Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification

Brain dynamics supported by a hierarchy of complex correlation patterns defining a robust functional architecture

Functional magnetic resonance imaging (fMRI) provides insights into cognitive processes with significant clinical potential. However, delays in brain region communication and dynamic variations are often overlooked in functional network studies. We demonstrate that networks extracted from fMRI cross-correlation matrices, considering time lags between signals, show remarkable reliability when focusing on statistical distributions of network properties. This reveals a robust brain functional connectivity pattern, featuring a sparse backbone of strong 0-lag correlations and weaker links capturing coordination at various time delays. This dynamic yet stable network architecture is consistent across rats, marmosets, and humans, as well as in electroencephalogram (EEG) data, indicating potential universality in brain dynamics. Second-order properties of the dynamic functional network reveal a remarkably stable hierarchy of functional correlations in both group-level comparisons and test-retest analyses. Validation using alcohol use disorder fMRI data uncovers broader shifts in network properties than previously reported, demonstrating the potential of this method for identifying disease biomarkers.

Sparse Graph Representation Learning Based on Reinforcement Learning for Personalized Mild Cognitive Impairment (MCI) Diagnosis

Resting-state functional magnetic resonance imaging (rs-fMRI) has gained attention as a reliable technique for investigating the intrinsic function patterns of the brain. It facilitates the extraction of functional connectivity networks (FCNs) that capture synchronized activity patterns among regions of interest (ROIs). Analyzing FCNs enables the identification of distinctive connectivity patterns associated with mild cognitive impairment (MCI). For MCI diagnosis, various sparse representation techniques have been introduced, including statistical- and deep learning-based methods. However, these methods face limitations due to their reliance on supervised learning schemes, which restrict the exploration necessary for probing novel solutions. To overcome such limitation, prior work has incorporated reinforcement learning (RL) to dynamically select ROIs, but effective exploration remains challenging due to the vast search space during training. To tackle this issue, in this study, we propose an advanced RL-based framework that utilizes a divide-and-conquer approach to decompose the FCN construction task into smaller sub-problems in a subject-specific manner, enabling efficient exploration under each sub-problem condition. Additionally, we leverage the learned value function to determine the sparsity level of FCNs, considering individual characteristics of FCNs. We validate the effectiveness of our proposed framework by demonstrating its superior performance in MCI diagnosis on publicly available cohort datasets.

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.

Dynamic multilayer functional connectivity detects preclinical and clinical Alzheimer's disease

Increasing evidence suggests that patients with Alzheimer's disease present alterations in functional connectivity but previous results have not always been consistent. One of the reasons that may account for this inconsistency is the lack of consideration of temporal dynamics. To address this limitation, here we studied the dynamic modular organization on resting-state functional magnetic resonance imaging across different stages of Alzheimer's disease using a novel multilayer brain network approach. Participants from preclinical and clinical Alzheimer's disease stages were included. Temporal multilayer networks were used to assess time-varying modular organization. Logistic regression models were employed for disease stage discrimination, and partial least squares analyses examined associations between dynamic measures with cognition and pathology. Temporal multilayer functional measures distinguished all groups, particularly preclinical stages, overcoming the discriminatory power of risk factors such as age, sex, and APOE ϵ4 carriership. Dynamic multilayer functional measures exhibited strong associations with cognition as well as amyloid and tau pathology. Dynamic multilayer functional connectivity shows promise as a functional imaging biomarker for both early- and late-stage Alzheimer's disease diagnosis.

Dynamic functional connectivity analysis with temporal convolutional network for attention deficit/hyperactivity disorder identification

Introduction

Dynamic functional connectivity (dFC), which can capture the abnormality of brain activity over time in resting-state functional magnetic resonance imaging (rs-fMRI) data, has a natural advantage in revealing the abnormal mechanism of brain activity in patients with Attention Deficit/Hyperactivity Disorder (ADHD). Several deep learning methods have been proposed to learn dynamic changes from rs-fMRI for FC analysis, and achieved superior performance than those using static FC. However, most existing methods only consider dependencies of two adjacent timestamps, which is limited when the change is related to the course of many timestamps.

Methods

In this paper, we propose a novel Temporal Dependence neural Network (TDNet) for FC representation learning and temporal-dependence relationship tracking from rs-fMRI time series for automated ADHD identification. Specifically, we first partition rs-fMRI time series into a sequence of consecutive and non-overlapping segments. For each segment, we design an FC generation module to learn more discriminative representations to construct dynamic FCs. Then, we employ the Temporal Convolutional Network (TCN) to efficiently capture long-range temporal patterns with dilated convolutions, followed by three fully connected layers for disease prediction.

Results

As the results, we found that considering the dynamic characteristics of rs-fMRI time series data is beneficial to obtain better diagnostic performance. In addition, dynamic FC networks generated in a data-driven manner are more informative than those constructed by Pearson correlation coefficients.

Discussion

We validate the effectiveness of the proposed approach through extensive experiments on the public ADHD-200 database, and the results demonstrate the superiority of the proposed model over state-of-the-art methods in ADHD identification.

Classification of bipolar disorders using the multilayer modularity in dynamic minimum spanning tree from resting state fMRI

The diagnosis of bipolar disorders (BD) mainly depends on the clinical history and behavior observation, while only using clinical tools often limits the diagnosis accuracy. The study aimed to create a novel BD diagnosis framework using multilayer modularity in the dynamic minimum spanning tree (MST). We collected 45 un-medicated BD patients and 47 healthy controls (HC). The sliding window approach was utilized to construct dynamic MST via resting-state functional magnetic resonance imaging (fMRI) data. Firstly, we used three null models to explore the effectiveness of multilayer modularity in dynamic MST. Furthermore, the module allegiance exacted from dynamic MST was applied to train a classifier to discriminate BD patients. Finally, we explored the influence of the FC estimator and MST scale on the performance of the model. The findings indicated that multilayer modularity in the dynamic MST was not a random process in the human brain. And the model achieved an accuracy of 83.70% for identifying BD patients. In addition, we found the default mode network, subcortical network (SubC), and attention network played a key role in the classification. These findings suggested that the multilayer modularity in dynamic MST could highlight the difference between HC and BD patients, which opened up a new diagnostic tool for BD patients.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09907-x.

Constructing high-order functional networks based on hypergraph for diagnosis of autism spectrum disorders

Introduction

High-order functional connectivity networks (FCNs) that reflect the connection relationships among multiple brain regions have become important tools for exploring the deep workings of the brain and revealing the mechanisms of brain diseases. The traditional high-order FCN constructed based on the "correlation of correlations" strategy, is a representative method for conducting whole-brain connectivity analysis and revealing global network characteristics. However, whole-brain connectivity analysis may be affected by noise carried by less important brain regions, resulting in redundant information and affecting the accuracy and reliability of the analysis. Moreover, this type of analysis has a high computational complexity.

Methods

To address these issues, a new method for constructing high-order FCN based on hypergraphs is proposed in this article, which is used to accurately capture the real interaction relationships among brain regions. Specifically, first, a low-order FCN reflecting the connection relationships between pairs of brain regions based on resting-state functional Magnetic Resonance Imaging (rs-fMRI) time series is constructed, the method first constructs the low-order FCN that reflects the connection relationships between pairs of brain regions based on rs-fMRI time series, and then selects the "good friends" of each brain region from hypergraph perspective, which refers to the local friend circles with closer relationships. Then, the rs-fMRI time series corresponding to the "good friends" in each brain region's friend circle are averaged to obtain a sequence that reflects the intimacy between brain regions in each friend circle. Finally, hypergraph high-order FCN, which reflects the interaction relationships among multiple brain regions, is obtained by calculating the correlations based on the sequence of friend circles.

Results

The experimental results demonstrate that the proposed method outperforms traditional high-order FCN construction methods. Furthermore, integrating the high-order FCN constructed based on hypergraphs and the low-order FCN through feature fusion to achieve complementary information improves the accuracy of assisting in the diagnosis of brain diseases.

