A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear: application to schizophrenia, bipolar, and schizoaffective disorders

Morinda officinalis oligosaccharides modulate the default-mode network homogeneity in major depressive disorder at rest

BACKGROUND

While prior studies have explored the efficacy of Morinda officinalis oligosaccharides (MOs) as a treatment for patients with major depressive disorder (MDD), the mechanistic basis for the effects of MOs on brain function or the default-mode network (DMN) has yet to be characterized. The objective of this was to examine the effects of MOs treatment on functional connectivity in different regions of the DMN.

METHODS

In total, 27 MDD patients and 29 healthy control subjects (HCs) underwent resting-state functional magnetic resonance imaging. The patients were then treated with MOs for 8 weeks, and scanning was performed at baseline and the end of the 8-week treatment period. Changes in DMN homogeneity associated with MOs treatment were assessed using network homogeneity (NH) analyses of the imaging data, and pattern classification approaches were employed to determine whether abnormal baseline NH deficits could differentiate between MDD patients and controls. The ability of NH abnormalities to predict patient responses to MOs treatment was also evaluated.

RESULTS

Relative to HCs, patients exhibited a baseline reduction in NH values in the right precuneus (PCu). At the end of the 8-week treatment period, the MDD patients showed reduced and increased NH values in the right PCu and left superior medial frontal gyrus (SMFG), respectively. Compared to these patients at baseline, the 8-week MOs treatment was associated with reduced NH values in the right angular gyrus and increased NH values in the left middle temporal gyrus and the right PCu. Support vector machine (SVM) analyses revealed that NH abnormalities in the right PCu and left SMFG were the most accurate (87.50%) for differentiating between MDD patients and HCs.

CONCLUSION

These results indicated that MOs treatment could alter default-mode NH in patients with MDD. The results provide a foundation for elucidation of the effects of MOs on brain function and suggest that the distinctive NH patterns observed in this study may be useful as imaging biomarkers for distinguishing between patients with MDD and healthy subjects.

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.

The overlap across psychotic disorders: A functional network connectivity analysis

Functional network connectivity (FNC) has previously been shown to distinguish patient groups from healthy controls (HC). However, the overlap across psychiatric disorders such as schizophrenia (SZ), bipolar (BP), and schizoaffective disorder (SAD) is not evident yet. This study focuses on studying the overlap across these three psychotic disorders in both dynamic and static FNC (dFNC/sFNC). We used resting-state fMRI, demographics, and clinical information from the Bipolar-Schizophrenia Network on Intermediate Phenotypes cohort (BSNIP). The data includes three groups of patients with schizophrenia (SZ, N = 181), bipolar (BP, N = 163), and schizoaffective (SAD, N = 130) and HC (N = 238) groups. After estimating each individual's dFNC, we group them into three distinct states. We evaluated two dFNC features, including occupancy rate (OCR) and distance travelled over time. Finally, the extracted features, including both sFNC and dFNC, are tested statistically across patients and HC groups. In addition, we explored the link between the clinical scores and the extracted features. We evaluated the connectivity patterns and their overlap among SZ, BP, and SAD disorders (false discovery rate or FDR corrected p < 0.05). Results showed dFNC captured unique information about overlap across disorders where all disorder groups showed similar pattern of activity in state 2. Moreover, the results showed similar patterns between SZ and SAD in state 1 which was different than BP. Finally, the distance travelled feature of SZ (average R = 0.245, p < 0.01) and combined distance travelled from all disorders was predictive of the PANSS symptoms scores (average R = 0.147, p < 0.01).

Cognitive impairment in schizophrenia is associated with prefrontal-striatal functional hypoconnectivity and striatal dopaminergic abnormalities

BACKGROUND

A better understanding of the mechanisms underlying cognitive impairment in schizophrenia is imperative, as it causes poor functional outcomes and a lack of effective treatments.

AIMS

This study aimed to investigate the relationships of two proposed main pathophysiology of schizophrenia, altered prefrontal-striatal connectivity and the dopamine system, with cognitive impairment and their interactions.

METHODS

Thirty-three patients with schizophrenia and 27 healthy controls (HCs) who are right-handed and matched for age and sex were recruited. We evaluated their cognition, functional connectivity (FC) between the dorsolateral prefrontal cortex (DLPFC)/middle frontal gyrus (MiFG) and striatum, and the availability of striatal dopamine transporter (DAT) using a cognitive battery investigating attention, memory, and executive function, resting-state functional magnetic resonance imaging with group independent component analysis and single-photon emission computed tomography with 99mTc-TRODAT.

RESULTS

Patients with schizophrenia exhibited poorer cognitive performance, reduced FC between DLPFC/MiFG and the caudate nucleus (CN) or putamen, decreased DAT availability in the left CN, and decreased right-left DAT asymmetry in the CN compared to HCs. In patients with schizophrenia, altered imaging markers are associated with cognitive impairments, especially the relationship between DLPFC/MiFG-putamen FC and attention and between DAT asymmetry in the CN and executive function.

CONCLUSIONS

This study is the first to demonstrate how prefrontal-striatal hypoconnectivity and altered striatal DAT markers are associated with different domains of cognitive impairment in schizophrenia. More research is needed to evaluate their complex relationships and potential therapeutic implications.

Posterior default mode network is associated with the social performance in male children with autism spectrum disorder: A dynamic causal modeling analysis based on triple-network model

The triple-network model has been widely applied in neuropsychiatric disorders including autism spectrum disorder (ASD). However, the mechanism of causal regulations within the triple-network and their relations with symptoms of ASD remains unclear. 81 male ASD and 80 well matched typically developing control (TDC) were included in this study, recruited from Autism Brain Image Data Exchange-I datasets. Spatial reference-based independent component analysis was used to identify the anterior and posterior part of default-mode network (aDMN and pDMN), salience network (SN), and bilateral executive-control network (ECN) from resting-state functional magnetic resonance imaging data. Spectral dynamic causal model and parametric empirical Bayes with Bayesian model reduction/average were adopted to explore the effective connectivity (EC) within triple-network and the relationship between EC and autism diagnostic observation schedule (ADOS) scores. After adjusting for age and site effect, ASD and TDC groups both showed inhibition patterns. Compared with TDC, ASD group showed weaker self-inhibition in aDMN and pDMN, stronger inhibition in pDMN→aDMN, weaker inhibition in aDMN→LECN, pDMN→SN, LECN→SN, and LECN→RECN. Furthermore, negative relationships between ADOS scores and pDMN self-inhibition strength, as well as with the EC of pDMN→aDMN were observed in ASD group. The present study reveals imbalanced effective connections within triple-networks in ASD children. More attentions should be focused at the pDMN, which modulates the core symptoms of ASD and may serve as an important region for ASD diagnosis and the target region for ASD treatments.

Exploring functional dysconnectivity in schizophrenia: alterations in eigenvector centrality mapping and insights into related genes from transcriptional profiles

Schizophrenia is a mental health disorder characterized by functional dysconnectivity. Eigenvector centrality mapping (ECM) has been employed to investigate alterations in functional connectivity in schizophrenia, yet the results lack consistency, and the genetic mechanisms underlying these changes remain unclear. In this study, whole-brain voxel-wise ECM analyses were conducted on resting-state functional magnetic resonance imaging data. A cohort of 91 patients with schizophrenia and 91 matched healthy controls were included during the discovery stage. Additionally, in the replication stage, 153 individuals with schizophrenia and 182 healthy individuals participated. Subsequently, a comprehensive analysis was performed using an independent transcriptional database derived from six postmortem healthy adult brains to explore potential genetic factors influencing the observed functional dysconnectivity, and to investigate the roles of identified genes in neural processes and pathways. The results revealed significant and reliable alterations in the ECM across multiple brain regions in schizophrenia. Specifically, there was a significant decrease in ECM in the bilateral superior and middle temporal gyrus, and an increase in the bilateral thalamus in both the discovery and replication stages. Furthermore, transcriptional analysis revealed 420 genes whose expression patterns were related to changes in ECM, and these genes were enriched mainly in biological processes associated with synaptic signaling and transmission. Together, this study enhances our knowledge of the neural processes and pathways involved in schizophrenia, shedding light on the genetic factors that may be linked to functional dysconnectivity in this disorder.

