Common and unique multimodal covarying patterns in autism spectrum disorder subtypes

Links between brain structure and function in children with autism spectrum disorder by parallel independent component analysis

Autism spectrum disorder (ASD) is a neurodevelopmental disorder accompanied by structural and functional changes in the brain. However, the relationship between brain structure and function in children with ASD remains largely obscure. In the current study, parallel independent component analysis (pICA) was performed to identify inter-modality associations by drawing on information from different modalities. Structural and resting-state functional magnetic resonance imaging data from 105 children with ASD and 102 typically developing children (obtained from the open-access Autism Brain Imaging Data Exchange database) were combined through the pICA framework. Features of structural and functional modalities were represented by the voxel-based morphometry (VBM) and amplitude of low-frequency fluctuations (ALFF), respectively. The relationship between the structural and functional components derived from the pICA was investigated by Pearson's correlation analysis, and between-group differences in these components were analyzed through the two-sample t-test. Finally, multivariate support vector regression analysis was used to analyze the relationship between the structural/functional components and Autism Diagnostic Observation Schedule (ADOS) subscores in the ASD group. This study found a significant association between VBM and ALFF components in ASD. Significant between-group differences were detected in the loading coefficients of the VBM component. Furthermore, the ALFF component loading coefficients predicted the subscores of communication and repetitive stereotypic behaviors of the ADOS. Likewise, the VBM component loading coefficients predicted the ADOS communication subscore in ASD. These findings provide evidence of a link between brain function and structure, yielding new insights into the neural mechanisms of ASD.

The promise of precision functional mapping for neuroimaging in psychiatry

Precision functional mapping (PFM) is a neuroimaging approach to reliably estimate metrics of brain function from individual people via the collection of large amounts of fMRI data (hours per person). This method has revealed much about the inter-individual variation of functional brain networks. While standard group-level studies, in which we average brain measures across groups of people, are important in understanding the generalizable neural underpinnings of neuropsychiatric disorders, many disorders are heterogeneous in nature. This heterogeneity often complicates clinical care, leading to patient uncertainty when considering prognosis or treatment options. We posit that PFM methods may help streamline clinical care in the future, fast-tracking the choice of personalized treatment that is most compatible with the individual. In this review, we provide a history of PFM studies, foundational results highlighting the benefits of PFM methods in the pursuit of an advanced understanding of individual differences in functional network organization, and possible avenues where PFM can contribute to clinical translation of neuroimaging research results in the way of personalized treatment in psychiatry.

Local activity alterations in autism spectrum disorder correlate with neurotransmitter properties and ketamine induced brain changes

Autism spectrum disorder (ASD) is a neurodevelopmental condition associated with altered resting-state brain function. An increased excitation-inhibition (E/I) ratio is discussed as a potential pathomechanism but in-vivo evidence of disturbed neurotransmission underlying these functional alterations remains scarce. We compared rs-fMRI local activity (LCOR) between ASD (N=405, N=395) and neurotypical controls (N=473, N=474) in two independent cohorts (ABIDE1 and ABIDE2). We then tested how these LCOR alterations co-localize with specific neurotransmitter systems derived from nuclear imaging and compared them with E/I changes induced by GABAergic (midazolam) and glutamatergic medication (ketamine). Across both cohorts, ASD subjects consistently exhibited reduced LCOR, particularly in higher-order default mode network nodes, alongside increases in bilateral temporal regions, the cerebellum, and brainstem. These LCOR alterations negatively co-localized with dopaminergic (D1, D2, DAT), glutamatergic (NMDA, mGluR5), GABAergic (GABAa) and cholinergic neurotransmission (VAChT). The NMDA-antagonist ketamine, but not GABAa-potentiator midazolam, induced LCOR changes which co-localize with D1, NMDA and GABAa receptors, thereby resembling alterations observed in ASD. We find consistent local activity alterations in ASD to be spatially associated with several major neurotransmitter systems. NMDA-antagonist ketamine induced neurochemical changes similar to ASD-related alterations, supporting the notion that pharmacological modulation of the E/I balance in healthy individuals can induce ASD-like functional brain changes. These findings provide novel insights into neurophysiological mechanisms underlying ASD.

