Search

Revealing associations among various structural and functional patterns of the brain can yield highly informative results about the healthy and disordered brain. Studies using neuroimaging data have more recently begun to utilize the information within as well as across various functional and anatomical domains (i.e., groups of brain networks). However, most whole-brain approaches assume similar complexity of interactions throughout the brain. Here we investigate the hypothesis that interactions between brain networks capture varying amounts of complexity, and that we can better capture this information by varying the complexity of the model subspace structure based on available training data. To do this, we employ a Bayesian optimization-based framework known as the Tree Parzen Estimator (TPE) to identify, exploit and analyze patterns of variation in the information encoded by temporal information extracted from functional magnetic resonance imaging (fMRI) subdomains of the brain. Using a repeated cross-validation procedure on a schizophrenia classification task, we demonstrate evidence that interactions between specific functional subdomains are better characterized by more sophisticated model architectures compared to less complicated ones required by the others for optimally contributing towards classification and understanding the brain's functional interactions. We show that functional subdomains known to be involved in schizophrenia require more complex architectures to optimally unravel discriminatory information about the disorder. Our study points to the need for adaptive, hierarchical learning frameworks that cater differently to the features from different subdomains, not only for a better prediction but also for enabling the identification of features predicting the outcome of interest.

BackgroundA number of studies in recent years have explored whole-brain dynamic connectivity using pairwise approaches. There has been less focus on trying to analyze brain dynamics in higher dimensions over time.MethodsWe introduce a new approach that analyzes time series trajectories to identify high traffic nodes in a high dimensional space. First, functional magnetic resonance imaging (fMRI) data are decomposed using spatial ICA to a set of maps and their associated time series. Next, density is calculated for each time point and high-density points are clustered to identify a small set of high traffic nodes. We validated our method using simulations and then implemented it on a real data set.ResultsWe present a novel approach that captures dynamics within a high dimensional space and also does not use any windowing in contrast to many existing approaches. The approach enables one to characterize and study the time series in a potentially high dimensional space, rather than looking at each component pair separately. Our results show that schizophrenia patients have a lower dynamism compared to healthy controls. In addition, we find patients spend more time in nodes associated with the default mode network and less time in components strongly correlated with auditory and sensorimotor regions. Interestingly, we also found that subjects oscillate between state pairs that show opposite spatial maps, suggesting an oscillatory pattern.ConclusionOur proposed method provides a novel approach to analyze the data in its native high dimensional space and can possibly provide new information that is undetectable using other methods.

ObjectiveMultimodal measurements of the same phenomena provide complementary information and highlight different perspectives, albeit each with their own limitations. A focus on a single modality may lead to incorrect inferences, which is especially important when a studied phenomenon is a disease. In this paper, we introduce a method that takes advantage of multimodal data in addressing the hypotheses of disconnectivity and dysfunction within schizophrenia (SZ).MethodsWe start with estimating and visualizing links within and among extracted multimodal data features using a Gaussian graphical model (GGM). We then propose a modularity-based method that can be applied to the GGM to identify links that are associated with mental illness across a multimodal data set. Through simulation and real data, we show our approach reveals important information about disease-related network disruptions that are missed with a focus on a single modality. We use functional MRI (fMRI), diffusion MRI (dMRI), and structural MRI (sMRI) to compute the fractional amplitude of low frequency fluctuations (fALFF), fractional anisotropy (FA), and gray matter (GM) concentration maps. These three modalities are analyzed using our modularity method.ResultsOur results show missing links that are only captured by the cross-modal information that may play an important role in disconnectivity between the components.ConclusionWe identified multimodal (fALFF, FA and GM) disconnectivity in the default mode network area in patients with SZ, which would not have been detectable in a single modality.SignificanceThe proposed approach provides an important new tool for capturing information that is distributed among multiple imaging modalities.

The brain is a complex, multiscale dynamical system composed of many interacting regions. Knowledge of the spatiotemporal organization of these interactions is critical for establishing a solid understanding of the brain's functional architecture and the relationship between neural dynamics and cognition in health and disease. The possibility of studying these dynamics through careful analysis of neuroimaging data has catalyzed substantial interest in methods that estimate time-resolved fluctuations in functional connectivity (often referred to as "dynamic" or time-varying functional connectivity; TVFC). At the same time, debates have emerged regarding the application of TVFC analyses to resting fMRI data, and about the statistical validity, physiological origins, and cognitive and behavioral relevance of resting TVFC. These and other unresolved issues complicate interpretation of resting TVFC findings and limit the insights that can be gained from this promising new research area. This article brings together scientists with a variety of perspectives on resting TVFC to review the current literature in light of these issues. We introduce core concepts, define key terms, summarize controversies and open questions, and present a forward-looking perspective on how resting TVFC analyses can be rigorously and productively applied to investigate a wide range of questions in cognitive and systems neuroscience.