Identifying two distinct neuroanatomical subtypes of first-episode depression using heterogeneity through discriminative analysis

BACKGROUND

Neurobiological heterogeneity in depression remains largely unknown, leading to inconsistent neuroimaging findings.

METHODS

Here, we adopted a novel proposed machine learning method ground on gray matter volumes (GMVs) to investigate neuroanatomical subtypes of first-episode treatment-naïve depression. GMVs were obtained from high-resolution T1-weighted images of 195 patients with first-episode, treatment-naïve depression and 78 matched healthy controls (HCs). Then we explored distinct subtypes of depression by employing heterogeneity through discriminative analysis (HYDRA) with regional GMVs as features.

RESULTS

Two prominently divergent subtypes of first-episode depression were identified, exhibiting opposite structural alterations compared with HCs but no different demographic features. Subtype 1 presented widespread increased GMVs mainly located in frontal, parietal, temporal cortex and partially located in limbic system. Subtype 2 presented widespread decreased GMVs mainly located in thalamus, cerebellum, limbic system and partially located in frontal, parietal, temporal cortex. Subtype 2 had smaller TIV and longer illness duration than Subtype 1. And TIV in Subtype 1 was positively correlated with age of onset while not in Subtype 2, probably implying the different potential neuropathological mechanisms.

LIMITATIONS

Despite results obtained in this study were validated by employing another brain atlas, the conclusions were acquired from a single dataset.

CONCLUSIONS

This study revealed two distinguishing neuroanatomical subtypes of first-episode depression, which provides new insights into underlying biological mechanisms of the heterogeneity in depression and might be helpful for accurate clinical diagnosis and future treatment.

Neural signatures of shared subjective affective engagement and disengagement during movie viewing

When watching a negative emotional movie, we differ from person to person in the ease with which we engage and the difficulty with which we disengage throughout a temporally evolving narrative. We investigated neural responses of emotional processing, by considering inter-individual synchronization in subjective emotional engagement and disengagement. The neural underpinnings of these shared responses are ideally studied in naturalistic scenarios like movie viewing, wherein individuals emotionally engage and disengage at their own time and pace throughout the course of a narrative. Despite the rich data that naturalistic designs can bring to the study, there is a challenge in determining time-resolved behavioral markers of subjective engagement and disengagement and their underlying neural responses. We used a within-subject cross-over design instructing 22 subjects to watch clips of either neutral or sad content while undergoing functional magnetic resonance imaging (fMRI). Participants watched the same movies a second time while continuously annotating the perceived emotional intensity, thus enabling the mapping of brain activity and emotional experience. Our analyses revealed that between-participant similarity in waxing (engagement) and waning (disengagement) of emotional intensity was directly related to the between-participant similarity in spatiotemporal patterns of brain activation during the movie(s). Similar patterns of engagement reflected common activation in the bilateral ventromedial prefrontal cortex, regions often involved in self-referenced evaluation and generation of negative emotions. Similar patterns of disengagement reflected common activation in central executive and default mode network regions often involved in top-down emotion regulation. Together this work helps to better understand cognitive and neural mechanisms underpinning engagement and disengagement from emotionally evocative narratives.

Revisiting Functional Dysconnectivity: a Review of Three Model Frameworks in Schizophrenia

PURPOSE OF REVIEW

Over the last decade, evidence suggests that a combination of behavioral and neuroimaging findings can help illuminate changes in functional dysconnectivity in schizophrenia. We review the recent connectivity literature considering several vital models, considering connectivity findings, and relationships with clinical symptoms. We reviewed resting state fMRI studies from 2017 to 2023. We summarized the role of two sets of brain networks (cerebello-thalamo-cortical (CTCC) and the triple network set) across three hypothesized models of schizophrenia etiology (neurodevelopmental, vulnerability-stress, and neurotransmitter hypotheses).

RECENT FINDINGS

The neurotransmitter and neurodevelopmental models best explained CTCC-subcortical dysfunction, which was consistently connected to symptom severity and motor symptoms. Triple network dysconnectivity was linked to deficits in executive functioning, and the salience network (SN)-default mode network dysconnectivity was tied to disordered thought and attentional deficits. This paper links behavioral symptoms of schizophrenia (symptom severity, motor, executive functioning, and attentional deficits) to various hypothesized mechanisms.

Uncovering the Neural Correlates of Anhedonia Subtypes in Major Depressive Disorder: Implications for Intervention Strategies

Major depressive disorder (MDD) represents a serious public health concern, negatively affecting individuals' quality of life and making a substantial contribution to the global burden of disease. Anhedonia is a core symptom of MDD and is associated with poor treatment outcomes. Variability in anhedonia components within MDD has been observed, suggesting heterogeneity in psychopathology across subgroups. However, little is known about anhedonia subgroups in MDD and their underlying neural correlates across subgroups. To address this question, we employed a hierarchical cluster analysis based on Temporal Experience of Pleasure Scale subscales in 60 first-episode, drug-naive MDD patients and 32 healthy controls. Then we conducted a connectome-wide association study and whole-brain voxel-wise functional analyses for identified subgroups. There were three main findings: (1) three subgroups with different anhedonia profiles were identified using a data mining approach; (2) several parts of the reward network (especially pallidum and dorsal striatum) were associated with anticipatory and consummatory pleasure; (3) different patterns of within- and between-network connectivity contributed to the disparities of anhedonia profiles across three MDD subgroups. Here, we show that anhedonia in MDD is not uniform and can be categorized into distinct subgroups, and our research contributes to the understanding of neural underpinnings, offering potential treatment directions. This work emphasizes the need for tailored approaches in the complex landscape of MDD. The identification of homogeneous, stable, and neurobiologically valid MDD subtypes could significantly enhance our comprehension and management of this multifaceted condition.

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.

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.

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.

Prediction of suicidality in bipolar disorder using variability of intrinsic brain activity and machine learning

Bipolar disorder (BD) is associated with marked suicidal susceptibility, particularly during a major depressive episode. However, the evaluation of suicidal risk remains challenging since it relies mainly on self-reported information from patients. Hence, it is necessary to complement neuroimaging features with advanced machine learning techniques in order to predict suicidal behavior in BD patients. In this study, a total of 288 participants, including 75 BD suicide attempters, 101 BD nonattempters and 112 healthy controls, underwent a resting-state functional magnetic resonance imaging (rs-fMRI). Intrinsic brain activity was measured by amplitude of low-frequency fluctuation (ALFF). We trained and tested a two-level k-nearest neighbors (k-NN) model based on resting-state variability of ALFF with fivefold cross-validation. BD suicide attempters had increased dynamic ALFF values in the right anterior cingulate cortex, left thalamus and right precuneus. Compared to other machine learning methods, our proposed framework had a promising performance with 83.52% accuracy, 78.75% sensitivity and 87.50% specificity. The trained models could also replicate and validate the results in an independent cohort with 72.72% accuracy. These findings based on a relatively large data set, provide a promising way of combining fMRI data with machine learning technique to reliably predict suicide attempt at an individual level in bipolar depression. Overall, this work might enhance our understanding of the neurobiology of suicidal behavior by detecting clinically defined disruptions in the dynamics of instinct brain activity.

Aberrant global and local dynamic properties in schizophrenia with instantaneous phase method based on Hilbert transform

BACKGROUND

Emerging functional imaging studies suggest that schizophrenia is associated with aberrant spatiotemporal interaction which may result in aberrant global and local dynamic properties.

