Biology subjects

Calhoun, V.

Publications and source records attributed to Calhoun, V..

At least 127 records · Page 7Linked to original sources

bioRxiv2022

SVR-based Multimodal Active Subspace Analysis for the Brain using Neuroimaging Data

Understanding the patterns of changes in brain function and structure due to various disorders and diseases is of utmost importance. There have been numerous efforts toward successful biomarker discovery for complex brain disorders by evaluating neuroimaging datasets with novel analytical frameworks. However, due to the multi-faceted nature of the disorders involving a wide and overlapping range of symptoms as well as complex changes in structural and functional brain networks, it is increasingly important to devise computational frameworks that can consider the underlying patterns of heterogeneous changes with specific target assessments, at the same time producing a summarizing output from the high-dimensional neuroimaging data. While various machine learning approaches focus on diagnostic prediction, many learning frameworks analyze important features at the level of brain regions involved in prediction using supervised methods. Unsupervised learning methods have also been utilized to break down the neuroimaging features into lower dimensional components. However, most learning frameworks either do not consider the target assessment information while extracting brain subspaces, or can extract only higher dimensional importance associations as an ordered list of involved features, making manual interpretation at the level of subspaces difficult. We present a novel multimodal active subspace learning framework to understand various subspaces within the brain that are associated with changes in particular biological and cognitive traits. For a given cognitive or biological trait, our framework performs a decomposition of the feature importances to extract robust multimodal subspaces that define the most significant change in the given trait. Through a rigorous cross-validation procedure on an Alzheimers disease (AD) dataset, we show that our framework can extract subspaces covering both functional and structural modalities, which are specific to a given clinical assessment (like memory and other cognitive skills) and also retain predictive performance in standard machine learning algorithms. We show that our framework not only uncovers AD-related brain regions (e.g., hippocampus, entorhinal cortex) in the associated brain subspaces, but also enables an automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and cognitive skill proficiency related to brain disorders like AD.

neuroscience↗

bioRxiv2022

Exploring Relationships between Functional Network Connectivity and Cognition with an Explainable Clustering Approach

The application of clustering algorithms to fMRI functional network connectivity (FNC) data has been extensively studied over the past decade. When applied to FNC, these analyses assign samples to an optimal number of groups without a priori assumptions. Through these groupings, studies have provided insights into the dynamics of network connectivity through the identification of different brain states and have identified subgroups of individuals with unique brain activity. However, the manner in which underlying brain networks influence the identified groups is yet to be fully understood. In this study, we apply k-means clustering to resting-state fMRI-based static FNC data collected from 37,784 healthy individuals. We identified 2 groups of individuals with statistically significant differences in cognitive performance in several test metrics. Then, by applying two different versions of G2PC, a global permutation feature importance approach, and logistic regression with elastic net regularization, we were able to identify the relative importance of brain network pairs and their underlying features to the resulting groups. Through these approaches, together with the visualization of centroids connectivity matrices, we were able to explain the observed differences in cognition in terms of specific key brain networks. We expect that our results will shed further light upon the effect of underlying brain networks on encountered cognitive differences between groups with unique brain activity.

bioinformatics↗

bioRxiv2022

Intrinsic Neural Timescales in Autism Spectrum Disorder and Schizophrenia. A Replication and Direct Comparison Study

Intrinsic neural timescales (INT) reflect the duration for which brain areas store information. A posterior - anterior hierarchy of increasingly longer INT has been revealed in both typically developed individuals (TD), as well as patients diagnosed with autism spectrum disorder (ASD) and schizophrenia (SZ), though INT are, overall, shorter in both patient groups. In the present study, we attempted to replicate previously reported group differences by comparing INT of TD to ASD and SZ. We replicated the previously reported result showing reduced INT in the left lateral occipital gyrus and the right post-central gyrus in SZ compared to TD. For the first time, we also directly compared the INT of the two patient groups and found that these same two areas show significantly reduced INT in SZ compared to ASD. In ASD, significant correlations were found between INT and their clinical and phenotypic characteristics. Our results point to the left lateral occipital gyrus and the right post-central gyrus as holding potential for further diagnostic refinement of SZ.

