DFNC analysis pipeline. This DFNC pipeline forms an integrated dynamic functional connectivity (FC) analysis framework, which consists of brain functional network parcellation, dynamic FC feature extraction, and FC dynamics examination. The statistical analysis demonstrates that extensive dynamic connection changes in the elderly concerning the transient brain state and the method of functional interaction in the brain. In addition, various machine learning algorithms have been developed to verify the ability of dynamic FC features to distinguish the age stage. The fraction time of DFNC states has the highest performance, which can achieve a classification accuracy of over 88% by a decision tree. The results proved there are dynamic FC alterations in the elderly, and the alteration was found to be correlated with mnemonic discrimination ability and could have an impact on the balance of functional integration and segregation.

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification

This paper uses EEG data to introduce an approach for classifying right and left-hand classes in Motor Imagery (MI) tasks. The Kernel Cross-Spectral Functional Connectivity Network (KCS-FCnet) method addresses these limitations by providing richer spatial-temporal-spectral feature maps, a simpler architecture, and a more interpretable approach for EEG-driven MI discrimination. In particular, KCS-FCnet uses a single 1D-convolutional-based neural network to extract temporal-frequency features from raw EEG data and a cross-spectral Gaussian kernel connectivity layer to model channel functional relationships. As a result, the functional connectivity feature map reduces the number of parameters, improving interpretability by extracting meaningful patterns related to MI tasks. These patterns can be adapted to the subject's unique characteristics. The validation results prove that introducing KCS-FCnet shallow architecture is a promising approach for EEG-based MI classification with the potential for real-world use in brain-computer interface systems.

Automated major depressive disorder diagnosis using a dual-input deep learning model and image generation from EEG signals

Major depressive disorder (MDD) is conventionally diagnosed through a questionnaire. Since approaches to diagnose MDD may lead to inaccurate diagnoses, many studies have presented electroencephalogram (EEG)-based machine learning techniques. The present paper introduces a deep learning approach based on image construction from EEGs. Two images are constructed from EEGs based on spectral and functional connectivity features. Afterward, the constructed images are applied to a two-stream convolutional neural network, and the outputs are concatenated. Finally, the concatenating result is applied to a sequential model of long–short-term memory, fully connected, and softmax layers to classify each sample into the MDD and healthy control (HC) classes. To validate the proposed approach, a public EEG dataset was used consisting of EEG data recorded from 34 MDD patients and 30 HC-matched participants. This framework obtained an AC of 98.03%, SE of 98.85%, SP of 97.19%, F1 of 98.07%, and FDR of 2.69% for the random splitting assessment method and achieved an average AC of 99.11%, SE of 98.97%, SP of 99.25%, F1 of 99.13%, and FDR of 0.71% using a 10-fold cross-validation process. Considering the accurate performance of the proposed method, it can be developed as a computer-aided diagnosis tool to diagnose MDD automatically.

Environmental effects on brain functional networks in a juvenile twin population

The brain’s intrinsic organization into large-scale functional networks, the resting state networks (RSN), shows complex inter-individual variability, consolidated during development. Nevertheless, the role of gene and environment on developmental brain functional connectivity (FC) remains largely unknown. Twin design represents an optimal platform to shed light on these effects acting on RSN characteristics. In this study, we applied statistical twin methods to resting-state functional magnetic resonance imaging (rs-fMRI) scans from 50 young twin pairs (aged 10–30 years) to preliminarily explore developmental determinants of brain FC. Multi-scale FC features were extracted and tested for applicability of classical ACE and ADE twin designs. Epistatic genetic effects were also assessed. In our sample, genetic and environmental effects on the brain functional connections largely varied between brain regions and FC features, showing good consistency at multiple spatial scales. Although we found selective contributions of common environment on temporo-occipital connections and of genetics on frontotemporal connections, the unique environment showed a predominant effect on FC link- and node-level features. Despite the lack of accurate genetic modeling, our preliminary results showed complex relationships between genes, environment, and functional brain connections during development. A predominant role of the unique environment on multi-scale RSN characteristics was suggested, which needs replications on independent samples. Future investigations should especially focus on nonadditive genetic effects, which remain largely unexplored.

