Functional Connectivity Features Research Articles

Electroencephalogram Functional Connectivity Analysis and Classification of Mental Arithmetic Working Memory Task

Analyzing brain activity during mental arithmetic tasks provides insight into psychological disorders such as ADHD, dyscalculia, and autism. While most research is conducted on the static functional connectivity of the brain while performing a cognitive task, the dynamic changes of the brain, which provide meaningful information for diagnosing individual differences in cognitive tasks, are often ignored. This paper aims to classify electroencephalogram (EEG) signals for rest vs. mental arithmetic task performance, using Bayesian functional connectivity features in the sensor space as inputs into a graph convolutional network. The subject-specific (intrasubject) classification performed on 36 subjects for rest vs. mental arithmetic task performance achieved the highest subject-specific classification accuracy of 98% and an average accuracy of 91% in the beta frequency band, outperforming state-of-the-art methods. In addition, statistical analysis confirms the consistency of Bayesian functional connectivity features compared to traditional functional connectivity features. Furthermore, the graph-theoretical analysis of functional connectivity networks reveals that good-performance subjects had higher global efficiency, betweenness centrality, and closeness centrality than bad-performance subjects. The ablation study on the classification of three cognitive states (subtraction, music, and memory) achieved a classification accuracy of 97%, and visual working memory (n-back task) achieved a classification accuracy of 94%, confirming the consistency and reliability of the proposed methodology.

Altered static and dynamic cerebellar-cerebral functional connectivity in acute pontine infarction.

This study investigates abnormalities in cerebellar-cerebral static and dynamic functional connectivity among patients with acute pontine infarction, examining the relationship between these connectivity changes and behavioral dysfunction. Resting-state functional magnetic resonance imaging was utilized to collect data from 45 patients within seven days post-pontine infarction and 34 normal controls. Seed-based static and dynamic functional connectivity analyses identified divergences in cerebellar-cerebral connectivity features between pontine infarction patients and normal controls. Correlations between abnormal functional connectivity features and behavioral scores were explored. Compared to normal controls, left pontine infarction patients exhibited significantly increased static functional connectivity within the executive, affective-limbic, and motor networks. Conversely, right pontine infarction patients demonstrated decreased static functional connectivity in the executive, affective-limbic, and default mode networks, alongside an increase in the executive and motor networks. Decreased temporal variability of dynamic functional connectivity was observed in the executive and default mode networks among left pontine infarction patients. Furthermore, abnormalities in static and dynamic functional connectivity within the executive network correlated with motor and working memory performance in patients. These findings suggest that alterations in cerebellar-cerebral static and dynamic functional connectivity could underpin the behavioral dysfunctions observed in acute pontine infarction patients.

Resting-state functional connectivity in children cooled for neonatal encephalopathy.

Therapeutic hypothermia improves outcomes following neonatal hypoxic-ischaemic encephalopathy, reducing cases of death and severe disability such as cerebral palsy compared with normothermia management. However, when cooled children reach early school-age, they have cognitive and motor impairments which are associated with underlying alterations to brain structure and white matter connectivity. It is unknown whether these differences in structural connectivity are associated with differences in functional connectivity between cooled children and healthy controls. Resting-state functional MRI has been used to characterize static and dynamic functional connectivity in children, both with typical development and those with neurodevelopmental disorders. Previous studies of resting-state brain networks in children with hypoxic-ischaemic encephalopathy have focussed on the neonatal period. In this study, we used resting-state fMRI to investigate static and dynamic functional connectivity in children aged 6-8 years who were cooled for neonatal hypoxic-ischaemic without cerebral palsy [n = 22, median age (interquartile range) 7.08 (6.85-7.52) years] and healthy controls matched for age, sex and socioeconomic status [n = 20, median age (interquartile range) 6.75 (6.48-7.25) years]. Using group independent component analysis, we identified 31 intrinsic functional connectivity networks consistent with those previously reported in children and adults. We found no case-control differences in the spatial maps of these intrinsic connectivity networks. We constructed subject-specific static functional connectivity networks by measuring pairwise Pearson correlations between component time courses and found no case-control differences in functional connectivity after false discovery rate correction. To study the time-varying organization of resting-state networks, we used sliding window correlations and deep clustering to investigate dynamic functional connectivity characteristics. We found k = 4 repetitively occurring functional connectivity states, which exhibited no case-control differences in dwell time, fractional occupancy or state functional connectivity matrices. In this small cohort, the spatiotemporal characteristics of resting-state brain networks in cooled children without severe disability were too subtle to be differentiated from healthy controls at early school-age, despite underlying differences in brain structure and white matter connectivity, possibly reflecting a level of recovery of healthy resting-state brain function. To our knowledge, this is the first study to investigate resting-state functional connectivity in children with hypoxic-ischaemic encephalopathy beyond the neonatal period and the first to investigate dynamic functional connectivity in any children with hypoxic-ischaemic encephalopathy.