BackgroundDynamic functional network connectivity (dFNC) of the brain has attracted considerable attention recently. Many approaches have been suggested to study dFNC with sliding window Pearson correlation (SWPC) being the most well-known. SWPC needs a relatively large sample size to reach a robust estimation but using large window sizes prevents us to detect rapid changes in dFNC.New methodHere we first calculate the gradients of each time series pair and use the magnitude of these gradients to calculate weighted average of shared trajectory (WAST) as a new estimator for dFNC.ResultsUsing WAST to compare healthy control and schizophrenia patients using a large dataset, we show disconnectivity between different regions associated with schizophrenia. In addition, WAST results reveals patients with schizophrenia stay longer in a connectivity state with negative connectivity between motor and sensory regions than do healthy controls.Comparison with existing methodsWe compare WAST with SWPC and multiplication of temporal derivatives (MTD) using different simulation scenarios. We show that WAST enables us to detect very rapid changes in dFNC (undetected by SWPC) while MTD performance is generally lower.ConclusionsAs large window sizes are unable to detect short states, using shorter window size is desirable if the estimator is robust enough. We provide evidence that WAST requires fewer samples (compared to SWPC) to reach a robust estimation. As a result, we were able to identify rapidly varying dFNC patterns undetected by SWPC while still being able to robustly estimate slower dFNC patterns.

It has been widely shown that genomic factors influence both risk for schizophrenia and variation in functional brain connectivity. Moreover, schizophrenia is characterized by disrupted brain connectivity. In this work, we proposed a genome-connectome bipartite graph model to perform imaging genomic analysis. Functional network connectivity (FNC) was estimated after decomposing resting state functional magnetic resonance imaging data from both healthy controls (HC) and patients with schizophrenia (SZ) into spatial brain components using group independent component analysis (G-ICA). Then 83 FNC connections showing a group difference (HC vs SZ) were selected as fMRI nodes, and eighty-one schizophrenia-related single nucleotide polymorphisms (SNPs) were selected as genetic nodes respectively in the bipartite graph. Edges connecting pairs of genetic and fMRI nodes were defined based on the SNP-FNC associations across subjects evaluated by a general linear model. Results show that some SNP nodes in the bipartite graph have a high degree implying they are influential in modulating brain connectivity and may be more strongly associated with the risk of schizophrenia than other SNPs. A bi-clustering analysis detected a cluster with 15 SNPs interacting with 38 FNC connections, most of which were within or between somato-motor and visual brain areas. This suggests that the activity of these brain regions may be related to common SNPs and provides insights into the pathology of schizophrenia. The findings suggest that the SNP-FNC bipartite graph approach is a novel model to investigate genetic influences on functional brain connectivity in mental illness.

Brain functional networks identified from fMRI data can provide potential biomarkers for brain disorders. Group independent component analysis (GICA) is popular for extracting brain functional networks from multiple subjects. In GICA, different strategies exist for reconstructing subject-specific networks from the group-level networks. However, it is unknown whether these strategies have different sensitivities to group differences and abilities in distinguishing patients. Among GICA, spatio-temporal regression (STR) and spatially constrained ICA approaches such as group information guided ICA (GIG-ICA) can be used to propagate components (indicating networks) to a new subject that is not included in the original subjects. In this study, based on the same a priori network maps, we reconstructed subject-specific networks using these two methods separately from resting-state fMRI data of 151 schizophrenia patients (SZs) and 163 healthy controls (HCs). We investigated group differences in the estimated functional networks and the functional network connectivity (FNC) obtained by each method. The networks were also used as features in a cross-validated support vector machine (SVM) for classifying SZs and HCs. We selected features using different strategies to provide a comprehensive comparison between the two methods. GIG-ICA generally showed greater sensitivity in statistical analysis and better classification performance (accuracy 76.45 ± 8.9%, sensitivity 0.74 ± 0.11, specificity 0.79 ± 0.11) than STR (accuracy 67.45 ± 8.13%, sensitivity 0.65 ± 0.11, specificity 0.71 ± 0.11). Importantly, results were also consistent when applied to an independent dataset including 82 HCs and 82 SZs. Our work suggests that the functional networks estimated by GIG-ICA are more sensitive to group differences, and GIG-ICA is promising for identifying image-derived biomarkers of brain disease.

BackgroundThe N400 event-related potential (ERP) is triggered by meaningful stimuli that are incongruous, or unmatched, with their semantic context. Functional magnetic resonance imaging (fMRI) studies have identified brain regions activated by semantic incongruity, but their precise links to the N400 ERP are unclear. In schizophrenia (SZ), N400 amplitude reduction is thought to reflect overly broad associations in semantic networks, but the abnormalities in brain networks underlying deficient N400 remain unknown. We utilized joint independent component analysis (JICA) to link temporal patterns in ERPs to neuroanatomical patterns from fMRI and investigate relationships between N400 amplitude and neuroanatomical activation in SZ patients and healthy controls (HC).MethodsSZ patients (n = 24) and HC participants (n = 25) performed a picture-word matching task, in which words were either matched (APPLE→apple) by preceding pictures, or were unmatched by semantically related (in-category; IC, APPLE→lemon) or unrelated (out of category; OC, APPLE→cow) pictures, in separate ERP and fMRI sessions. A JICA "data fusion" analysis was conducted to identify the fMRI brain regions specifically associated with the ERP N400 component. SZ and HC loading weights were compared and correlations with clinical symptoms were assessed.ResultsJICA identified an ERP-fMRI "fused" component that captured the N400, with loading weights that were reduced in SZ. The JICA map for the IC condition showed peaks of activation in the cingulate, precuneus, bilateral temporal poles and cerebellum, whereas the JICA map from the OC condition was linked primarily to visual cortical activation and the left temporal pole. Among SZ patients, fMRI activity from the IC condition was inversely correlated with unusual thought content.ConclusionsThe neural networks associated with the N400 ERP response to semantic violations depends on conceptual relatedness. These findings are consistent with a distributed network underlying neural responses to semantic incongruity including unimodal visual areas as well as integrative, transmodal areas. Unusual thoughts in SZ may reflect impaired processing in transmodal hub regions such as the precuneus, leading to overly broad semantic associations.