Comparison of autism spectrum disorder subtypes based on functional and structural factors

Autism spectrum disorder (ASD) is a series of neurodevelopmental disorders that may affect a patient's social, behavioral, and communication abilities. As a typical mental illness, ASD is not a single disorder. ASD is often divided into subtypes, such as autism, Asperger's, and pervasive developmental disorder-not otherwise specified (PDD-NOS). Studying the differences among brain networks of the subtypes has great significance for the diagnosis and treatment of ASD. To date, many studies have analyzed the brain activity of ASD as a single mental disorder, whereas few have focused on its subtypes. To address this problem, we explored whether indices derived from functional and structural magnetic resonance imaging (MRI) data exhibited significant dissimilarities between subtypes. Utilizing a brain pattern feature extraction method from fMRI based on tensor decomposition, amplitude of low-frequency fluctuation and its fractional values of fMRI, and gray matter volume derived from MRI, impairments of function in the subcortical network and default mode network of autism were found to lead to major differences from the other two subtypes. Our results provide a systematic comparison of the three common ASD subtypes, which may provide evidence for the discrimination between ASD subtypes.

Abnormal multimodal neuroimaging patterns associated with social deficits in male autism spectrum disorder

Atypical social impairments (i.e., impaired social cognition and social communication) are vital manifestations of autism spectrum disorder (ASD) patients, and the incidence rate of ASD is significantly higher in males than in females. Characterizing the atypical brain patterns underlying social deficits of ASD is significant for understanding the pathogenesis. However, there are no robust imaging biomarkers that are specific to ASD, which may be due to neurobiological complexity and limitations of single-modality research. To describe the multimodal brain patterns related to social deficits in ASD, we highlighted the potential functional role of white matter (WM) and incorporated WM functional activity and gray matter structure into multimodal fusion. Gray matter volume (GMV) and fractional amplitude of low-frequency fluctuations of WM (WM-fALFF) were combined by fusion analysis model adopting the social behavior. Our results revealed multimodal spatial patterns associated with Social Responsiveness Scale multiple scores in ASD. Specifically, GMV exhibited a consistent brain pattern, in which salience network and limbic system were commonly identified associated with all multiple social impairments. More divergent brain patterns in WM-fALFF were explored, suggesting that WM functional activity is more sensitive to ASD's complex social impairments. Moreover, brain regions related to social impairment may be potentially interconnected across modalities. Cross-site validation established the repeatability of our results. Our research findings contribute to understanding the neural mechanisms underlying social disorders in ASD and affirm the feasibility of identifying biomarkers from functional activity in WM.

Individual Deviation-Based Functional Hypergraph for Identifying Subtypes of Autism Spectrum Disorder

Heterogeneity has been one of the main barriers to understanding and treatment of autism spectrum disorder (ASD). Previous studies have identified several subtypes of ASD through unsupervised clustering analysis. However, most of them primarily depicted the pairwise similarity between individuals through second-order relationships, relying solely on patient data for their calculation. This leads to an underestimation of the complexity inherent in inter-individual relationships and the diagnostic information provided by typical development (TD). To address this, we utilized an elastic net model to construct an individual deviation-based hypergraph (ID-Hypergraph) based on functional MRI data. We then conducted a novel community detection clustering algorithm to the ID-Hypergraph, with the aim of identifying subtypes of ASD. By applying this framework to the Autism Brain Imaging Data Exchange repository data (discovery: 147/125, ASD/TD; replication: 134/132, ASD/TD), we identified four reproducible ASD subtypes with roughly similar patterns of ALFF between the discovery and replication datasets. Moreover, these subtypes significantly varied in communication domains. In addition, we achieved over 80% accuracy for the classification between these subtypes. Taken together, our study demonstrated the effectiveness of identifying subtypes of ASD through the ID-hypergraph, highlighting its potential in elucidating the heterogeneity of ASD and diagnosing ASD subtypes.

Symptom-guided multimodal neuroimage fusion patterns in children with attention-deficit/hyperactivity disorder and its potential "brain structure-function-cognition-behavior" pathological pathways

