Generalized Recurrent Neural Network accommodating Dynamic Causal Modeling for functional MRI analysis

Exploring Brain Effective Connectivity Networks Through Spatiotemporal Graph Convolutional Models

Learning brain effective connectivity networks (ECN) from functional magnetic resonance imaging (fMRI) data has gained much attention in recent years. With the successful applications of deep learning in numerous fields, several brain ECN learning methods based on deep learning have been reported in the literature. However, current methods ignore the deep temporal features of fMRI data and fail to fully employ the spatial topological relationship between brain regions. In this article, we propose a novel method for learning brain ECN based on spatiotemporal graph convolutional models (STGCM), named STGCMEC, in which we first adopt the temporal convolutional network to extract the deep temporal features of fMRI data and utilize the graph convolutional network to update the spatial features of each brain region by aggregating information from neighborhoods, which makes the features of brain regions more discriminative. Then, based on such features of brain regions, we design a joint loss function to guide STGCMEC to learn the brain ECN, which includes a task prediction loss and a graph regularization loss. The experimental results on a simulated dataset and a real Alzheimer's disease neuroimaging initiative (ADNI) dataset show that the proposed STGCMEC is able to better learn brain ECN compared with some state-of-the-art methods.

Dementia classification using a graph neural network on imaging of effective brain connectivity

Alzheimer's disease (AD) and Parkinson's disease (PD) are two of the most common forms of neurodegenerative diseases. The literature suggests that effective brain connectivity (EBC) has the potential to track differences between AD, PD and healthy controls (HC). However, how to effectively use EBC estimations for the research of disease diagnosis remains an open problem. To deal with complex brain networks, graph neural network (GNN) has been increasingly popular in very recent years and the effectiveness of combining EBC and GNN techniques has been unexplored in the field of dementia diagnosis. In this study, a novel directed structure learning GNN (DSL-GNN) was developed and performed on the imaging of EBC estimations and power spectrum density (PSD) features. In comparison to the previous studies on GNN, our proposed approach enhanced the functionality for processing directional information, which builds the basis for more efficiently performing GNN on EBC. Another contribution of this study is the creation of a new framework for applying univariate and multivariate features simultaneously in a classification task. The proposed framework and DSL-GNN are validated in four discrimination tasks and our approach exhibited the best performance, against the existing methods, with the highest accuracy of 94.0% (AD vs. HC), 94.2% (PD vs. HC), 97.4% (AD vs. PD) and 93.0% (AD vs. PD vs. HC). In a word, this research provides a robust analytical framework to deal with complex brain networks containing causal directional information and implies promising potential in the diagnosis of two of the most common neurodegenerative conditions.

Amortization Transformer for Brain Effective Connectivity Estimation from fMRI Data

Using machine learning methods to estimate brain effective connectivity networks from functional magnetic resonance imaging (fMRI) data has garnered significant attention in the fields of neuroinformatics and bioinformatics. However, existing methods usually require retraining the model for each subject, which ignores the knowledge shared across subjects. In this paper, we propose a novel framework for estimating effective connectivity based on an amortization transformer, named AT-EC. In detail, AT-EC first employs an amortization transformer to model the dynamics of fMRI time series and infer brain effective connectivity across different subjects, which can train an amortized model that leverages the shared knowledge from different subjects. Then, an assisted learning mechanism based on functional connectivity is designed to assist the estimation of the brain effective connectivity network. Experimental results on both simulated and real-world data demonstrate the efficacy of our method.

A Survey on Brain Effective Connectivity Network Learning

Human brain effective connectivity characterizes the causal effects of neural activities among different brain regions. Studies of brain effective connectivity networks (ECNs) for different populations contribute significantly to the understanding of the pathological mechanism associated with neuropsychiatric diseases and facilitate finding new brain network imaging markers for the early diagnosis and evaluation for the treatment of cerebral diseases. A deeper understanding of brain ECNs also greatly promotes brain-inspired artificial intelligence (AI) research in the context of brain-like neural networks and machine learning. Thus, how to picture and grasp deeper features of brain ECNs from functional magnetic resonance imaging (fMRI) data is currently an important and active research area of the human brain connectome. In this survey, we first show some typical applications and analyze existing challenging problems in learning brain ECNs from fMRI data. Second, we give a taxonomy of ECN learning methods from the perspective of computational science and describe some representative methods in each category. Third, we summarize commonly used evaluation metrics and conduct a performance comparison of several typical algorithms both on simulated and real datasets. Finally, we present the prospects and references for researchers engaged in learning ECNs.