The relationship between depressive symptoms and cognitive function in Alzheimer's disease: The mediating effect of amygdala functional connectivity and radiomic features

BackgroundDepressive symptoms are common in Alzheimer's disease (AD) and are associated with cognitive function. Amygdala functional connectivity (FC) and radiomic features related to depression and cognition. However, studies have yet to explore the neural mechanisms underlying these associations. MethodsWe enrolled eighty-two AD patients with depressive symptoms (ADD) and 85 healthy controls (HCs) in this study. We compared amygdala FC using the seed-based approach between ADD patients and HCs. The least absolute shrinkage and selection operator (LASSO) was used to select amygdala radiomic features. A support vector machine (SVM) model was constructed based on the identified radiomic features to distinguish ADD from HCs. We used mediation analyses to explore the mediating effects of amygdala radiomic features and amygdala FC on cognition. ResultsWe found that ADD patients showed decreased amygdala FC with posterior cingulate cortex, middle frontal gyrus (MFG), and parahippocampal gyrus involved in the default mode network compared to HCs. The area under the receiver operating characteristic curve (AUC) of the amygdala radiomic model was 0.95 for ADD patients and HCs. Notably, the mediation model demonstrated that amygdala FC with the MFG and amygdala-based radiomic features mediated the relationship between depressive symptoms and cognitive function in AD. LimitationsThis study is a cross-sectional study and lacks longitudinal data. ConclusionOur findings may not only expand existing biological knowledge of the relationship between cognition and depressive symptoms in AD from the perspective of brain function and structure but also may ultimately provide potential targets for personalized treatment strategies.

Source-Space Brain Functional Connectivity Features in Electroencephalogram-Based Driver Fatigue Classification

This study examined the brain source space functional connectivity from the electroencephalogram (EEG) activity of 48 participants during a driving simulation experiment where they drove until fatigue developed. Source-space functional connectivity (FC) analysis is a state-of-the-art method for understanding connections between brain regions that may indicate psychological differences. Multi-band FC in the brain source space was constructed using the phased lag index (PLI) method and used as features to train an SVM classification model to classify driver fatigue and alert conditions. With a subset of critical connections in the beta band, a classification accuracy of 93% was achieved. Additionally, the source-space FC feature extractor demonstrated superiority over other methods, such as PSD and sensor-space FC, in classifying fatigue. The results suggested that source-space FC is a discriminative biomarker for detecting driving fatigue.

Emotion recognition using spatial-temporal EEG features through convolutional graph attention network

Objective. Constructing an efficient human emotion recognition model based on electroencephalogram (EEG) signals is significant for realizing emotional brain–computer interaction and improving machine intelligence. Approach. In this paper, we present a spatial-temporal feature fused convolutional graph attention network (STFCGAT) model based on multi-channel EEG signals for human emotion recognition. First, we combined the single-channel differential entropy (DE) feature with the cross-channel functional connectivity (FC) feature to extract both the temporal variation and spatial topological information of EEG. After that, a novel convolutional graph attention network was used to fuse the DE and FC features and further extract higher-level graph structural information with sufficient expressive power for emotion recognition. Furthermore, we introduced a multi-headed attention mechanism in graph neural networks to improve the generalization ability of the model. Main results. We evaluated the emotion recognition performance of our proposed model on the public SEED and DEAP datasets, which achieved a classification accuracy of 99.11% ± 0.83% and 94.83% ± 3.41% in the subject-dependent and subject-independent experiments on the SEED dataset, and achieved an accuracy of 91.19% ± 1.24% and 92.03% ± 4.57% for discrimination of arousal and valence in subject-independent experiments on DEAP dataset. Notably, our model achieved state-of-the-art performance on cross-subject emotion recognition tasks for both datasets. In addition, we gained insight into the proposed frame through both the ablation experiments and the analysis of spatial patterns of FC and DE features. Significance. All these results prove the effectiveness of the STFCGAT architecture for emotion recognition and also indicate that there are significant differences in the spatial-temporal characteristics of the brain under different emotional states.

Discovering functional connectivity features characterizing multiple sclerosis phenotypes using explainable artificial intelligence.

Multiple sclerosis (MS) is a neurological condition characterized by severe structural brain damage and by functional reorganization of the main brain networks that try to limit the clinical consequences of structural burden. Resting-state (RS) functional connectivity (FC) abnormalities found in this condition were shown to be variable across different MS phases, according to the severity of clinical manifestations. The article describes a system exploiting machine learning on RS FC matrices to discriminate different MS phenotypes and to identify relevant functional connections for MS stage characterization. To this end, the system exploits some mathematical properties of covariance-based RS FC representation, which can be described by a Riemannian manifold. The classification performance of the proposed framework was significantly above the chance level for all MS phenotypes. Moreover, the proposed system was successful in identifying relevant RS FC alterations contributing to an accurate phenotype classification.

