We present a didactic introduction to spectral Dynamic Causal Modelling (DCM), a Bayesian state-space modelling approach used to infer effective connectivity from non-invasive neuroimaging data. Spectral DCM is currently the most widely applied DCM variant for resting-state functional MRI analysis. Our aim is to explain its technical foundations to an audience with limited expertise in state-space modelling and spectral data analysis. Particular attention will be paid to cross-spectral density, which is the most distinctive feature of spectral DCM and is closely related to functional connectivity, as measured by (zero-lag) Pearson correlations. In fact, the model parameters estimated by spectral DCM are those that best reproduce the cross-correlations between all measurements--at all time lags--including the zero-lag correlations that are usually interpreted as functional connectivity. We derive the functional connectivity matrix from the model equations and show how changing a single effective connectivity parameter can affect all pairwise correlations. To complicate matters, the pairs of brain regions showing the largest changes in functional connectivity do not necessarily coincide with those presenting the largest changes in effective connectivity. We discuss the implications and conclude with a comprehensive summary of the assumptions and limitations of spectral DCM.
Brain network analysis is a useful approach to studying human brain disorders because it can distinguish patients from healthy people by detecting abnormal connections. Due to the complementary information from multiple modal neuroimages, multimodal fusion technology has a lot of potential for improving prediction performance. However, effective fusion of multimodal medical images to achieve complementarity is still a challenging problem. In this paper, a novel hierarchical structural-functional connectivity fusing (HSCF) model is proposed to construct brain structural-functional connectivity matrices and predict abnormal brain connections based on functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI). Specifically, the prior knowledge is incorporated into the separators for disentangling each modality of information by the graph convolutional networks (GCN). And a disentangled cosine distance loss is devised to ensure the disentanglement's effectiveness. Moreover, the hierarchical representation fusion module is designed to effectively maximize the combination of relevant and effective features between modalities, which makes the generated structural-functional connectivity more robust and discriminative in the cognitive disease analysis. Results from a wide range of tests performed on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) database show that the proposed model performs better than competing approaches in terms of classification evaluation. In general, the proposed HSCF model is a promising model for generating brain structural-functional connectivities and identifying abnormal brain connections as cognitive disease progresses.
The decoding of brain neural networks has been an intriguing topic in neuroscience for a well-rounded understanding of different types of brain disorders and cognitive stimuli. Integrating different types of connectivity, e.g., Functional Connectivity (FC) and Structural Connectivity (SC), from multi-modal imaging techniques can take their complementary information into account and therefore have the potential to get better decoding capability. However, traditional approaches for integrating FC and SC overlook the dynamical variations, which stand a great chance to over-generalize the brain neural network. In this paper, we propose a Joint kernel Graph Attention Network (JGAT), which is a new multi-modal temporal graph attention network framework. It integrates the data from functional Magnetic Resonance Images (fMRI) and Diffusion Weighted Imaging (DWI) while preserving the dynamic information at the same time. We conduct brain-decoding tasks with our JGAT on four independent datasets: three of 7T fMRI datasets from the Human Connectome Project (HCP) and one from animal neural recordings. Furthermore, with Attention Scores (AS) and Frame Scores (FS) computed and learned from the model, we can locate several informative temporal segments and build meaningful dynamical pathways along the temporal domain for the HCP datasets. The URL to the code of JGAT model: https://github.com/BRAINML-GT/JGAT.
Integrating the brain structural and functional connectivity features is of great significance in both exploring brain science and analyzing cognitive impairment clinically. However, it remains a challenge to effectively fuse structural and functional features in exploring the brain network. In this paper, a novel brain structure-function fusing-representation learning (BSFL) model is proposed to effectively learn fused representation from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (fMRI) for mild cognitive impairment (MCI) analysis. Specifically, the decomposition-fusion framework is developed to first decompose the feature space into the union of the uniform and the unique spaces for each modality, and then adaptively fuse the decomposed features to learn MCI-related representation. Moreover, a knowledge-aware transformer module is designed to automatically capture local and global connectivity features throughout the brain. Also, a uniform-unique contrastive loss is further devised to make the decomposition more effective and enhance the complementarity of structural and functional features. The extensive experiments demonstrate that the proposed model achieves better performance than other competitive methods in predicting and analyzing MCI. More importantly, the proposed model could be a potential tool for reconstructing unified brain networks and predicting abnormal connections during the degenerative processes in MCI.