Dynamic Effective Connectivity using Physiologically informed Dynamic Causal Model with Recurrent Units: A functional Magnetic Resonance Imaging simulation study

Functional MRI (fMRI) is an indirect reflection of neuronal activity. Using generative biophysical model of fMRI data such as Dynamic Causal Model (DCM), the underlying neuronal activities of different brain areas and their causal interactions (i.e., effective connectivity) can be calculated. Most DCM studies typically consider the effective connectivity to be static for a cognitive task within an experimental run. However, changes in experimental conditions during complex tasks such as movie-watching might result in temporal variations in the connectivity strengths. In this fMRI simulation study, we leverage state-of-the-art Physiologically informed DCM (P-DCM) along with a recurrent window approach and discretization of the equations to infer the underlying neuronal dynamics and concurrently the dynamic (time-varying) effective connectivities between various brain regions for task-based fMRI. Results from simulation studies on 3- and 10-region models showed that functional magnetic resonance imaging (fMRI) blood oxygenation level-dependent (BOLD) responses and effective connectivity time-courses can be accurately predicted and distinguished from faulty graphical connectivity models representing cognitive hypotheses. In summary, we propose and validate a novel approach to determine dynamic effective connectivity between brain areas during complex cognitive tasks by combining P-DCM with recurrent units.

Brain Connectivity Based Graph Convolutional Networks and Its Application to Infant Age Prediction

Infancy is a critical period for the human brain development, and brain age is one of the indices for the brain development status associated with neuroimaging data. The difference between the predicted age based on neuroimaging and the chronological age can provide an important early indicator of deviation from the normal developmental trajectory. In this study, we utilize the Graph Convolutional Network (GCN) to predict the infant brain age based on resting-state fMRI data. The brain connectivity obtained from rs-fMRI can be represented as a graph with brain regions as nodes and functional connections as edges. However, since the brain connectivity is a fully connected graph with features on edges, current GCN cannot be directly used for it is a node-based method for sparse graphs. Hence, we propose an edge-based Graph Path Convolution (GPC) method, which aggregates the information from different paths and can be naturally applied on dense graphs. We refer the whole model as Brain Connectivity Graph Convolutional Networks (BC-GCN). Further, two upgraded network structures are proposed by including the residual and attention modules, referred as BC-GCN-Res and BC-GCN-SE to emphasize the information of the original data and enhance influential channels. Moreover, we design a two-stage coarse-to-fine framework, which determines the age group first and then predicts the age using group-specific BC-GCN-SE models. To avoid accumulated errors from the first stage, a cross-group training strategy is adopted for the second stage regression models. We conduct experiments on infant fMRI scans from 6 to 811 days of age. The coarse-to-fine framework shows significant improvements when being applied to several models (reducing error over 10 days). Comparing with state-of-the-art methods, our proposed model BC-GCN-SE with coarse-to-fine framework reduces the mean absolute error of the prediction from >70 days to 49.9 days. The code is now available at https://github.com/SCUT-Xinlab/BC-GCN.

Hybrid Deep Learning Predictor for Smart Agriculture Sensing Based on Empirical Mode Decomposition and Gated Recurrent Unit Group Model

Smart agricultural sensing has enabled great advantages in practical applications recently, making it one of the most important and valuable systems. For outdoor plantation farms, the prediction of climate data, such as temperature, wind speed, and humidity, enables the planning and control of agricultural production to improve the yield and quality of crops. However, it is not easy to accurately predict climate trends because the sensing data are complex, nonlinear, and contain multiple components. This study proposes a hybrid deep learning predictor, in which an empirical mode decomposition (EMD) method is used to decompose the climate data into fixed component groups with different frequency characteristics, then a gated recurrent unit (GRU) network is trained for each group as the sub-predictor, and finally the results from the GRU are added to obtain the prediction result. Experiments based on climate data from an agricultural Internet of Things (IoT) system verify the development of the proposed model. The prediction results show that the proposed predictor can obtain more accurate predictions of temperature, wind speed, and humidity data to meet the needs of precision agricultural production.

Deep Hybrid Model Based on EMD with Classification by Frequency Characteristics for Long-Term Air Quality Prediction

Air pollution (mainly PM2.5) is one of the main environmental problems about air quality. Air pollution prediction and early warning is a prerequisite for air pollution prevention and control. However, it is not easy to accurately predict the long-term trend because the collected PM2.5 data have complex nonlinearity with multiple components of different frequency characteristics. This study proposes a hybrid deep learning predictor, in which the PM2.5 data are decomposed into components by empirical mode decomposition (EMD) firstly, and a convolutional neural network (CNN) is built to classify all the components into a fixed number of groups based on the frequency characteristics. Then, a gated-recurrent-unit (GRU) network is trained for each group as the sub-predictor, and the results from the three GRUs are fused to obtain the prediction result. Experiments based on the PM2.5 data from Beijing verify the proposed model, and the prediction results show that the decomposition and classification can develop the accuracy of the proposed predictor for air pollution prediction greatly.