METHODS

We investigated the dynamic functional connectivity (FC) by using instantaneous phase method based on Hilbert transform to detect abnormal spatiotemporal interaction in schizophrenia. Based on resting-state functional magnetic resonance imaging, two independent datasets were included, with 114 subjects from COBRE [51 schizophrenia patients (SZ) and 63 healthy controls (HCs)] and 96 from OpenfMRI (36 SZ and 60 HCs). Phase differences and instantaneous coupling matrices were firstly calculated at all time points by extracting instantaneous parameters. Global [global synchrony and intertemporal closeness (ITC)] and local dynamic features [strength of FC (sFC) and variability of FC (vFC)] were compared between two groups. Support vector machine (SVM) was used to estimate the ability to discriminate two groups by using all aberrant features.

RESULTS

We found SZ had lower global synchrony and ITC than HCs on both datasets. Furthermore, SZ had a significant decrease in sFC but an increase in vFC, which were mainly located at prefrontal cortex, anterior cingulate cortex, temporal cortex and visual cortex or temporal cortex and hippocampus, forming significant dynamic subnetworks. SVM analysis revealed a high degree of balanced accuracy (85.75%) on the basis of all aberrant dynamic features.

CONCLUSIONS

SZ has worse overall spatiotemporal stability and extensive FC subnetwork lesions compared to HCs, which to some extent elucidates the pathophysiological mechanism of schizophrenia, providing insight into time-variation properties of patients with other mental illnesses.

Applications of generative adversarial networks in neuroimaging and clinical neuroscience

Generative adversarial networks (GANs) are one powerful type of deep learning models that have been successfully utilized in numerous fields. They belong to the broader family of generative methods, which learn to generate realistic data with a probabilistic model by learning distributions from real samples. In the clinical context, GANs have shown enhanced capabilities in capturing spatially complex, nonlinear, and potentially subtle disease effects compared to traditional generative methods. This review critically appraises the existing literature on the applications of GANs in imaging studies of various neurological conditions, including Alzheimer's disease, brain tumors, brain aging, and multiple sclerosis. We provide an intuitive explanation of various GAN methods for each application and further discuss the main challenges, open questions, and promising future directions of leveraging GANs in neuroimaging. We aim to bridge the gap between advanced deep learning methods and neurology research by highlighting how GANs can be leveraged to support clinical decision making and contribute to a better understanding of the structural and functional patterns of brain diseases.

IABC: A Toolbox for Intelligent Analysis of Brain Connectivity

Brain functional networks and connectivity have played an important role in exploring brain function for understanding the brain and disclosing the mechanisms of brain disorders. Independent component analysis (ICA) is one of the most widely applied data-driven methods to extract brain functional networks/connectivity. However, it is hard to guarantee the reliability of networks/connectivity due to the randomness of component order and the difficulty in selecting an optimal component number in ICA. To facilitate the analysis of brain functional networks and connectivity using ICA, we developed a MATLAB toolbox called Intelligent Analysis of Brain Connectivity (IABC). IABC incorporates our previously proposed group information guided independent component analysis (GIG-ICA), NeuroMark, and splitting-merging assisted reliable ICA (SMART ICA) methods, which can estimate reliable individual-subject neuroimaging measures for further analysis. After user inputs functional magnetic resonance imaging (fMRI) data of multiple subjects that are regularly organized (e.g., in Brain Imaging Data Structure (BIDS)) and clicks a few buttons to set parameters, IABC automatically outputs brain functional networks, their related time courses, and functional network connectivity of each subject. All these neuroimaging measures are promising for providing clues in understanding brain function and differentiating brain disorders.

Psychotic Symptom, Mood, and Cognition-associated Multimodal MRI Reveal Shared Links to the Salience Network Within the Psychosis Spectrum Disorders

Schizophrenia (SZ), schizoaffective disorder (SAD), and psychotic bipolar disorder share substantial overlap in clinical phenotypes, associated brain abnormalities and risk genes, making reliable diagnosis among the three illness challenging, especially in the absence of distinguishing biomarkers. This investigation aims to identify multimodal brain networks related to psychotic symptom, mood, and cognition through reference-guided fusion to discriminate among SZ, SAD, and BP. Psychotic symptom, mood, and cognition were used as references to supervise functional and structural magnetic resonance imaging (MRI) fusion to identify multimodal brain networks for SZ, SAD, and BP individually. These features were then used to assess the ability in discriminating among SZ, SAD, and BP. We observed shared links to functional and structural covariation in prefrontal, medial temporal, anterior cingulate, and insular cortices among SZ, SAD, and BP, although they were linked with different clinical domains. The salience (SAN), default mode (DMN), and fronto-limbic (FLN) networks were the three identified multimodal MRI features within the psychosis spectrum disorders from psychotic symptom, mood, and cognition associations. In addition, using these networks, we can classify patients and controls and distinguish among SZ, SAD, and BP, including their first-degree relatives. The identified multimodal SAN may be informative regarding neural mechanisms of comorbidity for psychosis spectrum disorders, along with DMN and FLN may serve as potential biomarkers in discriminating among SZ, SAD, and BP, which may help investigators better understand the underlying mechanisms of psychotic comorbidity from three different disorders via a multimodal neuroimaging perspective.

Exploring the Hypothesis of a Schizophrenia and Bipolar Disorder Continuum: Biological, Genetic and Pharmacologic Data

Present time nosology has its roots in Kraepelin's demarcation of schizophrenia and bipolar disorder. However, accumulating evidence has shed light on several commonalities between the two disorders, and some authors have advocated for the consideration of a disease continuum. Here, we review previous genetic, biological and pharmacological findings that provide the basis for this conceptualization. There is a cross-disease heritability, and they share single-nucleotide polymorphisms in some common genes. EEG and imaging patterns have a number of similarities, namely reduced white matter integrity and abnormal connectivity. Dopamine, serotonin, GABA and glutamate systems have dysfunctional features, some of which are identical among the disorders. Finally, cellular calcium regulation and mitochondrial function are, also, impaired in the two.

Mouse Brain MRI: Including In Vivo, Ex Vivo, and fcMRI for the Study of Microcephaly

With its sensitivity to soft tissue, MRI is a powerful tool for the study of the neuroanatomical manifestations of a variety of conditions, such as microcephaly-related morbidities that are not easily visualized by other imaging techniques, such as CT. In addition to structural imaging, more recently, researchers have found changes in brain function in a wide range of neurological conditions-highlighting the utility of MRI for the study of microcephaly.In this methods chapter, basic mouse preparation and the acquisition of data for in vivo anatomical MRI will be discussed. Additionally, we will provide our protocol for the perfusion and fixation of brain tissue with gadolinium contrast agent. Following that, the process of optimization of system parameters will be shown for anatomical imaging of in vivo and ex vivo brain tissue. Lastly, the chapter will detail a protocol for fcMRI along with a discussion of considerations specific to functional imaging.

Altered spatio-temporal state patterns for functional dynamics estimation in first-episode drug-naive major depression

Patients with major depressive disorder (MDD) display affective and cognitive impairments. Although MDD-associated abnormalities of brain function and structure have been explored in depth, the relationships between MDD and spatio-temporal large-scale functional networks have not been evaluated in large-sample datasets. We employed data from International Big-Data Center for Depression Research (IBCDR), and comparable 543 healthy controls (HC) and 314 first-episode drug-naive (FEDN) MDD patients were included. We used a multivariate pattern classification method to learn informative spatio-temporal functional states. Brain states of each participant were extracted for functional dynamic estimation using an independent component analysis. Then, a multi-kernel pattern classification method was developed to identify discriminative spatio-temporal states associated with FEDN MDD. Finally, statistical analysis was applied to intrinsic and clinical brain characteristics. Compared with HC, FEDN MDD patients exhibited altered spatio-temporal functional states of the default mode network (DMN), the salience network, a hub network (centered on the dorsolateral prefrontal cortex), and a relatively complex coupling network (visual, DMN, motor-somatosensory and subcortical networks). Multi-kernel classification models to distinguish patients from HC obtained areas under the receiver operating characteristic curves up to 0.80. Classification scores correlated with Hamilton Depression Rating Scale scores and age at MDD onset. FEDN MDD patients had multiple abnormal spatio-temporal functional states. Classification scores derived from these states were related to symptom severity. The assessment of spatio-temporal states may represent a powerful clinical and research tool to distinguish between neuropsychiatric patients and controls.