The "brain-cognition-behavior" process is an important pathological pathway in children with attention-deficit/hyperactivity disorder (ADHD). Symptom guided multimodal neuroimaging fusion can capture behaviorally relevant and intrinsically linked structural and functional features, which can help to construct a systematic model of the pathology. Analyzing the multimodal neuroimage fusion pattern and exploring how these brain features affect executive function (EF) and leads to behavioral impairment is the focus of this study. Based on gray matter volume (GMV) and fractional amplitude of low frequency fluctuation (fALFF) for 152 ADHD and 102 healthy controls (HC), the total symptom score (TO) was set as a reference to identify co-varying components. Based on the correlation between the identified co-varying components and EF, further mediation analysis was used to explore the relationship between brain image features, EF and clinical symptoms. This study found that the abnormalities of GMV and fALFF in ADHD are mainly located in the default mode network (DMN) and prefrontal-striatal-cerebellar circuits, respectively. GMV in ADHD influences the TO through Metacognition Index, while fALFF in HC mediates the TO through behavior regulation index (BRI). Further analysis revealed that GMV in HC influences fALFF, which further modulates BRI and subsequently affects hyperactivity-impulsivity score. To conclude, structural brain abnormalities in the DMN in ADHD may affect local brain function in the prefrontal-striatal-cerebellar circuit, making it difficult to regulate EF in terms of inhibit, shift, and emotional control, and ultimately leading to hyperactive-impulsive behavior.

Identifying psychosis subtypes use individualized covariance structural differential networks and multi-site clustering

BACKGROUND

Similarities among schizophrenia (SZ), schizoaffective disorder (SAD) and bipolar disorder (BP) including clinical phenotypes, brain alterations and risk genes, make it challenging to perform reliable separation among them. However, previous subtype identification that transcend traditional diagnostic boundaries were based on group-level neuroimaging features, ignoring individual-level inferences.

METHODS

455 psychoses (178 SZs, 134 SADs and 143 BPs), their first-degree relatives (N = 453) and healthy controls (HCs, N = 220) were collected from Bipolar-Schizophrenia Network on Intermediate Phenotypes (B-SNIP I) consortium. Individualized covariance structural differential networks (ICSDNs) were constructed for each patient and multi-site clustering was used to identify psychosis subtypes. Group differences between subtypes in clinical phenotypes and voxel-wise fractional amplitude of low frequency fluctuation (fALFF) were calculated, as well as between the corresponding relatives.

RESULTS

Two psychosis subtypes were identified with increased whole brain structural covariance, with decreased connectivity between amygdala-hippocampus and temporal-occipital cortex in subtype I (S-I) compared to subtype II (S-II), which was replicated under different clustering methods, number of edges and across datasets (B-SNIP II) and different brain atlases. S-I had higher emotional-related symptoms than S-II and showed significant fALFF decrease in temporal and occipital cortex, while S-II was more similar to HC. This pattern was consistently validated on relatives of S-I and S-II in both fALFF and clinical symptoms.

CONCLUSIONS

These findings reconcile categorical and dimensional perspectives of psychosis neurobiological heterogeneity, indicating that relatives of S-I might have greater predisposition in developing psychosis, while relatives of S-II are more likely to be healthy. This study contributes to the development of neuroimaging informed diagnostic classifications within psychosis spectrum.

Reduced covariation between brain morphometry and local spontaneous activity in young children with ASD

While disruptions in brain maturation in the first years of life in ASD are well documented, little is known about how the brain structure and function are related in young children with ASD compared to typically developing peers. We applied a multivariate pattern analysis to examine the covariation patterns between brain morphometry and local brain spontaneous activity in 38 toddlers and preschoolers with ASD and 31 typically developing children using T1-weighted structural MRI and resting-state fMRI data acquired during natural sleep. The results revealed significantly reduced brain structure-function correlations in ASD. The resultant brain structure and function composite indices were associated with age among typically developing children, but not among those with ASD, suggesting mistiming of typical brain maturational trajectories early in life in autism. Additionally, the brain function composite indices were associated with the overall developmental and adaptive behavior skills in the ASD group, highlighting the neurodevelopmental significance of early local brain activity in autism.

Delineating a Pathway for the Discovery of Functional Connectome Biomarkers of Autism

The promise of individually tailored care for autism has driven efforts to establish biomarkers. This chapter appraises the state of precision-medicine research focused on biomarkers based on the functional brain connectome. This work is grounded on abundant evidence supporting the brain dysconnection model of autism and the advantages of resting-state functional MRI (R-fMRI) for studying the brain in vivo. After considering biomarker requirements of consistency and clinical relevance, we provide a scoping review of R-fMRI studies of individual prediction in autism. In the past 10 years, responding to the availability of open data through the Autism Brain Imaging Data Exchange, machine learning studies have surged. Nearly all have focused on diagnostic label classification. These efforts have shown that autism prediction is feasible using functional connectome markers, with accuracy reported well above chance. In parallel, emerging approaches more directly addressing autism heterogeneity are paving the way for much-needed biomarkers of longitudinal outcome and treatment response. We conclude with key challenges to be addressed by the next generation of studies.

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.

Autism Spectrum Disorder detection framework for children based on federated learning integrated CNN-LSTM

The incidence of Autism Spectrum Disorder (ASD) among children, attributed to genetics and environmental factors, has been increasing daily. ASD is a non-curable neurodevelopmental disorder that affects children's communication, behavior, social interaction, and learning skills. While machine learning has been employed for ASD detection in children, existing ASD frameworks offer limited services to monitor and improve the health of ASD patients. This paper presents a complex and efficient ASD framework with comprehensive services to enhance the results of existing ASD frameworks. Our proposed approach is the Federated Learning-enabled CNN-LSTM (FCNN-LSTM) scheme, designed for ASD detection in children using multimodal datasets. The ASD framework is built in a distributed computing environment where different ASD laboratories are connected to the central hospital. The FCNN-LSTM scheme enables local laboratories to train and validate different datasets, including Ages and Stages Questionnaires (ASQ), Facial Communication and Symbolic Behavior Scales (CSBS) Dataset, Parents Evaluate Developmental Status (PEDS), Modified Checklist for Autism in Toddlers (M-CHAT), and Screening Tool for Autism in Toddlers and Children (STAT) datasets, on different computing laboratories. To ensure the security of patient data, we have implemented a security mechanism based on advanced standard encryption (AES) within the federated learning environment. This mechanism allows all laboratories to offload and download data securely. We integrate all trained datasets into the aggregated nodes and make the final decision for ASD patients based on the decision process tree. Additionally, we have designed various Internet of Things (IoT) applications to improve the efficiency of ASD patients and achieve more optimal learning results. Simulation results demonstrate that our proposed framework achieves an ASD detection accuracy of approximately 99% compared to all existing ASD frameworks.

Stratifying ASD and characterizing the functional connectivity of subtypes in resting-state fMRI

BACKGROUND

Although stratifying autism spectrum disorder (ASD) into different subtypes is a common effort in the research field, few papers have characterized the functional connectivity alterations of ASD subgroups classified by their clinical presentations.

METHODS

This is a case-control rs-fMRI study, based on large samples of open database (Autism Brain Imaging Data Exchange, ABIDE). The rs-MRI data from n=415 ASD patients (males n=357), and n=574 typical development (TD) controls (males n=410) were included. Clinical features of ASD were extracted and classified using data from each patient's Autism Diagnostic Interview-Revised (ADI-R) evaluation. Each subtype of ASD was characterized by local functional connectivity using regional homogeneity (ReHo) for assessment, remote functional connectivity using voxel-mirrored homotopic connectivity (VMHC) for assessment, the whole-brain functional connectivity, and graph theoretical features. These identified imaging properties from each subtype were integrated to create a machine learning model for classifying ASD patients into the subtypes based on their rs-fMRI data, and an independent dataset was used to validate the model.

RESULTS

All ASD participants were classified into Cluster-1 (patients with more severe impairment) and Cluster-2 (patients with moderate impairment) according to the dimensional scores of ADI-R. When compared to the TD group, Cluster-1 demonstrated increased local connection and decreased remote connectivity, and widespread hyper- and hypo-connectivity variations in the whole-brain functional connectivity. Cluster-2 was quite similar to the TD group in both local and remote connectivity. But at the level of whole-brain functional connectivity, the MCC-related connections were specifically impaired in Cluster-2. These properties of functional connectivity were fused to build a machine learning model, which achieved ~75% for identifying ASD subtypes (Cluster-1 accuracy = 81.75%; Cluster-2 accuracy = 76.48%).

CONCLUSIONS

The stratification of ASD by clinical presentations can help to minimize disease heterogeneity and highlight the distinguished properties of brain connectivity in ASD subtypes.

Intrinsic neural timescales in autism spectrum disorder and schizophrenia. A replication and direct comparison study

Intrinsic neural timescales (INT) reflect the duration for which brain areas store information. A posterior-anterior hierarchy of increasingly longer INT has been revealed in both typically developed individuals (TD), as well as persons diagnosed with autism spectrum disorder (ASD) and schizophrenia (SZ), though INT are, overall, shorter in both patient groups. In the present study, we aimed to replicate previously reported group differences by comparing INT of TD to ASD and SZ. We partially replicated the previously reported result, showing reduced INT in the left lateral occipital gyrus and the right post-central gyrus in SZ compared to TD. We also directly compared the INT of the two patient groups and found that these same two areas show significantly reduced INT in SZ compared to ASD. Previously reported correlations between INT and symptom severity were not replicated in the current project. Our findings serve to circumscribe the brain areas that can potentially play a determinant role in observed sensory peculiarities in ASD and SZ.

Disrupted network integration and segregation involving the default mode network in autism spectrum disorder

Changes in the brain's default mode network (DMN) in the resting state are closely related to autism spectrum disorder (ASD). Module segmentation can effectively elucidate the neural mechanism of ASD and explore intra- and inter-network connections by means of the participation coefficient (PC). We used that resting-state fMRI data from 269 ASD patients and 340 healthy controls (HCs) in the current study. From the results, ASD subjects showed a significantly higher PC of the DMN than HC subjects. This difference was related to lower intra-module connections within the DMN and higher inter-network connections between the DMN and other networks. When the subjects were split into age groups, the results were verified in the 7-12- and 12-18-year-old age groups but not in the young adult group (18-25 years). When the subjects were divided according to different subtypes of ASD, the results were also observed in the classic autism and pervasive developmental disorder groups, but not in the Asperger disorder group. In conclusions, less developed network segregation in the DMN could be a valid biomarker for ASD. This provides network scientists with new insights into the intermodular connectivity configurations of complex networks from different dimensions in a systematic and comprehensive manner.

Individual brain regulation as learned via neurofeedback is related to affective changes in adolescents with autism spectrum disorder

BACKGROUND

Emotions often play a role in neurofeedback (NF) regulation strategies. However, investigations of the relationship between the induced neuronal changes and improvements in affective domains are scarce in electroencephalography-based studies. Thus, we extended the findings of the first study on slow cortical potential (SCP) NF in autism spectrum disorder (ASD) by linking affective changes to whole-brain activity during rest and regulation.

METHODS

Forty-one male adolescents with ASD were scanned twice at rest using functional magnetic resonance imaging. Between scans, half underwent NF training, whereas the other half received treatment as usual. Furthermore, parents reported on their child's affective characteristics at each measurement. The NF group had to alternatingly produce negative and positive SCP shifts during training and was additionally scanned using functional magnetic resonance imaging while applying their developed regulation strategies.

RESULTS

No significant treatment group-by-time interactions in affective or resting-state measures were found. However, we found increases of resting activity in the anterior cingulate cortex and right inferior temporal gyrus as well as improvements in affective characteristics over both groups. Activation corresponding to SCP differentiation in these regions correlated with the affective improvements. A further correlation was found for Rolandic operculum activation corresponding to positive SCP shifts. There were no significant correlations with the respective achieved SCP regulation during NF training.

CONCLUSION

SCP NF in ASD did not lead to superior improvements in neuronal or affective functioning compared to treatment as usual. However, the affective changes might be related to the individual strategies and their corresponding activation patterns as indicated by significant correlations on the whole-brain level. Trial registration This clinical trial was registered at drks.de (DRKS00012339) on 20th April, 2017.

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.

Inter-individual heterogeneity of functional brain networks in children with autism spectrum disorder

BACKGROUND

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with considerable clinical heterogeneity. This study aimed to explore the heterogeneity of ASD based on inter-individual heterogeneity of functional brain networks.

METHODS

Resting-state functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange database were used in this study for 105 children with ASD and 102 demographically matched typical controls (TC) children. Functional connectivity (FC) networks were first obtained for ASD and TC groups, and inter-individual deviation of functional connectivity (IDFC) from the TC group was then calculated for each individual with ASD. A k-means clustering algorithm was used to obtain ASD subtypes based on IDFC patterns. The FC patterns were further compared between ASD subtypes and the TC group from the brain region, network, and whole-brain levels. The relationship between IDFC and the severity of clinical symptoms of ASD for ASD subtypes was also analyzed using a support vector regression model.

RESULTS

Two ASD subtypes were identified based on the IDFC patterns. Compared with the TC group, the ASD subtype 1 group exhibited a hypoconnectivity pattern and the ASD subtype 2 group exhibited a hyperconnectivity pattern. IDFC for ASD subtype 1 and subtype 2 was found to predict the severity of social communication impairments and the severity of restricted and repetitive behaviors in ASD, respectively.

LIMITATIONS

Only male children were selected for this study, which limits the ability to study the effects of gender and development on ASD heterogeneity.

CONCLUSIONS

These results suggest the existence of subtypes with different FC patterns in ASD and provide insight into the complex pathophysiological mechanism of clinical manifestations of ASD.

Multi-modal intermediate integrative methods in neuropsychiatric disorders: A review

The etiology of neuropsychiatric disorders involves complex biological processes at different omics layers, such as genomics, transcriptomics, epigenetics, proteomics, and metabolomics. The advent of high-throughput technology, as well as the availability of large open-source datasets, has ushered in a new era in system biology, necessitating the integration of various types of omics data. The complexity of biological mechanisms, the limitations of integrative strategies, and the heterogeneity of multi-omics data have all presented significant challenges to computational scientists. In comparison to early and late integration, intermediate integration may transform each data type into appropriate intermediate representations using various data transformation techniques, allowing it to capture more complementary information contained in each omics and highlight new interactions across omics layers. Here, we reviewed multi-modal intermediate integrative techniques based on component analysis, matrix factorization, similarity network, multiple kernel learning, Bayesian network, artificial neural networks, and graph transformation, as well as their applications in neuropsychiatric domains. We depicted advancements in these approaches and compared the strengths and weaknesses of each method examined. We believe that our findings will aid researchers in their understanding of the transformation and integration of multi-omics data in neuropsychiatric disorders.

Cluster Analysis of Short Sensory Profile Data Reveals Sensory-Based Subgroups in Autism Spectrum Disorder

Autism spectrum disorder is a common, heterogeneous neurodevelopmental disorder lacking targeted treatments. Additional features include restricted, repetitive patterns of behaviors and differences in sensory processing. We hypothesized that detailed sensory features including modality specific hyper- and hypo-sensitivity could be used to identify clinically recognizable subgroups with unique underlying gene variants. Participants included 378 individuals with a clinical diagnosis of autism spectrum disorder who contributed Short Sensory Profile data assessing the frequency of sensory behaviors and whole genome sequencing results to the Autism Speaks' MSSNG database. Sensory phenotypes in this cohort were not randomly distributed with 10 patterns describing 43% (162/378) of participants. Cross comparison of two independent cluster analyses on sensory responses identified six distinct sensory-based subgroups. We then characterized subgroups by calculating the percent of patients in each subgroup who had variants with a Combined Annotation Dependent Depletion (CADD) score of 15 or greater in each of 24,896 genes. Each subgroup exhibited a unique pattern of genes with a high frequency of variants. These results support the use of sensory features to identify autism spectrum disorder subgroups with shared genetic variants.

Derivation and utility of schizophrenia polygenic risk associated multimodal MRI frontotemporal network

Schizophrenia is a highly heritable psychiatric disorder characterized by widespread functional and structural brain abnormalities. However, previous association studies between MRI and polygenic risk were mostly ROI-based single modality analyses, rather than identifying brain-based multimodal predictive biomarkers. Based on schizophrenia polygenic risk scores (PRS) from healthy white people within the UK Biobank dataset (N = 22,459), we discovered a robust PRS-associated brain pattern with smaller gray matter volume and decreased functional activation in frontotemporal cortex, which distinguished schizophrenia from controls with >83% accuracy, and predicted cognition and symptoms across 4 independent schizophrenia cohorts. Further multi-disease comparisons demonstrated that these identified frontotemporal alterations were most severe in schizophrenia and schizo-affective patients, milder in bipolar disorder, and indistinguishable from controls in autism, depression and attention-deficit hyperactivity disorder. These findings indicate the potential of the identified PRS-associated multimodal frontotemporal network to serve as a trans-diagnostic gene intermediated brain biomarker specific to schizophrenia.

Interpreting Brain Biomarkers: Challenges and solutions in interpreting machine learning-based predictive neuroimaging

Predictive modeling of neuroimaging data (predictive neuroimaging) for evaluating individual differences in various behavioral phenotypes and clinical outcomes is of growing interest. However, the field is experiencing challenges regarding the interpretability of the results. Approaches to defining the specific contribution of functional connections, regions, or networks in prediction models are urgently needed, which may help explore the underlying mechanisms. In this article, we systematically review the methods and applications for interpreting brain signatures derived from predictive neuroimaging based on a survey of 326 research articles. Strengths, limitations, and the suitable conditions for major interpretation strategies are also deliberated. In-depth discussion of common issues in existing literature and the corresponding recommendations to address these pitfalls are provided. We highly recommend exhaustive validation on the reliability and interpretability of the biomarkers across multiple datasets and contexts, which thereby could translate technical advances in neuroimaging into concrete improvements in precision medicine.

Multimodal brain deficits shared in early-onset and adult-onset schizophrenia predict positive symptoms regardless of illness stage

Incidence of schizophrenia (SZ) has two predominant peaks, in adolescent and young adult. Early‐onset schizophrenia provides an opportunity to explore the neuropathology of SZ early in the disorder and without the confound of antipsychotic mediation. However, it remains unexplored what deficits are shared or differ between adolescent early‐onset (EOS) and adult‐onset schizophrenia (AOS) patients. Here, based on 529 participants recruited from three independent cohorts, we explored AOS and EOS common and unique co‐varying patterns by jointly analyzing three MRI features: fractional amplitude of low‐frequency fluctuations (fALFF), gray matter (GM), and functional network connectivity (FNC). Furthermore, a prediction model was built to evaluate whether the common deficits in drug‐naive SZ could be replicated in chronic patients. Results demonstrated that (1) both EOS and AOS patients showed decreased fALFF and GM in default mode network, increased fALFF and GM in the sub‐cortical network, and aberrant FNC primarily related to middle temporal gyrus; (2) the commonly identified regions in drug‐naive SZ correlate with PANSS positive significantly, which can also predict PANSS positive in chronic SZ with longer duration of illness. Collectively, results suggest that multimodal imaging signatures shared by two types of drug‐naive SZ are also associated with positive symptom severity in chronic SZ and may be vital for understanding the progressive schizophrenic brain structural and functional deficits.

Three-way parallel group independent component analysis: Fusion of spatial and spatiotemporal magnetic resonance imaging data

Advances in imaging acquisition techniques allow multiple imaging modalities to be collected from the same subject. Each individual modality offers limited yet unique views of the functional, structural, or dynamic temporal features of the brain. Multimodal fusion provides effective ways to leverage these complementary perspectives from multiple modalities. However, the majority of current multimodal fusion approaches involving functional magnetic resonance imaging (fMRI) are limited to 3D feature summaries that do not incorporate its rich temporal information. Thus, we propose a novel three-way parallel group independent component analysis (pGICA) fusion method that incorporates the first-level 4D fMRI data (temporal information included) by parallelizing group ICA into parallel ICA via a unified optimization framework. A new variability matrix was defined to capture subject-wise functional variability and then link it to the mixing matrices of the other two modalities. Simulation results show that the three-way pGICA provides highly accurate cross-modality linkage estimation under both weakly and strongly correlated conditions, as well as comparable source estimation under different noise levels. Results using real brain imaging data identified one linked functional-structural-diffusion component associated to differences between schizophrenia and controls. This was replicated in an independent cohort, and the identified components were also correlated with major cognitive domains. Functional network connectivity revealed visual-subcortical and default mode-cerebellum pairs that discriminate between schizophrenia and controls. Overall, both simulation and real data results support the use of three-way pGICA to identify multimodal spatiotemporal links and to pursue the study of brain disorders under a single unifying multimodal framework.

Evidence from Characteristics and Comorbidities Suggesting That Asperger Syndrome Is a Subtype of Autism Spectrum Disorder

The current version of the American Psychiatric Association's Diagnostic and Statistical Manual of Mental Disorders (DSM-V) does not consider Asperger syndrome a diagnostic category. This study was undertaken to see if there is evidence that this diagnosis should be reinstated. An online survey was conducted to examine symptoms and behaviors associated with the current diagnostic criteria of autism spectrum disorders (ASD) (DSM-V), and those associated with Asperger syndrome based on the previous version (DSM-IV-TR). The study also examined other characteristics historically associated with autism, as well as impairments often reported in infancy/young childhood and medical comorbidities frequently associated with autism. The sample included 251 individuals who had received a diagnosis of Asperger syndrome and 1888 who were diagnosed with autism or ASD. Numerous similarities and differences were found between the two groups. The findings are discussed in relation to reestablishing Asperger syndrome as a valid diagnostic category as well as a subtype of ASD.