Discussion

In addition, the effectiveness of our method has only been validated in the diagnosis of ASD. For future work, we plan to extend this method to other brain connectivity patterns.

Temporal Dynamic Alterations of Regional Homogeneity in Parkinson's Disease: A Resting-State fMRI Study

Brain activity is time varying and dynamic, even in the resting state. However, little attention has been paid to the dynamic alterations in regional brain activity in Parkinson's disease (PD). We aimed to test for differences in dynamic regional homogeneity (dReHo) between PD patients and healthy controls (HCs) and to further investigate the pathophysiological meaning of this altered dReHo in PD. We included 57 PD patients and 31 HCs with rs-fMRI scans and neuropsychological examinations. Then, ReHo and dReHo were calculated for all subjects. We compared ReHo and dReHo between PD patients and HCs and then analyzed the associations between altered dReHo variability and clinical/neuropsychological measurements. Support vector machines (SVMs) were also used to assist in differentiating PD patients from HCs using the classification values of dReHo. The results showed that PD patients had increased ReHo in the bilateral medial temporal lobe and decreased ReHo in the right posterior cerebellar lobe, right precentral gyrus, and supplementary motor area, compared with controls. The coefficient of variation (CV) of dReHo was considerably higher in the precuneus in PD patients compared with HCs, and the CV of dReHo in the precuneus was found to be highly associated with HAMD, HAMA, and NMSQ scores. Multiple linear regression analysis controlling for demographic, clinical, and neuropsychiatric variables confirmed the association between altered dReHo and HAMD. Using the leave-one-out cross validation procedure, 98% (p < 0.001) of individuals were properly identified using the SVM classifier. These results provide new evidence for the aberrant resting-state brain activity in the precuneus of PD patients and its role in neuropsychiatric symptoms in PD.

Multicenter and Multichannel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.

SD-CNN: A static-dynamic convolutional neural network for functional brain networks

Static functional connections (sFCs) and dynamic functional connections (dFCs) have been widely used in the resting-state functional MRI (rs-fMRI) analysis. sFCs, calculated based on entire rs-fMRI scans, can accurately describe the static topology of the brain network. dFCs, estimated by dividing rs-fMRI scans into a series of short sliding windows, are used to reveal time-varying changes in FC patterns. Currently, how to jointly use sFCs and dFCs to identify brain diseases under the framework of deep learning is still a hot issue. To this end, we propose a static-dynamic convolutional neural network for functional brain networks, which involves a static pathway and a dynamic pathway for taking full advantages of sFCs and dFCs. Specifically, the static pathway, using high-resolution convolution filters (i.e., convolution filters with a high number of channels) at a single adjacency matrix of sFCs, is performed to capture static FC patterns. The dynamic pathway, using low-resolution convolution filters at each adjacency matrix of dFCs, is performed to capture time-varying FC patterns. Two types of diffusion connections are used in this model for encouraging the transfer of information between the static pathway and the dynamic pathway, which can make the learned features more discriminative. Furthermore, a static and dynamic combination classifier is introduced to combine features from two pathways for identifying brain diseases. Experiments on two real datasets demonstrate the effectiveness and advantages of our proposed method.

A pairwise functional connectivity similarity measure method based on few-shot learning for early MCI detection

Alzheimer's disease is an irreversible neurological disease, therefore prompt diagnosis during its early stage, i.e., early mild cognitive impairment (MCI), is crucial for effective treatment. In this paper, we propose an automatic diagnosis method, a few-shot learning-based pairwise functional connectivity (FC) similarity measure method, to detect early MCI. We first employ a sliding window strategy to generate a dynamic functional connectivity network (FCN) using each subject's rs-fMRI data. Then, normal controls (NCs) and early MCI patients are distinguished by measuring the similarity between the dynamic FC series of corresponding brain regions of interest (ROIs) pairs in different subjects. However, previous studies have shown that FC patterns in different ROI-pairs contribute differently to disease classification. To enable the FCs of different ROI-pairs to make corresponding contributions to disease classification, we adopt a self-attention mechanism to weight the FC features. We evaluated the suggested strategy using rs-fMRI data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the results point to the viability of our approach for detecting MCI at an early stage.

Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis

Introduction

The brain functional network can describe the spontaneous activity of nerve cells and reveal the subtle abnormal changes associated with brain disease. It has been widely used for analyzing early Alzheimer's disease (AD) and exploring pathological mechanisms. However, the current methods of constructing functional connectivity networks from functional magnetic resonance imaging (fMRI) heavily depend on the software toolboxes, which may lead to errors in connection strength estimation and bad performance in disease analysis because of many subjective settings.

Methods

To solve this problem, in this paper, a novel Adversarial Temporal-Spatial Aligned Transformer (ATAT) model is proposed to automatically map 4D fMRI into functional connectivity network for early AD analysis. By incorporating the volume and location of anatomical brain regions, the region-guided feature learning network can roughly focus on local features for each brain region. Also, the spatial-temporal aligned transformer network is developed to adaptively adjust boundary features of adjacent regions and capture global functional connectivity patterns of distant regions. Furthermore, a multi-channel temporal discriminator is devised to distinguish the joint distributions of the multi-region time series from the generator and the real sample.

Results

Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) proved the effectiveness and superior performance of the proposed model in early AD prediction and progression analysis.

Discussion

To verify the reliability of the proposed model, the detected important ROIs are compared with clinical studies and show partial consistency. Furthermore, the most significant altered connectivity reflects the main characteristics associated with AD.

Conclusion

Generally, the proposed ATAT provides a new perspective in constructing functional connectivity networks and is able to evaluate the disease-related changing characteristics at different stages for neuroscience exploration and clinical disease analysis.

Different Dynamic Nodal Properties Contribute to Cognitive Impairment in Patients with White Matter Hyperintensities

White matter hyperintensities (WMHs) are commonly observed in older adults and are associated with cognitive impairment. Although previous studies have found abnormal functional connectivities in patients with WMHs based on static functional magnetic resonance imaging (fMRI), the topological properties in the context of brain dynamics remain relatively unexplored. Herein, we explored disrupted dynamic topological properties of functional network connectivity in patients with WMHs and its relationship with cognitive impairment. We included 36 healthy controls (HC) and 104 patients with mild WMHs (n = 39), moderate WMHs (n = 37), and severe (n = 28) WMHs. The fMRI data of all participants were analyzed using Anatomical Automatic Labeling (AAL) and a sliding-window approach to generate dynamic functional connectivity matrics. Then, graph theory methods were applied to calculate the topological properties. Comprehensive neuropsychological scales were used to assess cognitive functions. Relationships between cognitive functions and abnormal dynamic topological properties were evaluated by Pearson’s correlation. We found that the patients with WMHs had higher temporal variability in regional properties, including betweenness centrality, nodal efficiencies, and nodal clustering coefficient. Furthermore, we found that the degree of centrality was related to executive function and memory, and the local coefficient correlated to executive function. Our results indicate that patients with WMHs have higher temporal variabilities in regional properties and are associated with executive and memory function.

Brain state transition analysis using ultra-fast fMRI differentiates MCI from cognitively normal controls

Purpose

Conventional resting-state fMRI studies indicate that many cortical and subcortical regions have altered function in Alzheimer's disease (AD) but the nature of this alteration has remained unclear. Ultrafast fMRIs with sub-second acquisition times have the potential to improve signal contrast and enable advanced analyses to understand temporal interactions between brain regions as opposed to spatial interactions. In this work, we leverage such fast fMRI acquisitions from Alzheimer's disease Neuroimaging Initiative to understand temporal differences in the interactions between resting-state networks in 55 older adults with mild cognitive impairment (MCI) and 50 cognitively normal healthy controls.