Aberrant functional connectivity associated with drug response in patients with newly diagnosed epilepsy.

To analyze the local functional activity and connectivity features of the brain associated with drug response inpatients newly diagnosed with epilepsy (NDE) who are naïve to anti-seizure medication (ASM). Recruited patients, underwent functional magnetic resonance imaging at baseline, and were assigned to the well-controlled (WC, n = 28) or uncontrolled (UC, n = 11) groups based on their response to ASM. Healthy participants were included in the control group (HC, n = 29). The amplitudes of low-frequency fluctuation (ALFF) and fractional ALFF (fALFF) were used to measure local functional activity, and voxel-wise degree centrality (DC) and seed-based functional connectivity (FC) were used to evaluate the connecting intensity of the brain areas. Compared to the HC and WC groups, the UC group had higher ALFF values in the left posterior central gyrus (PoCG.L) and left inferior temporal gyrus (ITG.L) and higher DC in the bilateral PoCG (Gaussian random field correction, voxel-level P < 0.001, and cluster-level P < 0.05). Both PoCG and ITG.L in the UC group showed stronger FC with multiple brain regions, mainly located in the occipital and temporal lobes, compared to the HC or WC group, while the WC group showed decreased or similar FC compared to the HC group. Excessive enhancement of brain functional activity or connecting intensity in ASM-naïve patients with NDE may be associated with a higher risk of poor drug response.

Integration of temporal & spatial properties of dynamic functional connectivity based on two-directional two-dimensional principal component analysis for disease analysis.

Dynamic functional connectivity, derived from resting-state functional magnetic resonance imaging (rs-fMRI), has emerged as a crucial instrument for investigating and supporting the diagnosis of neurological disorders. However, prevalent features of dynamic functional connectivity predominantly capture either temporal or spatial properties, such as mean and global efficiency, neglecting the significant information embedded in the fusion of spatial and temporal attributes. In addition, dynamic functional connectivity suffers from the problem of temporal mismatch, i.e., the functional connectivity of different subjects at the same time point cannot be matched. To address these problems, this article introduces a novel feature extraction framework grounded in two-directional two-dimensional principal component analysis. This framework is designed to extract features that integrate both spatial and temporal properties of dynamic functional connectivity. Additionally, we propose to use Fourier transform to extract temporal-invariance properties contained in dynamic functional connectivity. Experimental findings underscore the superior performance of features extracted by this framework in classification experiments compared to features capturing individual properties.

Behaviour-correlated profiles of cerebellar-cerebral functional connectivity observed in independent neurodevelopmental disorder cohorts

The cerebellum, through its connectivity with the cerebral cortex, plays an integral role in regulating cognitive and affective processes, and its dysregulation can result in neurodevelopmental disorder (NDD)-related behavioural deficits. Identifying cerebellar-cerebral functional connectivity (FC) profiles in children with NDDs can provide insight into common connectivity profiles and their correlation to NDD-related behaviours. 479 participants from the Province of Ontario Neurodevelopmental Disorders (POND) network (typically developing = 93, Autism Spectrum Disorder = 172, Attention Deficit/Hyperactivity Disorder = 161, Obsessive-Compulsive Disorder = 53, mean age = 12.2) underwent resting-state functional magnetic resonance imaging and behaviour testing (Social Communication Questionnaire, Toronto Obsessive-Compulsive Scale, and Child Behaviour Checklist – Attentional Problems Subscale). FC components maximally correlated to behaviour were identified using canonical correlation analysis. Results were then validated by repeating the investigation in 556 participants from an independent NDD cohort provided from a separate consortium (Healthy Brain Network (HBN)). Replication of canonical components was quantified by correlating the feature vectors between the two cohorts. The two cerebellar-cerebral FC components that replicated to the greatest extent were correlated to, respectively, obsessive-compulsive behaviour (behaviour feature vectors, rPOND-HBN = −0.97; FC feature vectors, rPOND-HBN = −0.68) and social communication deficit contrasted against attention deficit behaviour (behaviour feature vectors, rPOND-HBN = −0.99; FC feature vectors, rPOND-HBN = −0.78). The statistically stable (|z| > 1.96) features of the FC feature vectors, measured via bootstrap re-sampling, predominantly comprised of correlations between cerebellar attentional and control network regions and cerebral attentional, default mode, and control network regions. In both cohorts, spectral clustering on FC loading values resulted in subject clusters mixed across diagnostic categories, but no cluster was significantly enriched for any given diagnosis as measured via chi-squared test (p > 0.05). Overall, two behaviour-correlated components of cerebellar-cerebral functional connectivity were observed in two independent cohorts. This suggests the existence of generalizable cerebellar network differences that span across NDD diagnostic boundaries.