Probabilistic graphical models have become an important unsupervised learning tool for detecting network structures for a variety of problems, including the estimation of functional neuronal connectivity from two-photon calcium imaging data. However, in the context of calcium imaging, technological limitations only allow for partially overlapping layers of neurons in a brain region of interest to be jointly recorded. In this case, graph estimation for the full data requires inference for edge selection when many pairs of neurons have no simultaneous observations. This leads to the Graph Quilting problem, which seeks to estimate a graph in the presence of block-missingness in the empirical covariance matrix. Solutions for the Graph Quilting problem have previously been studied for Gaussian graphical models; however, neural activity data from calcium imaging are often non-Gaussian, thereby requiring a more flexible modeling approach. Thus, in our work, we study two approaches for nonparanormal Graph Quilting based on the Gaussian copula graphical model, namely a maximum likelihood procedure and a low-rank based framework. We provide theoretical guarantees on edge recovery for the former approach under similar conditions to those previously developed for the Gaussian setting, and we investigate the empirical performance of both methods using simulations as well as real data calcium imaging data. Our approaches yield more scientifically meaningful functional connectivity estimates compared to existing Gaussian graph quilting methods for this calcium imaging data set.
The functional network of the brain continually adapts to changing environmental demands. The environmental changes closely connect with changes of active cognitive processes. In recent years, the network approach has emerged as a promising method for analyzing the neurophysiological mechanisms that underlie psychological functions. The present study examines topological characteristics of functional brain networks in resting state and in cognitive load, provided by the execution of the Sternberg Item Recognition Paradigm (SIRP) based on electroencephalographic data. We propose that the topological properties of the functional networks in the human brain are distinct between cognitive load and resting state with higher integration in the networks during cognitive load. It was shown that topological features of functional connectomes strongly depend on the type of cognitive process performed by the subject and change in accordance with task change. The analysis also demonstrated that functional connectivity during working memory tasks showed a faster emergence of homology groups generators, supporting the idea of a relationship between the initial stages of working memory execution and an increase in faster network integration, with connector hubs playing a crucial role.
Functional connectivity (FC) is one of the most common inputs to fMRI-based predictive models, due to a combination of its simplicity and robustness. However, there may be a lack of theoretical models for the generation of FC. In this work, we present a straightforward decomposition of FC into a set of basis states of sine waves with an additional jitter component. We show that the decomposition matches the predictive ability of FC after including 5-10 bases. We also find that both the decomposition and its residual have approximately equal predictive value, and when combined into an ensemble, exceed the AUC of FC-based prediction by up to 5%. Additionally, we find the residual can be used for subject fingerprinting, with 97.3% same-subject, different-scan identifiability, compared to 62.5% for FC. Unlike PCA or Factor Analysis methods, our method does not require knowledge of a population to perform its decomposition; a single subject is enough. Our decomposition of FC into two equally-predictive components may lead to a novel appreciation of group differences in patient populations. Additionally, we generate synthetic patient FC based on user-specified characteristics such as age, sex, and disease diagnosis. By creating synthetic datasets or augmentations we may reduce the high financial burden associated with fMRI data acquisition.
The study's objective is to explore the distinctions in the functional brain network connectivity between Alzheimer's Disease (AD) patients and normal controls using Functional Magnetic Resonance Imaging (fMRI). The study included 590 individuals, with 175 having AD dementia and 415 age-, gender-, and handedness-matched normal controls. The connectivity of functional brain networks was measured using ROI-to-ROI and ROI-to-Voxel connectivity analyses. The findings reveal a general decrease in functional connectivity among the AD group in comparison to the normal control group. These results advance our comprehension of AD pathophysiology and could assist in identifying AD biomarkers.
We propose a node clustering method for time-varying graphs based on the assumption that the cluster labels are changed smoothly over time. Clustering is one of the fundamental tasks in many science and engineering fields including signal processing, machine learning, and data mining. Although most existing studies focus on the clustering of nodes in static graphs, we often encounter time-varying graphs for time-series data, e.g., social networks, brain functional connectivity, and point clouds. In this paper, we formulate a node clustering of time-varying graphs as an optimization problem based on spectral clustering, with a smoothness constraint of the node labels. We solve the problem with a primal-dual splitting algorithm. Experiments on synthetic and real-world time-varying graphs are performed to validate the effectiveness of the proposed approach.