Methods

We used a sliding window approach followed by k-means clustering. At each window, we computed connectivity i.e., correlations within and across the regions of the default mode, salience, dorsal attention, and frontoparietal network. Visual and somatosensory networks were excluded due to their lack of association with AD. Using the Davies-Bouldin index, we identified clusters of windows with distinct connectivity patterns, also referred to as brain states. The fMRI time courses were converted into time courses depicting brain state transition. From these state time course, we calculated the dwell time for each state i.e., how long a participant spent in each state. We determined how likely a participant transitioned between brain states. Both metrics were compared between MCI participants and controls using a false discovery rate correction of multiple comparisons at a threshold of. 0.05.

Results

We identified 8 distinct brain states representing connectivity within and between the resting state networks. We identified three transitions that were different between controls and MCI, all involving transitions in connectivity between frontoparietal, dorsal attention, and default mode networks (p<0.04).

Conclusion

We show that ultra-fast fMRI paired with dynamic functional connectivity analysis allows us to capture temporal transitions between brain states. Most changes were associated with transitions between the frontoparietal and dorsal attention networks connectivity and their interaction with the default mode network. Although future work needs to validate these findings, the brain networks identified in our work are known to interact with each other and play an important role in cognitive function and memory impairment in AD.

Dynamic Brain Connectivity in Resting-State FMRI Using Spectral ICA and Graph Approach: Application to Healthy Controls and Multiple Sclerosis

Multiple sclerosis (MS) is a neuroinflammatory disease that involves structural and functional damage to the brain. It changes the functional connectivity of the brain between and within networks. Resting-state functional magnetic resonance imaging (fMRI) enables us to measure functional correlation and independence between different brain regions. In recent years, statistical methods, including independent component analysis (ICA) and graph-based analysis, have been widely used in fMRI studies. Furthermore, topological properties of the brain have been appeared as significant features of neuroscience studies. Most studies are focused on graph analysis and ICA methods, rather than considering spectral approaches. Here, we developed a new framework to measure brain connectivity (in static and dynamic formats) and incorporate it to study fMRI data from MS patients and healthy controls (HCs). For this purpose, a spectral ICA method is proposed to extract the nodes of the brain graph. Spectral ICA extracts more reliable components and decreases the processing time in calculation of the static brain connectivity. Compared to Infomax ICA, dynamic range and low-frequency to high-frequency power ratio (fALFF) show better results using the proposed ICA. It is also helpful in selection of the states for dynamic connectivity. Furthermore, the dynamic connectivity-based extracted components from spectral ICA are estimated using a mutual information method and based on correlation of sliding time-windowed on selected IC time courses. First-level and second-level connectivity states are calculated using correlations of connectivity strength between graph nodes (spectral ICA components). Finally, static and dynamic connectivity are analyzed based on correlation nodes percolated by an anatomical automatic labeling (AAL) atlas. Despite static and dynamic connectivity results of AAL correlations not showing any significant changes between MS and HC, our results based on spectral ICA in static and dynamic connectivity showed significantly decreased connectivity in MS patients in the anterior cingulate cortex, whereas it was significantly weaker in the core but stronger at the periphery of the posterior cingulate cortex.

Deep Spatio-Temporal Attention-based Recurrent Network from Dynamic Adaptive Functional Connectivity for MCI Identification

Most existing methods of constructing dynamic functional connectivity (dFC) network obtain the connectivity strength via the sliding window correlation (SWC) method, which estimates the connectivity strength at each time segment, rather than at each time point, and thus is difficult to produce accurate dFC network due to the influence of the window type and window width. Furthermore, the deep learning methods may not capture the discriminative spatio-temporal information that is closely related to disease, thus impacting the performance of (mild cognitive impairment) MCI identification. In this paper, a novel spatio-temporal attention-based bidirectional gated recurrent unit (STA-BiGRU) network is proposed to extract inherent spatio-temporal information from a dynamic adaptive functional connectivity (dAFC) network for MCI diagnosis. Specifically, we adopt a group lasso-based Kalman filter algorithm to obtain the dAFC network with more accurate connectivity strength at each time step. Then a spatial attention module with self-attention and a temporal attention module with multiple temporal attention vectors are incorporated into the BiGRU network to extract more discriminative disease-related spatio-temporal information. Finally, the spatio-temporal regularizations are employed to better guide the attention learning of STA-BiGRU network to enhance the robustness of the deep network. Experimental results show that the proposed framework achieves mean accuracies of 90.2%, 90.0%, and 81.5%, respectively, for three MCI classification tasks. This study provides a more effective deep spatio-temporal attention-based recurrent network and obtains good performance and interpretability of deep learning for psychiatry diagnosis research.

Brain disorder prediction with dynamic multivariate spatio-temporal features: Application to Alzheimer’s disease and autism spectrum disorder

The dynamic functional connectivity (dFC) in functional magnetic resonance imaging (fMRI) is beneficial for the analysis and diagnosis of neurological brain diseases. The dFCs between regions of interest (ROIs) are generally delineated by a specific template and clustered into multiple different states. However, these models inevitably fell into the model-driven self-contained system which ignored the diversity at spatial level and the dynamics at time level of the data. In this study, we proposed a spatial and time domain feature extraction approach for Alzheimer’s disease (AD) and autism spectrum disorder (ASD)-assisted diagnosis which exploited the dynamic connectivity among independent functional sub networks in brain. Briefly, independent sub networks were obtained by applying spatial independent component analysis (SICA) to the preprocessed fMRI data. Then, a sliding window approach was used to segment the time series of the spatial components. After that, the functional connections within the window were obtained sequentially. Finally, a temporal signal-sensitive long short-term memory (LSTM) network was used for classification. The experimental results on Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Autism Brain Imaging Data Exchange (ABIDE) datasets showed that the proposed method effectively predicted the disease at the early stage and outperformed the existing algorithms. The dFCs between the different components of the brain could be used as biomarkers for the diagnosis of diseases such as AD and ASD, providing a reliable basis for the study of brain connectomics.

Temporal-spatial dynamic functional connectivity analysis in schizophrenia classification

With the development of resting-state functional magnetic resonance imaging (rs-fMRI) technology, the functional connectivity network (FCN) which reflects the statistical similarity of temporal activity between brain regions has shown promising results for the identification of neuropsychiatric disorders. Alteration in FCN is believed to have the potential to locate biomarkers for classifying or predicting schizophrenia (SZ) from healthy control. However, the traditional FCN analysis with stationary assumption, i.e., static functional connectivity network (SFCN) at the time only measures the simple functional connectivity among brain regions, ignoring the dynamic changes of functional connectivity and the high-order dynamic interactions. In this article, the dynamic functional connectivity network (DFCN) is constructed to delineate the characteristic of connectivity variation across time. A high-order functional connectivity network (HFCN) designed based on DFCN, could characterize more complex spatial interactions across multiple brain regions with the potential to reflect complex functional segregation and integration. Specifically, the temporal variability and the high-order network topology features, which characterize the brain FCNs from region and connectivity aspects, are extracted from DFCN and HFCN, respectively. Experiment results on SZ identification prove that our method is more effective (i.e., obtaining a significantly higher classification accuracy, 81.82%) than other competing methods. Post hoc inspection of the informative features in the individualized classification task further could serve as the potential biomarkers for identifying associated aberrant connectivity in SZ.

High-order brain functional network for electroencephalography-based diagnosis of major depressive disorder

Brain functional network (BFN) based on electroencephalography (EEG) has been widely used to diagnose brain diseases, such as major depressive disorder (MDD). However, most existing BFNs only consider the correlation between two channels, ignoring the high-level interaction among multiple channels that contain more rich information for diagnosing brain diseases. In such a sense, the BFN is called low-order BFN (LO-BFN). In order to fully explore the high-level interactive information among multiple channels of the EEG signals, a scheme for constructing a high-order BFN (HO-BFN) based on the “correlation’s correlation” strategy is proposed in this paper. Specifically, the entire EEG time series is firstly divided into multiple epochs by sliding window. For each epoch, the short-term correlation between channels is calculated to construct a LO-BFN. The correlation time series of all channel pairs are formulated by these LO-BFNs obtained from all epochs to describe the dynamic change of short-term correlation along the time. To construct HO-BFN, we cluster all correlation time series to avoid the problems caused by high dimensionality, and the correlation of the average correlation time series from different clusters is calculated to reflect the high-order correlation among multiple channels. Experimental results demonstrate the efficiency of the proposed HO-BFN in MDD identification, and its integration with the LO-BFN can further improve the recognition rate.