neuroscience↗

bioRxiv2022

Explicitly Nonlinear Dynamic Functional Network Connectivity In Resting-State fMRI Data

Most dynamic functional connectivity in fMRI data is focused on linear correlations, and to our knowledge, no study has studied whole brain explicitly nonlinear dynamic relationships within the data. While some approaches have attempted to study overall connectivity more generally using flexible models, we are particularly interested in whether the non-linear relationships, above and beyond linear, are capturing unique information. This study thus proposes an approach to assess the explicitly nonlinear dynamic functional network connectivity derived from the relationship among independent component analysis time courses. Linear relationships were removed at each time point to evaluate, typically ignored, explicitly nonlinear dFNC using normalized mutual information. Simulations showed the proposed method accurately estimated NMI over time, even within relatively short windows of data. Results on fMRI data included 151 schizophrenia patients, and 163 healthy controls showed three unique, highly structured, mostly long-range, functional states that also showed significant group differences. This analysis identifies a higher level of explicitly nonlinear dependencies in transient connectivity within the visual network in healthy controls compared to schizophrenia patients. In particular, nonlinear relationships tend to be more widespread than linear ones. We also find highly significant differences in the relative co-occurrence of linear and explicitly nonlinear states in HC and SZ, suggesting these may be an important aspect of the disorder. Overall, this work suggests that quantifying nonlinear dependencies of dynamic functional connectivity may provide a complementary and potentially valuable tool for studying brain function by exposing relevant variation that is typically ignored.

neuroscience↗

bioRxiv2022

Fine temporal brain network structure modularizes and localizes differently in men and women: Insights from a novel explainability framework

AO_SCPLOWBSTRACTC_SCPLOWDeep learning has become an effective tool for classifying biological sex based on functional magnetic resonance imaging (fMRI), but research on what features within the brain are most relevant to this classification is still lacking. Model interpretability has become a powerful way to understand "black box" deep-learning models and select features within the input data that are most relevant to the correct classification. However, very little work has been done employing these methods to understand the relationship between the temporal dimension of functional imaging signals and classification of biological sex, nor has there been attention paid to rectifying problems and limitations associated with feature explanation models, e.g. underspecification and instability. We provide a methodology to limit the impact of underspecification on the stability of the measured feature importance, and then, using intrinsic connectivity networks (ICNs) from fMRI data, we provide a deep exploration of sex differences among functional brain networks. We report numerous conclusions, including activity differences in the visual and cognitive domains, as well as major connectivity differences.

neuroscience↗

bioRxiv2022

Examining Effects of Schizophrenia on EEG with Explainable Deep Learning Models

Schizophrenia (SZ) is a mental disorder that affects millions of people globally. At this time, diagnosis of SZ is based upon symptoms, which can vary from patient to patient and create difficulty with diagnosis. To address this issue, researchers have begun to look for neurological biomarkers of SZ and develop methods for automated diagnosis. In recent years, several studies have applied deep learning to raw EEG for automated SZ diagnosis. However, the use of raw time-series data makes explainability more difficult than it is for traditional machine learning algorithms trained on manually engineered features. As such, none of these studies have sought to explain their models, which is problematic within a healthcare context where explainability is a critical component. In this study, we apply perturbation-based explainability approaches to gain insight into the spectral and spatial features learned by two distinct deep learning models trained on raw EEG for SZ diagnosis for the first time. We develop convolutional neural network (CNN) and CNN long short-term memory network (CNN-LSTM) architectures. Results show that both models prioritize the T8 and C3 electrodes and the {delta}- and {gamma}-bands, which agrees with previous literature and supports the overall utility of our models. This study represents a step forward in the implementation of deep learning models for clinical SZ diagnosis, and it is our hope that it will inspire the more widespread application of explainability methods for insight into deep learning models trained for SZ diagnosis in the future.

bioinformatics↗

bioRxiv2022

iSparse kmeans: a two-step clustering approach for big dynamic functional network connectivity data