Resting State Networks (RSNs) of the brain extracted from Resting State functional Magnetic Resonance Imaging (RS-fMRI) are used in the pre-surgical planning to guide the neurosurgeon. This is difficult, though, as expert knowledge is required to label each of the RSNs. There is a lack of efficient and standardized methods to be used in clinical workflows. Additionally, these methods need to be generalizable since the method needs to work well regardless of the acquisition technique. We propose an accurate, fast, and lightweight deep learning approach to label RSNs. Group Independent Component Analysis (ICA) was used to extract large scale functional connectivity patterns in the cohort and dual regression was used to back project them on individual subject RSNs. We compare a Multi-Layer Perceptron (MLP) based method with 2D and 3D Convolutional Neural Networks (CNNs) and find that the MLP is faster and more accurate. The MLP method performs as good or better than other works despite its compact size. We prove the generalizability of our method by showing that the MLP performs at 100% accuracy in the holdout dataset and 98.3% accuracy in three other sites' fMRI acquisitions.
Schizophrenia (SZ) is a brain disorder leading to detached mind's normally integrated processes. Hence, the exploration of the symptoms in relation to functional connectivity (FC) had great relevance in the field. FC can be investigated on different levels, going from global features to single edges between regions, revealing diffuse and localized dysconnection patterns. In this context, SZ is characterized by a diverse global integration with reduced connectivity in specific areas of the Default Mode Network (DMN). However, the assessment of FC presents various sources of uncertainty. This study proposes a multi-level approach for more robust group-comparison. FC between 74 AAL brain areas of 15 healthy controls (HC) and 12 SZ subjects were used. Multi-level analyses and graph topological indexes evaluation were carried out by the previously published SPIDER-NET tool. Robustness was augmented by bootstrapped (BOOT) data and the stability was evaluated by removing one (RST1) or two subjects (RST2). The DMN subgraph was evaluated, toegether with overall local indexes and connection weights to enhance common activations/deactivations. At a global level, expected trends were found. The robustness assessment tests highlighted more stable results for BOOT compared to the direct data testing. Conversely, significant results were found in the analysis at lower levels. The DMN highlighted reduced connectivity and strength as well as increased deactivation in the SZ group. At local level, 13 areas were found to be significantly different ($p<0.05$), highlighting a greater divergence in the frontal lobe. These results were confirmed analyzing the negative edges, suggesting inverted connectivity between prefronto-temporal areas. In conclusion, multi-level analysis supported by BOOT is highly recommended, especially when diffuse and localized dysconnections must be investigated in limited samples.
Whether, when, and how causal interactions between neurons can be meaningfully studied from observations of neural activity alone are vital questions in neural data analysis. Here we aim to better outline the concept of functional connectivity for the specific situation where systems neuroscientists aim to study synapses using spike train recordings. In some cases, cross-correlations between the spikes of two neurons are such that, although we may not be able to say that a relationship is causal without experimental manipulations, models based on synaptic connections provide precise explanations of the data. Additionally, there is often strong circumstantial evidence that pairs of neurons are monosynaptically connected. Here we illustrate how circumstantial evidence for or against synapses can be systematically assessed and show how models of synaptic effects can provide testable predictions for pair-wise spike statistics. We use case studies from large-scale multi-electrode spike recordings to illustrate key points and to demonstrate how modeling synaptic effects using large-scale spike recordings opens a wide range of data analytic questions.
The process of integration of inputs from several sensory modalities in the human brain is referred to as multisensory integration. Age-related cognitive decline leads to a loss in the ability of the brain to conceive multisensory inputs. There has been considerable work done in the study of such cognitive changes for the old age groups. However, in the case of middle age groups, such analysis is limited. Motivated by this, in the current work, EEG-based functional connectivity during audiovisual temporal asynchrony integration task for middle-aged groups is explored. Investigation has been carried out during different tasks such as: unimodal audio, unimodal visual, and variations of audio-visual stimulus. A correlation-based functional connectivity analysis is done, and the changes among different age groups including: young (18-25 years), transition from young to middle age (25-33 years), and medium (33-41 years), are observed. Furthermore, features extracted from the connectivity graphs have been used to classify among the different age groups. Classification accuracies of $89.4\%$ and $88.4\%$ are obtained for the Audio and Audio-50-Visual stimuli cases with a Random Forest based classifier, thereby validating the efficacy of the proposed method.
