Tractography-Based Score for Learning Effective Connectivity From Multimodal Imaging Data Using Dynamic Bayesian Networks
TL;DR: A novel anatomically informed (AI) score that evaluates fitness of a given connectivity structure to both DTI and fMRI data simultaneously is proposed that is employed in structure learning of DBN given the data.
Abstract: Objective: Effective connectivity (EC) is the methodology for determining functional-integration among the functionally active segregated regions of the brain. By definition [1] EC is “the causal influence exerted by one neuronal group on another” which is constrained by anatomical connectivity (AC) (axonal connections). AC is necessary for EC but does not fully determine it, because synaptic communication occurs dynamically in a context-dependent fashion. Although there is a vast emerging evidence of structure–function relationship using multimodal imaging studies, till date only a few studies have done joint modeling of the two modalities: functional MRI (fMRI) and diffusion tensor imaging (DTI). We aim to propose a unified probabilistic framework that combines information from both sources to learn EC using dynamic Bayesian networks (DBNs). Method: DBNs are probabilistic graphical temporal models that learn EC in an exploratory fashion. Specifically, we propose a novel anatomically informed (AI) score that evaluates fitness of a given connectivity structure to both DTI and fMRI data simultaneously. The AI score is employed in structure learning of DBN given the data. Results: Experiments with synthetic-data demonstrate the face validity of structure learning with our AI score over anatomically uninformed counterpart. Moreover, real-data results are cross-validated by performing classification-experiments. Conclusion: EC inferred on real fMRI-DTI datasets is found to be consistent with previous literature and show promising results in light of the AC present as compared to other classically used techniques such as Granger-causality. Significance: Multimodal analyses provide a more reliable basis for differentiating brain under abnormal/diseased conditions than the single modality analysis.
Citations
More filters
TL;DR: The experimental results indicate that the proposed variational inference method for the KDBN can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.
Abstract: Prediction intervals ( PIs ) for industrial time series can provide useful guidance for workers. Given that the failure of industrial sensors may cause the missing point in inputs, the existing kernel dynamic Bayesian networks ( KDBN ) , serving as an effective method for PIs construction, suffer from high computational load using the stochastic algorithm for inference. This study proposes a variational inference method for the KDBN for the purpose of fast inference, which avoids the time-consuming stochastic sampling. The proposed algorithm contains two stages. The first stage involves the inference of the missing inputs by using a local linearization based variational inference, and based on the computed posterior distributions over the missing inputs the second stage sees a Gaussian approximation for probability over the nodes in future time slices. To verify the effectiveness of the proposed method, a synthetic dataset and a practical dataset of generation flow of blast furnace gas ( BFG ) are employed with different ratios of missing inputs. The experimental results indicate that the proposed method can provide reliable PIs for the generation flow of BFG and it exhibits shorter computing time than the stochastic based one.
9 citations
Cites methods from "Tractography-Based Score for Learni..."
...To verify the performance of the proposed method, this study compares the experimental results of several other methods of PIs construction, including the KDBN with weighted likelihood inference (KDBN-WL) [25], the Bayesian multiple layer perceptron (Bayesian MLP) [13], and the bootstrap-based echo state networks (Bootstrap ESN) [20]....
[...]
...Besides, in [20], an ensemble model containing a number of reservoir computing networks was employed by using the bootstrap techniques, which was applied to the prediction of practical industrial data....
[...]
...Similarly, to further verify the performance of the proposed method for the BFG data, this study compares the experimental results of several other methods of PIs construction, including the KDBN-WL [25], the Bayesian MLP [13], and the bootstrap ESN [20]....
[...]
TL;DR: A new method, called ACOEC-FD, to learn EC networks from fMRI and diffusion tensor imaging (DTI) using ant colony optimization (ACO), which achieves multi-modal imaging data integration by incorporating anatomical constraint information into the heuristic function of probabilistic transition rules.