The Static and dynamic functional connectivity characteristics of the left temporoparietal junction region in schizophrenia patients with auditory verbal hallucinations during low-frequency rTMS treatment.

Auditory verbal hallucinations (AVH) are a core symptom of schizophrenia. Low-frequency (e.g., 1 Hz) repetitive transcranial magnetic stimulation (rTMS) targeting language processing regions (e.g., left TPJ) has been evident as a potential treatment for AVH. However, the underlying neural mechanisms of the rTMS treatment effect remain unclear. The present study aimed to investigate the effects of 1 Hz rTMS on functional connectivity (FC) of the temporoparietal junction area (TPJ) seed with the whole brain in schizophrenia patients with AVH. Using a single-blind placebo-controlled randomized clinical trial, 55 patients with AVH were randomly divided into active treatment group (n = 30) or placebo group (n = 25). The active treatment group receive 15-day 1 Hz rTMS stimulation to the left TPJ, whereas the placebo group received sham rTMS stimulation to the same site. Resting-state fMRI scans and clinical measures were acquired for all patients before and after treatment. The seed-based (left TPJ) static and DFC was used to assess the connectivity characteristics during rTMS treatment in patients with AVH. Overall, symptom improvement following 1 Hz rTMS treatment was found in the active treatment group, whereas no change occurred in the placebo group. Moreover, decreased static FC (SFC) of the left TPJ with the right temporal lobes, as well as increased SFC with the prefrontal cortex and subcortical structure were observed in active rTMS group. Increased dynamic FC (DFC) of the left TPJ with frontoparietal areas was also found in the active rTMS group. However, seed-based SFC and DFC were reduced to a great extent in the placebo group. In addition, these changed FC (SFC) strengths in the active rTMS group were associated with reduced severity of clinical outcomes (e.g., positive symptoms). The application of 1 Hz rTMS over the left TPJ may affect connectivity characteristics of the targeted region and contribute to clinical improvement, which shed light on the therapeutic effect of rTMS on schizophrenia with AVH.

Predictive signature of static and dynamic functional connectivity for ECT clinical outcomes.

Introduction: Electroconvulsive therapy (ECT) remains one of the most effective approaches for treatment-resistant depressive episodes, despite the potential cognitive impairment associated with this treatment. As a potent stimulator of neuroplasticity, ECT might normalize aberrant depression-related brain function via the brain's reconstruction by forming new neural connections. Multiple lines of evidence have demonstrated that functional connectivity (FC) changes are reliable indicators of antidepressant efficacy and cognitive changes from static and dynamic perspectives. However, no previous studies have directly ascertained whether and how different aspects of FC provide complementary information in terms of neuroimaging-based prediction of clinical outcomes. Methods: In this study, we implemented a fully automated independent component analysis framework to an ECT dataset with subjects (n = 50, age = 65.54 ± 8.92) randomized to three treatment amplitudes (600, 700, or 800 milliamperes [mA]). We extracted the static functional network connectivity (sFNC) and dynamic FNC (dFNC) features and employed a partial least square regression to build predictive models for antidepressant outcomes and cognitive changes. Results: We found that both antidepressant outcomes and memory changes can be robustly predicted by the changes in sFNC (permutation test p < 5.0 × 10-3). More interestingly, by adding dFNC information, the model achieved higher accuracy for predicting changes in the Hamilton Depression Rating Scale 24-item (HDRS24, t = 9.6434, p = 1.5 × 10-21). The predictive maps of clinical outcomes show a weakly negative correlation, indicating that the ECT-induced antidepressant outcomes and cognitive changes might be associated with different functional brain neuroplasticity. Discussion: The overall results reveal that dynamic FC is not redundant but reflects mechanisms of ECT that cannot be captured by its static counterpart, especially for the prediction of antidepressant efficacy. Tracking the predictive signatures of static and dynamic FC will help maximize antidepressant outcomes and cognitive safety with individualized ECT dosing.

Whole-brain functional gradients reveal cortical and subcortical alterations in patients with episodic migraine.