Computational limits to the legibility of the imaged human brain

Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal.Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging.We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05).Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.

Brain Structural Connectivity Guided Vision Transformers for Identification of Functional Connectivity Characteristics in Preterm Neonates.

Preterm birth is the leading cause of death in children under five years old, and is associated with a wide sequence of complications in both short and long term. In view of rapid neurodevelopment during the neonatal period, preterm neonates may exhibit considerable functional alterations compared to term ones. However, the identified functional alterations in previous studies merely achieve moderate classification performance, while more accurate functional characteristics with satisfying discrimination ability for better diagnosis and therapeutic treatment is underexplored. To address this problem, we propose a novel brain structural connectivity (SC) guided Vision Transformer (SCG-ViT) to identify functional connectivity (FC) differences among three neonatal groups: preterm, preterm with early postnatal experience, and term. Particularly, inspired by the neuroscience-derived information, a novel patch token of SC/FC matrix is defined, and the SC matrix is then adopted as an effective mask into the ViT model to screen out input FC patch embeddings with weaker SC, and to focus on stronger ones for better classification and identification of FC differences among the three groups. The experimental results on multi-modal MRI data of 437 neonatal brains from publicly released Developing Human Connectome Project (dHCP) demonstrate that SCG-ViT achieves superior classification ability compared to baseline models, and successfully identifies holistically different FC patterns among the three groups. Moreover, these different FCs are significantly correlated with the differential gene expressions of the three groups. In summary, SCG-ViT provides a powerfully brain-guided pipeline of adopting large-scale and data-intensive deep learning models for medical imaging-based diagnosis.

Transcriptomic and neuroimaging data integration enhances machine learning classification of schizophrenia.

Schizophrenia is a polygenic disorder associated with changes in brain structure and function. Integrating macroscale brain features with microscale genetic data may provide a more complete overview of the disease etiology and may serve as potential diagnostic markers for schizophrenia. We aim to systematically evaluate the impact of multi-scale neuroimaging and transcriptomic data fusion in schizophrenia classification models. We collected brain imaging data and blood RNA sequencing data from 43 patients with schizophrenia and 60 age- and gender-matched healthy controls, and we extracted multi-omics features of macroscale brain morphology, brain structural and functional connectivity, and gene transcription of schizophrenia risk genes. Multi-scale data fusion was performed using a machine learning integration framework, together with several conventional machine learning methods and neural networks for patient classification. We found that multi-omics data fusion in conventional machine learning models achieved the highest accuracy (AUC ~0.76-0.92) in contrast to the single-modality models, with AUC improvements of 8.88 to 22.64%. Similar findings were observed for the neural network, showing an increase of 16.57% for the multimodal classification model (accuracy71.43%) compared to the single-modal average. In addition, we identified several brain regions in the left posterior cingulate and right frontal pole that made a major contribution to disease classification. We provide empirical evidence for the increased accuracy achieved by imaging genetic data integration in schizophrenia classification. Multi-scale data fusion holds promise for enhancing diagnostic precision, facilitating early detection and personalizing treatment regimens in schizophrenia.

