Learning Clique Subgraphs in Structural Brain Network Classification with Application to Crystallized Cognition

Bayesian thresholded modeling for integrating brain node and network predictors

Progress in neuroscience has provided unprecedented opportunities to advance our understanding of brain alterations and their correspondence to phenotypic profiles. With data collected from various imaging techniques, studies have integrated different types of information ranging from brain structure, function, or metabolism. More recently, an emerging way to categorize imaging traits is through a metric hierarchy, including localized node-level measurements and interactive network-level metrics. However, limited research has been conducted to integrate these different hierarchies and achieve a better understanding of the neurobiological mechanisms and communications. In this work, we address this literature gap by proposing a Bayesian regression model under both vector-variate and matrix-variate predictors. To characterize the interplay between different predicting components, we propose a set of biologically plausible prior models centered on an innovative joint thresholded prior. This captures the coupling and grouping effect of signal patterns, as well as their spatial contiguity across brain anatomy. By developing a posterior inference, we can identify and quantify the uncertainty of signaling node- and network-level neuromarkers, as well as their predictive mechanism for phenotypic outcomes. Through extensive simulations, we demonstrate that our proposed method outperforms the alternative approaches substantially in both out-of-sample prediction and feature selection. By implementing the model to study children's general mental abilities, we establish a powerful predictive mechanism based on the identified task contrast traits and resting-state sub-networks.

Bayesian pathway analysis over brain network mediators for survival data

Technological advancements in noninvasive imaging facilitate the construction of whole brain interconnected networks, known as brain connectivity. Existing approaches to analyze brain connectivity frequently disaggregate the entire network into a vector of unique edges or summary measures, leading to a substantial loss of information. Motivated by the need to explore the effect mechanism among genetic exposure, brain connectivity, and time to disease onset with maximum information extraction, we propose a Bayesian approach to model the effect pathway between each of these components while quantifying the mediating role of brain networks. To accommodate the biological architectures of brain connectivity constructed along white matter fiber tracts, we develop a structural model which includes a symmetric matrix-variate accelerated failure time model for disease onset and a symmetric matrix response regression for the network-variate mediator. We further impose within-graph sparsity and between-graph shrinkage to identify informative network configurations and eliminate the interference of noisy components. Simulations are carried out to confirm the advantages of our proposed method over existing alternatives. By applying the proposed method to the landmark Alzheimer's Disease Neuroimaging Initiative study, we obtain neurobiologically plausible insights that may inform future intervention strategies.

Bayesian mixed model inference for genetic association under related samples with brain network phenotype

Genetic association studies for brain connectivity phenotypes have gained prominence due to advances in noninvasive imaging techniques and quantitative genetics. Brain connectivity traits, characterized by network configurations and unique biological structures, present distinct challenges compared to other quantitative phenotypes. Furthermore, the presence of sample relatedness in the most imaging genetics studies limits the feasibility of adopting existing network-response modeling. In this article, we fill this gap by proposing a Bayesian network-response mixed-effect model that considers a network-variate phenotype and incorporates population structures including pedigrees and unknown sample relatedness. To accommodate the inherent topological architecture associated with the genetic contributions to the phenotype, we model the effect components via a set of effect network configurations and impose an inter-network sparsity and intra-network shrinkage to dissect the phenotypic network configurations affected by the risk genetic variant. A Markov chain Monte Carlo (MCMC) algorithm is further developed to facilitate uncertainty quantification. We evaluate the performance of our model through extensive simulations. By further applying the method to study, the genetic bases for brain structural connectivity using data from the Human Connectome Project with excessive family structures, we obtain plausible and interpretable results. Beyond brain connectivity genetic studies, our proposed model also provides a general linear mixed-effect regression framework for network-variate outcomes.

BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping

Converging evidence increasingly suggests that psychiatric disorders, such as major depressive disorder (MDD) and autism spectrum disorder (ASD), are not unitary diseases, but rather heterogeneous syndromes that involve diverse, co-occurring symptoms and divergent responses to treatment. This clinical heterogeneity has hindered the progress of precision diagnosis and treatment effectiveness in psychiatric disorders. In this study, we propose BPI-GNN, a new interpretable graph neural network (GNN) framework for analyzing functional magnetic resonance images (fMRI), by leveraging the famed prototype learning. In addition, we introduce a novel generation process of prototype subgraph to discover essential edges of distinct prototypes and employ total correlation (TC) to ensure the independence of distinct prototype subgraph patterns. BPI-GNN can effectively discriminate psychiatric patients and healthy controls (HC), and identify biological meaningful subtypes of psychiatric disorders. We evaluate the performance of BPI-GNN against 11 popular brain network classification methods on three psychiatric datasets and observe that our BPI-GNN always achieves the highest diagnosis accuracy. More importantly, we examine differences in clinical symptom profiles and gene expression profiles among identified subtypes and observe that our identified brain-based subtypes have the clinical relevance. It also discovers the subtype biomarkers that align with current neuro-scientific knowledge.

Cocaine diminishes functional network robustness and destabilizes the energy landscape of neuronal activity in the medial prefrontal cortex

We present analysis of neuronal activity recordings from a subset of neurons in the medial prefrontal cortex of rats before and after the administration of cocaine. Using an underlying modern Hopfield model as a description for the neuronal network, combined with a machine learning approach, we compute the underlying functional connectivity of the neuronal network. We find that the functional connectivity changes after the administration of cocaine with both functional-excitatory and functional-inhibitory neurons being affected. Using conventional network analysis, we find that the diameter of the graph, or the shortest length between the two most distant nodes, increases with cocaine, suggesting that the neuronal network is less robust. We also find that the betweenness centrality scores for several of the functional-excitatory and functional-inhibitory neurons decrease significantly, while other scores remain essentially unchanged, to also suggest that the neuronal network is less robust. Finally, we study the distribution of neuronal activity and relate it to energy to find that cocaine drives the neuronal network towards destabilization in the energy landscape of neuronal activation. While this destabilization is presumably temporary given one administration of cocaine, perhaps this initial destabilization indicates a transition towards a new stable state with repeated cocaine administration. However, such analyses are useful more generally to understand how neuronal networks respond to perturbations.

Brain network classification based on dynamic graph attention information bottleneck

BACKGROUND AND OBJECTIVES

Graph neural networks (GNN) have demonstrated remarkable encoding capabilities in the context of brain network classification tasks. They excel at uncovering hidden static connections between brain states. However, brain network signals can be influenced by physiological traits and external variables during clinical detection, resulting in noisy brain graphs. Additionally, many existing algorithms for brain networks primarily focus on static topologies determined by threshold-based criteria, thereby overlooking the real-time variability in brain channel connectivity. These sources of noise and the persistence of static structures inevitably hinder the effective exchange of information during brain network computations.

METHODS

To address these challenges, we propose a novel framework called the dynamic graph attention information bottleneck (DGAIB). This framework is designed to dynamically enhance the input raw brain graph structure from the perspective of information theory and graph theory. First, we employ the Spearman function to construct a raw graph. Then, we use a graph information bottleneck (GIB) to optimize the internal graph connections by selectively masking redundant feature embeddings. Finally, we enhance the feature aggregation of each brain state by utilizing a graph attention network (GAT), which promotes improved information exchange among distinct brain regions within the model. These processed representations serve as input for subsequent classification tasks.

EXPERIMENT AND RESULTS

We systematically evaluated the robustness and generalizability of our proposed framework through a series of experiments. This evaluation included patient-specific experiments using the electroencephalography (EEG)-based CHB-MIT dataset and cross-patient experiments leveraging the functional magnetic resonance imaging (fMRI)-based ABIDE-I dataset from multiple perspectives.