Migraine is a type of headache with multiple neurological symptoms. Prior neuroimaging studies in patients with migraine based on functional magnetic resonance imaging have found regional as well as network-level alterations in brain function. Here, we expand on prior studies by establishing whole-brain functional connectivity patterns in patients with migraine using dimensionality reduction techniques. We studied functional brain connectivity in 50 patients with episodic migraine and sex- and age-matched healthy controls. Using dimensionality reduction techniques that project high-dimensional functional connectivity onto low-dimensional representations (i.e., eigenvectors), we found significant between-group differences in the eigenvectors between patients with migraine and healthy controls, particularly in the sensory/motor and limbic cortices. Furthermore, we assessed between-group differences in subcortical connectivity with subcortical weighted manifolds defined by subcortico-cortical connectivity multiplied by cortical eigenvectors and revealed significant alterations in the amygdala. Finally, leveraging supervised machine learning, we moderately predicted headache frequency using cortical and subcortical functional connectivity features, again indicating that sensory and limbic regions play a particularly important role in predicting migraine frequency. Our study confirmed that migraine is a hierarchical disease of the brain that shows alterations along the sensory-limbic axis, and therefore, the functional connectivity in these areas could be a useful marker to investigate migraine symptomatology.

An objective model for diagnosing comorbid cognitive impairment in patients with epilepsy based on the clinical-EEG functional connectivity features.

Cognitive impairment (CI) is a common disorder in patients with epilepsy (PWEs). Objective assessment method for diagnosing CI in PWEs would be beneficial in reality. This study proposed to construct a diagnostic model for CI in PWEs using the clinical and the phase locking value (PLV) functional connectivity features of the electroencephalogram (EEG). PWEs who met the inclusion and exclusion criteria were divided into a cognitively normal (CON) group (n = 55) and a CI group (n = 76). The 23 clinical features and 684 PLV EEG features at the time of patient visit were screened and ranked using the Fisher score. Adaptive Boosting (AdaBoost) and Gradient Boosting Decision Tree (GBDT) were used as algorithms to construct diagnostic models of CI in PWEs either with pure clinical features, pure PLV EEG features, or combined clinical and PLV EEG features. The performance of these models was assessed using a five-fold cross-validation method. GBDT-built model with combined clinical and PLV EEG features performed the best with accuracy, precision, recall, F1-score, and an area under the curve (AUC) of 90.11, 93.40, 89.50, 91.39, and 0.95%. The top 5 features found to influence the model performance based on the Fisher scores were the magnetic resonance imaging (MRI) findings of the head for abnormalities, educational attainment, PLV EEG in the beta (β)-band C3-F4, seizure frequency, and PLV EEG in theta (θ)-band Fp1-Fz. A total of 12 of the top 5% of features exhibited statistically different PLV EEG features, while eight of which were PLV EEG features in the θ band. The model constructed from the combined clinical and PLV EEG features could effectively identify CI in PWEs and possess the potential as a useful objective evaluation method. The PLV EEG in the θ band could be a potential biomarker for the complementary diagnosis of CI comorbid with epilepsy.

Predicting in vitro single-neuron firing rates upon pharmacological perturbation using Graph Neural Networks.

Modern Graph Neural Networks (GNNs) provide opportunities to study the determinants underlying the complex activity patterns of biological neuronal networks. In this study, we applied GNNs to a large-scale electrophysiological dataset of rodent primary neuronal networks obtained by means of high-density microelectrode arrays (HD-MEAs). HD-MEAs allow for long-term recording of extracellular spiking activity of individual neurons and networks and enable the extraction of physiologically relevant features at the single-neuron and population level. We employed established GNNs to generate a combined representation of single-neuron and connectivity features obtained from HD-MEA data, with the ultimate goal of predicting changes in single-neuron firing rate induced by a pharmacological perturbation. The aim of the main prediction task was to assess whether single-neuron and functional connectivity features, inferred under baseline conditions, were informative for predicting changes in neuronal activity in response to a perturbation with Bicuculline, a GABA A receptor antagonist. Our results suggest that the joint representation of node features and functional connectivity, extracted from a baseline recording, was informative for predicting firing rate changes of individual neurons after the perturbation. Specifically, our implementation of a GNN model with inductive learning capability (GraphSAGE) outperformed other prediction models that relied only on single-neuron features. We tested the generalizability of the results on two additional datasets of HD-MEA recordings-a second dataset with cultures perturbed with Bicuculline and a dataset perturbed with the GABA A receptor antagonist Gabazine. GraphSAGE models showed improved prediction accuracy over other prediction models. Our results demonstrate the added value of taking into account the functional connectivity between neurons and the potential of GNNs to study complex interactions between neurons.