BackgroundDynamic functional network connectivity (dFNC) estimated from resting-state functional magnetic imaging (rs-fMRI) studies the temporally varying of functional integration between brain networks. In a typical dFNC pipeline, a clustering stage to summarize the connectivity patterns that are transiently but reliably realized over the course of a scanning session. However, identifying the right number of clusters through a conventional clustering criterion computed by running the algorithm repeatedly, over a large range of cluster numbers is time-consuming and requires substantial computational power even for typical dFNC datasets, and the computational demands become prohibitive as datasets become larger and scans longer. Here we developed a new dFNC pipeline, called iterative sparse kmeans or iSparse kmeans, to analyze large dFNC data without having access to huge computational power. MethodIn iSparse kmeans, we implement two-step clustering. In the first step, we randomly use a sub-sample dFNC data and identify several sets of states at different model orders. In the second step, we aggregate all dFNC states estimated from all iterations in the first step and use this to identify the optimum number of clusters using the elbow criteria. Additionally, we use this new reduced dataset and estimate a final set of states by performing a second kmeans clustering on the aggregated dFNC states from the first k-means clustering. To validate the reproducibility of iSparse kmeans, we analyzed four dFNC datasets from the human connectome project (HCP). ResultsWe found that both conventional kmeans and iSparse kmeans generate similar brain dFNC states while iSparse kmeans is 27 times faster than the traditional method in finding the optimum number of clusters. We show that the results are replicated across four different datasets from HCP. ConclusionWe developed a new analytic pipeline which facilitates analysis of large dFNC datasets without having access to a huge computational power source. We validated the reproducibility of the result across multiple datasets.

bioinformatics↗

bioRxiv2022

Overlap across psychotic disorders: A functional network connectivity analysis

Functional network connectivity has previously been shown to distinguish patient groups from healthy controls (HC). However, the overlap across schizophrenia (SZ), bipolar (BP), and schizoaffective disorder (SAD) is not clear yet. This study focuses on finding overlap across these three psychotic disorders using dynamic FNC (dFNC) and compares it with static FNC (sFNC). We used resting-state fMRI, demographics, and clinical information from the Bipolar- Schizophrenia Network on Intermediate Phenotypes cohort. The data includes three groups of patients with schizophrenia (SZP, N=102), bipolar (BPP, N=102), and schizoaffective (SADP, N=102), their relatives SZR (N=102), BPR (N=102), SADR (N=102), and HC (N=118) groups. After estimating each individuals dFNC, we put them into three identical states. We estimated five different features, including occupancy rate (OCR), number of transitions, the total number of transitions, and the total distance traveled. Finally, the extracted features are tested statistically across patients and HC groups. In addition, we explored the link between the clinical scores and the extracted features. We found that the OCR difference between SZP and SZR in state2, between BPP and HC in state1, and between SADP and HC in state2. Also, state2 OCR separates SZP from BPP, state 3 OCR separates BPP from SZP and SADP. Moreover, the OCR and traveled distance feature extracted from SZ and BP could significantly predict PANSS Total and PANSS General scores. Finally, combined distance features of all disorders showed a significant relationship to PANSS Total and PANSS General scores.

neuroscience↗

bioRxiv2021

Neuroimaging signature associated with symptom exacerbation in early-stage psychosis

Recent reports have indicated that the occurrence of symptom exacerbation in early-stage psychosis could result in brain changes. Such a symptom exacerbation is frequently called relapse, which underlies a poorer disease outcome. Thus, it is important to identify neuroimaging alterations that are specifically seen in patients who experience relapse in early-stage psychosis. We hypothesized that this specific patient group may be more homogenous in disease-associated signatures likely to be linked to relapse, compared with the overall patient group. Such sub-stratified patient group and neuroimaging signatures would be useful for the biological understanding of relapse. To address this goal, we conducted a cross-sectional study (85 patients with early-stage psychosis and 94 healthy controls) with the use of medical records in a retrospective manner. To define the specific sub-group with the past experience of relapse, we used hospitalization due to psychotic symptom exacerbation, according to many publications that used this factor as a proxy for relapse. By examining resting-state functional connectivity (FC) for the study subjects, we validated our hypothesis and defined 131 FCs possibly associated with relapse. Through these studies, 3 brain regions (the thalamus, precentral gyrus, and dorsal anterior cingulate cortex) were underscored.