Machine learning based on functional and structural connectivity in mild cognitive impairment

ObjectiveAlzheimer's disease (AD) is a chronic, degenerative neurological disorder characterized by progressive cognitive decline and mental behavioral abnormalities. Mild cognitive impairment (MCI) is regarded as a transitional stage in the progression from normal elderly individuals to patients with AD. While studies have identified abnormalities in brain connectivity in patients with MCI, including functional and structural connectivity, accurately identifying patients with MCI in clinical screening remains challenging. We hypothesized that utilizing machine learning (ML) based on both functional and structural connectivity could yield meaningful results in distinguishing between patients with MCI and normal elderly individuals, so as to provide valuable information for early diagnosis and precise evaluation of patients with MCI. MethodsFollowing clinical criteria, we recruited 32 patients with MCI for the patient group, and 32 normal elderly individuals for the control group. All subjects underwent examinations for resting-state functional magnetic resonance imaging (rs-fMRI) and diffusion tensor imaging (DTI). Subsequently, significant functional and structural connectivity features were selected and combined with a support vector machine for classification of the patient and control groups. ResultsWe observed significantly different functional connectivity in the frontal lobe and putamen between the MCI group and normal controls. The results based on functional connectivity features demonstrated a classification accuracy of 71.88% and an area under the curve (AUC) value of 0.78. In terms of structural connectivity, we found that decreased fractional anisotropy in patients with MCI was significantly associated with Montreal Cognitive Assessment scores, specifically in regions such as the precuneus and cingulate gyrus. The classification results using the structural connectivity feature yielded an accuracy of 92.19% and an AUC value of 0.99. Lastly, combining functional and structural connectivity features resulted in a classification accuracy and AUC value of 93.75% and 0.99, respectively. ConclusionsIn this study, we demonstrated a high classification performance, underscoring the potential of both brain functional and structural connectivity in distinguishing patients with MCI from normal elderly individuals. Furthermore, the integration of functional connectivity and structural connectivity features indicated that utilizing rs-fMRI and DTI could enhance the accuracy and specificity of identifying patients with MCI compared with relying on a single neuroimaging technique.

Preoperative structural-functional coupling at the default mode network predicts surgical outcomes of temporal lobe epilepsy.

Structural-functional coupling (SFC) has shown great promise in predicting postsurgical seizure recurrence in patients with temporal lobe epilepsy (TLE). In this study, we aimed to clarify the global alterations in SFC in TLE patients and predict their surgical outcomes using SFC features. This study analyzed presurgical diffusion and functional magnetic resonance imaging data from 71 TLE patients and 48 healthy controls (HCs). TLE patients were categorized into seizure-free (SF) and non-seizure-free (nSF) groups based on postsurgical recurrence. Individual functional connectivity (FC), structural connectivity (SC), and SFC were quantified at the regional and modular levels. The data were compared between the TLE and HC groups as well as among the TLE, SF, and nSF groups. The features of SFC, SC, and FC were categorized into three datasets: the modular SFC dataset, regional SFC dataset, and SC/FC dataset. Each dataset was independently integrated into a cross-validated machine learning model to classify surgical outcomes. Compared with HCs, the visual and subcortical modules exhibited decoupling in TLE patients (p < .05). Multiple default mode network (DMN)-related SFCs were significantly higher in the nSF group than in the SF group (p < .05). Models trained using the modular SFC dataset demonstrated the highest predictive performance. The final prediction model achieved an area under the receiver operating characteristic curve of .893 with an overall accuracy of .887. Presurgical hyper-SFC in the DMN was strongly associated with postoperative seizure recurrence. Furthermore, our results introduce a novel SFC-based machine learning model to precisely classify the surgical outcomes of TLE.

Effects of rhythmic visual cues on cortical activation and functional connectivity features during stepping: an fNIRS study.

Rhythmic visual cues (RVCs) may influence gait initiation by modulating cognition resources. However, it is unknown how RVCs modulate cognitive resources allocation during gait movements. This study focused on investigating the effects of RVCs on cortical hemodynamic response features during stepping to evaluate the changes of cognitive resources. We recorded cerebral hemoglobin concentration changes of 14 channels in 17 healthy subjects using functional near-infrared spectroscopy (fNIRS) during stepping tasks under exposure to RVCs and non-rhythmic visual cues (NRVCs). We reported mean oxygenated hemoglobin (HbO) concentration changes, β-values, and functional connectivity (FC) between channels. The results showed that, the RVC conditions revealed lower HbO responses compared to the NRVC conditions during the preparation and early stepping. Correspondingly, the β-values reflected that RVCs elicited lower hemodynamic responses than NRVCs, and there was a decreasing trend in stimulus-evoked cortical activation as the task progressed. However, the FC between channels were stronger under RVCs than under NRVCs during the stepping progress, and there were more significant differences in FC during the early stepping. In conclusion, there were lower cognitive demand and stronger FC under RVC conditions than NRVC conditions, which indicated higher efficiency of cognitive resources allocation during stepping tasks. This study may provide a new insight for further understanding the mechanism on how RVCs alleviate freezing of gait.