Diagnostic identification of chronic insomnia using ALFF and FC features of resting-state functional MRI and logistic regression approach

This study investigated whether the amplitude of low-frequency fluctuation (ALFF) and functional connectivity (FC) features could be used as potentially neurological markers to identify chronic insomnia (CI) using resting-state functional MRI and machine learning method logistic regression (LR). This study included 49 CI patients and 47 healthy controls (HC). Voxel-wise features, including the amplitude of low-frequency fluctuations (ALFF) and functional connectivity (FC), were extracted from resting-state functional magnetic resonance brain images. Then, we divided the data into two independent cohorts for training (44 CI patients and 42 HC patients), and independent validation (5 CI patients and 5 HC patients) by using logistic regression. The model was evaluated using 20 rounds of fivefold cross‑validation for training. In particular, a two-sample t-test (GRF corrected, p-voxel < 0.001, p-cluster < 0.05) was used for feature selection during the model training. Finally, single‑shot testing of the final model was performed on the independent validation cohort. A correlation analysis (Bonferroni correction, p < 0.05/4) was also conducted to determine whether the features contributing to the prediction were correlated with clinical characteristics, including the Insomnia Severity Index (ISI), Pittsburgh sleep quality index (PSQI), self-rating anxiety scale (SAS), and self-rating depression scale (SDS). Results showed that resting-state features had a discrimination accuracy of 86.40%, with a sensitivity of 93.00% and specificity of 79.80%. The area under the curve (AUC) was 0.89 (all {P}_{mathrm{permutation}}< 0.001). The ALFF and FC features showed significant differences between the CI patients and HC. The regions contributing to the prediction mainly included the anterior cingulate, prefrontal cortex, orbital part of the frontal lobe, angular gyrus, cingulate gyrus, praecuneus, parietal lobe, temporal gyrus, superior temporal gyrus, and middle temporal gyrus. Furthermore, some specific functional connectivity among related regions was positively correlated with the ISI, and also negatively related to the SDS in correlation analysis. Our current study suggested that ALFF and FC in the regions contributing to diagnostic identification might serve as potential neuromarkers for CI.

BrainTGL: A dynamic graph representation learning model for brain network analysis

Modeling the dynamics characteristics in functional brain networks (FBNs) is important for understanding the functional mechanism of the human brain. However, the current works do not fully consider the potential complex spatial and temporal correlations in human brain. To solve this problem, we propose a temporal graph representation learning framework for brain networks (BrainTGL). The framework involves a temporal graph pooling for eliminating the noisy edges as well as data inconsistency, and a dual temporal graph learning for capturing the spatio-temporal features of the temporal graphs. The proposed method has been evaluated in both tasks of brain disease (ASD, MDD and BD) diagnosis/gender classification (classification task) and subtype identification (clustering task) on the four datasets: Human Connectome Project (HCP), Autism Brain Imaging Data Exchange (ABIDE), NMU-MDD and NMU-BD. A large improvement is achieved for the ASD diagnosis. Specifically, our model outperforms the GroupINN and ST-GCN by an average increase of 4.2% and 8.6% on accuracy, respectively, demonstrating its advantages in comparison to the state-of-the-art methods based on functional connectivity features or learned spatio-temporal features. The results demonstrate that learning the spatial–temporal brain network representation for modeling dynamics characteristics in FBNs can improve the model’s performance on both disease diagnosis and subtype identification tasks for multiple disorders. Apart from performance, the improvements of computational efficiency and convergence speed reduce training costs.

Decreased default mode network functional connectivity with visual processing regions as potential biomarkers for delayed neurocognitive recovery: A resting-state fMRI study and machine-learning analysis.