neuroscience↗

bioRxiv2021

Learning Active Multimodal Subspaces in the Brain

Here we introduce a multimodal framework to identify subspaces in the human brain that are defined by collective changes in structural and functional measures and are actively linked to demographic, biological and cognitive indicators in a population. We determine the multimodal subspaces using principles of active subspace learning (ASL) and demonstrate its application on a sample learning task (biological ageing) on a Schizophrenia dataset. The proposed multimodal ASL method successfully identifies latent brain representations as subsets of brain regions and connections forming co-varying subspaces in association with biological age. We show that Schizophrenia is characterized by different subspace patterns compared to those in a cognitively normal brain. The multimodal features generated by projecting structural and functional MRI components onto these active subspaces perform better than several PCA-based transformations and equally well when compared to non-transformed features on the studied learning task. In essence, the proposed method successfully learns active brain subspaces associated with a specific brain condition but inferred from the brain imaging data along with the biological/cognitive traits of interest.

neuroscience↗

bioRxiv2021

Multi-model Order ICA: A Data-driven Method for Evaluating Brain Functional Network Connectivity Within and Between Multiple Spatial Scales

BackgroundWhile functional connectivity is widely studied, there has been little work studying functional connectivity at different spatial scales. Likewise, the relationship of functional connectivity between spatial scales is unknown. MethodsWe proposed an independent component analysis (ICA) - based approach to capture information at multiple model orders (component numbers) and to evaluate functional network connectivity (FNC) both within and between model orders. We evaluated the approach by studying group differences in the context of a study of resting fMRI (rsfMRI) data collected from schizophrenia (SZ) individuals and healthy controls (HC). The predictive ability of FNC at multiple spatial scales was assessed using support vector machine (SVM)-based classification. ResultsIn addition to consistent predictive patterns at both multiple-model orders and single model orders, unique predictive information was seen at multiple-model orders and in the interaction between model orders. We observed that the FNC between model order 25 and 50 maintained the highest predictive information between HC and SZ. Results highlighted the predictive ability of the somatomotor and visual domains both within and between model orders compared to other functional domains. Also, subcortical-somatomotor, temporal-somatomotor, and temporal-subcortical FNCs had relatively high weights in predicting SZ. ConclusionsIn sum, multi-model order ICA provides a more comprehensive way to study FNC, produces meaningful and interesting results which are applicable to future studies. We shared the spatial templates from this work at different model orders to provide a reference for the community, which can be leveraged in regression-based or fully automated (spatially constrained) ICA approaches. Impact StatementMulti-model order ICA provides a comprehensive way to study brain functional network connectivity within and between multiple spatial scales, highlighting findings that would have been ignored in single model order analysis. This work expands upon and adds to the relatively new literature on resting fMRI-based classification and prediction. Results highlighted the differentiating power of specific intrinsic connectivity networks on classifying brain disorders of schizophrenia patients and healthy participants, at different spatial scales. The spatial templates from this work provide a reference for the community, which can be leveraged in regression-based or fully automated ICA approaches.

neuroscience↗

bioRxiv2021

Nonlinear Functional Network Connectivity In Resting fMRI Data

In this work, we focus on explicitly nonlinear relationships in functional networks. We introduce a technique using normalized mutual information (MI), that calculates the nonlinear correlation between different brain regions. We demonstrate our proposed approach using simulated data, then apply it to a dataset previously studied in (Damaraju et al., 2014). This resting-state fMRI data included 151 schizophrenia patients and 163 age- and gender-matched healthy controls. We first decomposed these data using group independent component analysis (ICA) and yielded 47 functionally relevant intrinsic connectivity networks. Our analysis showed a modularized nonlinear relationship among brain functional networks that was particularly noticeable in the sensory and visual cortex. Interestingly, the modularity appears both meaningful and distinct from that revealed by the linear approach. Group analysis identified significant differences in nonlinear dependencies between schizophrenia patients and healthy controls particularly in visual cortex, with controls showing more nonlinearity in most cases. Certain domains, including cognitive control, and default mode, appeared much less nonlinear, whereas links between the visual and other domains showed evidence of substantial nonlinear and modular properties. Overall, these results suggest that quantifying nonlinear dependencies of functional connectivity may provide a complementary and potentially important tool for studying brain function by exposing relevant variation that is typically ignored. Further, we propose a method that captures both linear and nonlinear effects in a boosted approach. This method increases the sensitivity to group differences in comparison to the standard linear approach, at the cost of being unable to separate linear and nonlinear effects.