Convolutional Recurrent Neural Network for Dynamic Functional MRI Analysis and Brain Disease Identification

Dynamic functional connectivity (dFC) networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) help us understand fundamental dynamic characteristics of human brains, thereby providing an efficient solution for automated identification of brain diseases, such as Alzheimer's disease (AD) and its prodromal stage. Existing studies have applied deep learning methods to dFC network analysis and achieved good performance compared with traditional machine learning methods. However, they seldom take advantage of sequential information conveyed in dFC networks that could be informative to improve the diagnosis performance. In this paper, we propose a convolutional recurrent neural network (CRNN) for automated brain disease classification with rs-fMRI data. Specifically, we first construct dFC networks from rs-fMRI data using a sliding window strategy. Then, we employ three convolutional layers and long short-term memory (LSTM) layer to extract high-level features of dFC networks and also preserve the sequential information of extracted features, followed by three fully connected layers for brain disease classification. Experimental results on 174 subjects with 563 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate the effectiveness of our proposed method in binary and multi-category classification tasks.

Multiview Feature Learning With Multiatlas-Based Functional Connectivity Networks for MCI Diagnosis

Functional connectivity (FC) networks built from resting-state functional magnetic resonance imaging (rs-fMRI) has shown promising results for the diagnosis of Alzheimer's disease and its prodromal stage, that is, mild cognitive impairment (MCI). FC is usually estimated as a temporal correlation of regional mean rs-fMRI signals between any pair of brain regions, and these regions are traditionally parcellated with a particular brain atlas. Most existing studies have adopted a predefined brain atlas for all subjects. However, the constructed FC networks inevitably ignore the potentially important subject-specific information, particularly, the subject-specific brain parcellation. Similar to the drawback of the "single view" (versus the "multiview" learning) in medical image-based classification, FC networks constructed based on a single atlas may not be sufficient to reveal the underlying complicated differences between normal controls and disease-affected patients due to the potential bias from that particular atlas. In this study, we propose a multiview feature learning method with multiatlas-based FC networks to improve MCI diagnosis. Specifically, a three-step transformation is implemented to generate multiple individually specified atlases from the standard automated anatomical labeling template, from which a set of atlas exemplars is selected. Multiple FC networks are constructed based on these preselected atlas exemplars, providing multiple views of the FC network-based feature representations for each subject. We then devise a multitask learning algorithm for joint feature selection from the constructed multiple FC networks. The selected features are jointly fed into a support vector machine classifier for multiatlas-based MCI diagnosis. Extensive experimental comparisons are carried out between the proposed method and other competing approaches, including the traditional single-atlas-based method. The results indicate that our method significantly improves the MCI classification, demonstrating its promise in the brain connectome-based individualized diagnosis of brain diseases.

Time-varying dynamic network model for dynamic resting state functional connectivity in fMRI and MEG imaging

Dynamic resting state functional connectivity (RSFC) characterizes fluctuations that occur over time in functional brain networks. Existing methods to extract dynamic RSFCs, such as sliding-window and clustering methods that are inherently non-adaptive, have various limitations such as high-dimensionality, an inability to reconstruct brain signals, insufficiency of data for reliable estimation, insensitivity to rapid changes in dynamics, and a lack of generalizability across multiply functional imaging modalities. To overcome these deficiencies, we develop a novel and unifying time-varying dynamic network (TVDN) framework for examining dynamic resting state functional connectivity. TVDN includes a generative model that describes the relation between a low-dimensional dynamic RSFC and the brain signals, and an inference algorithm that automatically and adaptively learns the low-dimensional manifold of dynamic RSFC and detects dynamic state transitions in data. TVDN is applicable to multiple modalities of functional neuroimaging such as fMRI and MEG/EEG. The estimated low-dimensional dynamic RSFCs manifold directly links to the frequency content of brain signals. Hence we can evaluate TVDN performance by examining whether learnt features can reconstruct observed brain signals. We conduct comprehensive simulations to evaluate TVDN under hypothetical settings. We then demonstrate the application of TVDN with real fMRI and MEG data, and compare the results with existing benchmarks. Results demonstrate that TVDN is able to correctly capture the dynamics of brain activity and more robustly detect brain state switching both in resting state fMRI and MEG data.

Temporal Grading Index of Functional Network Topology Predicts Pain Perception of Patients With Chronic Back Pain

Chronic back pain (CBP) is a maladaptive health problem affecting the brain function and behavior of the patient. Accumulating evidence has shown that CBP may alter the organization of functional brain networks; however, whether the severity of CBP is associated with changes in dynamics of functional network topology remains unclear. Here, we generated dynamic functional networks based on resting-state functional magnetic resonance imaging (rs-fMRI) of 34 patients with CBP and 34 age-matched healthy controls (HC) in the OpenPain database via a sliding window approach, and extracted nodal degree, clustering coefficient (CC), and participation coefficient (PC) of all windows as features to characterize changes of network topology at temporal scale. A novel feature, named temporal grading index (TGI), was proposed to quantify the temporal deviation of each network property of a patient with CBP to the normal oscillation of the HCs. The TGI of the three features achieved outstanding performance in predicting pain intensity on three commonly used regression models (i.e., SVR, Lasso, and elastic net) through a 5-fold cross-validation strategy, with the minimum mean square error of 0.25 ± 0.05; and the TGI was not related to depression symptoms of the patients. Furthermore, compared to the HCs, brain regions that contributed most to prediction showed significantly higher CC and lower PC across time windows in the CBP cohort. These results highlighted spatiotemporal changes in functional network topology in patients with CBP, which might serve as a valuable biomarker for assessing the sensation of pain in the brain and may facilitate the development of CBP management/therapy approaches.

Functional Connectivity Dynamics Altered of the Resting Brain in Subjective Cognitive Decline

Background

Subjective cognitive decline (SCD) appears in the preclinical stage of the Alzheimer's disease continuum. In this stage, dynamic features are more sensitive than static features to reflect early subtle changes in functional brain connectivity. Therefore, we studied local and extended dynamic connectivity of the resting brain of people with SCD to determine their intrinsic brain changes.

Methods

We enrolled cognitively normal older adults from the communities and divided them into SCD and normal control (NC) groups. We used mean dynamic amplitude of low-frequency fluctuation (mdALFF) to evaluate region of interest (ROI)-wise local dynamic connectivity of resting-state functional MRI. The dynamic functional connectivity (dFC) between ROIs was tested by whole-brain-based statistics.

Results

When comparing SCD (N = 40) with NC (N = 45), mdALFF_mean decreased at right inferior parietal lobule (IPL) of the frontoparietal network (FPN). Still, it increased at the right middle temporal gyrus (MTG) of the ventral attention network (VAN) and right calcarine of the visual network (VIS). Also, the mdALFF_var (variance) increased at the left superior temporal gyrus of AUD, right MTG of VAN, right globus pallidum of the cingulo-opercular network (CON), and right lingual gyrus of VIS. Furthermore, mdALFF_mean at right IPL of FPN are correlated negatively with subjective complaints and positively with objective cognitive performance. In the dFC seeded from the ROIs with local mdALFF group differences, SCD showed a generally lower dFC_mean and higher dFC_var (variance) to other regions of the brain. These weakened and unstable functional connectivity appeared among FPN, CON, the default mode network, and the salience network, the large-scale networks of the triple network model for organizing neural resource allocations.