Neuroanatomical subtypes of schizophrenia and relationship with illness duration and deficit status

BACKGROUND

The heterogeneity of schizophrenia (SCZ) regarding psychopathology, illness trajectory and their inter-relationships with underlying neural substrates remain incompletely understood. In a bid to reduce illness heterogeneity using neural substrates, our study aimed to replicate the findings of an earlier study by Chand et al. (2020). We employed brain structural measures for subtyping SCZ patients, and evaluate each subtype's relationship with clinical features such as illness duration, psychotic psychopathology, and additionally deficit status.

METHODS

Overall, 240 subjects (160 SCZ patients, 80 healthy controls) were recruited for this study. The participants underwent brain structural magnetic resonance imaging scans and clinical rating using the Positive and Negative Syndrome Scale. Neuroanatomical subtypes of SCZ were identified using "Heterogeneity through discriminative analysis" (HYDRA), a clustering technique which accounted for relevant covariates and the inter-group normalized percentage changes in brain volume were also calculated.

RESULTS

As replicated, two neuroanatomical subtypes (SG-1 and SG-2) were found amongst our patients with SCZ. The subtype SG-1 was associated with enlargements in the third and lateral ventricles, volume increase in the basal ganglia (putamen, caudate, pallidum), longer illness duration, and deficit status. The subtype SG-2 was associated with reductions of cortical and subcortical structures (hippocampus, thalamus, basal ganglia).

CONCLUSIONS

These replicated findings have clinical implications in the early intervention, response monitoring, and prognostication of SCZ. Future studies may adopt a multi-modal neuroimaging approach to enhance insights into the neurobiological composition of relevant subtypes.

Decentralized Brain Age Estimation Using MRI Data

Recent studies have demonstrated that neuroimaging data can be used to estimate biological brain age, as it captures information about the neuroanatomical and functional changes the brain undergoes during development and the aging process. However, researchers often have limited access to neuroimaging data because of its challenging and expensive acquisition process, thereby limiting the effectiveness of the predictive model. Decentralized models provide a way to build more accurate and generalizable prediction models, bypassing the traditional data-sharing methodology. In this work, we propose a decentralized method for biological brain age estimation using support vector regression models and evaluate it on three different feature sets, including both volumetric and voxelwise structural MRI data as well as resting functional MRI data. The results demonstrate that our decentralized brain age regression models can achieve similar performance compared to the models trained with all the data in one location.

A new multimodality fusion classification approach to explore the uniqueness of schizophrenia and autism spectrum disorder

Schizophrenia (SZ) and autism spectrum disorder (ASD) sharing overlapping symptoms have a long history of diagnostic confusion. It is unclear what their differences at a brain level are. Here, we propose a multimodality fusion classification approach to investigate their divergence in brain function and structure. Using brain functional network connectivity (FNC) calculated from resting-state fMRI data and gray matter volume (GMV) estimated from sMRI data, we classify the two disorders using the main data (335 SZ and 380 ASD patients) via an unbiased 10-fold cross-validation pipeline, and also validate the classification generalization ability on an independent cohort (120 SZ and 349 ASD patients). The classification accuracy reached up to 83.08% for the testing data and 72.10% for the independent data, significantly better than the results from using the single-modality features. The discriminative FNCs that were automatically selected primarily involved the sub-cortical, default mode, and visual domains. Interestingly, all discriminative FNCs relating to the default mode network showed an intermediate strength in healthy controls (HCs) between SZ and ASD patients. Their GMV differences were mainly driven by the frontal gyrus, temporal gyrus, and insula. Regarding these regions, the mean GMV of HC fell intermediate between that of SZ and ASD, and ASD showed the highest GMV. The middle frontal gyrus was associated with both functional and structural differences. In summary, our work reveals the unique neuroimaging characteristics of SZ and ASD that can achieve high and generalizable classification accuracy, supporting their potential as disorder-specific neural substrates of the two entwined disorders.

Comparing the Effectiveness of Brain Structural Imaging, Resting-state fMRI, and Naturalistic fMRI in Recognizing Social Anxiety Disorder in Children and Adolescents

Social anxiety disorder (SAD) is a common anxiety disorder in childhood and adolescence. Studies on SAD in adults have reported both structural and functional aberrancies of the brain at the group level. However, evidence has shown differences in anxiety-related brain abnormalities between adolescents and adults. Since children and adolescents can afford limited scan time, optimizing the scan tasks is essential for SAD research in children and adolescents. Thus, we need to address whether brain structure, resting-state fMRI, and naturalistic imaging enable individualized identification of SAD in children and adolescents, which measurement is more effective, and whether pooling multi-modal features can improve the identification of SAD. We comprehensively addressed these questions by building machine learning models based on parcel-wise brain features. We found that naturalistic fMRI yielded higher classification accuracy (69.17%) than the other modalities and the classification performance showed dependence on the contents of the movie. The classification models also identified contributing brain regions, some of which exhibited correlations with the symptoms scores of SAD. However, pooling brain features from the three modalities did not help enhance the classification accuracy. These results support the application of carefully designed naturalistic imaging in recognizing children and adolescents at risk of SAD.

SSPNet: An interpretable 3D-CNN for classification of schizophrenia using phase maps of resting-state complex-valued fMRI data

Convolutional neural networks (CNNs) have shown promising results in classifying individuals with mental disorders such as schizophrenia using resting-state fMRI data. However, complex-valued fMRI data is rarely used since additional phase data introduces high-level noise though it is potentially useful information for the context of classification. As such, we propose to use spatial source phase (SSP) maps derived from complex-valued fMRI data as the CNN input. The SSP maps are not only less noisy, but also more sensitive to spatial activation changes caused by mental disorders than magnitude maps. We build a 3D-CNN framework with two convolutional layers (named SSPNet) to fully explore the 3D structure and voxel-level relationships from the SSP maps. Two interpretability modules, consisting of saliency map generation and gradient-weighted class activation mapping (Grad-CAM), are incorporated into the well-trained SSPNet to provide additional information helpful for understanding the output. Experimental results from classifying schizophrenia patients (SZs) and healthy controls (HCs) show that the proposed SSPNet significantly improved accuracy and AUC compared to CNN using magnitude maps extracted from either magnitude-only (by 23.4 and 23.6% for DMN) or complex-valued fMRI data (by 10.6 and 5.8% for DMN). SSPNet captured more prominent HC-SZ differences in saliency maps, and Grad-CAM localized all contributing brain regions with opposite strengths for HCs and SZs within SSP maps. These results indicate the potential of SSPNet as a sensitive tool that may be useful for the development of brain-based biomarkers of mental disorders.

Mapping relationships among schizophrenia, bipolar and schizoaffective disorders: A deep classification and clustering framework using fMRI time series

BACKGROUND

Psychiatric disorders are categorized using self-report and observational information rather than biological data. There is also considerable symptomatic overlap between different types of psychiatric disorders, which makes diagnostic categorization and multi-class classification challenging.

METHODS

In this work, we propose a unified framework for supervised classification and unsupervised clustering of psychotic disorders using brain imaging data. A new multi-scale recurrent neural network (MsRNN) model was developed and applied to fMRI time courses (TCs) for multi-class classification. The high-level representations of the original TCs were then submitted to a tSNE clustering model for visualizing the group differences between disorders. A leave-one-feature-out approach was used for disorder-related biomarker identification.