Brain multimodal co-alterations related to delay discounting: a multimodal MRI fusion analysis in persons with and without cocaine use disorder

BACKGROUND

Delay discounting has been proposed as a behavioral marker of substance use disorders. Innovative analytic approaches that integrate information from multiple neuroimaging modalities can provide new insights into the complex effects of drug use on the brain. This study implemented a supervised multimodal fusion approach to reveal neural networks associated with delay discounting that distinguish persons with and without cocaine use disorder (CUD).

METHODS

Adults with (n = 35) and without (n = 37) CUD completed a magnetic resonance imaging (MRI) scan to acquire high-resolution anatomical, resting-state functional, and diffusion-weighted images. Pre-computed features from each data modality included whole-brain voxel-wise maps for gray matter volume, fractional anisotropy, and regional homogeneity, respectively. With delay discounting as the reference, multimodal canonical component analysis plus joint independent component analysis was used to identify co-alterations in brain structure and function.

RESULTS

The sample was 58% male and 78% African-American. As expected, participants with CUD had higher delay discounting compared to those without CUD. One joint component was identified that correlated with delay discounting across all modalities, involving regions in the thalamus, dorsal striatum, frontopolar cortex, occipital lobe, and corpus callosum. The components were negatively correlated with delay discounting, such that weaker loadings were associated with higher discounting. The component loadings were lower in persons with CUD, meaning the component was expressed less strongly.

CONCLUSIONS

Our findings reveal structural and functional co-alterations linked to delay discounting, particularly in brain regions involved in reward salience, executive control, and visual attention and connecting white matter tracts. Importantly, these multimodal networks were weaker in persons with CUD, indicating less cognitive control that may contribute to impulsive behaviors.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Node Centrality Measures Identify Relevant Structural MRI Features of Subjects with Autism

Autism spectrum disorders (ASDs) are a heterogeneous group of neurodevelopmental conditions characterized by impairments in social interaction and communication and restricted patterns of behavior, interests, and activities. Although the etiopathogenesis of idiopathic ASD has not been fully elucidated, compelling evidence suggests an interaction between genetic liability and environmental factors in producing early alterations of structural and functional brain development that are detectable by magnetic resonance imaging (MRI) at the group level. This work shows the results of a network-based approach to characterize not only variations in the values of the extracted features but also in their mutual relationships that might reflect underlying brain structural differences between autistic subjects and healthy controls. We applied a network-based analysis on sMRI data from the Autism Brain Imaging Data Exchange I (ABIDE-I) database, containing 419 features extracted with FreeSurfer software. Two networks were generated: one from subjects with autistic disorder (AUT) (DSM-IV-TR), and one from typically developing controls (TD), adopting a subsampling strategy to overcome class imbalance (235 AUT, 418 TD). We compared the distribution of several node centrality measures and observed significant inter-class differences in averaged centralities. Moreover, a single-node analysis allowed us to identify the most relevant features that distinguished the groups.

China Multi-Center Preschool Autism Project (CMPAP): Design and Methodologies to Identify Clinical Symptom Features and Biomarkers of Autism Spectrum Disorders

Background: The etiology of autism spectrum disorder (ASD) has not yet been fully identified, but it seems to be triggered by complex genetic and environmental risk factors. Moreover, the tremendous etiological and clinical differences among individuals with ASD has had a major negative impact on early diagnosis and individualized treatment. Earlier diagnosis of precise clinical subtypes of ASD could lead to individualized treatment and a better prognosis. However, few large-scale epidemiological studies have explored precise clinical subtypes and clinically meaningful biomarkers, especially in China. Methods and Design: The China Multi-center Preschool Autism Project (CMPAP) includes nearly 3,000 children-1,469 individuals with ASD and 1,499 typically-developing (TD) controls-from 13 cities in China. Using a case-control design, each participant was comprehensively characterized in terms of feeding and disease history, maternal history, family history, clinical core symptoms, comorbidities, biochemical markers, genomics, urine/fecal metabonomics, and intestinal flora. In addition, data on environmental risk factors were obtained using interviews and electronic medical records. Conclusion: The study was designed to: (1) investigate age at diagnosis and treatment and family and social support for preschool children with ASD in China, (2) develop a more accurate clinical subtype and intervention system for the ICD-11, and (3) find the specific genes and environmental markers of different subtypes, which will help in the development of early diagnosis and individual intervention programs for preschool children with ASD. This study will provide the basis for improving national health policies for ASD in China.