Conclusion

The local dynamic connectivity of SCD decreased in brain regions of cognitive executive control. Meanwhile, compensatory visual efforts and bottom-up attention rose. Mixed decrease and compensatory increase of dynamics of intrinsic brain activity suggest the transitional nature of SCD. The FPN local dynamics balance subjective and objective cognition and maintain cognitive preservation in preclinical dementia. Aberrant triple network model features the dFC alternations of SCD. Finally, the right lateralization phenomenon emerged early in the dementia continuum and affected local dynamic connectivity.

Altered static and dynamic voxel-mirrored homotopic connectivity in patients with frontal glioma

Contralateral regions play critical role in functional compensation in glioma patients. Voxel-mirrored homotopic connectivity (VMHC) characterizes the intrinsic functional connectivity (FC) of the brain, considered to have a regional functional basis. We aimed to investigate the alterations of brain regional function and VMHC in patients with frontal glioma, and further investigated the correlation between these alterations and cognition. We enrolled patients with frontal glioma and matched healthy controls (HC). We chose degree centrality (DC), regional homogeneity (ReHo), and VMHC to investigate the alterations of regional function and intrinsic FC in patients. Furthermore, partial correlation analyses were conducted to explore the relationship between imaging functional indicators and cognitions. Compared with HC, patients showed decreased static VMHC within right and left middle frontal gyrus (MFG.R, MFG.L), left superior frontal gyrus (SFG.L), right precuneus (PCUN.R), and left precuneus (PCUN.L), decreased static DC within left cingulate gyrus (CG.L), right superior frontal gyrus (SFG.R), and right postcentral gyrus (POCG.R), decreased static ReHo within CG.L, decreased dynamic ReHo within right inferior parietal lobule (IPL.R), but increased dynamic VMHC (dVMHC) within PCUN.R and PCUN.L. Furthermore, values of decreased VMHC within MFG.R, decreased DC within CG.L, decreased ReHo within CG.L, and increased dVMHC within PCUN.R were significantly positively correlated with cognitive functions. We preliminarily confirmed glioma causes regional dysfunction and disturbs long-distance FC, and long-distance FC showed strong instability in patients with frontal glioma. Meanwhile, the correlation analyses indicated directions for cognitive protection in patients with frontal glioma.

Resting-state dynamic functional connectivity predicts the psychosocial stress response

Acute stress triggers a complex cascade of psychological, physiological, and neural responses, which show large and enduring individual differences. Although previous studies have examined the relationship between the stress response and dynamic features of the brain's resting state, no study has used the brain's dynamic activity in the resting state to predict individual differences in the psychosocial stress response. In the current study, resting-state scans of forty-eight healthy participants were collected, and then their individual acute stress responses during the Montreal Imaging Stress Test (MIST) paradigm were recorded. Results defined a connectivity state (CS) characterized by positive correlations across the whole brain during resting-state that could negatively predict participants' feelings of social evaluative threat during stress tasks. Another CS characterized by negative correlations between the frontal-parietal network (FPN) and almost all other networks, except the dorsal attentional network (DAN), could predict participants' subjective stress, feelings of uncontrollability, and feelings of social evaluative threat. However, no CS could predict participants' salivary cortisol stress response. Overall, these results suggested that the brain state characterized as attentional regulation, linking self-control, and top-down regulation ability, could predict the psychosocial stress response. This study also developed an objective indicator for predicting human stress responses.

It Is Time to Study Overlapping Molecular and Circuit Pathophysiologies in Alzheimer's and Lewy Body Disease Spectra

Alzheimer's disease (AD) is the leading cause of dementia due to neurodegeneration and is characterized by extracellular senile plaques composed of amyloid β1 - 42 (Aβ) as well as intracellular neurofibrillary tangles consisting of phosphorylated tau (p-tau). Dementia with Lewy bodies constitutes a continuous spectrum with Parkinson's disease, collectively termed Lewy body disease (LBD). LBD is characterized by intracellular Lewy bodies containing α-synuclein (α-syn). The core clinical features of AD and LBD spectra are distinct, but the two spectra share common cognitive and behavioral symptoms. The accumulation of pathological proteins, which acquire pathogenicity through conformational changes, has long been investigated on a protein-by-protein basis. However, recent evidence suggests that interactions among these molecules may be critical to pathogenesis. For example, Aβ/tau promotes α-syn pathology, and α-syn modulates p-tau pathology. Furthermore, clinical evidence suggests that these interactions may explain the overlapping pathology between AD and LBD in molecular imaging and post-mortem studies. Additionally, a recent hypothesis points to a common mechanism of prion-like progression of these pathological proteins, via neural circuits, in both AD and LBD. This suggests a need for understanding connectomics and their alterations in AD and LBD from both pathological and functional perspectives. In AD, reduced connectivity in the default mode network is considered a hallmark of the disease. In LBD, previous studies have emphasized abnormalities in the basal ganglia and sensorimotor networks; however, these account for movement disorders only. Knowledge about network abnormalities common to AD and LBD is scarce because few previous neuroimaging studies investigated AD and LBD as a comprehensive cohort. In this paper, we review research on the distribution and interactions of pathological proteins in the brain in AD and LBD, after briefly summarizing their clinical and neuropsychological manifestations. We also describe the brain functional and connectivity changes following abnormal protein accumulation in AD and LBD. Finally, we argue for the necessity of neuroimaging studies that examine AD and LBD cases as a continuous spectrum especially from the proteinopathy and neurocircuitopathy viewpoints. The findings from such a unified AD and Parkinson's disease (PD) cohort study should provide a new comprehensive perspective and key data for guiding disease modification therapies targeting the pathological proteins in AD and LBD.

Fronto-temporal functional disconnection precedes hippocampal atrophy in clinically confirmed multi-domain amnestic Mild Cognitive Impairment

Mild Cognitive Impairment (MCI) is fraught with high false positive diagnostic errors. The high rate of false positive diagnosis hampers attempts to identify reliable and valid biomarkers for MCI. Recent research suggests that aberrant functional neurocircuitries emerge prior to significant cognitive deficits. The aim of the present study was to examine this in clinically confirmed multi-domain amnestic-MCI (mdaMCI) using an established, multi-time point, methodology for minimizing false positive diagnosis. Structural and resting-state functional MRI data were acquired in healthy controls (HC, n=24), clinically-confirmed multi-domain amnestic-MCI (mdaMCI, n=14) and mild Alzheimer's Dementia (mAD, n=6). Group differences in cortical thickness, hippocampal volume and functional connectivity were investigated. Hippocampal subvolumes differentiated mAD from HC and mdaMCI. Functional decoupling of fronto-temporal networks implicated in memory and executive function differentiated HC and mdaMCI. Decreased functional connectivity in these networks was associated with poorer cognitive performance scores. Preliminary findings suggest the large-scale decoupling of fronto-temporal networks associated with cognitive decline precedes measurable structural neurodegeneration in clinically confirmed MCI and may represent a potential biomarker for disease progression.

Constructing Multi-view High-order Functional Connectivity Networks for Diagnosis of Autism Spectrum Disorder

Brain functional connectivity network (FCN) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of in terest (ROIs), without exploring more informative higher-level inter actions among multiple ROIs which could be beneficial to disease diagnosis. To fully explore the discriminative information provided by different brain networks, a cluster-based multi-view high-order FCN (Ho-FCN) framework is proposed in this paper. Specifically, we first group the functional connectivity (FC) time series into different clusters and compute the multi-order central moment series for the FC time series in each cluster. Then we utilize the correlation of central moment series between different clusters to reveal the high-order FC relationships among multiple ROIs. In addition, to address the phase mismatch issue in conventional FCNs, we also adopt the central moments of the correlation time series as the temporal-invariance features to capture the dynamic characteristics of low-order dynamic FCN (Lo-D-FCN). Experimental results on the ABIDE dataset validate that: 1) the proposed multi-view Ho-FCNs is able to explore rich discriminative information for ASD diagnosis; 2) the phase mismatch issue can be well circumvented by using central moments; and 3) the combination of different types of FCNs can significantly improve the diagnostic accuracy of ASD (86.2%).