The abnormal functional connectivity (FC) pattern of default mode network (DMN) may be key markers for early identification of various cognitive disorders. However, the whole-brain FC changes of DMN in delayed neurocognitive recovery (DNR) are still unclear. Our study was aimed at exploring the whole-brain FC patterns of all regions in DMN and the potential features as biomarkers for the prediction of DNR using machine-learning algorithms. Resting-state functional magnetic resonance imaging (fMRI) was conducted before surgery on 74 patients undergoing non-cardiac surgery. Seed-based whole-brain FC with 18 core regions located in the DMN was performed, and FC features that were statistically different between the DNR and non-DNR patients after false discovery correction were extracted. Afterward, based on the extracted FC features, machine-learning algorithms such as support vector machine, logistic regression, decision tree, and random forest were established to recognize DNR. The machine learning experiment procedure mainly included three following steps: feature standardization, parameter adjustment, and performance comparison. Finally, independent testing was conducted to validate the established prediction model. The algorithm performance was evaluated by a permutation test. We found significantly decreased DMN connectivity with the brain regions involved in visual processing in DNR patients than in non-DNR patients. The best result was obtained from the random forest algorithm based on the 20 decision trees (estimators). The random forest model achieved the accuracy, sensitivity, and specificity of 84.0, 63.1, and 89.5%, respectively. The area under the receiver operating characteristic curve of the classifier reached 86.4%. The feature that contributed the most to the random forest model was the FC between the left retrosplenial cortex/posterior cingulate cortex and left precuneus. The decreased FC of DMN with regions involved in visual processing might be effective markers for the prediction of DNR and could provide new insights into the neural mechanisms of DNR. : Chinese Clinical Trial Registry, ChiCTR-DCD-15006096.

White-matter degradation and dynamical compensation support age-related functional alterations in human brain.

Structural connectivity of the brain at different ages is analyzed using diffusion-weighted magnetic resonance imaging (MRI) data. The largest decrease of streamlines is found in frontal regions and for long inter-hemispheric links. The average length of the tracts also decreases, but the clustering is unaffected. From functional MRI we identify age-related changes of dynamic functional connectivity (dFC) and spatial covariation features of functional connectivity (FC) links captured by metaconnectivity. They indicate more stable dFC, but wider range and variance of MC, whereas static features of FC did not show any significant differences with age. We implement individual connectivity in whole-brain models and test several hypotheses for the mechanisms of operation among underlying neural system. We demonstrate that age-related functional fingerprints are only supported if the model accounts for: (i) compensation of the individual brains for the overall loss of structural connectivity and (ii) decrease of propagation velocity due to the loss of myelination. We also show that with these 2 conditions, it is sufficient to decompose the time-delays as bimodal distribution that only distinguishes between intra- and inter-hemispheric delays, and that the same working point also captures the static FC the best, and produces the largest variability at slow time-scales.

The topology of fMRI-based networks defines the performance of a graph neural network for the classification of patients with major depressive disorder

Deep learning approaches are state-of-the-art computational tools employed at analyzing big data in fundamental and applied science. Recently, they gained popularity in neuroscience and medicine due to their ability to recognize hidden patterns and nonlinear relations in large amounts of nonstationary and ambiguous neuroimaging biomedical data. Analysis of functional connectivity matrices is a perfect example of such a computational task assigned to deep learning. Here, we trained a graph neural network (GNN) to classify the major depressive disorder (MDD) based on the topological features of the brain functional connectivity identified using fMRI technology. We show that the most important feature of the functional brain network is the shortest path, which defines the optimal number of GNN layers to ensure the most accurate classification in patients with MDD. The proposed GNN-based classifier reaches an accuracy of 93%, which is in line with the achievements of the best connectivity-based classifiers for MDD. The maximal F1-score is observed when we input the sparse graph consisting of 2.5% of the connections of the original one, which avoids feeding large amounts of data to the GNN and reduces overfitting.

Improving Multi-Site Autism Classification via Site-Dependence Minimization and Second-Order Functional Connectivity.

Machine learning has been widely used to develop classification models for autism spectrum disorder (ASD) using neuroimaging data. Recently, studies have shifted towards using large multi-site neuroimaging datasets to boost the clinical applicability and statistical power of results. However, the classification performance is hindered by the heterogeneous nature of agglomerative datasets. In this paper, we propose new methods for multi-site autism classification using the Autism Brain Imaging Data Exchange (ABIDE) dataset. We firstly propose a new second-order measure of functional connectivity (FC) named as Tangent Pearson embedding to extract better features for classification. Then we assess the statistical dependence between acquisition sites and FC features, and take a domain adaptation approach to minimize the site dependence of FC features to improve classification. Our analysis shows that 1) statistical dependence between site and FC features is statistically significant at the 5% level, and 2) extracting second-order features from neuroimaging data and minimizing their site dependence can improve over state-of-the-art (SOTA) classification results, achieving a classification accuracy of 73%. The code is available at https://github.com/kundaMwiza/fMRI-site-adaptation.