neuroscience↗

bioRxiv2021

A Novel Local Explainability Approach for Spectral Insight into Raw EEG-Based Deep Learning Classifiers

The frequency domain of electroencephalography (EEG) data has developed as a particularly important area of EEG analysis. EEG spectra have been analyzed with explainable machine learning and deep learning methods. However, as deep learning has developed, most studies use raw EEG data, which is not well-suited for traditional explainability methods. Several studies have introduced methods for spectral insight into classifiers trained on raw EEG data. These studies have provided global insight into the frequency bands that are generally important to a classifier but do not provide local insight into the frequency bands important for the classification of individual samples. This local explainability could be particularly helpful for EEG analysis domains like sleep stage classification that feature multiple evolving states. We present a novel local spectral explainability approach and use it to explain a convolutional neural network trained for automated sleep stage classification. We use our approach to show how the relative importance of different frequency bands varies over time and even within the same sleep stages. Furthermore, to better understand how our approach compares to existing methods, we compare a global estimate of spectral importance generated from our local results with an existing global spectral importance approach. We find that the {delta} band is most important for most sleep stages, though {beta} is most important for the non-rapid eye movement 2 (NREM2) sleep stage. Additionally, {theta} is particularly important for identifying Awake and NREM1 samples. Our study represents the first approach developed for local spectral insight into deep learning classifiers trained on raw EEG time series.

bioinformatics↗

bioRxiv2021

A Novel Local Ablation Approach for Explaining Multimodal Classifiers

With the growing use of multimodal data for deep learning classification in healthcare research, more studies have begun to present explainability methods for insight into multimodal classifiers. Among these studies, few have utilized local explainability methods, which could provide (1) insight into the classification of each sample and (2) an opportunity to better understand the effects of demographic and clinical variables within datasets (e.g., medication of subjects in electrophysiology data). To the best of our knowledge, this opportunity has not yet been explored within multimodal classification. We present a novel local ablation approach that shows the importance of each modality to the correct classification of each class and explore the effects of demographic and clinical variables upon the classifier. As a use-case, we train a convolutional neural network for automated sleep staging with electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) data. We find that EEG is the most important modality across most stages, though EOG is particular important for non-rapid eye movement stage 1. Further, we identify significant relationships between the local explanations and subject age, sex, and state of medication which suggest that the classifier learned specific features associated with these variables across multiple modalities and correctly classified samples. Our novel explainability approach has implications for many fields involving multimodal classification. Moreover, our examination of the degree to which demographic and clinical variables may affect classifiers could provide direction for future studies in automated biomarker discovery.

bioinformatics↗

bioRxiv2021

A METHOD FOR INTEGRATIVE ANALYSIS OF LOCAL AND GLOBAL BRAIN DYNAMICS

The most common pipelines for studying time-varying network connectivity in resting state functional magnetic resonance imaging (rs-fMRI) operate at the whole brain level, capturing a small discrete set of "states" that best represent time-resolved joint measures of connectivity over all network pairs in the brain. This whole-brain hidden Markov model (HMM) approach "uniformizes" the dynamics over what is typically more than 1000 pairs of networks, forcing each time-resolved high-dimensional observation into its best-matched high-dimensional state. While straightforward and convenient, this HMM simplification obscures functional and temporal nonstationarities that could reveal systematic, informative features of resting state brain dynamics at a more granular scale. We introduce a framework for studying functionally localized dynamics that intrinsically embeds them within a whole-brain HMM frame of reference. The approach is validated in a large rs-fMRI schizophrenia study where it identifies group differences in localized patterns of entropy and dynamics that help explain consistently observed differences between schizophrenia patients and controls in occupancy of whole-brain dFNC states more mechanistically.

neuroscience↗

bioRxiv2021

An interpretable connectivity-based decoding model for classification of chronic marijuana use

BackgroundPsychiatric neuroimaging typically proceeds with one of two approaches: encoding models, which aim to model neural mechanisms, or decoding models, which aim to predict behavioral or clinical characteristics from brain imaging data. In this study, we seek to combine these aims by developing interpretable decoding models that offer both accurate prediction and novel neural insights. We demonstrate the effectiveness of this combined approach in a case study of chronic marijuana use. MethodsChronic marijuana (MJ) users (n=195) and non-using healthy controls (n=128) completed a cue-elicited craving task during functional magnetic resonance imaging. Linear machine learning methods were used to classify individuals into chronic MJ users and non-users based on task-evoked, whole-brain functional connectivity. We then used graph theoretic analyses to identify predictive functional connectivities among brain regions that contributed most substantially to the classification of chronic marijuana use. ResultsWe obtained high (~80% out-of-sample) accuracy across four different classification models, demonstrating that task-evoked, whole-brain functional connectivity can successfully differentiate chronic marijuana users from non-users. Subsequent network analyses revealed key predictive regions (e.g., anterior cingulate cortex, dorsolateral prefrontal cortex, and precuneus) that are often implicated in neuroimaging studies of substance use disorders, as well as some key exceptions. We also identified a core set of networks of brain regions that contributed to successful classification, comprised of many of the same predictive regions. ConclusionsOur dual aims of accurate prediction and interpretability were successful, producing a predictive model that also provides interpretability at the neural level. This novel approach may complement other predictive-exploratory approaches for a more complete understanding of neural mechanisms in drug use and other neuropsychiatric disorders.

neuroscience↗

bioRxiv2021

A novel 5D brain parcellation approach based on spatio-temporal encoding of resting fMRI data from deep residual learning

ObjectiveBrain parcellation is an essential aspect of computational neuroimaging research and deals with segmenting the brain into (possibly overlapping) sub-regions employed to study brain anatomy or function. In the context of functional parcellation, brain organization which is often measured via temporal metrics such as coherence, is highly dynamic. This dynamic aspect is ignored in most research, which typically applies anatomically based, fixed regions for each individual, and can produce misleading results. MethodsIn this work, we propose a novel spatio-temporal-network (5D) brain parcellation scheme utilizing a deep residual network to predict the probability of each voxel belonging to a brain network at each point in time. ResultsWe trained 53 4D brain networks and evaluate the ability of these networks to capture spatial and temporal dynamics as well as to show sensitivity to individual or group-level variation (in our case with age). ConclusionThe proposed system generates informative spatio-temporal networks that vary not only across individuals but also over time and space. SignificanceThe dynamic 5D nature of the developed approach provides a powerful framework that expands on existing work and has potential to identify novel and typically ignored findings when studying the healthy and disordered brain.

neuroscience↗

bioRxiv2021

The link between static and dynamic brain functional network connectivity and genetic risk of Alzheimer's disease

Apolipoprotein E (APOE) polymorphic alleles are genetic factors associated with Alzheimers disease (AD) risk. Although previous studies have explored the link between AD genetic risk and static functional network connectivity (sFNC), to the best of our knowledge, no previous studies have evaluated the association between dynamic FNC (dFNC) and AD genetic risk. Here, we examined the link between sFNC, dFNC, and AD genetic risk with a reproducible, data-driven approach. We used rs-fMRI, demographic, and APOE data from cognitively normal individuals (N=894) between 42 to 95 years of age (mean = 70 years). We divided individuals into low, moderate, and high-risk groups. Using Pearson correlation, we calculated sFNC across seven brain networks. We also calculated dFNC with a sliding window and Pearson correlation. The dFNC windows were partitioned into three distinct states with k-means clustering. Next, we calculated the amount of time each subject spent in each state, called occupancy rate or OCR. We compared both sFNC and OCR, estimated from dFNC, across individuals with different genetic risk and found that both sFNC and dFNC are related to AD genetic risk. We found that higher AD risk reduces within-visual sensory network (VSN) sFNC and that individuals with higher AD risk spend more time in a state with lower within-VSN dFNC. Additionally, we found that AD genetic risk affects whole-brain sFNC and dFNC in women but not in men. In conclusion, we presented novel insights into the links between sFNC, dFNC, and AD genetic risk.

neuroscience↗