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph structures and used simple GNN architectures for the diagnosis of AD. In this work, we propose a novel adaptive gated graph convolutional network (AGGCN) that can provide explainable predictions. AGGCN adaptively learns graph structures by combining convolution-based node feature enhancement with a correlation-based measure of power spectral density similarity. Furthermore, the gated graph convolution can dynamically weigh the contribution of various spatial scales. The proposed model achieves high accuracy in both eyes-closed and eyes-open conditions, indicating the stability of learned representations. Finally, we demonstrate that the proposed AGGCN model generates consistent explanations of its predictions that might be relevant for further study of AD-related alterations of brain networks.
The available evidence suggests that dynamic functional connectivity (dFC) can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia(SZ) patients. Hence, an advanced dynamic brain network analysis model called the temporal brain category graph convolutional network (Temporal-BCGCN) was employed. Firstly, a unique dynamic brain network analysis module, DSF-BrainNet, was designed to construct dynamic synchronization features. Subsequently, a revolutionary graph convolution method, TemporalConv, was proposed, based on the synchronous temporal properties of feature. Finally, the first modular abnormal hemispherical lateralization test tool in deep learning based on rs-fMRI data, named CategoryPool, was proposed. This study was validated on COBRE and UCLA datasets and achieved 83.62% and 89.71% average accuracies, respectively, outperforming the baseline model and other state-of-the-art methods. The ablation results also demonstrate the advantages of TemporalConv over the traditional edge feature graph convolution approach and the improvement of CategoryPool over the classical graph pooling approach. Interestingly, this study showed that the lower order perceptual system and higher order network regions in the left hemisphere are more severely dysfunctional than in the right hemisphere in SZ and reaffirms the importance of the left medial superior frontal gyrus in SZ. Our core code is available at: https://github.com/swfen/Temporal-BCGCN.
The analysis of EEG/MEG functional connectivity has become an important tool in neural research. Especially the high time resolution of EEG/MEG enables important insight into the functioning of the human brain. To date, functional connectivity is commonly estimated offline, i.e., after the conclusion of the experiment. However, online computation of functional connectivity has the potential to enable unique experimental paradigms. For example, changes of functional connectivity due to learning processes could be tracked in real time and the experiment be adjusted based on these observations. Furthermore, the connectivity estimates can be used for neurofeedback applications or the instantaneous inspection of measurement results. In this study, we present the implementation and evaluation of online sensor and source space functional connectivity estimation in the open-source software MNE Scan. Online capable implementations of several functional connectivity metrics were established in the Connectivity library within MNE-CPP and made available as a plugin in MNE Scan. Online capability was achieved by enforcing multithreading and high efficiency for all computations, so that repeated computations were avoided wherever possible, which allows for a major speed-up in the case of overlapping intervalls. We present comprehensive performance evaluations of these implementations proving the online capability for the computation of large all-to-all functional connectivity networks. As a proof of principle, we demonstrate the feasibility of online functional connectivity estimation in the evaluation of somatosensory evoked brain activity.
This study proposes a novel heterogeneous graph convolutional neural network (HGCNN) to handle complex brain fMRI data at regional and across-region levels. We introduce a generic formulation of spectral filters on heterogeneous graphs by introducing the $k-th$ Hodge-Laplacian (HL) operator. In particular, we propose Laguerre polynomial approximations of HL spectral filters and prove that their spatial localization on graphs is related to the polynomial order. Furthermore, based on the bijection property of boundary operators on simplex graphs, we introduce a generic topological graph pooling (TGPool) method that can be used at any dimensional simplices. This study designs HL-node, HL-edge, and HL-HGCNN neural networks to learn signal representation at a graph node, edge levels, and both, respectively. Our experiments employ fMRI from the Adolescent Brain Cognitive Development (ABCD; n=7693) to predict general intelligence. Our results demonstrate the advantage of the HL-edge network over the HL-node network when functional brain connectivity is considered as features. The HL-HGCNN outperforms the state-of-the-art graph neural networks (GNNs) approaches, such as GAT, BrainGNN, dGCN, BrainNetCNN, and Hypergraph NN. The functional connectivity features learned from the HL-HGCNN are meaningful in interpreting neural circuits related to general intelligence.