Auto-weighted centralised multi-task learning via integrating functional and structural connectivity for subjective cognitive decline diagnosis

Early diagnosis and intervention of mild cognitive impairment (MCI) and its early stage (i.e., subjective cognitive decline (SCD)) is able to delay or reverse the disease progression. However, discrimination between SCD, MCI and healthy subjects accurately remains challenging. This paper proposes an auto-weighted centralised multi-task (AWCMT) learning framework for differential diagnosis of SCD and MCI. AWCMT is based on structural and functional connectivity information inferred from magnetic resonance imaging (MRI). To be specific, we devise a novel multi-task learning algorithm to combine neuroimaging functional and structural connective information. We construct a functional brain network through a sparse and low-rank machine learning method, and also a structural brain network via fibre bundle tracking. Those two networks are constructed separately and independently. Multi-task learning is then used to identify features integration of functional and structural connectivity. Hence, we can learn each task's significance automatically in a balanced way. By combining the functional and structural information, the most informative features of SCD and MCI are obtained for diagnosis. The extensive experiments on the public and self-collected datasets demonstrate that the proposed algorithm obtains better performance in classifying SCD, MCI and healthy people than traditional algorithms. The newly proposed method has good interpretability as it is able to discover the most disease-related brain regions and their connectivity. The results agree well with current clinical findings and provide new insights into early AD detection based on the multi-modal neuroimaging technique.

Diagnosis of obsessive-compulsive disorder via spatial similarity-aware learning and fused deep polynomial network

Obsessive-compulsive disorder (OCD) is a type of hereditary mental illness, which seriously affect the normal life of the patients. Sparse learning has been widely used in detecting brain diseases objectively by removing redundant information and retaining monitor valuable biological characteristics from the brain functional connectivity network (BFCN). However, most existing methods ignore the relationship between brain regions in each subject. To solve this problem, this paper proposes a spatial similarity-aware learning (SSL) model to build BFCNs. Specifically, we embrace the spatial relationship between adjacent or bilaterally symmetric brain regions via a smoothing regularization term in the model. We develop a novel fused deep polynomial network (FDPN) model to further learn the powerful information and attempt to solve the problem of curse of dimensionality using BFCN features. In the FDPN model, we stack a multi-layer deep polynomial network (DPN) and integrate the features from multiple output layers via the weighting mechanism. In this way, the FDPN method not only can identify the high-level informative features of BFCN but also can solve the problem of curse of dimensionality. A novel framework is proposed to detect OCD and unaffected first-degree relatives (UFDRs), which combines deep learning and traditional machine learning methods. We validate our algorithm in the resting-state functional magnetic resonance imaging (rs-fMRI) dataset collected by the local hospital and achieve promising performance.

Detecting Risk Gene and Pathogenic Brain Region in EMCI Using a Novel GERF Algorithm Based on Brain Imaging and Genetic Data

Fusion analysis of disease-related multi-modal data is becoming increasingly important to illuminate the pathogenesis of complex brain diseases. However, owing to the small amount and high dimension of multi-modal data, current machine learning methods do not fully achieve the high veracity and reliability of fusion feature selection. In this paper, we propose a genetic-evolutionary random forest (GERF) algorithm to discover the risk genes and disease-related brain regions of early mild cognitive impairment (EMCI) based on the genetic data and resting-state functional magnetic resonance imaging (rs-fMRI) data. Classical correlation analysis method is used to explore the association between brain regions and genes, and fusion features are constructed. The genetic-evolutionary idea is introduced to enhance the classification performance, and to extract the optimal features effectively. The proposed GERF algorithm is evaluated by the public Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the results show that the algorithm achieves satisfactory classification accuracy in small sample learning. Moreover, we compare the GERF algorithm with other methods to prove its superiority. Furthermore, we propose the overall framework of detecting pathogenic factors, which can be accurately and efficiently applied to the multi-modal data analysis of EMCI and be able to extend to other diseases. This work provides a novel insight for early diagnosis and clinicopathologic analysis of EMCI, which facilitates clinical medicine to control further deterioration of diseases and is good for the accurate electric shock using transcranial magnetic stimulation.

Constructing high-order functional connectivity network based on central moment features for diagnosis of autism spectrum disorder

The sliding-window-based dynamic functional connectivity network (D-FCN) has been becoming an increasingly useful tool for understanding the changes of brain connectivity patterns and the association of neurological diseases with these dynamic variations. However, conventional D-FCN is essentially low-order network, which only reflects the pairwise interaction pattern between brain regions and thus overlooking the high-order interactions among multiple brain regions. In addition, D-FCN is innate with temporal sensitivity issue, i.e., D-FCN is sensitive to the chronological order of its subnetworks. To deal with the above issues, we propose a novel high-order functional connectivity network framework based on the central moment feature of D-FCN. Specifically, we firstly adopt a central moment approach to extract multiple central moment feature matrices from D-FCN. Furthermore, we regard the matrices as the profiles to build multiple high-order functional connectivity networks which further capture the higher level and more complex interaction relationships among multiple brain regions. Finally, we use the voting strategy to combine the high-order networks with D-FCN for autism spectrum disorder diagnosis. Experimental results show that the combination of multiple functional connectivity networks achieves accuracy of 88.06%, and the best single network achieves accuracy of 79.5%.

Classification of patients with AD from healthy controls using entropy-based measures of causality brain networks

BACKGROUND

Machine learning and pattern recognition have been widely used in rs-fMRI data to investigate Alzheimer's disease (AD). However, many previous methods extracted discriminative features based on functional correlations, which may ignore the asynchronous causality influence of neural activities.

NEW METHOD

We propose a novel method for AD diagnosis using Sample Entropy to measure the neural complexity of the brain causality network. Granger Causality analysis with a sliding time window was applied on rs-fMRI data of 29 AD patients and 30 cognitive normal (CN) controls to compute the whole brain's causality series. We further grouped these causality series into clusters by agglomerative hierarchical clustering algorithm and computed Sample Entropy of the clusters as the classification features.

RESULTS

We explored four different classifiers, i.e., XGBoost, SVM cluster, Random Forest, and SVM, based on the above features. An accuracy of 89.83%, with a sensitivity of 90.00% and a specificity of 89.66%, was achieved with the optimal feature subsets using the SVM classifier.

COMPARISON WITH EXISTING METHODS

With the same dataset, the performances of the proposed method were generally higher than those of conventional methods for AD classification based on Pearson's correlation network, dynamic Pearson's correlation network, High-order correlation network, and causality correlation network.

CONCLUSIONS

Our method demonstrates the measure of Sample Entropy with causality connection as a powerful tool to classify AD patients from CN controls, and provides a deep insight into the neuropathogenesis of AD.

Modeling dynamic characteristics of brain functional connectivity networks using resting-state functional MRI

Dynamic network analysis using resting-state functional magnetic resonance imaging (rs-fMRI) provides a great insight into fundamentally dynamic characteristics of human brains, thus providing an efficient solution to automated brain disease identification. Previous studies usually pay less attention to evolution of global network structures over time in each brain's rs-fMRI time series, and also treat network-based feature extraction and classifier training as two separate tasks. To address these issues, we propose a temporal dynamics learning (TDL) method for network-based brain disease identification using rs-fMRI time-series data, through which network feature extraction and classifier training are integrated into the unified framework. Specifically, we first partition rs-fMRI time series into a sequence of segments using overlapping sliding windows, and then construct longitudinally ordered functional connectivity networks. To model the global temporal evolution patterns of these successive networks, we introduce a group-fused Lasso regularizer in our TDL framework, while the specific network architecture is induced by an ℓ₁-norm regularizer. Besides, we develop an efficient optimization algorithm to solve the proposed objective function via the Alternating Direction Method of Multipliers (ADMM). Compared with previous studies, the proposed TDL model can not only explicitly model the evolving connectivity patterns of global networks over time, but also capture unique characteristics of each network defined at each segment. We evaluate our TDL on three real autism spectrum disorder (ASD) datasets with rs-fMRI data, achieving superior results in ASD identification compared with several state-of-the-art methods.