Genetic underpinnings of brain structural connectome for young adults

With distinct advantages in power over behavioral phenotypes, brain imaging traits have become emerging endophenotypes to dissect molecular contributions to behaviors and neuropsychiatric illnesses. Among different imaging features, brain structural connectivity (i.e., structural connectome) which summarizes the anatomical connections between different brain regions is one of the most cutting edge while under-investigated traits; and the genetic influence on the structural connectome variation remains highly elusive. Relying on a landmark imaging genetics study for young adults, we develop a biologically plausible brain network response shrinkage model to comprehensively characterize the relationship between high dimensional genetic variants and the structural connectome phenotype. Under a unified Bayesian framework, we accommodate the topology of brain network and biological architecture within the genome; and eventually establish a mechanistic mapping between genetic biomarkers and the associated brain sub-network units. An efficient expectation-maximization algorithm is developed to estimate the model and ensure computing feasibility. In the application to the Human Connectome Project Young Adult (HCP-YA) data, we establish the genetic underpinnings which are highly interpretable under functional annotation and brain tissue eQTL analysis, for the brain white matter tracts connecting the hippocampus and two cerebral hemispheres. We also show the superiority of our method in extensive simulations.

General psychopathology factor (p-factor) prediction using resting-state functional connectivity and a scanner-generalization neural network

The general psychopathology factor (p-factor) represents shared variance across mental disorders based on psychopathologic symptoms. The Adolescent Brain Cognitive Development (ABCD) Study offers an unprecedented opportunity to investigate functional networks (FNs) from functional magnetic resonance imaging (fMRI) associated with the psychopathology of an adolescent cohort (n > 10,000). However, the heterogeneities associated with the use of multiple sites and multiple scanners in the ABCD Study need to be overcome to improve the prediction of the p-factor using fMRI. We proposed a scanner-generalization neural network (SGNN) to predict the individual p-factor by systematically reducing the scanner effect for resting-state functional connectivity (RSFC). We included 6905 adolescents from 18 sites whose fMRI data were collected using either Siemens or GE scanners. The p-factor was estimated based on the Child Behavior Checklist (CBCL) scores available in the ABCD study using exploratory factor analysis. We evaluated the Pearson's correlation coefficients (CCs) for p-factor prediction via leave-one/two-site-out cross-validation (LOSOCV/LTSOCV) and identified important FNs from the weight features (WFs) of the SGNN. The CCs were higher for the SGNN than for alternative models when using both LOSOCV (0.1631 ± 0.0673 for the SGNN vs. 0.1497 ± 0.0710 for kernel ridge regression [KRR]; p < 0.05 from a two-tailed paired t-test) and LTSOCV (0.1469 ± 0.0381 for the SGNN vs. 0.1394 ± 0.0359 for KRR; p = 0.01). It was found that (a) the default-mode and dorsal attention FNs were important for p-factor prediction, and (b) the intra-visual FN was important for scanner generalization. We demonstrated the efficacy of our novel SGNN model for p-factor prediction while simultaneously eliminating scanner-related confounding effects for RSFC.

Single-index models with functional connectivity network predictors

Functional connectivity is defined as the undirected association between two or more functional magnetic resonance imaging (fMRI) time series. Increasingly, subject-level functional connectivity data have been used to predict and classify clinical outcomes and subject attributes. We propose a single-index model wherein response variables and sparse functional connectivity network valued predictors are linked by an unspecified smooth function in order to accommodate potentially nonlinear relationships. We exploit the network structure of functional connectivity by imposing meaningful sparsity constraints, which lead not only to the identification of association of interactions between regions with the response but also the assessment of whether or not the functional connectivity associated with a brain region is related to the response variable. We demonstrate the effectiveness of the proposed model in simulation studies and in an application to a resting-state fMRI data set from the Human Connectome Project to model fluid intelligence and sex and to identify predictive links between brain regions.