Interictal EEG source connectivity to localize the epileptogenic zone in patients with drug-resistant epilepsy: A machine learning approach.

To deconstruct the epileptogenic networks of patients with drug-resistant epilepsy (DRE) using source functional connectivity (FC) analysis; unveil the FC biomarkers of the epileptogenic zone (EZ); and develop machine learning (ML) models to estimate the EZ using brief interictal electroencephalography (EEG) data. We analyzed scalp EEG from 50 patients with DRE who had surgery. We reconstructed the activity (electrical source imaging [ESI]) of virtual sensors (VSs) across the whole cortex and computed FC separately for epileptiform and non-epileptiform EEG epochs (with or without spikes). In patients with good outcome (Engel 1a), four cortical regions were defined: EZ (resection) and three non-epileptogenic zones (NEZs) in the same and opposite hemispheres. Region-specific FC features in six frequency bands and three spatial ranges (long, short, inner) were compared between regions (Wilcoxon sign-rank). We developed ML classifiers to identify the VSs in the EZ using VS-specific FC features. Cross-validation was performed using good outcome data. Performance was compared with poor outcomes and interictal spike localization. FC differed between EZ and NEZs (p < .05) during non-epileptiform and epileptiform epochs, showing higher FC in the EZ than its homotopic contralateral NEZ. During epileptiform epochs, the NEZ in the epileptogenic hemisphere showed higher FC than its contralateral NEZ. In good outcome patients, the ML classifiers reached 75% accuracy to the resection (91% sensitivity; 74% specificity; distance from EZ: 38 mm) using epileptiform epochs (gamma and beta frequency bands) and 62% accuracy using broadband non-epileptiform epochs, both outperforming spike localization (accuracy = 47%; p < .05; distance from EZ: 57 mm). Lower performance was seen in poor outcomes. We present an FC approach to extract EZ biomarkers from brief EEG data. Increased FC in various frequencies characterized the EZ during epileptiform and non-epileptiform epochs. FC-based ML models identified the resection better in good than poor outcome patients, demonstrating their potential for presurgical use in pediatric DRE.

Functional connectivity characteristics of the brain network involved in prickle perception of single fiber stimulation.

The complex network connections, information transmission and organization play key roles in brain cognition on sensory stimulation. Previous studies showed that several brain regions of somatosensory, motor, emotional, cognitive, etc. are linked to fabric-evoked prickle. But the functional connectivity characteristics of the brain network involved in prickle perception is still unclear. In the present study, resting state fMRI (functional magnetic resonance imaging) with functional connectivity analysis was adopted to build the initial brain functional network, and task fMRI with psychophysiological interaction analysis was employed to investigate modulation features of prickling task to functional connections in the brain network. The results showed that, in resting state, six groups or sub-networks can be identified in the prickle network, and when the subjects performed the prickling task, functional connectivity strength between some seed regions (e.g., somatosensory regions and precuneus, emotional regions and the prefrontal cortex, etc.) in the network increased. Combining resting-state fMRI with task fMRI is a feasible and promising method to study functional connectivity characteristics of the brain network involved in prickle perception. It is inferred that the "itch" ingredient of prickle sensation was transmitted from somatosensory cortices to precuneus, and emotional attribute (e.g., pain) from somatosensory cortices to the prefrontal cortex and at last to emotional regions.