RESULTS

When studying fMRI from schizophrenia, psychotic bipolar disorder, schizoaffective disorder, and healthy individuals, the accuracy of a 4-class classification reached 46%, significantly above chance. The hippocampus, supplementary motor area and paracentral lobule were discovered as the most contributing regional TCs in the multi-class classification. Beyond this, visualization of the tSNE clustering suggested that the disease severity can be captured and schizoaffective disorder (SAD) may be separated into two subtypes. SAD cluster1 has significantly higher Positive And Negative Syndrome Scale (PANSS) scores than SAD cluster2 in PANSS negative2 (emotional withdrawal), general2 (anxiety), general3 (guilt feelings), general4 (tension).

CONCLUSIONS

The proposed deep classification and clustering framework is not only able to identify psychiatric disorders with high accuracy, but also interpret the correlation between brain networks and specific psychiatric disorders, and reveal the relationship between them. This work provides a promising way to investigate a spectrum of similar disorders using neuroimaging-based measures.

Moving beyond the 'CAP' of the Iceberg: Intrinsic connectivity networks in fMRI are continuously engaging and overlapping

Resting-state functional magnetic resonance imaging is currently the mainstay of functional neuroimaging and has allowed researchers to identify intrinsic connectivity networks (aka functional networks) at different spatial scales. However, little is known about the temporal profiles of these networks and whether it is best to model them as continuous phenomena in both space and time or, rather, as a set of temporally discrete events. Both categories have been supported by series of studies with promising findings. However, a critical question is whether focusing only on time points presumed to contain isolated neural events and disregarding the rest of the data is missing important information, potentially leading to misleading conclusions. In this work, we argue that brain networks identified within the spontaneous blood oxygenation level-dependent (BOLD) signal are not limited to temporally sparse burst moments and that these event present time points (EPTs) contain valuable but incomplete information about the underlying functional patterns. We focus on the default mode and show evidence that is consistent with its continuous presence in the BOLD signal, including during the event absent time points (EATs), i.e., time points that exhibit minimum activity and are the least likely to contain an event. Moreover, our findings suggest that EPTs may not contain all the available information about their corresponding networks. We observe distinct default mode connectivity patterns obtained from all time points (AllTPs), EPTs, and EATs. We show evidence of robust relationships with schizophrenia symptoms that are both common and unique to each of the sets of time points (AllTPs, EPTs, EATs), likely related to transient patterns of connectivity. Together, these findings indicate the importance of leveraging the full temporal data in functional studies, including those using event-detection approaches.

Abnormal Default Mode Network Homogeneity in Major Depressive Disorder With Gastrointestinal Symptoms at Rest

Background

Gastrointestinal (GI) symptoms are prominent in many patients with major depressive disorder (MDD). However, it remains unclear whether MDD patients with GI symptoms have brain imaging alterations in the default mode network (DMN) regions.

Methods

A total of 35 MDD patients with GI symptoms, 17 MDD patients without GI symptoms, and 28 healthy controls (HCs) were recruited. All participants underwent resting-state functional magnetic resonance imaging scans. Network homogeneity (NH) and support vector machine (SVM) methods were used to analyze the imaging data.

Results

Gastrointestinal group showed higher 17-item Hamilton Rating Scale for Depression total scores and factor scores than the non-GI group. Compared with the non-GI group and HCs, the GI group showed decreased NH in the right middle temporal gyrus (MTG) and increased NH in the right precuneus (PCu). The SVM results showed that a combination of NH values of the right PCu and the right MTG exhibited the highest accuracy of 88.46% (46/52) to discriminate MDD patients with GI symptoms from those without GI symptoms.

Conclusion

Major depressive disorder patients with GI symptoms have more severe depressive symptoms than those without GI symptoms. Distinctive NH patterns in the DMN exist in MDD patients with GI symptoms, which can be applied as a potential brain imaging marker to discriminate MDD patients with GI symptoms from those without GI symptoms.

Effect of Impaired Stereoscopic Vision on Large-Scale Resting-State Functional Network Connectivity in Comitant Exotropia Patients

Background

Comitant exotropia (CE) is a common eye movement disorder, characterized by impaired eye movements and stereoscopic vision. CE patients reportedly exhibit changes in the central nervous system. However, it remains unclear whether large-scale brain network changes occur in CE patients.

Purpose

This study investigated the effects of exotropia and stereoscopic vision dysfunction on large-scale brain networks in CE patients via independent component analysis (ICA).

Methods

Twenty-eight CE patients (mean age, 15.80 ± 2.46 years) and 27 healthy controls (HCs; mean age, 16.00 ± 2.68 years; closely matched for age, sex, and education) underwent resting-state magnetic resonance imaging. ICA was applied to extract resting-state networks (RSNs) in both groups. Two-sample’s t-tests were conducted to investigate intranetwork functional connectivity (FC) within RSNs and interactions among RSNs between the two groups.

Results

Compared with the HC group, the CE group showed increased intranetwork FC in the bilateral postcentral gyrus of the sensorimotor network (SMN). The CE group also showed decreased intranetwork FC in the right cerebellum_8 of the cerebellum network (CER), the right superior temporal gyrus of the auditory network (AN), and the right middle occipital gyrus of the visual network (VN). Moreover, functional network connectivity (FNC) analysis showed that CER-AN, SMN-VN, SN-DMN, and DMN-VN connections were significantly altered between the two groups.

Conclusion

Comitant exotropia patients had abnormal brain networks related to the CER, SMN, AN, and VN. Our results offer important insights into the neural mechanisms of eye movements and stereoscopic vision dysfunction in CE patients.

Specific brain network predictors of interventions with different mechanisms for tinnitus patients

BACKGROUND

The aberrant brain network that gives rise to the phantom sound of tinnitus is believed to determine the effectiveness of tinnitus therapies involving neuromodulation with repetitive transcranial magnetic stimulation (rTMS) and sound therapy utilizing tailor-made notch music training (TMNMT). To test this hypothesis, we determined how effective rTMS or TMNMT were in ameliorating tinnitus in patients with different functional brain networks.

METHODS

Resting-state functional MRI was used to construct brain functional networks in patients with tinnitus (41 males/45 females, mean age 49.53±11.19 years) and gender-matched healthy controls (22 males/35 females, mean age 46.23±10.23 years) with independent component analysis (ICA). A 2 × 2 analysis of variance with treatment outcomes (Effective group, EG/Ineffective group, IG) and treatment types (rTMS/TMNMT) was used to test the interaction between outcomes and treatment types associated with functional network connections (FNCs).

FINDINGS

The optimal neuroimaging indicator for responding to rTMS (AUC 0.804, sensitivity 0.700, specificity 0.913) was FNCs in the salience network-right frontoparietal network (SN-RFPN) while for responding to TMNMT (AUC 0.764, sensitivity 0.864, specificity 0.667) was the combination of FNCs in the auditory network- salience network (AUN-SN) and auditory network-cerebellar network (AUN-CN).

INTERPRETATION

Tinnitus patients with higher FNCs in the SN-RFPN is associated with a recommendation for rTMS whereas patients with lower FNCs in the AUN-SN and AUN-CN would suggest TMNMT as the better choice. These results indicate that brain network-based measures aid in the selection of the optimal form of treatment for a patient contributing to advances in precision medicine.

FUNDING

Yuexin Cai is supported by Key R&D Program of Guangdong Province, China (Grant No. 2018B030339001), National Natural Science Foundation of China (82071062), Natural Science Foundation of Guangdong province (2021A1515012038), the Fundamental Research Funds for the Central Universities (20ykpy91), and Sun Yat-Sen Clinical Research Cultivating Program (SYS-Q-201903). Yu-Chen Chen is supported by Medical Science and Technology Development Foundation of Nanjing Department of Health (No. ZKX20037), and Natural Science Foundation of Jiangsu Province (No. BK20211008).