Individuals at clinical high-risk (CHR) for psychosis are characterized by attenuated psychotic symptoms. Only a minority of CHR individuals convert to full-blown psychosis. Therefore, there is a strong interest in identifying neurobiological abnormalities underlying the psychosis risk syndrome. Dynamic functional connectivity (DFC) captures time-varying connectivity over short time scales, and has the potential to reveal complex brain functional organization. Based on resting-state functional magnetic resonance imaging (fMRI) data from 70 healthy controls (HCs), 53 CHR individuals, and 58 early illness schizophrenia (ESZ) patients, we applied a novel group information guided ICA (GIG-ICA) to estimate inherent connectivity states from DFC, and then investigated group differences. We found that ESZ patients showed more aberrant connectivities and greater alterations than CHR individuals. Results also suggested that disease-related connectivity states occurred in CHR and ESZ groups. Regarding the dominant state with the highest contribution to dynamic connectivity, ESZ patients exhibited greater impairments than CHR individuals primarily in the cerebellum, frontal cortex, thalamus and temporal cortex, while CHR and ESZ populations shared common aberrances mainly in the supplementary motor area, parahippocampal gyrus and postcentral cortex. CHR-specific changes were also found in the connections between the superior frontal gyrus and calcarine cortex in the dominant state. Our findings suggest that CHR individuals generally show an intermediate functional connectivity pattern between HCs and SZ patients but also have unique connectivity alterations.

Hallucinations characterize schizophrenia, with approximately 59% of patients reporting auditory hallucinations and 27% reporting visual hallucinations. Prior neuroimaging studies suggest that hallucinations are linked to disrupted communication across distributed (sensory, salience-monitoring and subcortical) networks. Yet, our understanding of the neurophysiological mechanisms that underlie auditory and visual hallucinations in schizophrenia remains limited. This study integrates two resting-state functional magnetic resonance imaging (fMRI) analysis methods - amplitudes of low-frequency fluctuations (ALFF) and functional network connectivity (FNC) - to explore the hypotheses that (1) abnormal FNC between salience and sensory (visual/auditory) networks underlies hallucinations in schizophrenia, and (2) disrupted hippocampal oscillations (as measured by hippocampal ALFF) beget changes in FNC linked to hallucinations. Our first hypothesis was supported by the finding that schizophrenia patients reporting hallucinations have higher FNC between the salience network and an associative auditory network relative to healthy controls. Hippocampal ALFF was negatively associated with FNC between primary auditory cortex and the salience network in healthy subjects, but was positively associated with FNC between these networks in patients reporting hallucinations. These findings provide indirect support favoring our second hypothesis. We suggest future studies integrate fMRI with electroencephalogram (EEG) and/or magnetoencephalogram (MEG) methods to directly probe the temporal relation between altered hippocampal oscillations and changes in cross-network functional communication.

Prior resting-state functional magnetic resonance imaging (fMRI) analyses have identified patterns of functional connectivity associated with hallucinations in schizophrenia (Sz). In this study, we performed an analysis of the mean amplitude of low-frequency fluctuations (ALFF) to compare resting state spontaneous low-frequency fluctuations in patients with Sz who report experiencing hallucinations impacting different sensory modalities. By exploring dynamics across 2 low-frequency passbands (slow-4 and slow-5), we assessed the impact of hallucination modality and frequency range on spatial ALFF variation. Drawing from a sample of Sz and healthy controls studied as part of the Functional Imaging Biomedical Informatics Research Network (FBIRN), we replicated prior findings showing that patients with Sz have decreased ALFF in the posterior brain in comparison to controls. Remarkably, we found that patients that endorsed visual hallucinations did not show this pattern of reduced ALFF in the back of the brain. These patients also had elevated ALFF in the left hippocampus in comparison to patients that endorsed auditory (but not visual) hallucinations. Moreover, left hippocampal ALFF across all the cases was related to reported hallucination severity in both the auditory and visual domains, and not overall positive symptoms. This supports the hypothesis that dynamic changes in the ALFF in the hippocampus underlie severity of hallucinations that impact different sensory modalities.

ObjectiveWe introduce a method for analyzing dynamically changing functional magnetic resonance imaging (fMRI) network connectivity estimates as they vary within and between broad functional domains. The method captures evidence of intertemporal directionality in cross joint functional-domain influence and extends standard whole-brain dynamic network connectivity approaches into additional functionally meaningful dimensions by evaluating transition probabilities between clustered intradomain and interdomain connectivity patterns.  Results: In applying this method to a large (N = 314) multisite resting-state fMRI dataset balanced between schizophrenia patients and healthy controls, we find evidence of joint functional domains that are global catalyzers, broadly shaping downstream functional relationships throughout the brain. Multiple interesting differences between patients and controls in both time-varying joint functional-domain connectivity patterns and in cross joint functional-domain intertemporal information flow were identified. Conclusion and Significance: Our proposed approach, thus, unifies the concepts of brain connectivity and interdomain connectivity and provides a powerful new way to evaluate functional connectivity data in the context of both the healthy and diseased brain.

Clinical research employing functional magnetic resonance imaging (fMRI) is often conducted within the connectionist paradigm, focusing on patterns of connectivity between voxels, regions of interest (ROIs) or spatially distributed functional networks. Connectivity-based analyses are concerned with pairwise correlations of the temporal activation associated with restrictions of the whole-brain hemodynamic signal to locations of a priori interest. There is a more abstract question however that such spatially granular correlation-based approaches do not elucidate: Are the broad spatiotemporal organizing principles of brains in certain populations distinguishable from those of others? Global patterns (in space and time) of hemodynamic activation are rarely scrutinized for features that might characterize complex psychiatric conditions, aging effects or gender-among other variables of potential interest to researchers. We introduce a canonical, transparent technique for characterizing the role in overall brain activation of spatially scaled periodic patterns with given temporal recurrence rates. A core feature of our technique is the spatiotemporal spectral profile (STSP), a readily interpretable 2D reduction of the native four-dimensional brain × time frequency domain that is still "big enough" to capture important group differences in globally patterned brain activation. Its power to distinguish populations of interest is demonstrated on a large balanced multi-site resting fMRI dataset with nearly equal numbers of schizophrenia patients and healthy controls. Our analysis reveals striking differences in the spatiotemporal organization of brain activity that correlate with the presence of diagnosed schizophrenia, as well as with gender and age. To the best of our knowledge, this is the first demonstration that a 4D frequency domain analysis of full volume fMRI data exposes clinically or demographically relevant differences in resting-state brain function.

Schizophrenia (SZ) is a debilitating mental illness characterized by adolescence or early adulthood onset of psychosis, positive and negative symptoms, as well as cognitive impairments. Despite a plethora of studies leveraging functional connectivity (FC) from functional magnetic resonance imaging (fMRI) to predict symptoms and cognitive impairments of SZ, the findings have exhibited great heterogeneity. We aimed to identify congruous and replicable connectivity patterns capable of predicting positive and negative symptoms as well as cognitive impairments in SZ. Predictable functional connections (FCs) were identified by employing an individualized prediction model, whose replicability was further evaluated across three independent cohorts (BSNIP, SZ = 174; COBRE, SZ = 100; FBIRN, SZ = 161). Across cohorts, we observed that altered FCs in frontal‐temporal‐cingulate‐thalamic network were replicable in prediction of positive symptoms, while sensorimotor network was predictive of negative symptoms. Temporal‐parahippocampal network was consistently identified to be associated with reduced cognitive function. These replicable 23 FCs effectively distinguished SZ from healthy controls (HC) across three cohorts (82.7%, 90.2%, and 86.1%). Furthermore, models built using these replicable FCs showed comparable accuracies to those built using the whole‐brain features in predicting symptoms/cognition of SZ across the three cohorts (r =.17–.33, p <.05). Overall, our findings provide new insights into the neural underpinnings of SZ symptoms/cognition and offer potential targets for further research and possible clinical interventions. [ABSTRACT FROM AUTHOR]

This report provides practical recommendations for the design and execution of multicenter functional MRI (MC-fMRI) studies based on the collective experience of the Function Biomedical Informatics Research Network (FBIRN). The study was inspired by many requests from the fMRI community to FBIRN group members for advice on how to conduct MC-fMRI studies. The introduction briefly discusses the advantages and complexities of MC-fMRI studies. Prerequisites for MC-fMRI studies are addressed before delving into the practical aspects of carefully and efficiently setting up a MC-fMRI study. Practical multisite aspects include: (i) establishing and verifying scan parameters including scanner types and magnetic fields, (ii) establishing and monitoring of a scanner quality program, (iii) developing task paradigms and scan session documentation, (iv) establishing clinical and scanner training to ensure consistency over time, (v) developing means for uploading, storing, and monitoring of imaging and other data, (vi) the use of a traveling fMRI expert, and (vii) collectively analyzing imaging data and disseminating results. We conclude that when MC-fMRI studies are organized well with careful attention to unification of hardware, software and procedural aspects, the process can be a highly effective means for accessing a desired participant demographics while accelerating scientific discovery.

Network neuroscience, a multidisciplinary field merging insights from neuroscience and network theory, offers a profound understanding of neural network intricacies. However, the impact of varying node sizes on computed graph metrics in neuroimaging data remains underexplored. This study addresses this gap by adopting a data-driven methodology to delineate functional nodes and assess their influence on graph metrics. Using the Neuromark framework, automated independent component analysis is applied to resting state fMRI data, capturing functional network connectivity (FNC) matrices. Global and local graph metrics reveal intricate connectivity patterns, emphasizing the need for nuanced analysis. Notably, node sizes, computed based on voxel counts, contribute to a novel metric termed 'node-metric coupling' (NMC). Correlations between graph metrics and node dimensions are consistently observed. The study extends its analysis to a dataset comprising Alzheimer's disease, mild cognitive impairment, and control subjects, showcasing the potential of NMC as a biomarker for brain disorders. The two key outcomes underscore the interplay between node sizes and resultant graph metrics within a given atlas, shedding light on an often-overlooked source of variability. Additionally, the study highlights the utility of NMC as a valuable biomarker, emphasizing the necessity of accounting for node sizes in future neuroimaging investigations. This work contributes to refining comparative studies employing diverse atlases and advocates for thoughtful consideration of intra-atlas node size in shaping graph metrics, paving the way for more robust neuroimaging research. [ABSTRACT FROM AUTHOR]

Brain networks extracted by independent component analysis (ICA) from magnitude‐only fMRI data are usually denoised using various amplitude‐based thresholds. By contrast, spatial source phase (SSP) or the phase information of ICA brain networks extracted from complex‐valued fMRI data, has provided a simple yet effective way to perform the denoising using a fixed phase change. In this work, we extend the approach to magnitude‐only fMRI data to avoid testing various amplitude thresholds for denoising magnitude maps extracted by ICA, as most studies do not save the complex‐valued data. The main idea is to generate a mathematical SSP map for a magnitude map using a mapping framework, and the mapping framework is built using complex‐valued fMRI data with a known SSP map. Here we leverage the fact that the phase map derived from phase fMRI data has similar phase information to the SSP map. After verifying the use of the magnitude data of complex‐valued fMRI, this framework is generalized to work with magnitude‐only data, allowing use of our approach even without the availability of the corresponding phase fMRI datasets. We test the proposed method using both simulated and experimental fMRI data including complex‐valued data from University of New Mexico and magnitude‐only data from Human Connectome Project. The results provide evidence that the mathematical SSP denoising with a fixed phase change is effective for denoising spatial maps from magnitude‐only fMRI data in terms of retaining more BOLD‐related activity and fewer unwanted voxels, compared with amplitude‐based thresholding. The proposed method provides a unified and efficient SSP approach to denoise ICA brain networks in fMRI data. [ABSTRACT FROM AUTHOR]

Alcohol use disorder (AUD) is a burden to society creating social and health problems. Detection of AUD and its effects on the brain are difficult to assess. This problem is enhanced by the comorbid use of other substances such as nicotine that has been present in previous studies. Recent machine learning algorithms have raised the attention of researchers as a useful tool in studying and detecting AUD. This work uses AUD and controls samples free of any other substance use to assess the performance of a set of commonly used machine learning classifiers detecting AUD from resting state functional network connectivity (rsFNC) derived from independent component analysis. The cohort used included 51 alcohol dependent subjects and 51 control subjects. Despite alcohol, none of the 102 subjects reported use of nicotine, cannabis or any other dependence or habit formation substance. Classification features consisted of whole brain rsFNC estimates undergoing a feature selection process using a random forest approach. Features were then fed to 10 different machine learning classifiers to be evaluated based on their classification performance. A neural network classifier showed the highest performance with an area under the curve (AUC) of 0.79. Other good performers with similar AUC scores were logistic regression, nearest neighbor, and support vector machine classifiers. The worst results were obtained with Gaussian process and quadratic discriminant analysis. The feature selection outcome pointed to functional connections between visual, sensorimotor, executive control, reward, and salience networks as the most relevant for classification. We conclude that AUD can be identified using machine learning classifiers in the absence of nicotine comorbidity. [ABSTRACT FROM AUTHOR]

Privacy concerns for rare disease data, institutional or IRB policies, access to local computational or storage resources or download capabilities are among the reasons that may preclude analyses that pool data to a single site. A growing number of multisite projects and consortia were formed to function in the federated environment to conduct productive research under constraints of this kind. In this scenario, a quality control tool that visualizes decentralized data in its entirety via global aggregation of local computations is especially important, as it would allow the screening of samples that cannot be jointly evaluated otherwise. To solve this issue, we present two algorithms: decentralized data stochastic neighbor embedding, dSNE, and its differentially private counterpart, DP‐dSNE. We leverage publicly available datasets to simultaneously map data samples located at different sites according to their similarities. Even though the data never leaves the individual sites, dSNE does not provide any formal privacy guarantees. To overcome that, we rely on differential privacy: a formal mathematical guarantee that protects individuals from being identified as contributors to a dataset. We implement DP‐dSNE with AdaCliP, a method recently proposed to add less noise to the gradients per iteration. We introduce metrics for measuring the embedding quality and validate our algorithms on these metrics against their centralized counterpart on two toy datasets. Our validation on six multisite neuroimaging datasets shows promising results for the quality control tasks of visualization and outlier detection, highlighting the potential of our private, decentralized visualization approach. [ABSTRACT FROM AUTHOR]

Prediction of cognitive ability latent factors such as general intelligence from neuroimaging has elucidated questions pertaining to their neural origins. However, predicting general intelligence from functional connectivity limit hypotheses to that specific domain, being agnostic to time‐distributed features and dynamics. We used an ensemble of recurrent neural networks to circumvent this limitation, bypassing feature extraction, to predict general intelligence from resting‐state functional magnetic resonance imaging regional signals of a large sample (n = 873) of Human Connectome Project adult subjects. Ablating common resting‐state networks (RSNs) and measuring degradation in performance, we show that model reliance can be mostly explained by network size. Using our approach based on the temporal variance of saliencies, that is, gradients of outputs with regards to inputs, we identify a candidate set of networks that more reliably affect performance in the prediction of general intelligence than similarly sized RSNs. Our approach allows us to further test the effect of local alterations on data and the expected changes in derived metrics such as functional connectivity and instantaneous innovations. [ABSTRACT FROM AUTHOR]

Objective: To understand the association between brain networks and behaviors of an individual, most studies build predictive models based on functional connectivity (FC) from a single dataset with linear analysis techniques. Such approaches may fail to capture the nonlinear structure of brain networks and neglect the complementary information contained in FC networks (FCNs) from multiple datasets. To address this challenging issue, we use multiview dimensionality reduction to extract a coherent low-dimensional representation of the FCNs from resting-state and emotion identification task-based functional magnetic resonance imaging (fMRI) datasets. Methods: We propose a scheme based on multiview diffusion map to extract intrinsic features while preserving the underlying geometric structure of high dimensional datasets. This method is robust to noise and small variations in the data. Results: After validation on the Philadelphia Neurodevelopmental Cohort data, the predictive model built from both resting-state and emotion identification task-based fMRI datasets outperforms the one using each individual fMRI dataset. In addition, the proposed model achieves better prediction performance than principal component analysis (PCA) and three other competing data fusion methods. Conclusion: Our framework for combing multiple FCNs in one predictive model exhibits improved prediction performance. Significance: To our knowledge, we demonstrate a first application of multiview diffusion map to successfully fuse different types of fMRI data for predicting fluid intelligence (gF). [ABSTRACT FROM AUTHOR]

Recent advances in imaging genetics make it possible to combine different types of data including medical images like functional magnetic resonance imaging (fMRI) and genetic data like single nucleotide polymorphisms (SNPs) for comprehensive diagnosis of mental disorders. Understanding complex interactions among these heterogeneous data may give rise to a new perspective, while at the same time demand statistical models for their integration. Various graphical models have been proposed for the study of interaction or association networks with continuous, binary, and count data as well as the mixture of them. However, limited efforts have been made for the multinomial case, for instance, SNP data. Our goal is therefore to fill the void by developing a graphical model for the integration of fMRI image and SNP data, which can provide deeper understanding of the unknown neurogenetic mechanism. In this article, we propose a latent Gaussian copula model for mixed data containing multinomial components. We assume that the discrete variable is obtained by discretizing a latent (unobserved) continuous variable and then create a semi-rank based estimator of the graph structure. The simulation results demonstrate that the proposed latent correlation has more steady and accurate performance than several existing methods in detecting graph structure. When applying to a real schizophrenia data consisting of SNP array and fMRI image collected by the Mind Clinical Imaging Consortium (MCIC), the proposed method reveals a set of distinct SNP-brain associations, which are verified to be biologically significant. The proposed model is statistically promising in handling mixed types of data including multinomial components, which can find widespread applications. To promote reproducible research, the R code is available at https://github.com/Aiying0512/LGCM. [ABSTRACT FROM AUTHOR]

Abstract Background Compressive sensing can provide a promising framework for accelerating fMRI image acquisition by allowing reconstructions from a limited number of frequency-domain samples. Unfortunately, the majority of compressive sensing studies are based on stochastic sampling geometries that cannot guarantee fast acquisitions that are needed for fMRI. The purpose of this study is to provide a comprehensive optimization framework that can be used to determine the optimal 2D stochastic or deterministic sampling geometry, as well as to provide optimal reconstruction parameter values for guaranteeing image quality in the reconstructed images. Methods We investigate the use of frequency-space (k-space) sampling based on: (i) 2D deterministic geometries of dyadic phase encoding (DPE) and spiral low pass (SLP) geometries, and (ii) 2D stochastic geometries based on random phase encoding (RPE) and random samples on a PDF (RSP). Overall, we consider over 36 frequency-sampling geometries at different sampling rates. For each geometry, we compute optimal reconstructions of single BOLD fMRI ON & OFF images, as well as BOLD fMRI activity maps based on the difference between the ON and OFF images. We also provide an optimization framework for determining the optimal parameters and sampling geometry prior to scanning. Results For each geometry, we show that reconstruction parameter optimization converged after just a few iterations. Parameter optimization led to significant image quality improvements. For activity detection, retaining only 20.3% of the samples using SLP gave a mean PSNR value of 57.58 dB. We also validated this result with the use of the Structural Similarity Index Matrix (SSIM) image quality metric. SSIM gave an excellent mean value of 0.9747 (max = 1). This indicates that excellent reconstruction results can be achieved. Median parameter values also gave excellent reconstruction results for the ON/OFF images using the SLP sampling geometry (mean SSIM > =0.93). Here, median parameter values were obtained using mean-SSIM optimization. This approach was also validated using leave-one-out. Conclusions We have found that compressive sensing parameter optimization can dramatically improve fMRI image reconstruction quality. Furthermore, 2D MRI scanning based on the SLP geometries consistently gave the best image reconstruction results. The implication of this result is that less complex sampling geometries will suffice over random sampling. We have also found that we can obtain stable parameter regions that can be used to achieve specific levels of image reconstruction quality when combined with specific k-space sampling geometries. Furthermore, median parameter values can be used to obtain excellent reconstruction results.

Schizophrenia (SZ) is a complex disease. Single nucleotide polymorphism (SNP), brain activity measured by functional magnetic resonance imaging (fMRI) and DNA methylation are all important biomarkers that can be used for the study of SZ. To our knowledge, there has been little effort to combine these three datasets together. In this study, we propose a group sparse joint nonnegative matrix factorization (GSJNMF) model to integrate SNP, fMRI, and DNA methylation for the identification of multi-dimensional modules associated with SZ, which can be used to study regulatory mechanisms underlying SZ at multiple levels. The proposed GSJNMF model projects multiple types of data onto a common feature space, in which heterogeneous variables with large coefficients on the same projected bases are used to identify multi-dimensional modules. We also incorporate group structure information available from each dataset. The genomic factors in such modules have significant correlations or functional associations with several brain activities. At the end, we have applied the method to the analysis of real data collected from the Mind Clinical Imaging Consortium (MCIC) for the study of SZ and identified significant biomarkers. These biomarkers were further used to discover genes and corresponding brain regions, which were confirmed to be significantly associated with SZ. [ABSTRACT FROM AUTHOR]

The current study set out to investigate the dynamic functional connectome in relation to long‐term recovery after mild to moderate traumatic brain injury (TBI). Longitudinal resting‐state functional MRI data were collected (at 1 and 3 months postinjury) from a prospectively enrolled cohort consisting of 68 patients with TBI (92% mild TBI) and 20 healthy subjects. Patients underwent a neuropsychological assessment at 3 months postinjury. Outcome was measured using the Glasgow Outcome Scale Extended (GOS‐E) at 6 months postinjury. The 57 patients who completed the GOS‐E were classified as recovered completely (GOS‐E = 8; n = 37) or incompletely (GOS‐E < 8; n = 20). Neuropsychological test scores were similar for all groups. Patients with incomplete recovery spent less time in a segregated brain state compared to recovered patients during the second visit. Also, these patients moved less frequently from one meta‐state to another as compared to healthy controls and recovered patients. Furthermore, incomplete recovery was associated with disruptions in cyclic state transition patterns, called attractors, during both visits. This study demonstrates that poor long‐term functional recovery is associated with alterations in dynamics between brain networks, which becomes more marked as a function of time. These results could be related to psychological processes rather than injury‐effects, which is an interesting area for further work. Another natural progression of the current study is to examine whether these dynamic measures can be used to monitor treatment effects. [ABSTRACT FROM AUTHOR]

Objective: Multi-modal functional magnetic resonance imaging has been widely used for brain research. Conventional data-fusion methods cannot capture complex relationship (e.g., nonlinear predictive relationship) between multiple data. This paper aims to develop a neural network framework to extract phenotype related cross-data relationships and use it to study the brain development. Methods: We propose a novel method, deep collaborative learning (DCL), to address the limitation of existing methods. DCL first uses a deep network to represent original data and then seeks their correlations, while also linking the data representation with phenotypical information. Results: We studied the difference of functional connectivity (FCs) between different age groups and also use FCs as a fingerprint to predict cognitive abilities. Our experiments demonstrated higher accuracy of using DCL over other conventional models when classifying populations of different ages and cognitive scores. Moreover, DCL revealed that brain connections became stronger at adolescence stage. Furthermore, DCL detected strong correlations between default mode network and other networks which were overlooked by linear canonical correlation analysis, demonstrating DCL's ability of detecting nonlinear correlations. Conclusion: The results verified the superiority of DCL over conventional data-fusion methods. In addition, the stronger brain connection demonstrated the importance of adolescence stage for brain development. Significance: DCL can better combine complex correlations between multiple data sets in addition to their fitting to phenotypes, with the potential to overcome the limitations of several current data-fusion models. [ABSTRACT FROM AUTHOR]

The study of dynamic functional network connectivity (dFNC) has been important to understand the healthy and diseased brain. Recent developments model groups of functionally related brain structures (defined as functional domains) as entities that can send and receive information. A domain analysis starts by detecting a finite set of connectivity patterns known as domain states within each functional domain. Dynamic functional domain connectivity (DFDC) is a novel information theoretic framework for studying the temporal sequence of the domain states and the amount of information shared among domains. In this setting, the information flow among functional domains can be compared to the flow of bits among entities in a digital network. Schizophrenia is a chronic psychiatric disorder which is associated with how the brain processes information. Here, we employed the DFDC framework to analyze a dataset containing resting-state fMRI scans from 163 healthy controls (HCs) and 151 schizophrenia patients (SZs). As in other information theory methods, this study measured domain state probabilities, entropy within each DFDC and the cross-domain mutual information (CDMI) between pairs of DFDC. Results indicate that SZs show significantly higher (transformed) entropy than HCs in subcortical (SC)-SC; default mode network (DMN)-visual (VIS) and frontoparietal (FRN)-VIS DFDCs. SZs also show lower (transformed) CDMI between SC-VIS vs. SC-sensorimotor (SM), attention (ATTN)-VIS vs. ATTN-SM and ATTN-SM vs. ATTN-ATTN DFDC pairs after correcting for multiple comparisons. These results imply that different DFDC pairs function in a more independent manner in SZs compared to HCs. Our findings present evidence of higher uncertainty and randomness in SZ brain function. [ABSTRACT FROM AUTHOR]

Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture the nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, the FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal $n$ -back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and $n$ -back task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ. [ABSTRACT FROM AUTHOR]

Schizophrenia (SZ) is a chronic and severe mental disorder that affects how a person thinks, feels, and behaves. It has been proposed that this disorder is related to disrupted brain connectivity, which has been verified by many studies. With the development of functional magnetic resonance imaging (fMRI), further exploration of brain connectivity was made possible. Region-based networks are commonly used for mapping brain connectivity. However, they fail to illustrate the connectivity within regions of interest (ROIs) and lose precise location information. Voxel-based networks provide higher precision, but are difficult to construct and interpret due to the high dimensionality of the data. In this paper, we adopt a novel high-dimensional Gaussian graphical model – $\psi$ -learning method, which can help ease computational burden and provide more accurate inference for the underlying networks. This method has been proven to be an equivalent measure of the partial correlation coefficient and, thus, is flexible for network comparison through statistical tests. The fMRI data we used were collected by the mind clinical imaging consortium using an auditory task in which there are 92 SZ patients and 116 healthy controls. We compared the networks at three different scales by using global measurements, community structure, and edge-wise comparisons within the networks. Our results reveal, at the highest voxel resolution, sets of distinct aberrant patterns for the SZ patients, and more precise local structures are provided within ROIs for further investigation. [ABSTRACT FROM AUTHOR]

Fusing complementary information from different modalities can lead to the discovery of more accurate diagnostic biomarkers for psychiatric disorders. However, biomarker discovery through data fusion is challenging since it requires extracting interpretable and reproducible patterns from data sets, consisting of shared/unshared patterns and of different orders. For example, multi-channel electroencephalography (EEG) signals from multiple subjects can be represented as a third-order tensor with modes: subject, time, and channel, while functional magnetic resonance imaging (fMRI) data may be in the form of subject by voxel matrices. Traditional data fusion methods rearrange higher-order tensors, such as EEG, as matrices to use matrix factorization-based approaches. In contrast, fusion methods based on coupled matrix and tensor factorizations (CMTF) exploit the potential multi-way structure of higher-order tensors. The CMTF approach has been shown to capture underlying patterns more accurately without imposing strong constraints on the latent neural patterns, i.e., biomarkers. In this paper, EEG, fMRI, and structural MRI (sMRI) data collected during an auditory oddball task (AOD) from a group of subjects consisting of patients with schizophrenia and healthy controls, are arranged as matrices and higher-order tensors coupled along the subject mode, and jointly analyzed using structure-revealing CMTF methods [also known as advanced CMTF (ACMTF)] focusing on unique identification of underlying patterns in the presence of shared/unshared patterns. We demonstrate that joint analysis of the EEG tensor and fMRI matrix using ACMTF reveals significant and biologically meaningful components in terms of differentiating between patients with schizophrenia and healthy controls while also providing spatial patterns with high resolution and improving the clustering performance compared to the analysis of only the EEG tensor. We also show that these patterns are reproducible, and study reproducibility for different model parameters. In comparison to the joint independent component analysis (jICA) data fusion approach, ACMTF provides easier interpretation of EEG data by revealing a single summary map of the topography for each component. Furthermore, fusion of sMRI data with EEG and fMRI through an ACMTF model provides structural patterns; however, we also show that when fusing data sets from multiple modalities, hence of very different nature, preprocessing plays a crucial role. [ABSTRACT FROM AUTHOR]

Highlights • GDMs effectively compare the results of factorization methods on real fMRI data. • IVA determines more related and discriminative networks than ICA. • ICA is more effective at emphasizing task-specific networks than IVA. Abstract Background The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. New method We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. Comparison with existing methods We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. Results Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. Conclusions These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses. [ABSTRACT FROM AUTHOR]