Deep learning based joint fusion approach to exploit anatomical and functional brain information in autism spectrum disorders

Background:The integration of the information encoded in multiparametric MRI images can enhance the performance of machine-learning classifiers. In this study, we investigate whether the combination of structural and functional MRI might improve the performances of a deep learning (DL) model trained to discriminate subjects with Autism Spectrum Disorders (ASD) with respect to typically developing controls (TD).Material and methodsWe analyzed both structural and functional MRI brain scans publicly available within the ABIDE I and II data collections. We considered 1383 male subjects with age between 5 and 40 years, including 680 subjects with ASD and 703 TD from 35 different acquisition sites. We extracted morphometric and functional brain features from MRI scans with the Freesurfer and the CPAC analysis packages, respectively. Then, due to the multisite nature of the dataset, we implemented a data harmonization protocol. The ASD vs. TD classification was carried out with a multiple-input DL model, consisting in a neural network which generates a fixed-length feature representation of the data of each modality (FR-NN), and a Dense Neural Network for classification (C-NN). Specifically, we implemented a joint fusion approach to multiple source data integration. The main advantage of the latter is that the loss is propagated back to the FR-NN during the training, thus creating informative feature representations for each data modality. Then, a C-NN, with a number of layers and neurons per layer to be optimized during the model training, performs the ASD-TD discrimination. The performance was evaluated by computing the Area under the Receiver Operating Characteristic curve within a nested 10-fold cross-validation. The brain features that drive the DL classification were identified by the SHAP explainability framework.ResultsThe AUC values of 0.66±0.05 and of 0.76±0.04 were obtained in the ASD vs. TD discrimination when only structural or functional features are considered, respectively. The joint fusion approach led to an AUC of 0.78±0.04. The set of structural and functional connectivity features identified as the most important for the two-class discrimination supports the idea that brain changes tend to occur in individuals with ASD in regions belonging to the Default Mode Network and to the Social Brain.ConclusionsOur results demonstrate that the multimodal joint fusion approach outperforms the classification results obtained with data acquired by a single MRI modality as it efficiently exploits the complementarity of structural and functional brain information.

Explainable Deep-Learning Prediction for Brain-Computer Interfaces Supported Lower Extremity Motor Gains Based on Multistate Fusion.

Predicting the potential for recovery of motor function in stroke patients who undergo specific rehabilitation treatments is an important and major challenge. Recently, electroencephalography (EEG) has shown potential in helping to determine the relationship between cortical neural activity and motor recovery. EEG recorded in different states could more accurately predict motor recovery than single-state recordings. Here, we design a multi-state (combining eyes closed, EC, and eyes open, EO) fusion neural network for predicting the motor recovery of patients with stroke after EEG-brain-computer-interface (BCI) rehabilitation training and use an explainable deep learning method to identify the most important features of EEG power spectral density and functional connectivity contributing to prediction. The prediction accuracy of the multi-states fusion network was 82%, significantly improved compared with a single-state model. The neural network explanation result demonstrated the important region and frequency oscillation bands. Specifically, in those two states, power spectral density and functional connectivity were shown as the regions and bands related to motor recovery in frontal, central, and occipital. Moreover, the motor recovery relation in bands, the power spectrum density shows the bands at delta and alpha bands. The functional connectivity shows the delta, theta, and alpha bands in the EC state; delta, theta, and beta mid at the EO state are related to motor recovery. Multi-state fusion neural networks, which combine multiple states of EEG signals into a single network, can increase the accuracy of predicting motor recovery after BCI training, and reveal the underlying mechanisms of motor recovery in brain activity.

Brain connectome-based imaging markers for identifiable signature of migraine with and without aura.

Cortical spreading depression (CSD) has been considered the prominent theory for migraine with aura (MwA). However, it is also argued that CSD can exist in patients in a silent state, and not manifest as aura. Thus, the MwA classification based on aura may be questionable. This study aimed to capture whole-brain connectome-based imaging markers with identifiable signatures for MwA and migraine without aura (MwoA). A total of 88 migraine patients (32 MwA) and 49 healthy controls (HC) underwent a diffusion tensor imaging and resting-state functional magnetic resonance imaging scan. The whole-brain structural connectivity (SC) and functional connectivity (FC) analysis was employed to extract imaging features. The extracted features were subjected to an all-relevant feature selection process within cross-validation loops to pinpoint attributes demonstrating substantial efficacy for patient categorization. Based on the identified features, the predictive ability of the random forest classifiers constructed with the 88 migraine patients' sample was tested using an independent sample of 32 migraine patients (eight MwA). Compared to MwoA and HC, MwA showed two reduced SC and six FC (five increased and one reduced) features [all P<0.01, after false discovery rate (FDR) correction], involving frontal areas, temporal areas, visual areas, amygdala, and thalamus. A total of four imaging features were significantly correlated with clinical rating scales in all patients (r=-0.38 to 0.47, P<0.01, after FDR correction). The predictive ability of the random forest classifiers achieved an accuracy of 78.1% in the external sample to identify MwA. The whole-brain connectivity features in our results may serve as connectome-based imaging markers for MwA identification. The alterations of SC and FC strength provide possible evidence in further understanding the heterogeneity and mechanism of MwA which may help for patient-specific decision-making.