Abstract: Identifying brain effective connectivity (EC) networks from neuroimaging data has become an effective tool that can evaluate normal brain functions and the injuries associated with neurodegenerative diseases. So far, there are many methods used to identify EC networks. However, most of the research currently focus on learning EC networks from single modal imaging data such as functional magnetic resonance imaging (fMRI) data. This paper proposes a new method, called ACOEC-FD, to learn EC networks from fMRI and diffusion tensor imaging (DTI) using ant colony optimization (ACO). First, ACOEC-FD uses DTI data to acquire some positively correlated relations among regions of interest (ROI), and takes them as anatomical constraint information to effectively restrict the search space of candidate arcs in an EC network. ACOEC-FD then achieves multi-modal imaging data integration by incorporating anatomical constraint information into the heuristic function of probabilistic transition rules to effectively encourage ants more likely to search for connections between structurally connected regions. Through simulation studies on generated datasets and real fMRI-DTI datasets, we demonstrate that the proposed approach results in improved inference results on EC compared to some methods that only used fMRI data.
7 citations
TL;DR: The presented methodology appears to be well-suited for fMRI, particularly given its lack of explicit dependence on temporal lag structure, and is readily applicable to whole-brain effective connectivity estimation.
Abstract: In functional magnetic resonance imaging (fMRI), functional connectivity is conventionally characterized by correlations between fMRI time series, which are intrinsically undirected measures of connectivity. Yet, some information about the directionality of network connections can nevertheless be extracted from the matrix of pairwise temporal correlations between all considered time series, when expressed in the frequency-domain as a cross-spectral density matrix. Using a sparsity prior, it then becomes possible to determine a unique directed network topology that best explains the observed undirected correlations, without having to rely on temporal precedence relationships that may not be valid in fMRI. Applying this method on simulated data with 100 nodes yielded excellent retrieval of the underlying directed networks under a wide variety of conditions. Importantly, the method did not depend on temporal precedence to establish directionality, thus reducing susceptibility to hemodynamic variability. The computational efficiency of the algorithm was sufficient to enable whole-brain estimations, thus circumventing the problem of missing nodes that otherwise occurs in partial-brain analyses. Applying the method to real resting-state fMRI data acquired with a high temporal resolution, the inferred networks showed good consistency with structural connectivity obtained from diffusion tractography in the same subjects. Interestingly, this agreement could also be seen when considering high-frequency rather than low-frequency connectivity (average correlation: r = 0.26 for f < 0.3 Hz, r = 0.43 for 0.3 < f < 5 Hz). Moreover, this concordance was significantly better (p < 0.05) than for networks obtained with conventional functional connectivity based on correlations (average correlation r = 0.18). The presented methodology thus appears to be well-suited for fMRI, particularly given its lack of explicit dependence on temporal lag structure, and is readily applicable to whole-brain effective connectivity estimation.
7 citations
Cites methods from "Tractography-Based Score for Learni..."
...SC is commonly used to constrain the estimation (Gilson et al., 2016; Crimi et al., 2017; Dang et al., 2018), or may be used independently to validate the estimated EC (Uddin et al., 2011; Bringmann et al., 2013)....
[...]
...SC is commonly used to constrain the estimation (Gilson et al., 2016; Crimi et al., 2017; Dang et al., 2018), or may be used independently to validate the estimated EC (Uddin et al....
[...]
TL;DR: Discrete Dynamic Bayesian Network (dDBN) is used in many challenging causal modelling applications, such as human brain connectivity, due to its multivariate, non-deterministic, and nonlinear capab...
Abstract: Discrete Dynamic Bayesian Network (dDBN) is used in many challenging causal modelling applications, such as human brain connectivity, due to its multivariate, non-deterministic, and nonlinear capab...
5 citations
TL;DR: Four machine learning tools are applied to address the challenge in the IFDI of cutting arms and the experimental results show that the support vector machines based on dynamic cuckoo outperform the other methods.
Abstract: Incipient fault detection and identification (IFDI) of cutting arms is a crucial guarantee for the smooth operation of a roadheader. However, the shortage of fault samples restricts the application of the fault diagnosis technique, and the data analysis tools should be optimized efficiently. In this study, four machine learning tools (the back-propagation neural network based on genetic algorithm optimization, the naive Bayes based on genetic algorithm optimization, the support vector machines based on particle swarm optimization, and the support vector machines based on dynamic cuckoo) are applied to address the challenge in the IFDI of cutting arms. The commonly measured current and vibration data cutting arms are used in the IFDI. The experimental results show that the support vector machines based on dynamic cuckoo outperform the other methods. Besides, the performance of the four methods under different operating conditions is compared. The fault cause of cutting arms of the roadheader is analyzed and the design improvement scheme for cutting arms is provided. This study provides a reference for improving the fault diagnosis of the roadheader.