Deep Learning of Static and Dynamic Brain Functional Networks for Early MCI Detection

While convolutional neural network (CNN) has been demonstrating powerful ability to learn hierarchical spatial features from medical images, it is still difficult to apply it directly to resting-state functional MRI (rs-fMRI) and the derived brain functional networks (BFNs). We propose a novel CNN framework to simultaneously learn embedded features from BFNs for brain disease diagnosis. Since BFNs can be built by considering both static and dynamic functional connectivity (FC), we first decompose rs-fMRI into multiple static BFNs with modified independent component analysis. Then, the voxel-wise variability in dynamic FC is used to quantify BFN dynamics. A set of paired 3D images representing static/dynamic BFNs can be fed into 3D CNNs, from which we can hierarchically and simultaneously learn static/dynamic BFN features. As a result, the dynamic BFN features can complement static BFN features and, at the meantime, different BFNs can help each other toward a joint and better classification. We validate our method with a publicly accessible, large cohort of rs-fMRI dataset in early-stage mild cognitive impairment (eMCI) diagnosis, which is one of the most challenging problems to the clinicians. By comparing with a conventional method, our method shows significant diagnostic performance improvement by almost 10%. This result demonstrates the effectiveness of deep learning in preclinical Alzheimer's disease diagnosis, based on the complex and high-dimensional voxel-wise spatiotemporal patterns of the resting-state brain functional connectomics. The framework provides a new but intuitive way to fully exploit deeply embedded diagnostic features from rs-fMRI for a better-individualized diagnosis of various neurological diseases.

Novel relative relevance score for estimating brain connectivity from fMRI data using an explainable neural network approach

BACKGROUND

Functional integration or connectivity in brain is directional, non-linear as well as variable in time-lagged dependence. Deep neural networks (DNN) have become an indispensable tool everywhere, by learning higher levels of abstract and complex patterns from raw data. However, in neuroscientific community they generally work as black-boxes, leading to the explanation of results difficult and less intuitive. We aim to propose a brain-connectivity measure based on an explainable NN (xNN) approach.

NEW METHOD

We build a NN-based predictor for regression problem. Since we aim to determine the contribution/relevance of past data-point from one region i in the prediction of current data-point from another region j, i.e. the higher-order connectivity between two brain-regions, we employ layer-wise relevance propagation (Bach et al., 2015) (LRP, a method for explaining DNN predictions), which has not been done before to the best of our knowledge. Specifically, we propose a novel score depending on weights as a quantitative measure of connectivity, called as relative relevance score (xNN-RRS). The RRS is an intuitive and transparent score. We provide an interpretation of the trained NN weights with-respect-to the brain-connectivity.

RESULTS

Face validity of our approach is demonstrated with experiments on simulated data, over existing methods. We also demonstrate construct validity of xNN-RRS in a resting-state fMRI experiment.

COMPARISON

Our approach shows superior performance, in terms of accuracy and computational complexity, over existing state-of-the-art methods for brain-connectivity estimation.

CONCLUSION

The proposed method is promising to serve as a first post-hoc explainable NN-approach for brain-connectivity analysis in clinical applications.

Variability and Reproducibility of Directed and Undirected Functional MRI Connectomes in the Human Brain

A growing number of studies are focusing on methods to estimate and analyze the functional connectome of the human brain. Graph theoretical measures are commonly employed to interpret and synthesize complex network-related information. While resting state functional MRI (rsfMRI) is often employed in this context, it is known to exhibit poor reproducibility, a key factor which is commonly neglected in typical cohort studies using connectomics-related measures as biomarkers. We aimed to fill this gap by analyzing and comparing the inter- and intra-subject variability of connectivity matrices, as well as graph-theoretical measures, in a large (n = 1003) database of young healthy subjects which underwent four consecutive rsfMRI sessions. We analyzed both directed (Granger Causality and Transfer Entropy) and undirected (Pearson Correlation and Partial Correlation) time-series association measures and related global and local graph-theoretical measures. While matrix weights exhibit a higher reproducibility in undirected, as opposed to directed, methods, this difference disappears when looking at global graph metrics and, in turn, exhibits strong regional dependence in local graphs metrics. Our results warrant caution in the interpretation of connectivity studies, and serve as a benchmark for future investigations by providing quantitative estimates for the inter- and intra-subject variabilities in both directed and undirected connectomic measures.