Predicting response to repetitive transcranial magnetic stimulation in patients with chronic insomnia disorder using electroencephalography: A pilot study

Predicting responsvienss to repetitive transcranial magnetic stimulation (rTMS) can facilitate personalized treatments with improved efficacy; however, predictive features related to this response are still lacking. We explored whether resting-state electroencephalography (rsEEG) functional connectivity measured at baseline or during treatment could predict the response to 10-day rTMS targeted to the right dorsolateral prefrontal cortex (DLPFC) in 36 patients with chronic insomnia disorder (CID). Pre- and post-treatment rsEEG scans and the Pittsburgh Sleep Quality Index (PSQI) were evaluated, with an additional rsEEG scan conducted after four rTMS sessions. Machine-learning approaches were employed to assess the ability of each connectivity measure to distinguish between responders (PSQI improvement > 25%) and non-responders (PSQI improvement ≤ 25%). Furthermore, we analyzed the connectivity trends of the two subgroups throughout the treatment. Our results revealed that the machine learning model based on baseline theta connectivity achieved the highest accuracy (AUC = 0.843) in predicting treatment response. Decreased baseline connectivity at the stimulated site was associated with higher responsiveness to TMS, emphasizing the significance of functional connectivity characteristics in rTMS treatment. These findings enhance the clinical application of EEG functional connectivity markers in predicting treatment outcomes.

Elucidating salient site-specific functional connectivity features and site-invariant biomarkers in schizophrenia via deep neural networks

Schizophrenia is a highly heterogeneous disorder and salient functional connectivity (FC) features have been observed to vary across study sites, warranting the need for methods that can differentiate between site-invariant FC biomarkers and site-specific salient FC features. We propose a technique named Semi-supervised learning with data HaRmonisation via Encoder-Decoder-classifier (SHRED) to examine these features from resting state functional magnetic resonance imaging scans gathered from four sites. Our approach involves an encoder-decoder-classifier architecture that simultaneously performs data harmonisation and semi-supervised learning (SSL) to deal with site differences and labelling inconsistencies across sites respectively. The minimisation of reconstruction loss from SSL was shown to improve model performance even within small datasets whilst data harmonisation often led to lower model generalisability, which was unaffected using the SHRED technique. We show that our proposed model produces site-invariant biomarkers, most notably the connection between transverse temporal gyrus and paracentral lobule. Site-specific salient FC features were also elucidated, especially implicating the paracentral lobule for our local dataset. Our examination of these salient FC features demonstrates how site-specific features and site-invariant biomarkers can be differentiated, which can deepen our understanding of the neurobiology of schizophrenia.

Regularity and variability of functional brain connectivity characteristics between gyri and sulci under naturalistic stimulus

The human cerebral cortex is folded into two fundamentally anatomical units: gyri and sulci. Previous studies have demonstrated the genetical, structural, and functional differences between gyri and sulci, providing a unique perspective for revealing the relationship among brain function, cognition, and behavior. While previous studies mainly focus on the functional differences between gyri and sulci under resting or task-evoked state, such characteristics under naturalistic stimulus (NS) which reflects real-world dynamic environments are largely unknown. To address this question, this study systematically investigates spatio-temporal functional connectivity (FC) characteristics between gyri and sulci under NS using a spatio-temporal graph convolutional network model. Based on the public Human Connectome Project dataset of 174 subjects with four different runs of both movie-watching NS and resting state 7T functional MRI data, we successfully identify unique FC features under NS, which are mainly involved in visual, auditory, emotional and cognitive control, and achieve high discriminative accuracy 93.06 % to resting state. Moreover, gyral regions as well as gyro-gyral connections consistently participate more as functional information exchange hubs than sulcal ones among these networks. This study provides novel insights into the functional brain mechanism under NS and lays a solid foundation for accurately mapping the brain anatomy-function relationship.