A Novel Unit-Based Personalized Fingerprint Feature Selection Strategy for Dynamic Functional Connectivity Networks

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

Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: A multicenter study

From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.

Constructing Dynamic Functional Networks via Weighted Regularization and Tensor Low-Rank Approximation for Early Mild Cognitive Impairment Classification

Brain functional networks constructed via regularization has been widely used in early mild cognitive impairment (eMCI) classification. However, few methods can properly reflect the similarities and differences of functional connections among different people. Most methods ignore some topological attributes, such as connection strength, which may delete strong functional connections in brain functional networks. To overcome these limitations, we propose a novel method to construct dynamic functional networks (DFN) based on weighted regularization (WR) and tensor low-rank approximation (TLA), and apply it to identify eMCI subjects from normal subjects. First, we introduce the WR term into the DFN construction and obtain WR-based DFNs (WRDFN). Then, we combine the WRDFNs of all subjects into a third-order tensor for TLA processing, and obtain the DFN based on WR and TLA (WRTDFN) of each subject in the tensor. We calculate the weighted-graph local clustering coefficient of each region in each WRTDFN as the effective feature, and use the t-test for feature selection. Finally, we train a linear support vector machine (SVM) classifier to classify the WRTDFNs of all subjects. Experimental results demonstrate that the proposed method can obtain DFNs with the scale-free property, and that the classification accuracy (ACC), the sensitivity (SEN), the specificity (SPE), and the area under curve (AUC) reach 87.0662% ± 0.3202%, 83.4363% ± 0.5076%, 90.6961% ± 0.3250% and 0.9431 ± 0.0023, respectively. We also achieve the best classification results compared with other comparable methods. This work can effectively improve the classification performance of DFNs constructed by existing methods for eMCI and has certain reference value for the early diagnosis of Alzheimer’s disease (AD).

Recognition of Cognitive Impairment in Adult Moyamoya Disease: A Classifier Based on High-Order Resting-State Functional Connectivity Network

Objective: Vascular cognitive impairment (VCI) is a common complication in adult patients with moyamoya disease (MMD), and is reversible by surgical revascularization in its early stage of mild VCI. However, accurate diagnosis of mild VCI is difficult based on neuropsychological examination alone. This study proposed a method of dynamic resting-state functional connectivity (FC) network to recognize global cognitive impairment in MMD. Methods: For MMD, 36 patients with VCI and 43 patients with intact cognition (Non-VCI) were included, as well as 26 normal controls (NCs). Using resting-state fMRI, dynamic low-order FC networks were first constructed with multiple brain regions which were generated through a sliding window approach and correlated in temporal dimension. In order to obtain more information of network interactions along the time, high-order FC networks were established by calculating correlations among each pair of brain regions. Afterwards, a sparse representation-based classifier was constructed to recognize MMD (experiment 1) and its cognitive impairment (experiment 2) with features extracted from both low- and high-order FC networks. Finally, the ten-fold cross-validation strategy was proposed to train and validate the performance of the classifier. Results: The three groups did not differ significantly in demographic features (p > 0.05), while the VCI group exhibited the lowest MMSE scores (p = 0.001). The Non-VCI and NCs groups did not differ significantly in MMSE scores (p = 0.054). As for the classification between MMD and NCs, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 90.70, 88.57, 93.67, and 73.08%, respectively. While for the classification between VCI and Non-VCI, the AUC, accuracy, sensitivity, and specificity of the classifier reached 91.02, 84.81, 80.56, and 88.37%, respectively. Conclusion: This study not only develops a promising classifier to recognize VCI in adult MMD in its early stage, but also implies the significance of time-varying properties in dynamic FC networks.

Multi-Scale Time-Series Kernel-Based Learning Method for Brain Disease Diagnosis

The functional magnetic resonance imaging (fMRI) is a noninvasive technique for studying brain activity, such as brain network analysis, neural disease automated diagnosis and so on. However, many existing methods have some drawbacks, such as limitations of graph theory, lack of global topology characteristic, local sensitivity of functional connectivity, and absence of temporal or context information. In addition to many numerical features, fMRI time series data also cover specific contextual knowledge and global fluctuation information. Here, we propose multi-scale time-series kernel-based learning model for brain disease diagnosis, based on Jensen-Shannon divergence. First, we calculate correlation value within and between brain regions over time. In addition, we extract multi-scale synergy expression probability distribution (interactional relation) between brain regions. Also, we produce state transition probability distribution (sequential relation) on single brain regions. Then, we build time-series kernel-based learning model based on Jensen-Shannon divergence to measure similarity of brain functional connectivity. Finally, we provide an efficient system to deal with brain network analysis and neural disease automated diagnosis. On Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, our proposed method achieves accuracy of 0.8994 and AUC of 0.8623. On Major Depressive Disorder (MDD) dataset, our proposed method achieves accuracy of 0.9166 and AUC of 0.9263. Experiments show that our proposed method outperforms other existing excellent neural disease automated diagnosis approaches. It shows that our novel prediction method performs great accurate for identification of brain diseases as well as existing outstanding prediction tools.

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Alzheimer's disease (AD) is a neurodegenerative disease with an irreversible and progressive process. To understand the brain functions and identify the biomarkers of AD and early stages of the disease [also known as, mild cognitive impairment (MCI)], it is crucial to build the brain functional connectivity network (BFCN) using resting-state functional magnetic resonance imaging (rs-fMRI). Existing methods have been mainly developed using only a single time-point rs-fMRI data for classification. In fact, multiple time-point data is more effective than a single time-point data in diagnosing brain diseases by monitoring the disease progression patterns using longitudinal analysis. In this article, we utilize multiple rs-fMRI time-point to identify early MCI (EMCI) and late MCI (LMCI), by integrating the fused sparse network (FSN) model with parameter-free centralized (PFC) learning. Specifically, we first construct the FSN framework by building multiple time-point BFCNs. The multitask learning via PFC is then leveraged for longitudinal analysis of EMCI and LMCI. Accordingly, we can jointly learn the multiple time-point features constructed from the BFCN model. The proposed PFC method can automatically balance the contributions of different time-point information via learned specific and common features. Finally, the selected multiple time-point features are fused by a similarity network fusion (SNF) method. Our proposed method is evaluated on the public AD neuroimaging initiative phase-2 (ADNI-2) database. The experimental results demonstrate that our method can achieve quite promising performance and outperform the state-of-the-art methods.

Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction

Graph convolution networks (GCN) have been successfully applied in disease prediction tasks as they capture interactions (i.e., edges and edge weights on the graph) between individual elements. The interactions in existing works are constructed by fusing similarity between imaging information and distance between non-imaging information, whereas disregarding the disease status of those individuals in the training set. Besides, the similarity is being evaluated by computing the correlation distance between feature vectors, which limits prediction performance, especially for predicting significant memory concern (SMC) and mild cognitive impairment (MCI). In this paper, we propose three mechanisms to improve GCN, namely similarity-aware adaptive calibrated GCN (SAC-GCN), for predicting SMC and MCI. First, we design a similarity-aware graph using different receptive fields to consider disease status. The labelled subjects on the graph are only connected with those labelled subjects with the same status. Second, we propose an adaptive mechanism to evaluate similarity. Specifically, we construct initial GCN with evaluating similarity by using traditional correlation distance, then pre-train the initial GCN by using training samples and use it to score all subjects. Then, the difference between these scores replaces correlation distance to update similarity. Last, we devise a calibration mechanism to fuse functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) information into edges. The proposed method is tested on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results demonstrate that our proposed method is useful to predict disease-induced deterioration and superior to other related algorithms, with a mean classification accuracy of 86.83% in our prediction tasks.