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Default mode network shows alterations for low-frequency fMRI fluctuations in euthymic bipolar disorder

Bipolar disorder (BD) is a psychiatric condition causing acute dysfunctional mood states and emotion regulation. Specific neuropsychological features are often present also among patients in euthymic phase, who do not show clear psychotic symptoms, and for whom the characterization from functional magnetic resonance imaging (fMRI) is very limited. This study aims at identifying the neural and behavioral correlates of the default mode network (DMN) using the fractional amplitude of low frequency fluctuations (fALFF). Eighteen euthymic BD patients (10 females; age = 54.50 ± 11.38 years) and sixteen healthy controls (HC) (8 females; age = 51.16 ± 11.44 years) underwent a 1.5T fMRI scan at rest. The DMN was extracted through independent component analysis. Then, DMN time series was used to compute the fALFF, which was correlated with clinical scales. From the between-group comparison, no significant differences emerged in correspondence to regions belonging to the DMN. For fALFF analysis, we reported significant increase of low-frequency fluctuations for lower frequencies, and decreases for higher frequencies compared to HC. Correlations with clinical scales showed that an increase in higher frequency spectral content was associated with lower levels of mania and higher levels of anxious symptoms, while an increase in lower frequencies was linked to lower depressive symptoms. Starting from our findings on the DMN in euthymic BD patients, we suggest that the fALFF derived from network time series represents a viable approach to investigate the behavioral correlates of resting state networks, and the pathophysiological mechanisms of different psychiatric conditions.

Dissemination in time and space in presymptomatic granulin mutation carriers: a GENFI spatial chronnectome study

The presymptomatic brain changes of granulin (GRN) disease, preceding by years frontotemporal dementia, has not been fully characterized. New approaches focus on the spatial chronnectome can capture both spatial network configurations and their dynamic changes over time. To investigate the spatial dynamics in 141 presymptomatic GRN mutation carriers and 282 noncarriers from the Genetic Frontotemporal dementia research Initiative cohort. We considered time-varying patterns of the default mode network, the language network, and the salience network, each summarized into 4 distinct recurring spatial configurations. Dwell time (DT) (the time each individual spends in each spatial state of each network), fractional occupacy (FO) (the total percentage of time spent by each individual in a state of a specific network) and total transition number (the total number of transitions performed by each individual in a specifict state) were considered. Correlations between DT, FO, and transition number and estimated years from expected symptom onset (EYO) and clinical performances were assessed. Presymptomatic GRN mutation carriers spent significantly more time in those spatial states characterised by greater activation of the insula and the parietal cortices, as compared to noncarriers (p < 0.05, FDR-corrected). A significant correlation between DT and FO of these spatial states and EYO was found, the longer the time spent in the spatial states, the closer the EYO. DT and FO significantly correlated with performances at tests tapping processing speed, with worse scores associated with increased spatial states' DT. Our results demonstrated that presymptomatic GRN disease presents a complex dynamic reorganization of brain connectivity. Change in both the spatial and temporal aspects of brain network connectivity could provide a unique glimpse into brain function and potentially allowing a more sophisticated evaluation of the earliest disease changes and the understanding of possible mechanisms in GRN disease.

Evidence of shared and distinct functional and structural brain signatures in schizophrenia and autism spectrum disorder

Schizophrenia (SZ) and autism spectrum disorder (ASD) share considerable clinical features and intertwined historical roots. It is greatly needed to explore their similarities and differences in pathophysiologic mechanisms. We assembled a large sample size of neuroimaging data (about 600 SZ patients, 1000 ASD patients, and 1700 healthy controls) to study the shared and unique brain abnormality of the two illnesses. We analyzed multi-scale brain functional connectivity among functional networks and brain regions, intra-network connectivity, and cerebral gray matter density and volume. Both SZ and ASD showed lower functional integration within default mode and sensorimotor domains, but increased interaction between cognitive control and default mode domains. The shared abnormalties in intra-network connectivity involved default mode, sensorimotor, and cognitive control networks. Reduced gray matter volume and density in the occipital gyrus and cerebellum were observed in both illnesses. Interestingly, ASD had overall weaker changes than SZ in the shared abnormalities. Interaction between visual and cognitive regions showed disorder-unique deficits. In summary, we provide strong neuroimaging evidence of the convergent and divergent changes in SZ and ASD that correlated with clinical features.

Pretreatment intranetwork connectivity can predict the outcomes in idiopathic tinnitus patients treated with sound therapy

Previous studies demonstrated that brain morphological differences and distinct patterns of neural activation exist in tinnitus patients with different prognoses after sound therapy. This study aimed to explore possible differences in intrinsic network‐level functional connectivity (FC) in patients with different outcomes after sound therapy (narrow band noise). We examined intrinsic FC using resting‐state functional magnetic resonance imaging in 78 idiopathic tinnitus patients (including 35 effectively treated and 43 ineffectively treated) and 52 healthy controls (HCs) via independent component analysis. We also investigated the associations between the differences in FC and clinical variables. Analyses revealed significantly altered intranetwork connectivity in the auditory network (AUN) and some nonauditory‐related networks in the EG/IG patients compared to HCs; compared with EG patients, IG patients showed decreased intranetwork connectivity in the anterior default mode network (aDMN) and AUN. Meanwhile, robust differences were also evident in internetwork connectivity between some nonauditory‐related networks (salience network and executive control network; posterior default mode network and dorsal attention network) in the EG relative to IG patients. We combined intranetwork connectivity in the aDMN and AUN as an imaging indicator to evaluate patient outcomes and screen patients before treatment; this approach reached a sensitivity of 94.3% and a specificity of 76.7%. Our study suggests that tinnitus patients with different outcomes show distinct network‐level functional reorganization patterns. Intranetwork connectivity in the aDMN and AUN may be indicators that can be used to predict prognoses in patients with idiopathic tinnitus and screen patients before sound therapy.

Identifying Autism Spectrum Disorder From Resting-State fMRI Using Deep Belief Network

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used to characterize the complex biomarkers based on the functional connectivity anomalies in the ASD. However, the diagnosis of ASD still adopts the symptom-based criteria by clinical observation. The existing computational models tend to achieve unreliable diagnostic classification on the large-scale aggregated data sets. In this work, we propose a novel graph-based classification model using the deep belief network (DBN) and the Autism Brain Imaging Data Exchange (ABIDE) database, which is a worldwide multisite functional and structural brain imaging data aggregation. The remarkable connectivity features are selected through a graph extension of K -nearest neighbors and then refined by a restricted path-based depth-first search algorithm. Thanks to the feature reduction, lower computational complexity could contribute to the shortening of the training time. The automatic hyperparameter-tuning technique is introduced to optimize the hyperparameters of the DBN by exploring the potential parameter space. The simulation experiments demonstrate the superior performance of our model, which is 6.4% higher than the best result reported on the ABIDE database. We also propose to use the data augmentation and the oversampling technique to identify further the possible subtypes within the ASD. The interpretability of our model enables the identification of the most remarkable autistic neural correlation patterns from the data-driven outcomes.

Multi-modal neuroimaging feature fusion via 3D Convolutional Neural Network architecture for schizophrenia diagnosis

Early and precise diagnosis of schizophrenia disorder (SZ) has an essential role in the quality of a patient’s life and future treatments. Structural and functional neuroimaging provides robust biomarkers for understanding the anatomical and functional changes associated with SZ. Each of the neuroimaging techniques shows only a different perspective on the functional or structural of the brain, while multi-modal fusion can reveal latent connections in the brain. In this paper, we propose an approach for the fusion of structural and functional brain data with a deep learning-based model to take advantage of data fusion and increase the accuracy of schizophrenia disorder diagnosis. The proposed method consists of an architecture of 3D convolutional neural networks (CNNs) that applied to magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and diffusion tensor imaging (DTI) extracted features. We use 3D MRI patches, fMRI spatial independent component analysis (ICA) map, and DTI fractional anisotropy (FA) as model inputs. Our method is validated on the COBRE dataset, and an average accuracy of 99.35% is obtained. The proposed method demonstrates promising classification performance and can be applied to real data.