Attention Deficit/Hyperactivity Disorder (ADHD) is one of the most common neurodevelopmental disorders in children and is characterised by inattention, impulsiveness and hyperactivity. While several studies have analysed the static functional connectivity in the resting-state functional MRI (rs-fMRI) of ADHD patients, detailed investigations are required to characterize the connectivity dynamics in the brain. In an attempt to establish a link between attention instability and the dynamic properties of Functional Connectivity (FC), we investigated the differences in temporal variability of FC between 40 children with ADHD and 40 Typically Developing (TD) children. Using a sliding-window method to segment the rs-fMRI scans in time, we employed seed-to-voxel correlation analysis for each window to obtain time-evolving seed connectivity maps for seeds placed in the posterior cingulate cortex (PCC) and the medial prefrontal cortex (mPFC). For each subject, the standard deviation of the voxel connectivity time series was used as a measure of the temporal variability of FC. Results showed that ADHD patients exhibited significantly higher variability in dFC than TD children in the cingulo-temporal, cingulo-parietal, fronto-temporal, and fronto-parietal networks ($p_{FWE} < 0.05$). Atypical temporal variability was observed in the left and right temporal gyri, the anterior cingulate cortex, and lateral regions of the right parietal cortex. The observations are consistent with visual attention issues, executive control deficit, and rightward parietal dysfunction reported in ADHD, respectively. These results help in understanding the disorder with a fresh perspective linking behavioural inattention with instability in FC in the brain.
Recent applications of pattern recognition techniques on brain connectome classification using functional connectivity (FC) are shifting towards acknowledging the non-Euclidean topology and dynamic aspects of brain connectivity across time. In this paper, a deep spatiotemporal variational Bayes (DSVB) framework is proposed to learn time-varying topological structures in dynamic FC networks for identifying autism spectrum disorder (ASD) in human participants. The framework incorporates a spatial-aware recurrent neural network with an attention-based message passing scheme to capture rich spatiotemporal patterns across dynamic FC networks. To overcome model overfitting on limited training datasets, an adversarial training strategy is introduced to learn graph embedding models that generalize well to unseen brain networks. Evaluation on the ABIDE resting-state functional magnetic resonance imaging dataset shows that our proposed framework substantially outperforms state-of-the-art methods in identifying patients with ASD. Dynamic FC analyses with DSVB-learned embeddings reveal apparent group differences between ASD and healthy controls in brain network connectivity patterns and switching dynamics of brain states. The code is available at https://github.com/Monash-NeuroAI/Deep-Spatiotemporal-Variational-Bayes.
Most packages for the analysis of fMRI-based functional connectivity (FC) and genomic data are used with a programming language interface, lacking an easy-to-navigate GUI frontend. This exacerbates two problems found in these types of data: demographic confounds and quality control in the face of high dimensionality of features. The reason is that it is too slow and cumbersome to use a programming interface to create all the necessary visualizations required to identify all correlations, confounding effects, or quality control problems in a dataset. To remedy this situation, we have developed ImageNomer, a data visualization and analysis tool that allows inspection of both subject-level and cohort-level demographic, genomic, and imaging features. The software is Python-based, runs in a self-contained Docker image, and contains a browser-based GUI frontend. We demonstrate the usefulness of ImageNomer by identifying an unexpected race confound when predicting achievement scores in the Philadelphia Neurodevelopmental Cohort (PNC) dataset. In the past, many studies have attempted to use FC to identify achievement-related features in fMRI. Using ImageNomer, we find a clear potential for confounding effects of race. Using correlation analysis in the ImageNomer software, we show that FCs correlated with Wide Range Achievement Test (WRAT) score are in fact more highly correlated with race. Investigating further, we find that whereas both FC and SNP (genomic) features can account for 10-15\% of WRAT score variation, this predictive ability disappears when controlling for race. In this work, we demonstrate the advantage of our ImageNomer GUI tool in data exploration and confound detection. Additionally, this work identifies race as a strong confound in FC data and casts doubt on the possibility of finding unbiased achievement-related features in fMRI and SNP data of healthy adolescents.