3 citations
References
More filters
TL;DR: The theoretical basis, computational strategy and application to empirical G-causality inference of the MVGC Toolbox are explained and the advantages of the Toolbox over previous methods in terms of computational accuracy and statistical inference are shown.
771 citations
"Tractography-Based Score for Learni..." refers methods in this paper
...after, the EC was learned using MCMC algorithm and scoring functions:BD and TBBD (π,D|S), and MVGC approach [38]....
[...]
...Multivariate Granger causality (MVGC) approach [38] was...
[...]
...Simulations were done in MATLAB, using toolboxes: Bayes Net Toolbox (BNT) [36], Inferring DBNs with MCMC toolbox [37] and MVGC toolbox [38]....
[...]
TL;DR: Neural activity dynamics considering the effects of experimental conditions map from neural activity to BOLD signal (nonlinear) and the consequences of these effects are described.
Abstract: Neural activity dynamics considering the effects of experimental conditions Mapping from neural activity to BOLD signal (nonlinear)
687 citations
Additional excerpts
...modeling (SEM) [14] and classical dynamic causal modeling (DCM) [15], require prior candidate structures with assumptions about existence and direction of influence between any...
[...]
...Thus the joint modeling of fMRI and DTI data employing DCM as the methodology for EC estimation, as in [11] suffers from the above mentioned shortcomings....
[...]
...However, advances in more efficient ways of searching for larger search spaces [16] have made DCM more exploratory as compared to the classical one proposed initially, while it still being deterministic in nature by identifying just the bilinear interactions....
[...]
...[16] K. Friston et al., “Network discovery with DCM,” NeuroImage, vol. 56, pp. 1202–1221, 2011....
[...]
...Confirmatory model-driven approaches, such as structural equation modeling (SEM) [14] and classical dynamic causal modeling (DCM) [15], require prior candidate structures with assumptions about existence and direction of influence between any 0018-9294 © 2017 IEEE....
[...]
TL;DR: A role for theta-frequency synchronization between the ventral hippocampus and the mPFC in anxiety is suggested, consistent with the notion that such synchronization is a general mechanism by which the hippocampus communicates with downstream structures of behavioral relevance.
615 citations
"Tractography-Based Score for Learni..." refers background in this paper
...supports “self-referential” or “introspective” mental activity [48], [55], memory and emotion (including anxiety) [56], [57]....
[...]
TL;DR: The findings demonstrate how the network inference performance varies with the training set size, the degree of inadequacy of prior assumptions, the experimental sampling strategy and the inclusion of further, sequence-based information.
Abstract: Motivation: Bayesian networks have been applied to infer genetic regulatory interactions from microarray gene expression data. This inference problem is particularly hard in that interactions between hundreds of genes have to be learned from very small data sets, typically containing only a few dozen time points during a cell cycle. Most previous studies have assessed the inference results on real gene expression data by comparing predicted genetic regulatory interactions with those known from the biological literature. This approach is controversial due to the absence of known gold standards, which renders the estimation of the sensitivity and specificity, that is, the true and (complementary) false detection rate, unreliable and difficult. The objective of the present study is to test the viability of the Bayesian network paradigm in a realistic simulation study. First, gene expression data are simulated from a realistic biological network involving DNAs, mRNAs, inactive protein monomers and active protein dimers. Then, interaction networks are inferred from these data in a reverse engineering approach, using Bayesian networks and Bayesian learning with Markov chain Monte Carlo. Results: The simulation results are presented as receiver operator characteristics curves. This allows estimating the proportion of spurious gene interactions incurred for a specified target proportion of recovered true interactions. The findings demonstrate how the network inference performance varies with the training set size, the degree of inadequacy of prior assumptions, the experimental sampling strategy and the inclusion of further, sequence-based information. Availability: The programs and data used in the present study are available from http://www.bioss.sari.ac.uk/~dirk/ Supplements
564 citations
"Tractography-Based Score for Learni..." refers methods in this paper
...(MCMC) method [21] is used for learning the structure of connectivity among brain regions from fMRI data, briefly given in...
[...]
...used for fMRI data [18]–[20] and also for other domains [21], [22]....
[...]
TL;DR: It is found that the DMN undergoes significant developmental changes in functional and structural connectivity, but these changes are not uniform across all DMN nodes, and maturation of PCC-mPFC structural connectivity is proposed to play an important role in the development of self-related and social-cognitive functions that emerge during adolescence.
479 citations