Brain Structural and Functional Reorganization in Tinnitus Patients Without Hearing Loss After Sound Therapy: A Preliminary Longitudinal Study

Sound therapy is one of the most common first-line treatments for idiopathic tinnitus. We aimed to investigate the brain structural and functional alterations between patients with idiopathic tinnitus without hearing loss (HL) and healthy controls (HCs) and between patients before and after sound therapy (narrow band noise). Structural and resting-state functional images were acquired from 13 tinnitus patients without HL and 18 HCs before and after 6 months of narrow band sound therapy (only patients received the treatment). Voxel-based morphometry (VBM) and independent component analysis (ICA) were conducted to separately investigate the brain structural and functional changes. Associations between brain changes and clinical variables were also performed. After the treatment, the % improvement of THI score was −1.30% (± 63.40%). Compared with HCs, tinnitus patients showed gray matter and white matter atrophy in the left middle temporal gyrus at baseline, and the gray matter volume was further reduced after the treatment. The patients also showed increased white matter volume in the cingulum (cingulate), right calcarine, left rolandic operculum, and left parietal and frontal lobes. Additionally, compared with HCs, tinnitus patients exhibited positive [medial visual network (mVN) and sensorimotor network (SMN), mVN and auditory network (AN)] and negative [mVN and lateral visual network (lVN)] internetwork functional connectivity (FC) at baseline and negative [left frontoparietal network (LFPN) and dorsal attention network (DAN), AN and posterior default mode network (pDMN)] internetwork FC after the narrow band sound therapy. The patients also showed negative [LFPN and right frontoparietal network (RFPN), LFPN and RFPN, anterior default mode network (aDMN) and AN, aDMN and DAN] internetwork FC after the treatment when compared with baseline. Our findings suggest that although the outcomes of idiopathic tinnitus patients without HL were not very good when the improvement of THI scores was used as an evaluation indicator, the patients experienced significant differences in auditory-related and non-auditory-related brain reorganization before and after the narrow band sound therapy, that is, sound therapy may have a significant effect on brain reorganization in patients with idiopathic tinnitus. This study may provide some new useful information for the understanding of mechanisms underlying idiopathic tinnitus.

Multiple overlapping dynamic patterns of the visual sensory network in schizophrenia

Although visual processing impairments have been explored in schizophrenia (SZ), their underlying neurobiology of the visual processing impairments has not been widely studied. Also, while some research has hinted at differences in information transfer and flow in SZ, there are few investigations of the dynamics of functional connectivity within visual networks. In this study, we analyzed resting-state fMRI data of the visual sensory network (VSN) in 160 healthy control (HC) subjects and 151 SZ subjects. We estimated 9 independent components within the VSN. Then, we calculated the dynamic functional network connectivity (dFNC) using the Pearson correlation. Next, using k-means clustering, we partitioned the dFNCs into five distinct states, and then we calculated the portion of time each subject spent in each state, which we termed the occupancy rate (OCR). Using OCR, we compared HC with SZ subjects and investigated the link between OCR and visual learning in SZ subjects. Besides, we compared the VSN functional connectivity of SZ and HC subjects in each state. We found that this network is indeed highly dynamic. Each state represents a unique connectivity pattern of fluctuations in VSN FNC, and all states showed significant disruption in SZ. Overall, HC showed stronger connectivity within the VSN in states. SZ subjects spent more time in a state in which the connectivity between the middle temporal gyrus and other regions of VNS is highly negative. Besides, OCR in a state with strong positive connectivity between the middle temporal gyrus and other regions correlated significantly with visual learning scores in SZ.

Machine Learning-Based Identification of Suicidal Risk in Patients With Schizophrenia Using Multi-Level Resting-State fMRI Features

BACKGROUND

Some studies suggest that as much as 40% of all causes of death in a group of patients with schizophrenia can be attributed to suicides and compared with the general population, patients with schizophrenia have an 8.5-fold greater suicide risk (SR). There is a vital need for accurate and reliable methods to predict the SR among patients with schizophrenia based on biological measures. However, it is unknown whether the suicidal risk in schizophrenia can be related to alterations in spontaneous brain activity, or if the resting-state functional magnetic resonance imaging (rsfMRI) measures can be used alongside machine learning (ML) algorithms in order to identify patients with SR.

METHODS

Fifty-nine participants including patients with schizophrenia with and without SR as well as age and gender-matched healthy underwent 13 min resting-state functional magnetic resonance imaging. Both static and dynamic indexes of the amplitude of low-frequency fluctuation (ALFF), the fractional amplitude of low-frequency fluctuations (fALFF), regional homogeneity as well as functional connectivity (FC) were calculated and used as an input for five machine learning algorithms: Gradient boosting (GB), LASSO, Logistic Regression (LR), Random Forest and Support Vector Machine.

RESULTS

All groups revealed different intra-network functional connectivity in ventral DMN and anterior SN. The best performance was reached for the LASSO applied to FC with an accuracy of 70% and AUROC of 0.76 (p < 0.05). Significant classification ability was also reached for GB and LR using fALFF and ALFF measures.

CONCLUSION

Our findings suggest that SR in schizophrenia can be seen on the level of DMN and SN functional connectivity alterations. ML algorithms were able to significantly differentiate SR patients. Our results could be useful in developing neuromarkers of SR in schizophrenia based on non-invasive rsfMRI.

Biotyping in psychosis: using multiple computational approaches with one data set

Focusing on biomarker identification and using biomarkers individually or in clusters to define biological subgroups in psychiatry requires a re-orientation from behavioral phenomenology to quantifying brain features, requiring big data approaches for data integration. Much still needs to be accomplished, not only to refine but also to build support for the application and customization of such an analytical phenotypic approach. In this review, we present some of what Bipolar-Schizophrenia Network for Intermediate Phenotypes (B-SNIP) has learned so far to guide future applications of multivariate phenotyping and their analyses to understanding psychosis. This paper describes several B-SNIP projects that use phenotype data and big data computations to generate novel outcomes and glimpse what phenotypes contribute to disease understanding and, with aspiration, to treatment. The source of the phenotypes varies from genetic data, structural neuroanatomic localization, immune markers, brain physiology, and cognition. We aim to see guiding principles emerge and areas of commonality revealed. And, we will need to demonstrate not only data stability but also the usefulness of biomarker information for subgroup identification enhancing target identification and treatment development.

The alteration of cognitive function networks in remitted patients with major depressive disorder: an independent component analysis

INTRODUCTION

Dysfunctional connectivity of resting-state functional networks has been observed in patients with major depressive disorder (MDD), particularly in cognitive function networks including the central executive network (CEN), default mode network (DMN) and salience network (SN). Findings from studies examining how aberrant functional connectivity (FC) changed after antidepressant treatment, however, have been inconsistent. Thus, the purpose of the present study was to explore potential mechanisms of altered cognitive function networks during resting-state between remitted major depressive disorder (rMDD) patients and healthy controls (HCs) and furthermore, the relationship between dysfunctional connectivity patterns in rMDD and clinical symptoms.

METHODOLOGY

In this study, 19 HCs and 19 rMDD patients were recruited for resting-state functional magnetic resonance imaging (fMRI) scanning. FC was evaluated with independent component analysis for CEN, DMN and SN. Two sample t tests were conducted to compare differences between rMDD and HCs. A Pearson correlation analysis was also performed to examine the relationship between connectivity of networks and cognitive function scores and clinical symptoms.