A Tensor-Based Framework for rs-fMRI Classification and Functional Connectivity Construction

Recently, machine learning methods have gained lots of attention from researchers seeking to analyze brain images such as Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to obtain a deeper understanding of the brain and such related diseases, for example, Alzheimer's disease. Finding the common patterns caused by a brain disorder through analysis of the functional connectivity (FC) network along with discriminating brain diseases from normal controls have long been the two principal goals in studying rs-fMRI data. The majority of FC extraction methods calculate the FC matrix for each subject and then use simple techniques to combine them and obtain a general FC matrix. In addition, the state-of-the-art classification techniques for finding subjects with brain disorders also rely on calculating an FC for each subject, vectorizing, and feeding them to the classifier. Considering these problems and based on multi-dimensional nature of the data, we have come up with a novel tensor framework in which a general FC matrix is obtained without the need to construct an FC matrix for each sample. This framework also allows us to reduce the dimensionality and create a novel discriminant function that rather than using FCs works directly with each sample, avoids vectorization in any step, and uses the test data in the training process without forcing any prior knowledge of its label into the classifier. Extensive experiments using the ADNI dataset demonstrate that our proposed framework effectively boosts the fMRI classification performance and reveals novel connectivity patterns in Alzheimer's disease at its early stages.

Dynamic Brain Connectivity in Resting State Functional MR Imaging

Dynamic functional connectivity adds another dimension to resting-state functional MR imaging analysis. In recent years, dynamic functional connectivity has been increasingly used in resting-state functional MR imaging, and several studies have demonstrated that dynamic functional connectivity patterns correlate with different physiologic and pathologic brain states. In fact, evidence suggests that dynamic functional connectivity is a more sensitive marker than static functional connectivity; therefore, it might be a promising tool to add to clinical functional neuroimaging. This article provides a broad overview of dynamic functional connectivity and reviews its general principles, techniques, and potential clinical applications.

Fusion of ULS Group Constrained High- and Low-Order Sparse Functional Connectivity Networks for MCI Classification

Functional connectivity networks, derived from resting-state fMRI data, have been found as effective biomarkers for identifying mild cognitive impairment (MCI) from healthy elderly. However, the traditional functional connectivity network is essentially a low-order network with the assumption that the brain activity is static over the entire scanning period, ignoring temporal variations among the correlations derived from brain region pairs. To overcome this limitation, we proposed a new type of sparse functional connectivity network to precisely describe the relationship of temporal correlations among brain regions. Specifically, instead of using the simple pairwise Pearson's correlation coefficient as connectivity, we first estimate the temporal low-order functional connectivity for each region pair based on an ULS Group constrained-UOLS regression algorithm, where a combination of ultra-least squares (ULS) criterion with a Group constrained topology structure detection algorithm is applied to detect the topology of functional connectivity networks, aided by an Ultra-Orthogonal Least Squares (UOLS) algorithm to estimate connectivity strength. Compared to the classical least squares criterion which only measures the discrepancy between the observed signals and the model prediction function, the ULS criterion takes into consideration the discrepancy between the weak derivatives of the observed signals and the model prediction function and thus avoids the overfitting problem. By using a similar approach, we then estimate the high-order functional connectivity from the low-order connectivity to characterize signal flows among the brain regions. We finally fuse the low-order and the high-order networks using two decision trees for MCI classification. Experimental results demonstrate the effectiveness of the proposed method on MCI classification.

Improved dynamic connection detection power in estimated dynamic functional connectivity considering multivariate dependencies between brain regions

To estimate dynamic functional connectivity (dFC), the conventional method of sliding window correlation (SWC) suffers from poor performance of dynamic connection detection. This stems from the equal weighting of observations, suboptimal time scale, nonsparse output, and the fact that it is bivariate. To overcome these limitations, we exploited the kernel-reweighted logistic regression (KELLER) algorithm, a method that is common in genetic studies, to estimate dFC in resting state functional magnetic resonance imaging (rs-fMRI) data. KELLER can estimate dFC through estimating both spatial and temporal patterns of functional connectivity between brain regions. This paper compares the performance of the proposed KELLER method with current methods (SWC and tapered-SWC (T-SWC) with different window lengths) based on both simulated and real rs-fMRI data. Estimated dFC networks were assessed for detecting dynamically connected brain region pairs with hypothesis testing. Simulation results revealed that KELLER can detect dynamic connections with a statistical power of 87.35% compared with 70.17% and 58.54% associated with T-SWC (p-value = .001) and SWC (p-value <.001), respectively. Results of these different methods applied on real rs-fMRI data were investigated for two aspects: calculating the similarity between identified mean dynamic pattern and identifying dynamic pattern in default mode network (DMN). In 68% of subjects, the results of T-SWC with window length of 100 s, among different window lengths, demonstrated the highest similarity to those of KELLER. With regards to DMN, KELLER estimated previously reported dynamic connection pairs between dorsal and ventral DMN while SWC-based method was unable to detect these dynamic connections.

Functional MRI-Specific Alterations in Executive Control Network in Mild Cognitive Impairment: An ALE Meta-Analysis

Background: Mild cognitive impairment (MCI) is regarded as a transitional stage between normal aging and Alzheimer's disease (AD) dementia. MCI individuals with deficits in executive function are at higher risk for progressing to AD dementia. Currently, there is no consistent result for alterations in the executive control network (ECN) in MCI, which makes early prediction of AD conversion difficult. The aim of the study was to find functional MRI-specific alterations in ECN in MCI patients by expounding on the convergence of brain regions with functional abnormalities in ECN.

Methods: We searched PubMed, Embase, and Web of Science to identify neuroimaging studies using methods including the amplitude of low frequency fluctuation/fractional amplitude of low-frequency fluctuation, regional homogeneity, and functional connectivity in MCI patients. Based on the Activation Likelihood Estimation algorithm, the coordinate-based meta-analysis and functional meta-analytic connectivity modeling were conducted.

Results: A total of 25 functional imaging studies with MCI patients were included in a quantitative meta-analysis. By summarizing the included articles, we obtained specific brain region changes, mainly including precuneus, cuneus, lingual gyrus, middle frontal gyrus, posterior cingulate cortex, and cerebellum posterior lobe, in the ECN based on these three methods. The specific abnormal brain regions indicated that there were interactions between the ECN and other networks.

Conclusions: This study confirms functional imaging specific abnormal markers in ECN and its interaction with other networks in MCI. It provides novel targets and pathways for individualized and precise interventions to delay the progression of MCI to AD.

Network change point detection in resting-state functional connectivity dynamics of mild cognitive impairment patients

Background/Objective: This study aims to characterize the differences on the short-term temporal network dynamics of the undirected and weighted whole-brain functional connectivity between healthy aging individuals and people with mild cognitive impairment (MCI). The Network Change Point Detection algorithm was applied to identify the significant change points in the resting-state fMRI register, and we analyzed the fluctuations in the topological properties of the sub-networks between significant change points. Method: Ten MCI patients matched by gender and age in 1:1 ratio to healthy controls screened during patient recruitment. A neuropsychological evaluation was done to both groups as well as functional magnetic images were obtained with a Philips 3.0T. All the images were preprocessed and statistically analyzed through dynamic point estimation tools. Results: No statistically significant differences were found between groups in the number of significant change points in the functional connectivity networks. However, an interaction effect of age and state was detected on the intra-participant variability of the network strength. Conclusions: The progression of states was associated to higher variability in the patient's group. Additionally, higher performance in the prospective and retrospective memory scale was associated with higher median network strength.

Deep Spatial-Temporal Feature Fusion From Adaptive Dynamic Functional Connectivity for MCI Identification

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities.