Group information guided ICA for fMRI data analysis

TS-AI: A deep learning pipeline for multimodal subject-specific parcellation with task contrasts synthesis

Accurate mapping of brain functional subregions at an individual level is crucial. Task-based functional MRI (tfMRI) captures subject-specific activation patterns during various functions and behaviors, facilitating the individual localization of functionally distinct subregions. However, acquiring high-quality tfMRI is time-consuming and resource-intensive in both scientific and clinical settings. The present study proposes a two-stage network model, TS-AI, to individualize an atlas on cortical surfaces through the prediction of tfMRI data. TS-AI first synthesizes a battery of task contrast maps for each individual by leveraging tract-wise anatomical connectivity and resting-state networks. These synthesized maps, along with feature maps of tract-wise anatomical connectivity and resting-state networks, are then fed into an end-to-end deep neural network to individualize an atlas. TS-AI enables the synthesized task contrast maps to be used in individual parcellation without the acquisition of actual task fMRI scans. In addition, a novel feature consistency loss is designed to assign vertices with similar features to the same parcel, which increases individual specificity and mitigates overfitting risks caused by the absence of individual parcellation ground truth. The individualized parcellations were validated by assessing test-retest reliability, homogeneity, and cognitive behavior prediction using diverse reference atlases and datasets, demonstrating the superior performance and generalizability of TS-AI. Sensitivity analysis yielded insights into region-specific features influencing individual variation in functional regionalization. Additionally, TS-AI identified accelerated shrinkage in the medial temporal and cingulate parcels during the progression of Alzheimer's disease, suggesting its potential in clinical research and applications.

4D dynamic spatial brain networks at rest linked to cognition show atypical variability and coupling in schizophrenia

Despite increasing interest in the dynamics of functional brain networks, most studies focus on the changing relationships over time between spatially static networks or regions. Here we propose an approach to study dynamic spatial brain networks in human resting state functional magnetic resonance imaging (rsfMRI) data and evaluate the temporal changes in the volumes of these 4D networks. Our results show significant volumetric coupling (i.e., synchronized shrinkage and growth) between networks during the scan, that we refer to as dynamic spatial network connectivity (dSNC). We find that several features of such dynamic spatial brain networks are associated with cognition, with higher dynamic variability in these networks and higher volumetric coupling between network pairs positively associated with cognitive performance. We show that these networks are modulated differently in individuals with schizophrenia versus typical controls, resulting in network growth or shrinkage, as well as altered focus of activity within a network. Schizophrenia also shows lower spatial dynamical variability in several networks, and lower volumetric coupling between pairs of networks, thus upholding the role of dynamic spatial brain networks in cognitive impairment seen in schizophrenia. Our data show evidence for the importance of studying the typically overlooked voxel-wise changes within and between brain networks.

A survey of brain functional network extraction methods using fMRI data

Functional network (FN) analyses play a pivotal role in uncovering insights into brain function and understanding the pathophysiology of various brain disorders. This paper focuses on classical and advanced methods for deriving brain FNs from functional magnetic resonance imaging (fMRI) data. We systematically review their foundational principles, advantages, shortcomings, and interrelations, encompassing both static and dynamic FN extraction approaches. In the context of static FN extraction, we present hypothesis-driven methods such as region of interest (ROI)-based approaches as well as data-driven methods including matrix decomposition, clustering, and deep learning. For dynamic FN extraction, both window-based and windowless methods are surveyed with respect to the estimation of time-varying FN and the subsequent computation of FN states. We also discuss the scope of application of the various methods and avenues for future improvements.

Spatial Dynamic Subspaces Encode Sex-Specific Schizophrenia Disruptions in Transient Network Overlap and Their Links to Genetic Risk

BACKGROUND

Schizophrenia research reveals sex differences in incidence, symptoms, genetic risk factors, and brain function. However, a knowledge gap remains regarding sex-specific schizophrenia alterations in brain function. Schizophrenia is considered a dysconnectivity syndrome, but the dynamic integration and segregation of brain networks are poorly understood. Recent advances in resting-state functional magnetic resonance imaging allow us to study spatial dynamics, the phenomenon of brain networks spatially evolving over time. Nevertheless, estimating time-resolved networks remains challenging due to low signal-to-noise ratio, limited short-time information, and uncertain network identification.

METHODS

We adapted a reference-informed network estimation technique to capture time-resolved networks and their dynamic spatial integration and segregation for 193 individuals with schizophrenia and 315 control participants. We focused on time-resolved spatial functional network connectivity, an estimate of network spatial coupling, to study sex-specific alterations in schizophrenia and their links to genomic data.

RESULTS

Our findings are consistent with the dysconnectivity and neurodevelopment hypotheses and with the cerebello-thalamo-cortical, triple-network, and frontoparietal dysconnectivity models, helping to unify them. The potential unification offers a new understanding of the underlying mechanisms. Notably, the posterior default mode/salience spatial functional network connectivity exhibits sex-specific schizophrenia alteration during the state with the highest global network integration and is correlated with genetic risk for schizophrenia. This dysfunction is reflected in regions with weak functional connectivity to corresponding networks.

CONCLUSIONS

Our method can effectively capture spatially dynamic networks, detect nuanced schizophrenia effects including sex-specific ones, and reveal the intricate relationship of dynamic information to genomic data. The results also underscore the clinical potential of dynamic spatial dependence and weak connectivity.

From impact to recovery: tracking mild traumatic brain injury with MRI-a pilot study and case series

Background

Diagnosis and recovery tracking of mild traumatic brain injury (mTBI) is often challenging due to the lack of clear findings on routine imaging techniques. This also complicates defining safe points for returning to activities.

Hypothesis/purpose

Quantitative susceptibility mapping (QSM) can provide information about cerebral venous oxygen saturation (CSvO2) in the context of brain injury. We tested the prediction that these imaging modalities would enable the detection of changes and recovery patterns in the brains of patients with mTBI.

Study design

In a case-control study, we recruited a cohort of 24 contact sport athletes for baseline QSM and resting-state functional MRI (rs-fMRI) scanning. Two of those who subsequently experienced head impact with significant post-injury symptoms underwent scans at 3, 7, 14 and 28 days post-injury; one had a boxing match without classical mTBI symptoms were also followed-up on.

Results

The cohort baseline QSM measurements of the straight sinus were established. The two injured athletes with post-impact symptoms consistent with mTBI had susceptibility results at days 3 and 7 post-impact that fell below the 25th percentile of the baseline values. The per cent amplitude fluctuation quantified from rs-fMRI agreed with the susceptibility trends in the straight sinus.

Conclusion

QSM holds promise as a diagnostic tool for tracking mTBI progression or recovery in contact sport head injury.

Neuroimage Analysis Methods and Artificial Intelligence Techniques for Reliable Biomarkers and Accurate Diagnosis of Schizophrenia: Achievements Made by Chinese Scholars Around the Past Decade

BACKGROUND AND HYPOTHESIS

Schizophrenia (SZ) is characterized by significant cognitive and behavioral disruptions. Neuroimaging techniques, particularly magnetic resonance imaging (MRI), have been widely utilized to investigate biomarkers of SZ, distinguish SZ from healthy conditions or other mental disorders, and explore biotypes within SZ or across SZ and other mental disorders, which aim to promote the accurate diagnosis of SZ. In China, research on SZ using MRI has grown considerably in recent years.

STUDY DESIGN

The article reviews advanced neuroimaging and artificial intelligence (AI) methods using single-modal or multimodal MRI to reveal the mechanism of SZ and promote accurate diagnosis of SZ, with a particular emphasis on the achievements made by Chinese scholars around the past decade.

STUDY RESULTS

Our article focuses on the methods for capturing subtle brain functional and structural properties from the high-dimensional MRI data, the multimodal fusion and feature selection methods for obtaining important and sparse neuroimaging features, the supervised statistical analysis and classification for distinguishing disorders, and the unsupervised clustering and semi-supervised learning methods for identifying neuroimage-based biotypes. Crucially, our article highlights the characteristics of each method and underscores the interconnections among various approaches regarding biomarker extraction and neuroimage-based diagnosis, which is beneficial not only for comprehending SZ but also for exploring other mental disorders.

CONCLUSIONS

We offer a valuable review of advanced neuroimage analysis and AI methods primarily focused on SZ research by Chinese scholars, aiming to promote the diagnosis, treatment, and prevention of SZ, as well as other mental disorders, both within China and internationally.

Time-varying phase synchronization of resting-state functional magnetic resonance imaging reveals a shift toward self-referential processes during sustained pain

ABSTRACT

Growing evidence has suggested that time-varying functional connectivity between different brain regions might underlie the dynamic experience of pain. This study used a novel, data-driven framework to characterize the dynamic interactions of large-scale brain networks during sustained pain by estimating recurrent patterns of phase-synchronization. Resting-state functional magnetic resonance imaging signals were collected from 50 healthy participants before (once) and after (twice) the onset of sustained pain that was induced by topical application of capsaicin cream. We first decoded the instantaneous phase of neural activity and then applied leading eigenvector dynamic analysis on the time-varying phase-synchronization. We identified 3 recurrent brain states that show distinctive phase-synchronization. The presence of state 1, characterized by phase-synchronization between the default mode network and auditory, visual, and sensorimotor networks, together with transitions towards this brain state, increased during sustained pain. These changes can account for the perceived pain intensity and reported unpleasantness induced by capsaicin application. In contrast, state 3, characterized by phase-synchronization between the cognitive control network and sensory networks, decreased after the onset of sustained pain. These results are indicative of a shift toward internally directed self-referential processes (state 1) and away from externally directed cognitive control processes (state 3) during sustained pain.

SMART (Splitting-Merging Assisted Reliable) Independent Component Analysis for Extracting Accurate Brain Functional Networks

Functional networks (FNs) hold significant promise in understanding brain function. Independent component analysis (ICA) has been applied in estimating FNs from functional magnetic resonance imaging (fMRI). However, determining an optimal model order for ICA remains challenging, leading to criticism about the reliability of FN estimation. Here, we propose a SMART (splitting-merging assisted reliable) ICA method that automatically extracts reliable FNs by clustering independent components (ICs) obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model orders. We extend SMART ICA to multi-subject fMRI analysis, validating its effectiveness using simulated and real fMRI data. Based on simulated data, the method accurately estimates both group-common and group-unique components and demonstrates robustness to parameters. Using two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects, the resulting reliable group-level FNs are greatly similar between the two cohorts, and interestingly the subject-specific FNs show progressive changes while age increases. Furthermore, both small-scale and large-scale brain FN templates are provided as benchmarks for future studies. Taken together, SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data, while also providing linkages between different FNs.

A Dynamic Entropy Approach Reveals Reduced Functional Network Connectivity Trajectory Complexity in Schizophrenia

Over the past decade and a half, dynamic functional imaging has revealed low-dimensional brain connectivity measures, identified potential common human spatial connectivity states, tracked the transition patterns of these states, and demonstrated meaningful transition alterations in disorders and over the course of development. Recently, researchers have begun to analyze these data from the perspective of dynamic systems and information theory in the hopes of understanding how these dynamics support less easily quantified processes, such as information processing, cortical hierarchy, and consciousness. Little attention has been paid to the effects of psychiatric disease on these measures, however. We begin to rectify this by examining the complexity of subject trajectories in state space through the lens of information theory. Specifically, we identify a basis for the dynamic functional connectivity state space and track subject trajectories through this space over the course of the scan. The dynamic complexity of these trajectories is assessed along each dimension of the proposed basis space. Using these estimates, we demonstrate that schizophrenia patients display substantially simpler trajectories than demographically matched healthy controls and that this drop in complexity concentrates along specific dimensions. We also demonstrate that entropy generation in at least one of these dimensions is linked to cognitive performance. Overall, the results suggest great value in applying dynamic systems theory to problems of neuroimaging and reveal a substantial drop in the complexity of schizophrenia patients' brain function.

A spatially constrained independent component analysis jointly informed by structural and functional network connectivity

There are a growing number of neuroimaging studies motivating joint structural and functional brain connectivity. Brain connectivity of different modalities provides insight into brain functional organization by leveraging complementary information, especially for brain disorders such as schizophrenia. In this paper, we propose a multi-modal independent component analysis (ICA) model that utilizes information from both structural and functional brain connectivity guided by spatial maps to estimate intrinsic connectivity networks (ICNs). Structural connectivity is estimated through whole-brain tractography on diffusion-weighted MRI (dMRI), while functional connectivity is derived from resting-state functional MRI (rs-fMRI). The proposed structural-functional connectivity and spatially constrained ICA (sfCICA) model estimates ICNs at the subject level using a multi-objective optimization framework. We evaluated our model using synthetic and real datasets (including dMRI and rs-fMRI from 149 schizophrenia patients and 162 controls). Multi-modal ICNs revealed enhanced functional coupling between ICNs with higher structural connectivity, improved modularity, and network distinction, particularly in schizophrenia. Statistical analysis of group differences showed more significant differences in the proposed model compared to the unimodal model. In summary, the sfCICA model showed benefits from being jointly informed by structural and functional connectivity. These findings suggest advantages in simultaneously learning effectively and enhancing connectivity estimates using structural connectivity.

Assistive tools for classifying neurological disorders using fMRI and deep learning: A guide and example

BACKGROUND

Deep-learning (DL) methods are rapidly changing the way researchers classify neurological disorders. For example, combining functional magnetic resonance imaging (fMRI) and DL has helped researchers identify functional biomarkers of neurological disorders (e.g., brain activation and connectivity) and pilot innovative diagnostic models. However, the knowledge required to perform DL analyses is often domain-specific and is not widely taught in the brain sciences (e.g., psychology, neuroscience, and cognitive science). Conversely, neurological diagnoses and neuroimaging training (e.g., fMRI) are largely restricted to the brain and medical sciences. In turn, these disciplinary knowledge barriers and distinct specializations can act as hurdles that prevent the combination of fMRI and DL pipelines. The complexity of fMRI and DL methods also hinders their clinical adoption and generalization to real-world diagnoses. For example, most current models are not designed for clinical settings or use by nonspecialized populations such as students, clinicians, and healthcare workers. Accordingly, there is a growing area of assistive tools (e.g., software and programming packages) that aim to streamline and increase the accessibility of fMRI and DL pipelines for the diagnoses of neurological disorders.

OBJECTIVES AND METHODS

In this study, we present an introductory guide to some popular DL and fMRI assistive tools. We also create an example autism spectrum disorder (ASD) classification model using assistive tools (e.g., Optuna, GIFT, and the ABIDE preprocessed repository), fMRI, and a convolutional neural network.

RESULTS

In turn, we provide researchers with a guide to assistive tools and give an example of a streamlined fMRI and DL pipeline.

CONCLUSIONS

We are confident that this study can help more researchers enter the field and create accessible fMRI and deep-learning diagnostic models for neurological disorders.

A deep learning approach for mental health quality prediction using functional network connectivity and assessment data

While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model's performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.

Neurobiology-based Cognitive Biotypes Using Multi-scale Intrinsic Connectivity Networks in Psychotic Disorders

Objective

Understanding the neurobiology of cognitive dysfunction in psychotic disorders remains elusive, as does developing effective interventions. Limited knowledge about the biological heterogeneity of cognitive dysfunction hinders progress. This study aimed to identify subgroups of patients with psychosis with distinct patterns of functional brain alterations related to cognition (cognitive biotypes).

Methods

B-SNIP consortium data (2,270 participants including participants with psychotic disorders, relatives, and controls) was analyzed. Researchers used reference-informed independent component analysis and the NeuroMark 100k multi-scale intrinsic connectivity networks (ICN) template to obtain subject-specific ICNs and whole-brain functional network connectivity (FNC). FNC features associated with cognitive performance were identified through multivariate joint analysis. K-means clustering identified subgroups of patients based on these features in a discovery set. Subgroups were further evaluated in a replication set and in relatives.

Results

Two biotypes with different functional brain alteration patterns were identified. Biotype 1 exhibited brain-wide alterations, involving hypoconnectivity in cerebellar-subcortical and somatomotor-visual networks and worse cognitive performance. Biotype 2 exhibited hyperconnectivity in somatomotor-subcortical networks and hypoconnectivity in somatomotor-high cognitive processing networks, and better preserved cognitive performance. Demographic, clinical, cognitive, and FNC characteristics of biotypes were consistent in discovery and replication sets, and in relatives. 70.12% of relatives belonged to the same biotype as their affected family members.

Conclusions

These findings suggest two distinctive psychosis-related cognitive biotypes with differing functional brain patterns shared with their relatives. Patient stratification based on these biotypes instead of traditional diagnosis may help to optimize future research and clinical trials addressing cognitive dysfunction in psychotic disorders.

A precision functional atlas of personalized network topography and probabilities

Although the general location of functional neural networks is similar across individuals, there is vast person-to-person topographic variability. To capture this, we implemented precision brain mapping functional magnetic resonance imaging methods to establish an open-source, method-flexible set of precision functional network atlases-the Masonic Institute for the Developing Brain (MIDB) Precision Brain Atlas. This atlas is an evolving resource comprising 53,273 individual-specific network maps, from more than 9,900 individuals, across ages and cohorts, including the Adolescent Brain Cognitive Development study, the Developmental Human Connectome Project and others. We also generated probabilistic network maps across multiple ages and integration zones (using a new overlapping mapping technique, Overlapping MultiNetwork Imaging). Using regions of high network invariance improved the reproducibility of executive function statistical maps in brain-wide associations compared to group average-based parcellations. Finally, we provide a potential use case for probabilistic maps for targeted neuromodulation. The atlas is expandable to alternative datasets with an online interface encouraging the scientific community to explore and contribute to understanding the human brain function more precisely.

pNet: A toolbox for personalized functional networks modeling

Personalized functional networks (FNs) derived from functional magnetic resonance imaging (fMRI) data are useful for characterizing individual variations in the brain functional topography associated with the brain development, aging, and disorders. To facilitate applications of the personalized FNs with enhanced reliability and reproducibility, we develop an open-source toolbox that is user-friendly, extendable, and includes rigorous quality control (QC), featuring multiple user interfaces (graphics, command line, and a step-by-step guideline) and job-scheduling for high performance computing (HPC) clusters. Particularly, the toolbox, named personalized functional network modeling (pNet), takes fMRI inputs in either volumetric or surface type, ensuring compatibility with multiple fMRI data formats, and computes personalized FNs using two distinct modeling methods: one method optimizes the functional coherence of FNs, while the other enhances their independence. Additionally, the toolbox provides HTML-based reports for QC and visualization of personalized FNs. The toolbox is developed in both MATLAB and Python platforms with a modular design to facilitate extension and modification by users familiar with either programming language. We have evaluated the toolbox on two fMRI datasets and demonstrated its effectiveness and user-friendliness with interactive and scripting examples. pNet is publicly available at https://github.com/MLDataAnalytics/pNet.

Searching Reproducible Brain Features using NeuroMark: Templates for Different Age Populations and Imaging Modalities

A primary challenge to the data-driven analysis is the balance between poor generalizability of population-based research and characterizing more subject-, study- and population-specific variability. We previously introduced a fully automated spatially constrained independent component analysis (ICA) framework called NeuroMark and its functional MRI (fMRI) template. NeuroMark has been successfully applied in numerous studies, identifying brain markers reproducible across datasets and disorders. The first NeuroMark template was constructed based on young adult cohorts. We recently expanded on this initiative by creating a standardized normative multi-spatial-scale functional template using over 100,000 subjects, aiming to improve generalizability and comparability across studies involving diverse cohorts. While a unified template across the lifespan is desirable, a comprehensive investigation of the similarities and differences between components from different age populations might help systematically transform our understanding of the human brain by revealing the most well-replicated and variable network features throughout the lifespan. In this work, we introduced two significant expansions of NeuroMark templates first by generating replicable fMRI templates for infants, adolescents, and aging cohorts, and second by incorporating structural MRI (sMRI) and diffusion MRI (dMRI) modalities. Specifically, we built spatiotemporal fMRI templates based on 6,000 resting-state scans from four datasets. This is the first attempt to create robust ICA templates covering dynamic brain development across the lifespan. For the sMRI and dMRI data, we used two large publicly available datasets including more than 30,000 scans to build reliable templates. We employed a spatial similarity analysis to identify replicable templates and investigate the degree to which unique and similar patterns are reflective in different age populations. Our results suggest remarkably high similarity of the resulting adapted components, even across extreme age differences. With the new templates, the NeuroMark framework allows us to perform age-specific adaptations and to capture features adaptable to each modality, therefore facilitating biomarker identification across brain disorders. In sum, the present work demonstrates the generalizability of NeuroMark templates and suggests the potential of new templates to boost accuracy in mental health research and advance our understanding of lifespan and cross-modal alterations.

Enhanced motor network engagement during reward gain anticipation in fibromyalgia

Reward motivation is essential in shaping human behavior and cognition. Both reward motivation and reward brain circuits are altered in chronic pain conditions, including fibromyalgia. In this study of fibromyalgia patients, we used a data-driven independent component analysis (ICA) approach to investigate how brain networks contribute to altered reward processing. From females with fibromyalgia (N = 24) and female healthy controls (N = 24), we acquired fMRI data while participants performed a monetary incentive delay (MID) reward task. After analyzing the task-based fMRI data using ICA to identify networks, we analyzed 3 networks of interest: motor network (left), value-driven attention network, and basal ganglia network. Then, we evaluated correlation coefficients between each network timecourse versus a task-based timecourse which modeled gain anticipation. Compared to controls, the fibromyalgia cohort demonstrated significantly stronger correlation between the left motor network timecourse and the gain anticipation timecourse, indicating the left motor network was more engaged with gain anticipation in fibromyalgia. In an exploratory analysis, we compared motor network engagement during early versus late phases of gain anticipation. Across cohorts, greater motor network engagement (i.e., stronger correlation between network and gain anticipation) occurred during the late timepoint, which reflected enhanced motor preparation immediately prior to response. Consistent with the main results, patients exhibited greater engagement of the motor network during both early and late phases compared with healthy controls. Visual-attention and basal ganglia networks revealed similar engagement in the task across groups. As indicated by post-hoc analyses, motor network engagement was positively related to anxiety and negatively related to reward responsiveness. In summary, we identified enhanced reward-task related engagement of the motor network in fibromyalgia using a novel data-driven ICA approach. Enhanced motor network engagement in fibromyalgia may relate to impaired reward motivation, heightened anxiety, and possibly to altered motor processing, such as restricted movement or dysregulated motor planning.

More reliable biomarkers and more accurate prediction for mental disorders using a label-noise filtering-based dimensional prediction method

The integration of neuroimaging with artificial intelligence is crucial for advancing the diagnosis of mental disorders. However, challenges arise from incomplete matching between diagnostic labels and neuroimaging. Here, we propose a label-noise filtering-based dimensional prediction (LAMP) method to identify reliable biomarkers and achieve accurate prediction for mental disorders. Our method proposes to utilize a label-noise filtering model to automatically filter out unclear cases from a neuroimaging perspective, and then the typical subjects whose diagnostic labels align with neuroimaging measures are used to construct a dimensional prediction model to score independent subjects. Using fMRI data of schizophrenia patients and healthy controls (n = 1,245), our method yields consistent scores to independent subjects, leading to more distinguishable relabeled groups with an enhanced classification accuracy of 31.89%. Additionally, it enables the exploration of stable abnormalities in schizophrenia. In summary, our LAMP method facilitates the identification of reliable biomarkers and accurate diagnosis of mental disorders using neuroimages.

A whole-brain neuromark resting-state fMRI analysis of first-episode and early psychosis: Evidence of aberrant cortical-subcortical-cerebellar functional circuitry

Psychosis (including symptoms of delusions, hallucinations, and disorganized conduct/speech) is a main feature of schizophrenia and is frequently present in other major psychiatric illnesses. Studies in individuals with first-episode (FEP) and early psychosis (EP) have the potential to interpret aberrant connectivity associated with psychosis during a period with minimal influence from medication and other confounds. The current study uses a data-driven whole-brain approach to examine patterns of aberrant functional network connectivity (FNC) in a multi-site dataset comprising resting-state functional magnetic resonance images (rs-fMRI) from 117 individuals with FEP or EP and 130 individuals without a psychiatric disorder, as controls. Accounting for age, sex, race, head motion, and multiple imaging sites, differences in FNC were identified between psychosis and control participants in cortical (namely the inferior frontal gyrus, superior medial frontal gyrus, postcentral gyrus, supplementary motor area, posterior cingulate cortex, and superior and middle temporal gyri), subcortical (the caudate, thalamus, subthalamus, and hippocampus), and cerebellar regions. The prominent pattern of reduced cerebellar connectivity in psychosis is especially noteworthy, as most studies focus on cortical and subcortical regions, neglecting the cerebellum. The dysconnectivity reported here may indicate disruptions in cortical-subcortical-cerebellar circuitry involved in rudimentary cognitive functions which may serve as reliable correlates of psychosis.

Modeling default mode network patterns via a universal spatio-temporal brain attention skip network

Designing a comprehensive four-dimensional resting-state functional magnetic resonance imaging (4D Rs-fMRI) based default mode network (DMN) modeling methodology to reveal the spatio-temporal patterns of individual DMN, is crucial for understanding the cognitive mechanisms of the brain and the pathogenesis of psychiatric disorders. However, there are still two limitations of existing approaches for DMN modeling. The approaches either (1) simply split the spatio-temporal components and ignore the overall character of the spatio-temporal patterns or (2) are biased in the process of feature extraction for DMN modeling, and their spatio-temporal accuracy is thus not warranted. To this end, we propose a novel Spatio-Temporal Brain Attention Skip Network (STBAS-Net) to model the personalized spatio-temporal patterns of the DMN. STBAS-Net consists of spatial and temporal components, where the multi-head attention skip connection block in the spatial component achieves detailed feature extraction and enhancement in the shallow stage. Under the guidance of spatial information, we technically fuse multiple spatio-temporal information in the temporal component, which dexterously exploits the overall spatio-temporal features and achieves mutual constraints of spatio-temporal patterns to characterize the spatio-temporal patterns of the DMN. We verify the proposed STBAS-Net on a publicly released 4D Rs-fMRI dataset and an EMCI dataset. The experimental results show that compared with existing advanced methods, the proposed network can more accurately model the personalized spatio-temporal patterns of the human brain DMN and successfully identify abnormal spatio-temporal patterns in EMCI patients. This study provides a potential tool for revealing the spatio-temporal patterns of the human brain DMN and is expected to provide an effective methodological framework for future exploration of abnormal brain spatio-temporal patterns and modeling of other functional brain networks.

Development and validation of a multimodal neuroimaging biomarker for electroconvulsive therapy outcome in depression: a multicenter machine learning analysis

BACKGROUND

Electroconvulsive therapy (ECT) is the most effective intervention for patients with treatment resistant depression. A clinical decision support tool could guide patient selection to improve the overall response rate and avoid ineffective treatments with adverse effects. Initial small-scale, monocenter studies indicate that both structural magnetic resonance imaging (sMRI) and functional MRI (fMRI) biomarkers may predict ECT outcome, but it is not known whether those results can generalize to data from other centers. The objective of this study was to develop and validate neuroimaging biomarkers for ECT outcome in a multicenter setting.

METHODS

Multimodal data (i.e. clinical, sMRI and resting-state fMRI) were collected from seven centers of the Global ECT-MRI Research Collaboration (GEMRIC). We used data from 189 depressed patients to evaluate which data modalities or combinations thereof could provide the best predictions for treatment remission (HAM-D score ⩽7) using a support vector machine classifier.

RESULTS

Remission classification using a combination of gray matter volume and functional connectivity led to good performing models with average 0.82-0.83 area under the curve (AUC) when trained and tested on samples coming from the three largest centers (N = 109), and remained acceptable when validated using leave-one-site-out cross-validation (0.70-0.73 AUC).

CONCLUSIONS

These results show that multimodal neuroimaging data can be used to predict remission with ECT for individual patients across different treatment centers, despite significant variability in clinical characteristics across centers. Future development of a clinical decision support tool applying these biomarkers may be feasible.

Intra-Atlas Node Size Effects on Graph Metrics in fMRI Data: Implications for Alzheimer's Disease and Cognitive Impairment

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.

Neuromark PET: A multivariate method for Estimating and comparing whole brain functional networks and connectomes from fMRI and PET data

Positron emission tomography (PET) and magnetic resonance imaging (MRI) are both widely used neuroimaging techniques to study brain function. Although whole brain resting functional MRI (fMRI) connectomes are widely used, the integration or association of whole brain functional connectomes with PET data are rarely done. This likely stems from the fact that PET data is typically analyzed by using a regions of interest approach, while whole brain spatial networks and their connectivity (covariation) receive much less attention. As a result, to date, there have been no direct comparisons between whole brain PET and fMRI connectomes. In this study, we present a method that uses spatially constrained independent component analysis (scICA) to estimate corresponding PET and fMRI connectomes and examine the relationship between them using mild cognitive impairment (MCI) datasets. Our results demonstrate highly modularized PET connectome patterns that complement those identified from resting fMRI. In particular, fMRI showed strong intra-domain connectivity with interdomain anticorrelation in sensorimotor and visual domains as well as default mode network. PET amyloid data showed similar strong intra-domain effects, but showed much higher correlations within cognitive control and default mode domains, as well as anticorrelation between cerebellum and other domains. The estimated PET networks have similar, but not identical, network spatial patterns to the resting fMRI networks, with the PET networks being slightly smoother and, in some cases, showing variations in subnodes. We also analyzed the differences between individuals with MCI receiving medication versus a placebo. Results show both common and modality specific treatment effects on fMRI and PET connectomes. From our fMRI analysis, we observed higher activation differences in various regions, such as the connection between the thalamus and middle occipital gyrus, as well as the insula and right middle occipital gyrus. Meanwhile, the PET analysis revealed increased activation between the anterior cingulate cortex and the left inferior parietal lobe, along with other regions, in individuals who received medication versus placebo. In sum, our novel approach identifies corresponding whole-brain PET and fMRI networks and connectomes. While we observed common patterns of network connectivity, our analysis of the MCI treatment and placebo groups revealed that each modality identifies a unique set of networks, highlighting differences between the two groups.

Dynamic fusion of genomics and functional network connectivity in UK biobank reveals static and time-varying SNP manifolds

Many psychiatric and neurological disorders show significant heritability, indicating strong genetic influence. In parallel, dynamic functional network connectivity (dFNC) measures functional temporal coupling between brain networks in a time-varying manner and has proven to identify disease-related changes in the brain. However, it remains largely unclear how genetic risk contributes to brain dysconnectivity that further manifests into clinical symptoms. The current work aimed to address this gap by proposing a novel joint ICA (jICA)-based "dynamic fusion" framework to identify dynamically tuned SNP manifolds by linking static SNPs to dynamic functional information of the brain. The sliding window approach was utilized to estimate four dFNC states and compute subject-level state-specific dFNC features. Each state of dFNC features were then combined with 12946 SZ risk SNPs for jICA decomposition, resulting in four parallel fusions in 32861 European ancestry individuals within the UK Biobank cohort. The identified joint SNP-dFNC components were further validated for SZ relevance in an aggregated SZ cohort, and compared for across-state similarity to indicate level of dynamism. The results supported that dynamic fusion yielded "static" and "dynamic" components (i.e., high and low across-state similarity, respectively) for SNP and dFNC modalities. As expected, the SNP components presented a mixture of static and dynamic manifolds, with the latter largely driven by fusion with dFNC. We also showed that some of the dynamic SNP manifolds uniquely elicited by fusion with state-specific dFNC features complemented each other in terms of biological interpretation. This dynamic fusion framework thus allows expanding the SNP modality to manifolds in the time dimension, which provides a unique lens to elicit unique SNP correlates of dFNC otherwise unseen, promising additional insights on how genetic risk links to disease-related dysconnectivity.

Multi feature fusion network for schizophrenia classification and abnormal brain network recognition

Schizophrenia classification and abnormal brain network recognition have an important research significance. Researchers have proposed many classification methods based on machine learning and deep learning. However, fewer studies utilized the advantages of complementary information from multi feature to learn the best representation of schizophrenia. In this study, we proposed a multi-feature fusion network (MFFN) using functional network connectivity (FNC) and time courses (TC) to distinguish schizophrenia patients from healthy controls. DNN backbone was adopted to learn the feature map of functional network connectivity, C-RNNAM backbone was designed to learn the feature map of time courses, and Deep SHAP was applied to obtain the most discriminative brain networks. We proved the effectiveness of this proposed model using the combining two public datasets and evaluated this model quantitatively using the evaluation indexes. The results showed that the functional network connectivity generated by independent component analysis has advantage in schizophrenia classification by comparing static and dynamic functional connections. This method obtained the best classification accuracy (ACC=87.30%, SPE=89.28%, SEN=85.71%, F1 =88.23%, and AUC=0.9081), and it demonstrated the superiority of this proposed model by comparing state-of-the-art methods. Ablation experiment also demonstrated that multi feature fusion and attention module can improve classification accuracy. The most discriminative brain networks showed that default mode network and visual network of schizophrenia patients have aberrant connections in brain networks. In conclusion, this method can identify schizophrenia effectively and visualize the abnormal brain network, and it has important clinical application value.

Longitudinal resting-state network connectivity changes in electroconvulsive therapy patients compared to healthy controls

OBJECTIVE

Electroconvulsive therapy (ECT) is effective for major depressive episodes. Understanding of underlying mechanisms has been increased by examining changes of brain connectivity but studies often do not correct for test-retest variability in healthy controls (HC). In this study, we investigated changes in resting-state networks after ECT in a multicenter study.

METHODS

Functional resting-state magnetic resonance imaging data, acquired before start and within one week after ECT, from 90 depressed patients were analyzed, as well as longitudinal data of 24 HC. Group-information guided independent component analysis (GIG-ICA) was used to spatially restrict decomposition to twelve canonical resting-state networks. Selected networks of interest were the default mode network (DMN), salience network (SN), and left and right frontoparietal network (LFPN, and RFPN). Whole-brain voxel-wise analyses were used to assess group differences at baseline, group by time interactions, and correlations with treatment effectiveness. In addition, between-network connectivity and within-network strengths were computed.

RESULTS

Within-network strength of the DMN was lower at baseline in ECT patients which increased after ECT compared to HC, after which no differences were detected. At baseline, ECT patients showed lower whole-brain voxel-wise DMN connectivity in the precuneus. Increase of within-network strength of the LFPN was correlated with treatment effectiveness. We did not find whole-brain voxel-wise or between-network changes.

CONCLUSION

DMN within-network connectivity normalized after ECT. Within-network increase of the LFPN in ECT patients was correlated with higher treatment effectiveness. In contrast to earlier studies, we found no whole-brain voxel-wise changes, which highlights the necessity to account for test-retest effects.

Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer's disease: Inter-cohort validation of Shanghai Memory Study and ADNI

Mild cognitive impairment (MCI) is a critical prodromal stage of Alzheimer's disease (AD), and the mechanism underlying the conversion is not fully explored. Construction and inter-cohort validation of imaging biomarkers for predicting MCI conversion is of great challenge at present, due to lack of longitudinal cohorts and poor reproducibility of various study-specific imaging indices. We proposed a novel framework for inter-cohort MCI conversion prediction, involving comparison of structural, static, and dynamic functional brain features from structural magnetic resonance imaging (sMRI) and resting-state functional MRI (fMRI) between MCI converters (MCI_C) and non-converters (MCI_NC), and support vector machine for construction of prediction models. A total of 218 MCI patients with 3-year follow-up outcome were selected from two independent cohorts: Shanghai Memory Study cohort for internal cross-validation, and Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for external validation. In comparison with MCI_NC, MCI_C were mainly characterized by atrophy, regional hyperactivity and inter-network hypo-connectivity, and dynamic alterations characterized by regional and connectional instability, involving medial temporal lobe (MTL), posterior parietal cortex (PPC), and occipital cortex. All imaging-based prediction models achieved an area under the curve (AUC) > 0.7 in both cohorts, with the multi-modality MRI models as the best with excellent performances of AUC > 0.85. Notably, the combination of static and dynamic fMRI resulted in overall better performance as relative to static or dynamic fMRI solely, supporting the contribution of dynamic features. This inter-cohort validation study provides a new insight into the mechanisms of MCI conversion involving brain dynamics, and paves a way for clinical use of structural and functional MRI biomarkers in future.

Identifying canonical and replicable multi-scale intrinsic connectivity networks in 100k+ resting-state fMRI datasets

Despite the known benefits of data-driven approaches, the lack of approaches for identifying functional neuroimaging patterns that capture both individual variations and inter-subject correspondence limits the clinical utility of rsfMRI and its application to single-subject analyses. Here, using rsfMRI data from over 100k individuals across private and public datasets, we identify replicable multi-spatial-scale canonical intrinsic connectivity network (ICN) templates via the use of multi-model-order independent component analysis (ICA). We also study the feasibility of estimating subject-specific ICNs via spatially constrained ICA. The results show that the subject-level ICN estimations vary as a function of the ICN itself, the data length, and the spatial resolution. In general, large-scale ICNs require less data to achieve specific levels of (within- and between-subject) spatial similarity with their templates. Importantly, increasing data length can reduce an ICN's subject-level specificity, suggesting longer scans may not always be desirable. We also find a positive linear relationship between data length and spatial smoothness (possibly due to averaging over intrinsic dynamics), suggesting studies examining optimized data length should consider spatial smoothness. Finally, consistency in spatial similarity between ICNs estimated using the full data and subsets across different data lengths suggests lower within-subject spatial similarity in shorter data is not wholly defined by lower reliability in ICN estimates, but may be an indication of meaningful brain dynamics which average out as data length increases.

dcSBM: A federated constrained source-based morphometry approach for multivariate brain structure mapping

The examination of multivariate brain morphometry patterns has gained attention in recent years, especially for their powerful exploratory capabilities in the study of differences between patients and controls. Among the many existing methods and tools for the analysis of brain anatomy based on structural magnetic resonance imaging data, data-driven source-based morphometry (SBM) focuses on the exploratory detection of such patterns. Here, we implement a semi-blind extension of SBM, called constrained source-based morphometry (constrained SBM), which enables the extraction of maximally independent reference-alike sources using the constrained independent component analysis (ICA) approach. To do this, we combine SBM with a set of reference components covering the full brain, derived from a large independent data set (UKBiobank), to provide a fully automated SBM framework. This also allows us to implement a federated version of constrained SBM (cSBM) to allow analysis of data that is not locally accessible. In our proposed decentralized constrained source-based morphometry (dcSBM), the original data never leaves the local site. Each site operates constrained ICA on its private local data using a common distributed computation platform. Next, an aggregator/master node aggregates the results estimated from each local site and applies statistical analysis to estimate the significance of the sources. Finally, we utilize two additional multisite patient data sets to validate our model by comparing the resulting group difference estimates from both cSBM and dcSBM.

Data-driven multimodal fusion: approaches and applications in psychiatric research

In the era of big data, where vast amounts of information are being generated and collected at an unprecedented rate, there is a pressing demand for innovative data-driven multi-modal fusion methods. These methods aim to integrate diverse neuroimaging perspectives to extract meaningful insights and attain a more comprehensive understanding of complex psychiatric disorders. However, analyzing each modality separately may only reveal partial insights or miss out on important correlations between different types of data. This is where data-driven multi-modal fusion techniques come into play. By combining information from multiple modalities in a synergistic manner, these methods enable us to uncover hidden patterns and relationships that would otherwise remain unnoticed. In this paper, we present an extensive overview of data-driven multimodal fusion approaches with or without prior information, with specific emphasis on canonical correlation analysis and independent component analysis. The applications of such fusion methods are wide-ranging and allow us to incorporate multiple factors such as genetics, environment, cognition, and treatment outcomes across various brain disorders. After summarizing the diverse neuropsychiatric magnetic resonance imaging fusion applications, we further discuss the emerging neuroimaging analyzing trends in big data, such as N-way multimodal fusion, deep learning approaches, and clinical translation. Overall, multimodal fusion emerges as an imperative approach providing valuable insights into the underlying neural basis of mental disorders, which can uncover subtle abnormalities or potential biomarkers that may benefit targeted treatments and personalized medical interventions.

Networks extracted from nonlinear fMRI connectivity exhibit unique spatial variation and enhanced sensitivity to differences between individuals with schizophrenia and controls

Functional magnetic resonance imaging (fMRI) studies often estimate brain intrinsic connectivity networks (ICNs) from temporal relationships between hemodynamic signals using approaches such as independent component analysis (ICA). While ICNs are thought to represent functional sources that play important roles in various psychological phenomena, current approaches have been tailored to identify ICNs that mainly reflect linear statistical relationships. However, the elements comprising neural systems often exhibit remarkably complex nonlinear interactions that may be involved in cognitive operations and altered in psychiatric conditions such as schizophrenia. Consequently, there is a need to develop methods capable of effectively capturing ICNs from measures that are sensitive to nonlinear relationships. Here, we advance a novel approach to estimate ICNs from explicitly nonlinear whole-brain functional connectivity (ENL-wFC) by transforming resting-state fMRI (rsfMRI) data into the connectivity domain, allowing us to capture unique information from distance correlation patterns that would be missed by linear whole-brain functional connectivity (LIN-wFC) analysis. Our findings provide evidence that ICNs commonly extracted from linear (LIN) relationships are also reflected in explicitly nonlinear (ENL) connectivity patterns. ENL ICN estimates exhibit higher reliability and stability, highlighting our approach's ability to effectively quantify ICNs from rsfMRI data. Additionally, we observed a consistent spatial gradient pattern between LIN and ENL ICNs with higher ENL weight in core ICN regions, suggesting that ICN function may be subserved by nonlinear processes concentrated within network centers. We also found that a uniquely identified ENL ICN distinguished individuals with schizophrenia from healthy controls while a uniquely identified LIN ICN did not, emphasizing the valuable complementary information that can be gained by incorporating measures that are sensitive to nonlinearity in future analyses. Moreover, the ENL estimates of ICNs associated with auditory, linguistic, sensorimotor, and self-referential processes exhibit heightened sensitivity towards differentiating between individuals with schizophrenia and controls compared to LIN counterparts, demonstrating the translational value of our approach and of the ENL estimates of ICNs that are frequently reported as disrupted in schizophrenia. In summary, our findings underscore the tremendous potential of connectivity domain ICA and nonlinear information in resolving complex brain phenomena and revolutionizing the landscape of clinical FC analysis.

Altered dynamic functional network connectivity and topological organization variance in patients with white matter hyperintensities

White matter hyperintensities (WMHs) of presumed vascular origin are important imaging biomarkers of cerebral small vessel disease (CSVD). Previous studies have verified abnormal functional brain networks in CSVD. However, most of these studies rely on static functional connectivity, and only a few focus on the varying severity of the WMHs. Hence, our study primarily explored the disrupted dynamic functional network connectivity (dFNC) and topological organization variance in patients with WMHs. This study included 38 patients with moderate WMHs, 47 with severe WMHs, and 68 healthy controls (HCs). Ten independent components were chosen using independent component analysis based on resting-state functional magnetic resonance imaging. The dFNC of each participant was estimated using sliding windows and k-means clustering. We identified three reproducible dFNC states. Among them, patients with WMHs had a significantly higher occurrence in the sparsely connected State 1, but a lower occurrence and shorter duration in the positive and stronger connected State 3. Regarding topological organization variance, patients with WMHs showed higher variance in local efficiency but not global efficiency compared to HCs. Among the WMH subgroups, patients with severe WMHs showed similar but more obvious alterations than those with moderate WMHs. These altered network characteristics indicated an imbalance between the functional segregation and integration of brain networks, which was correlated with global cognition, memory, executive functions, and visuospatial abilities. Our study confirmed aberrant dFNC state metrics and topological organization variance in patients with moderate-to-severe WMHs; thus, it might provide a new pathway for exploring the pathogenesis of cognitive impairment.

Detection of resting-state functional connectivity in the lumbar spinal cord with 3T MRI

Functional MRI (fMRI) of the spinal cord is an expanding area of research with potential to investigate neuronal activity in the central nervous system. We aimed to characterize the functional connectivity features of the human lumbar spinal cord using resting-state fMRI (rs-fMRI) at 3T, using region-based and data-driven analysis approaches. A 3D multi-shot gradient echo resting-state blood oxygenation level dependent-sensitive rs-fMRI protocol was implemented in 26 healthy participants. Average temporal signal-to-noise ratio in the gray matter was 16.35 ± 4.79 after denoising. Evidence of synchronous signal fluctuations in the ventral and dorsal horns with their contralateral counterparts was observed in representative participants using interactive, exploratory seed-based correlations. Group-wise average in-slice Pearson's correlations were 0.43 ± 0.17 between ventral horns, and 0.48 ± 0.16 between dorsal horns. Group spatial independent component analysis (ICA) was used to identify areas of coherent activity¸ and revealed components within the gray matter corresponding to anatomical regions. Lower-dimensionality ICA revealed bilateral components corresponding to ventral and dorsal networks. Additional separate ICAs were run on two subsets of the participant group, yielding two sets of components that showed visual consistency and moderate spatial overlap. This work shows feasibility of rs-fMRI to probe the functional features and organization of the lumbar spinal cord.

Comparative analysis of group information-guided independent component analysis and independent vector analysis for assessing brain functional network characteristics in autism spectrum disorder

Introduction

Group information-guided independent component analysis (GIG-ICA) and independent vector analysis (IVA) are two methods that improve estimation of subject-specific independent components in neuroimaging studies. These methods have shown better performance than traditional group independent component analysis (GICA) with respect to intersubject variability (ISV).

Methods

In this study, we compared the patterns of community structure, spatial variance, and prediction performance of GIG-ICA and IVA-GL, respectively. The dataset was obtained from the publicly available Autism Brain Imaging Data Exchange (ABIDE) database, comprising 75 healthy controls (HC) and 102 Autism Spectrum Disorder (ASD) participants. The greedy rule was used to match components from IVA-GL and GIG-ICA in order to compare the similarities between the two methods.

Results

Robust correspondence was observed between the two methods the following networks: cerebellum network (CRN; |r| = 0.7813), default mode network (DMN; |r| = 0.7263), self-reference network (SRN; |r| = 0.7818), ventral attention network (VAN; |r| = 0.7574), and visual network (VSN; |r| = 0.7503). Additionally, the Sensorimotor Network demonstrated the highest similarity between IVA-GL and GIG-ICA (SOM: |r| = 0.8125). Our findings revealed a significant difference in the number of modules identified by the two methods (HC: p < 0.001; ASD: p < 0.001). GIG-ICA identified significant differences in FNC between HC and ASD compared to IVA-GL. However, in correlation analysis, IVA-GL identified a statistically negative correlation between FNC of ASD and the social total subscore of the classic Autism Diagnostic Observation Schedule (ADOS: pi = -0.26, p = 0.0489). Moreover, both methods demonstrated similar prediction performances on age within specific networks, as indicated by GIG-ICA-CRN (R2 = 0.91, RMSE = 3.05) and IVA-VAN (R2 = 0.87, RMSE = 3.21).

Conclusion

In summary, IVA-GL demonstrated lower modularity, suggesting greater sensitivity in estimating networks with higher intersubject variability. The improved age prediction of cerebellar-attention networks underscores their importance in the developmental progression of ASD. Overall, IVA-GL may be appropriate for investigating disorders with greater variability, while GIG-ICA identifies functional networks with distinct modularity patterns.

Controversies and progress on standardization of large-scale brain network nomenclature

Progress in scientific disciplines is accompanied by standardization of terminology. Network neuroscience, at the level of macroscale organization of the brain, is beginning to confront the challenges associated with developing a taxonomy of its fundamental explanatory constructs. The Workgroup for HArmonized Taxonomy of NETworks (WHATNET) was formed in 2020 as an Organization for Human Brain Mapping (OHBM)-endorsed best practices committee to provide recommendations on points of consensus, identify open questions, and highlight areas of ongoing debate in the service of moving the field toward standardized reporting of network neuroscience results. The committee conducted a survey to catalog current practices in large-scale brain network nomenclature. A few well-known network names (e.g., default mode network) dominated responses to the survey, and a number of illuminating points of disagreement emerged. We summarize survey results and provide initial considerations and recommendations from the workgroup. This perspective piece includes a selective review of challenges to this enterprise, including (1) network scale, resolution, and hierarchies; (2) interindividual variability of networks; (3) dynamics and nonstationarity of networks; (4) consideration of network affiliations of subcortical structures; and (5) consideration of multimodal information. We close with minimal reporting guidelines for the cognitive and network neuroscience communities to adopt.

4D DYNAMIC SPATIAL BRAIN NETWORKS AT REST LINKED TO COGNITION SHOW ATYPICAL VARIABILITY AND COUPLING IN SCHIZOPHRENIA

Despite increasing interest in the dynamics of functional brain networks, most studies focus on the changing relationships over time between spatially static networks or regions. Here we propose an approach to study dynamic spatial brain net-works in human resting state functional magnetic resonance imaging (rsfMRI) data and evaluate the temporal changes in the volumes of these 4D networks. Our results show significant volumetric coupling (i.e., synchronized shrinkage and growth) between networks during the scan. We find that several features of such dynamic spatial brain networks are associated with cognition, with higher dynamic variability in these networks and higher volumetric coupling between network pairs positively associated with cognitive performance. We show that these networks are modulated differently in individuals with schizophrenia versus typical controls, resulting in network growth or shrinkage, as well as altered focus of activity within a network. Schizophrenia also shows lower spatial dynamical variability in several networks, and lower volumetric coupling between pairs of networks, thus upholding the role of dynamic spatial brain networks in cognitive impairment seen in schizophrenia. Our data show evidence for the importance of studying the typically overlooked voxelwise changes within and between brain networks.

Fronto-striatal dynamic connectivity is linked to dopaminergic motor response in Parkinson's disease

INTRODUCTION

Differences in dopaminergic motor response in Parkinson's disease (PD) patients can be related to PD subtypes, and previous fMRI studies associated dopaminergic motor response with corticostriatal functional connectivity. While traditional fMRI analyses have assessed the mean connectivity between regions of interest, an important aspect driving dopaminergic response might lie in the temporal dynamics in corticostriatal connections.

METHODS

This study aims to determine if altered resting-state dynamic functional network connectivity (DFC) is associated with dopaminergic motor response. To test this, static and DFC were assessed in 32 PD patients and 18 healthy controls (HC). Patients were grouped as low and high responders using a median split of their dopaminergic motor response.

RESULTS

Patients featuring a high dopaminergic motor response were observed to spend more time in a regionally integrated state compared to HC. Furthermore, DFC between the anterior midcingulate cortex/dorsal anterior cingulate cortex (aMCC/dACC) and putamen was lower in low responders during a more segregated state and correlated with dopaminergic motor response.

CONCLUSION

The findings of this study revealed that temporal dynamics of fronto-striatal connectivity are associated with clinically relevant information, which may be considered when assessing functional connectivity between regions involved in motor initiation.

Extracting functional connectivity brain networks at the resting state from pulsed arterial spin labeling data

Introduction

Functional connectivity in the brain is often studied with blood oxygenation level dependent (BOLD) resting state functional magnetic resonance imaging (rsfMRI), but the BOLD signal is several steps removed from neuronal activity. Arterial spin labeling (ASL), particularly pulsed ASL (PASL), has also the capacity to measure the blood-flow changes in response to activity. In this paper, we investigated the feasibility of extracting major brain networks from PASL data, in contrast with rsfMRI analsyis.

Materials and methods

In this retrospective study, we analyzed a cohort dataset that consists of 21 mild traumatic brain injury (mTBI) patients and 29 healthy controls, which was collected in a previous study. By extracting 10 major brain networks from the data of both PASL and rsfMRI, we contrasted their similarities and differences in the 10 networks extracted from both modalities.

Results

Our data demonstrated that PASL could be used to extract all 10 major brain networks. Eight out of 10 networks demonstrated over 60 % similarity to rsfMRI data. Meanwhile, there are similar but not identical changes in networks detected between mTBI patients and healthy controls with both modalities. Notably, the PASL-extracted default mode network (DMN), other than the rsfMRI-extracted DMN, includes some regions known to be associated with the DMN in other studies. It demonstrated that PASL data can be analyzed to identify resting state networks with reasonable reliability, even without rsfMRI data.

Conclusion

Our analysis provides an opportunity to extract functional connectivity information in heritage datasets in which ASL but not BOLD was collected.

Multi-study evaluation of neuroimaging-based prediction of medication class in mood disorders

Clinicians often face a dilemma in diagnosing bipolar disorder patients with complex symptoms who spend more time in a depressive state than a manic state. The current gold standard for such diagnosis, the Diagnostic and Statistical Manual (DSM), is not objectively grounded in pathophysiology. In such complex cases, relying solely on the DSM may result in misdiagnosis as major depressive disorder (MDD). A biologically-based classification algorithm that can accurately predict treatment response may help patients suffering from mood disorders. Here we used an algorithm to do so using neuroimaging data. We used the neuromark framework to learn a kernel function for support vector machine (SVM) on multiple feature subspaces. The neuromark framework achieves up to 95.45% accuracy, 0.90 sensitivity, and 0.92 specificity in predicting antidepressant (AD) vs. mood stabilizer (MS) response in patients. We incorporated two additional datasets to evaluate the generalizability of our approach. The trained algorithm achieved up to 89% accuracy, 0.88 sensitivity, and 0.89 specificity in predicting the DSM-based diagnosis on these datasets. We also translated the model to distinguish responders to treatment from nonresponders with up to 70% accuracy. This approach reveals multiple salient biomarkers of medication-class of response within mood disorders.

Spatial Dynamic Subspaces Encode Sex-Specific Schizophrenia Disruptions in Transient Network Overlap and its Links to Genetic Risk

Background

Recent advances in resting-state fMRI allow us to study spatial dynamics, the phenomenon of brain networks spatially evolving over time. However, most dynamic studies still use subject-specific, spatially-static nodes. As recent studies have demonstrated, incorporating time-resolved spatial properties is crucial for precise functional connectivity estimation and gaining unique insights into brain function. Nevertheless, estimating time-resolved networks poses challenges due to the low signal-to-noise ratio, limited information in short time segments, and uncertain identification of corresponding networks within and between subjects.

Methods

We adapt a reference-informed network estimation technique to capture time-resolved spatial networks and their dynamic spatial integration and segregation. We focus on time-resolved spatial functional network connectivity (spFNC), an estimate of network spatial coupling, to study sex-specific alterations in schizophrenia and their links to multi-factorial genomic data.

Results

Our findings are consistent with the dysconnectivity and neurodevelopment hypotheses and align with the cerebello-thalamo-cortical, triple-network, and frontoparietal dysconnectivity models, helping to unify them. The potential unification offers a new understanding of the underlying mechanisms. Notably, the posterior default mode/salience spFNC exhibits sex-specific schizophrenia alteration during the state with the highest global network integration and correlates with genetic risk for schizophrenia. This dysfunction is also reflected in high-dimensional (voxel-level) space in regions with weak functional connectivity to corresponding networks.

Conclusions

Our method can effectively capture spatially dynamic networks, detect nuanced SZ effects, and reveal the intricate relationship of dynamic information to genomic data. The results also underscore the potential of dynamic spatial dependence and weak connectivity in the clinical landscape.

Brain intrinsic magnetic susceptibility mapping depicts whole-brain functional connectivity balance of normal aging in lifespan

We hypothesized that brain normal aging maintains a balanced whole-brain functional connectivity (FC) in lifetime: some connections decline while other connections increase or retain, in a summation balance as a result of the cancellation of positive and negative connections. We validated this hypothesis through the use of the brain intrinsic magnetic susceptibility source (denoted by χ) as reconstructed from fMRI phase data. In implementation, we first acquired brain fMRI magnitude (m) and phase (p) data from a cohort of 245 healthy subjects in an age span of 20-60 years, then sought MRI-free brain χ source data by computationally solving an inverse mapping problem, thereby obtained triple datasets {χ, m, p} as brain images in different measurements. We performed GIG-ICA for brain function decomposition and constructed the FC matrices (χFC, mFC, pFC} (in size of 50 × 50 for a selection of 50 ICA nodes), followed by a comparative analysis on brain FC agings using {χ, m, p} data. In the results, we found that: (i) χFC aging upholds a FC balance in life span, in an intermediator between mFC and pFC agings by: mean(pFC) = -0.011 < mean(χFC) = 0.015 < mean(mFC) = 0.036; and (ii) the χFC aging exhibits a slight decline with a slightly downward fitting line in intermediation between the two slightly upward fitting lines for the mFC and pFC agings. On the rationale of the χ-depicted MRI-free brain functional state, the brain χFC aging is closer to the brain FC aging truth than the MRI-borne mFC and pFC agings.

The dynamic functional connectivity fingerprint of high-grade gliomas

Resting state fMRI has been used in many studies to investigate the impact of brain tumours on functional connectivity (FC). However, these studies have so far assumed that FC is stationary, disregarding the fact that the brain fluctuates over dynamic states. Here we utilised resting state fMRI data from 33 patients with high-grade gliomas and 33 healthy controls to examine the dynamic interplay between resting-state networks and to gain insights into the impact of brain tumours on functional dynamics. By employing Hidden Markov Models, we demonstrated that functional dynamics persist even in the presence of a high-grade glioma, and that patients exhibited a global decrease of connections strength, as well as of network segregation. Furthermore, through a multivariate analysis, we demonstrated that patients' cognitive scores are highly predictive of pathological dynamics, thus supporting our hypothesis that functional dynamics could serve as valuable biomarkers for better understanding the traits of high-grade gliomas.

Changes of creative ability and underlying brain network connectivity throughout the lifespan

Creativity, or divergent thinking, is essential to and supported by cognitive functions necessary for everyday tasks. The current study investigates divergent thinking and its neural mechanisms from adolescence to late adulthood. To do this, 180 healthy participants completed a creativity task called the egg task including 86 adolescents (mean age (SD) = 13.62 (1.98)), 52 young adults (24.92 (3.60), and 42 older adults (62.84 (7.02)). Additionally, a subsample of 111 participants completed a resting-state fMRI scan. After investigating the impact of age on different divergent thinking metrics, we investigated the impact of age on the association between divergent thinking and resting-state functional connectivity within and between major resting-state brain networks associated with creative thinking: the DMN, ECN, and SN. Adolescents tended to be less creative than both young and older adults in divergent thinking scores related to expansion creativity, and not in persistent creativity, while young and older adults performed relatively similar. We found that adolescents' functional integrity of the executive control network (ECN) was positively associated with expansion creativity, which was significantly different from the negative association in both the young and older adults. These results suggest that creative performance and supporting brain networks change throughout the lifespan.

Aging brain shows joint declines in brain within-network connectivity and between-network connectivity: a large-sample study (N > 6,000)

Introduction

Numerous studies have shown that aging has important effects on specific functional networks of the brain and leads to brain functional connectivity decline. However, no studies have addressed the effect of aging at the whole-brain level by studying both brain functional networks (i.e., within-network connectivity) and their interaction (i.e., between-network connectivity) as well as their joint changes.

Methods

In this work, based on a large sample size of neuroimaging data including 6300 healthy adults aged between 49 and 73 years from the UK Biobank project, we first use our previously proposed priori-driven independent component analysis (ICA) method, called NeuroMark, to extract the whole-brain functional networks (FNs) and the functional network connectivity (FNC) matrix. Next, we perform a two-level statistical analysis method to identify robust aging-related changes in FNs and FNCs, respectively. Finally, we propose a combined approach to explore the synergistic and paradoxical changes between FNs and FNCs.

Results

Results showed that the enhanced FNCs mainly occur between different functional domains, involving the default mode and cognitive control networks, while the reduced FNCs come from not only between different domains but also within the same domain, primarily relating to the visual network, cognitive control network, and cerebellum. Aging also greatly affects the connectivity within FNs, and the increased within-network connectivity along with aging are mainly within the sensorimotor network, while the decreased within-network connectivity significantly involves the default mode network. More importantly, many significant joint changes between FNs and FNCs involve default mode and sub-cortical networks. Furthermore, most synergistic changes are present between the FNCs with reduced amplitude and their linked FNs, and most paradoxical changes are present in the FNCs with enhanced amplitude and their linked FNs.

Discussion

In summary, our study emphasizes the diversity of brain aging and provides new evidence via novel exploratory perspectives for non-pathological aging of the whole brain.

Multi-model order spatially constrained ICA reveals highly replicable group differences and consistent predictive results from resting data: A large N fMRI schizophrenia study

Brain functional networks identified from resting functional magnetic resonance imaging (fMRI) data have the potential to reveal biomarkers for brain disorders, but studies of complex mental illnesses such as schizophrenia (SZ) often yield mixed results across replication studies. This is likely due in part to the complexity of the disorder, the short data acquisition time, and the limited ability of the approaches for brain imaging data mining. Therefore, the use of analytic approaches which can both capture individual variability while offering comparability across analyses is highly preferred. Fully blind data-driven approaches such as independent component analysis (ICA) are hard to compare across studies, and approaches that use fixed atlas-based regions can have limited sensitivity to individual sensitivity. By contrast, spatially constrained ICA (scICA) provides a hybrid, fully automated solution that can incorporate spatial network priors while also adapting to new subjects. However, scICA has thus far only been used with a single spatial scale (ICA dimensionality, i.e., ICA model order). In this work, we present an approach using multi-objective optimization scICA with reference algorithm (MOO-ICAR) to extract subject-specific intrinsic connectivity networks (ICNs) from fMRI data at multiple spatial scales, which also enables us to study interactions across spatial scales. We evaluate this approach using a large N (N > 1,600) study of schizophrenia divided into separate validation and replication sets. A multi-scale ICN template was estimated and labeled, then used as input into scICA which was computed on an individual subject level. We then performed a subsequent analysis of multiscale functional network connectivity (msFNC) to evaluate the patient data, including group differences and classification. Results showed highly consistent group differences in msFNC in regions including cerebellum, thalamus, and motor/auditory networks. Importantly, multiple msFNC pairs linking different spatial scales were implicated. The classification model built on the msFNC features obtained up to 85% F1 score, 83% precision, and 88% recall, indicating the strength of the proposed framework in detecting group differences between schizophrenia and the control group. Finally, we evaluated the relationship of the identified patterns to positive symptoms and found consistent results across datasets. The results verified the robustness of our framework in evaluating brain functional connectivity of schizophrenia at multiple spatial scales, implicated consistent and replicable brain networks, and highlighted a promising approach for leveraging resting fMRI data for brain biomarker development.

Intensive Blood Pressure Management Preserves Functional Connectivity in Patients with Hypertension from the Systolic Blood Pressure Intervention Randomized Trial

BACKGROUND AND PURPOSE

The Systolic Blood Pressure Intervention (SPRINT) randomized trial demonstrated that intensive blood pressure management resulted in slower progression of cerebral white matter hyperintensities, compared with standard therapy. We assessed longitudinal changes in brain functional connectivity to determine whether intensive treatment results in less decline in functional connectivity and how changes in brain functional connectivity relate to changes in brain structure.

MATERIALS AND METHODS

Five hundred forty-eight participants completed longitudinal brain MR imaging, including resting-state fMRI, during a median follow-up of 3.84 years. Functional brain networks were identified using independent component analysis, and a mean connectivity score was calculated for each network. Longitudinal changes in mean connectivity score were compared between treatment groups using a 2-sample t test, followed by a voxelwise t test. In the full cohort, adjusted linear regression analysis was performed between changes in the mean connectivity score and changes in structural MR imaging metrics.

RESULTS

Four hundred six participants had longitudinal imaging that passed quality control. The auditory-salience-language network demonstrated a significantly larger decline in the mean connectivity score in the standard treatment group relative to the intensive treatment group (P = .014), with regions of significant difference between treatment groups in the cingulate and right temporal/insular regions. There was no treatment group difference in other networks. Longitudinal changes in mean connectivity score of the default mode network but not the auditory-salience-language network demonstrated a significant correlation with longitudinal changes in white matter hyperintensities (P = .013).

CONCLUSIONS

Intensive treatment was associated with preservation of functional connectivity of the auditory-salience-language network, while mean network connectivity in other networks was not significantly different between intensive and standard therapy. A longitudinal increase in the white matter hyperintensity burden is associated with a decline in mean connectivity of the default mode network.

Developmental and aging resting functional magnetic resonance imaging brain state adaptations in adolescents and adults: A large N (>47K) study

The brain's functional architecture and organization undergo continual development and modification throughout adolescence. While it is well known that multiple factors govern brain maturation, the constantly evolving patterns of time-resolved functional connectivity are still unclear and understudied. We systematically evaluated over 47,000 youth and adult brains to bridge this gap, highlighting replicable time-resolved developmental and aging functional brain patterns. The largest difference between the two life stages was captured in a brain state that indicated coherent strengthening and modularization of functional coupling within the auditory, visual, and motor subdomains, supplemented by anticorrelation with other subdomains in adults. This distinctive pattern, which we replicated in independent data, was consistently less modular or absent in children and presented a negative association with age in adults, thus indicating an overall inverted U-shaped trajectory. This indicates greater synchrony, strengthening, modularization, and integration of the brain's functional connections beyond adolescence, and gradual decline of this pattern during the healthy aging process. We also found evidence that the developmental changes may also bring along a departure from the canonical static functional connectivity pattern in favor of more efficient and modularized utilization of the vast brain interconnections. State-based statistical summary measures presented robust and significant group differences that also showed significant age-related associations. The findings reported in this article support the idea of gradual developmental and aging brain state adaptation processes in different phases of life and warrant future research via lifespan studies to further authenticate the projected time-resolved brain state trajectories.

Reliability and clinical utility of spatially constrained estimates of intrinsic functional networks from very short fMRI scans

Resting-state functional network connectivity (rsFNC) has shown utility for identifying characteristic functional brain patterns in individuals with psychiatric and mood disorders, providing a promising avenue for biomarker development. However, several factors have precluded widespread clinical adoption of rsFNC diagnostics, namely a lack of standardized approaches for capturing comparable and reproducible imaging markers across individuals, as well as the disagreement on the amount of data required to robustly detect intrinsic connectivity networks (ICNs) and diagnostically relevant patterns of rsFNC at the individual subject level. Recently, spatially constrained independent component analysis (scICA) has been proposed as an automated method for extracting ICNs standardized to a chosen network template while still preserving individual variation. Leveraging the scICA methodology, which solves the former challenge of standardized neuroimaging markers, we investigate the latter challenge of identifying a minimally sufficient data length for clinical applications of resting-state fMRI (rsfMRI). Using a dataset containing rsfMRI scans of individuals with schizophrenia and controls (M = 310) as well as simulated rsfMRI, we evaluated the robustness of ICN and rsFNC estimates at both the subject- and group-level, as well as the performance of diagnostic classification, with respect to the length of the rsfMRI time course. We found individual estimates of ICNs and rsFNC from the full-length (5 min) reference time course were sufficiently approximated with just 3-3.5 min of data (r = 0.85, 0.88, respectively), and significant differences in group-average rsFNC could be sufficiently approximated with even less data, just 2 min (r = 0.86). These results from the shorter clinical data were largely consistent with the results from validation experiments using longer time series from both simulated (30 min) and real-world (14 min) datasets, in which estimates of subject-level FNC were reliably estimated with 3-5 min of data. Moreover, in the real-world data we found rsFNC and ICN estimates generated across the full range of data lengths (0.5-14 min) more reliably matched those generated from the first 5 min of scan time than those generated from the last 5 min, suggesting increased influence of "late scan" noise factors such as fatigue or drowsiness may limit the reliability of FNC from data collected after 10+ min of scan time, further supporting the notion of shorter scans. Lastly, a diagnostic classification model trained on just 2 min of data retained 97%-98% classification accuracy relative to that of the full-length reference model. Our results suggest that, when decomposed with scICA, rsfMRI scans of just 2-5 min show good clinical utility without significant loss of individual FNC information of longer scan lengths.

Understanding the heterogeneity of dynamic functional connectivity patterns in first-episode drug naïve depression using normative models

BACKGROUND

The heterogeneity of the clinical symptoms and presumptive neural pathologies has stunted progress toward identifying reproducible biomarkers and limited therapeutic interventions' effectiveness for the first episode drug-naïve major depressive disorders (FEDN-MDD). This study combined the dynamic features of fMRI data and normative modeling to quantitative and individualized metrics for delineating the biological heterogeneity of FEDN-MDD.

METHOD

Two hundred seventy-four adults with FEDN-MDD and 832 healthy controls from International Big-Data Center for Depression Research were included. Subject-specific dynamic brain networks and network fluctuation characteristics were computed for each subject using the group information-guided independent component analysis. Then, we mapped the heterogeneity of the dynamic features (network fluctuation characteristics and dynamic functional connectivity within brain networks) in the patients group via normative modeling.

RESULTS

The FEDN-MDD whose network fluctuation characteristics deviate from the normative model also showed significant differences within the default mode network, executive control network, and limbic network compared with healthy controls. Furthermore, the network fluctuation characteristics are significantly increased in patients with FEDN-MDD. About 4.74 % of the patients showed a deviation of dynamic functional connectivity, and only 3.35 % of the controls deviated from the normative model in above 100 connectivities. More patients than healthy controls showed extreme dynamic variabilities in above 100 connectivities.

CONCLUSIONS

This work evaluates the efficacy of an individualized approach based on normative modeling for understanding the heterogeneity of abnormal dynamic functional connectivity patterns in FEDN-MDD, and could be used as complementary to classical case-control comparisons.

Computing personalized brain functional networks from fMRI using self-supervised deep learning

A novel self-supervised deep learning (DL) method is developed to compute personalized brain functional networks (FNs) for characterizing brain functional neuroanatomy based on functional MRI (fMRI). Specifically, a DL model of convolutional neural networks with an encoder-decoder architecture is developed to compute personalized FNs directly from fMRI data. The DL model is trained to optimize functional homogeneity of personalized FNs without utilizing any external supervision in an end-to-end fashion. We demonstrate that a DL model trained on fMRI scans from the Human Connectome Project can identify personalized FNs and generalizes well across four different datasets. We further demonstrate that the identified personalized FNs are informative for predicting individual differences in behavior, brain development, and schizophrenia status. Taken together, the self-supervised DL allows for rapid, generalizable computation of personalized FNs.