RESULTS

Compared to healthy controls, remitted patients showed lower connectivity in CEN, mostly in the superior frontal gyrus (SFG), middle frontal gyrus (MFG), inferior parietal lobule (IPL) and part of the supramarginal gyrus (SMG). Conversely, the bilateral insula, part of the SMG (a key node of the CEN) and dorsal anterior cingulate cortex (dACC) of the DMN showed higher connectivity in rMDD patients. Pearson correlation results demonstrated that connectivity of the right IPL in CEN was positively correlated with cognitive function scores, and connectivity of the left insula was negatively correlated with BDI scores.

CONCLUSIONS

Though rMDD patients reached the standard of clinal remission, unique impairments of FC in cognitive function networks remained. Aberrant FC between cognitive function networks responsible for executive control was observed in rMDD and may be associated with residual clinical symptoms.

Organized Resting-state Functional Dysconnectivity of the Prefrontal Cortex in Patients with Schizophrenia

Schizophrenia has prominent functional dysconnectivity, especially in the prefrontal cortex (PFC). However, it is unclear whether in the same group of patients with schizophrenia, PFC functional dysconnectivity appears in an organized manner or is stochastically located in different subregions. By investigating the resting-state functional connectivity (rsFC) of each PFC subregion from the Brainnetome atlas in 40 schizophrenia patients and 40 healthy subjects, we found 24 altered connections in schizophrenia, and the connections were divided into four categories by a clustering analysis: increased connections within the PFC, increased connections between the inferior PFC and the thalamus/striatum, reduced connections between the PFC and the motor control areas, and reduced connections between the orbital PFC and the emotional perception regions. In addition, the four categories of rsFC showed distinct cognitive engagement patterns. Our findings suggest that PFC subregions have specific functional dysconnectivity patterns in schizophrenia and may reflect heterogeneous symptoms and cognitive deficits in schizophrenia.

Structural Brain Architectures Match Intrinsic Functional Networks and Vary across Domains: A Study from 15 000+ Individuals

Brain structural networks have been shown to consistently organize in functionally meaningful architectures covering the entire brain. However, to what extent brain structural architectures match the intrinsic functional networks in different functional domains remains under explored. In this study, based on independent component analysis, we revealed 45 pairs of structural-functional (S-F) component maps, distributing across nine functional domains, in both a discovery cohort (n = 6005) and a replication cohort (UK Biobank, n = 9214), providing a well-match multimodal spatial map template for public use. Further network module analysis suggested that unimodal cortical areas (e.g., somatomotor and visual networks) indicate higher S-F coherence, while heteromodal association cortices, especially the frontoparietal network (FPN), exhibit more S-F divergence. Collectively, these results suggest that the expanding and maturing brain association cortex demonstrates a higher degree of changes compared with unimodal cortex, which may lead to higher interindividual variability and lower S-F coherence.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Multifractal and Entropy-Based Analysis of Delta Band Neural Activity Reveals Altered Functional Connectivity Dynamics in Schizophrenia

Dynamic functional connectivity (DFC) was established in the past decade as a potent approach to reveal non-trivial, time-varying properties of neural interactions – such as their multifractality or information content –, that otherwise remain hidden from conventional static methods. Several neuropsychiatric disorders were shown to be associated with altered DFC, with schizophrenia (SZ) being one of the most intensely studied among such conditions. Here we analyzed resting-state electroencephalography recordings of 14 SZ patients and 14 age- and gender-matched healthy controls (HC). We reconstructed dynamic functional networks from delta band (0.5–4 Hz) neural activity and captured their spatiotemporal dynamics in various global network topological measures. The acquired network measure time series were made subject to dynamic analyses including multifractal analysis and entropy estimation. Besides group-level comparisons, we built a classifier to explore the potential of DFC features in classifying individual cases. We found stronger delta-band connectivity, as well as increased variance of DFC in SZ patients. Surrogate data testing verified the true multifractal nature of DFC in SZ, with patients expressing stronger long-range autocorrelation and degree of multifractality when compared to controls. Entropy analysis indicated reduced temporal complexity of DFC in SZ. When using these indices as features, an overall cross-validation accuracy surpassing 89% could be achieved in classifying individual cases. Our results imply that dynamic features of DFC such as its multifractal properties and entropy are potent markers of altered neural dynamics in SZ and carry significant potential not only in better understanding its pathophysiology but also in improving its diagnosis. The proposed framework is readily applicable for neuropsychiatric disorders other than schizophrenia.

Functional network connectivity (FNC)-based generative adversarial network (GAN) and its applications in classification of mental disorders

As a popular deep learning method, generative adversarial networks (GAN) have achieved outstanding performance in multiple classifications and segmentation tasks. However, the application of GANs to fMRI data is relatively rare. In this work, we proposed a functional network connectivity (FNC) based GAN for classifying psychotic disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent components (ICs). The proposed GAN model consisted of one discriminator (real FNCs) and one generator (fake FNCs), each has four fully-connected layers. The generator was trained to match the discriminator in the intermediate layers while simultaneously a new objective loss was determined for the generator to improve the whole classification performance. In a case for classifying 269 major depressive disorder (MDD) patients from 286 HCs, an average accuracy of 70.1% was achieved in 10-fold cross-validation, with at least 6% higher compared to the other 6 popular classification approaches (54.5-64.2%). In another application to discriminating 558 schizophrenia patients from 542 HCs from 7 sites, the proposed GAN model achieved 80.7% accuracy in leave-one-site-out prediction, outperforming support vector machine (SVM) and deep neural net (DNN) by 3%-6%. More importantly, we are able to identify the most contributing FNC nodes and edges with the strategy of leave-one-FNC-out recursively. To the best of our knowledge, this is the first attempt to apply the GAN model on the FNC-based classification of mental disorders. Such a framework promises wide utility and great potential in neuroimaging biomarker identification.

Two distinct neuroanatomical subtypes of schizophrenia revealed using machine learning

Neurobiological heterogeneity in schizophrenia is poorly understood and confounds current analyses. We investigated neuroanatomical subtypes in a multi-institutional multi-ethnic cohort, using novel semi-supervised machine learning methods designed to discover patterns associated with disease rather than normal anatomical variation. Structural MRI and clinical measures in established schizophrenia (n = 307) and healthy controls (n = 364) were analysed across three sites of PHENOM (Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging) consortium. Regional volumetric measures of grey matter, white matter, and CSF were used to identify distinct and reproducible neuroanatomical subtypes of schizophrenia. Two distinct neuroanatomical subtypes were found. Subtype 1 showed widespread lower grey matter volumes, most prominent in thalamus, nucleus accumbens, medial temporal, medial prefrontal/frontal and insular cortices. Subtype 2 showed increased volume in the basal ganglia and internal capsule, and otherwise normal brain volumes. Grey matter volume correlated negatively with illness duration in Subtype 1 (r = -0.201, P = 0.016) but not in Subtype 2 (r = -0.045, P = 0.652), potentially indicating different underlying neuropathological processes. The subtypes did not differ in age (t = -1.603, df = 305, P = 0.109), sex (chi-square = 0.013, df = 1, P = 0.910), illness duration (t = -0.167, df = 277, P = 0.868), antipsychotic dose (t = -0.439, df = 210, P = 0.521), age of illness onset (t = -1.355, df = 277, P = 0.177), positive symptoms (t = 0.249, df = 289, P = 0.803), negative symptoms (t = 0.151, df = 289, P = 0.879), or antipsychotic type (chi-square = 6.670, df = 3, P = 0.083). Subtype 1 had lower educational attainment than Subtype 2 (chi-square = 6.389, df = 2, P = 0.041). In conclusion, we discovered two distinct and highly reproducible neuroanatomical subtypes. Subtype 1 displayed widespread volume reduction correlating with illness duration, and worse premorbid functioning. Subtype 2 had normal and stable anatomy, except for larger basal ganglia and internal capsule, not explained by antipsychotic dose. These subtypes challenge the notion that brain volume loss is a general feature of schizophrenia and suggest differential aetiologies. They can facilitate strategies for clinical trial enrichment and stratification, and precision diagnostics.