Enhancing studies of the connectome in autism using the autism brain imaging data exchange II

Mapping the Landscape of Autism Research: A Scientometric Review (2011-2023)

This scientometric analysis maps the landscape of autism spectrum disorder (ASD) research between 2011 and 2023. By exploring patterns in publication growth, geographic distribution and institutional involvement, this study highlights evolving research themes, key contributors and collaborative networks. Our findings reveal a marked rise in ASD publications, particularly from 2020 onwards, with the United States, United Kingdom and China leading in contributions and collaborations. Scientometric analysis identifies a shift towards advanced machine learning techniques and neuroimaging in ASD studies, reflecting technological integration in research. Institutional analysis uncovers Vanderbilt University and Yale University as major contributors, with significant citation impacts across their publications. Furthermore, prominent funding sources, including the National Institutes of Health, underscore the critical role of funding in shaping research priorities. This comprehensive scientometric overview not only consolidates current knowledge but also serves as a resource to inform future research directions, enhancing interdisciplinary approaches to ASD understanding and intervention.

What is the best brain state to predict autistic traits?

Autism is a heterogeneous condition, and functional magnetic resonance imaging-based studies have advanced understanding of neurobiological correlates of autistic features. Nevertheless, little work has focused on the optimal brain states to reveal brain-phenotype relationships. In addition, there is a need to better understand the relevance of attentional abilities in mediating autistic features. Using connectome-based predictive modelling, we interrogate three datasets to determine scanning conditions that can boost prediction of clinically relevant phenotypes and assess generalizability. In dataset one, a sample of youth with autism and neurotypical participants, we find that a sustained attention task (the gradual onset continuous performance task) results in high prediction performance of autistic traits compared to a free-viewing social attention task and a resting-state condition. In dataset two, we observe the predictive network model of autistic traits generated from the sustained attention task generalizes to predict measures of attention in neurotypical adults. In dataset three, we show the same predictive network model of autistic traits from dataset one further generalizes to predict measures of social responsiveness in data from the Autism Brain Imaging Data Exchange. In sum, our data suggest that an in-scanner sustained attention challenge can help delineate robust markers of autistic traits and support the continued investigation of the optimal brain states under which to predict phenotypes in psychiatric conditions.

A review of artificial intelligence-based brain age estimation and its applications for related diseases

The study of brain age has emerged over the past decade, aiming to estimate a person's age based on brain imaging scans. Ideally, predicted brain age should match chronological age in healthy individuals. However, brain structure and function change in the presence of brain-related diseases. Consequently, brain age also changes in affected individuals, making the brain age gap (BAG)-the difference between brain age and chronological age-a potential biomarker for brain health, early screening, and identifying age-related cognitive decline and disorders. With the recent successes of artificial intelligence in healthcare, it is essential to track the latest advancements and highlight promising directions. This review paper presents recent machine learning techniques used in brain age estimation (BAE) studies. Typically, BAE models involve developing a machine learning regression model to capture age-related variations in brain structure from imaging scans of healthy individuals and automatically predict brain age for new subjects. The process also involves estimating BAG as a measure of brain health. While we discuss recent clinical applications of BAE methods, we also review studies of biological age that can be integrated into BAE research. Finally, we point out the current limitations of BAE's studies.

A multi-modal neuroimaging data release for Meige Syndrome and Facial Paralysis Research

The sharing of multimodal magnetic resonance imaging (MRI) data is of utmost importance in the field, as it enables a deeper understanding of facial nerve-related pathologies. However, there is a significant lack of multi-modal neuroimaging databases specifically focused on these conditions, which hampers our comprehensive knowledge of the neural foundations of facial paralysis. To address this critical gap and propel advancements in this area, we have released the Multimodal Neuroimaging Dataset of Meige Syndrome, Facial Paralysis, and Healthy Controls (MND-MFHC). This dataset includes detailed clinical assessments of 53 individuals with facial paralysis (FP), 31 patients with Meige syndrome (MS), and 102 healthy controls (HC). To promote open access, the BIDS-formatted data and associated quality control reports can be accessed through the Science Data Bank (SciDB). By sharing this comprehensive dataset, our aim is to facilitate further research and exploration into the intricate neural mechanisms underlying facial nerve-related pathologies.

Atypical brain network topology of the triple network and cortico-subcortical network in autism spectrum disorder

The default mode network (DMN), salience network (SN), and central executive control network (CEN) form the well-known triple network, providing a framework for understanding various neurodevelopmental and psychiatric disorders. However, the topology of this network remains unclear in autism spectrum disorder (ASD). To gain a more profound understanding of ASD, we explored the topology of the triple network in ASD. Additionally, the striatum and thalamus are pivotal centres of information transmission within the brain, and the realization of various brain functions requires the coordination of cortical and subcortical structures. Therefore, we also investigated the topology of the cortico-subcortical network in ASD, which consists of the DMN, SN, CEN, striatum, and thalamus. Resting-state functional magnetic resonance imaging data on 208 ASD patients and 278 typically developing (TD) controls (8-18 years old) were obtained from the Autism Brain Imaging Data Exchange database. We performed graph theory analysis on the triple network and the cortico-subcortical network. The results showed that the triple network's clustering coefficient, lambda, and network local efficiency values were significantly lower in ASD, and the nodal degree and efficiency of the medial prefrontal cortex also decreased. For the cortico-subcortical network, the sigma, clustering coefficient, gamma, and network local efficiency showed the same reduction, and the altered clustering coefficient negatively correlated with ASD manifestations. In addition, the interaction between the DMN and CEN was more robust in ASD patients. These findings enhance our understanding of ASD and suggest that subcortical structures should be more considered in future ASD related studies.

A lifespan-generalizable skull-stripping model for magnetic resonance images that leverages prior knowledge from brain atlases

In magnetic resonance imaging of the brain, an imaging-preprocessing step removes the skull and other non-brain tissue from the images. But methods for such a skull-stripping process often struggle with large data heterogeneity across medical sites and with dynamic changes in tissue contrast across lifespans. Here we report a skull-stripping model for magnetic resonance images that generalizes across lifespans by leveraging personalized priors from brain atlases. The model consists of a brain extraction module that provides an initial estimation of the brain tissue on an image, and a registration module that derives a personalized prior from an age-specific atlas. The model is substantially more accurate than state-of-the-art skull-stripping methods, as we show with a large and diverse dataset of 21,334 lifespans acquired from 18 sites with various imaging protocols and scanners, and it generates naturally consistent and seamless lifespan changes in brain volume, faithfully charting the underlying biological processes of brain development and ageing.

Molecular architecture of the altered cortical complexity in autism

Autism spectrum disorder (ASD) is characterized by difficulties in social interaction, communication challenges, and repetitive behaviors. Despite extensive research, the molecular mechanisms underlying these neurodevelopmental abnormalities remain elusive. We integrated microscale brain gene expression data with macroscale MRI data from 1829 participants, including individuals with ASD and typically developing controls, from the autism brain imaging data exchange I and II. Using fractal dimension as an index for quantifying cortical complexity, we identified significant regional alterations in ASD, within the left temporoparietal, left peripheral visual, right central visual, left somatomotor (including the insula), and left ventral attention networks. Partial least squares regression analysis revealed gene sets associated with these cortical complexity changes, enriched for biological functions related to synaptic transmission, synaptic plasticity, mitochondrial dysfunction, and chromatin organization. Cell-specific analyses, protein-protein interaction network analysis and gene temporal expression profiling further elucidated the dynamic molecular landscape associated with these alterations. These findings indicate that ASD-related alterations in cortical complexity are closely linked to specific genetic pathways. The combined analysis of neuroimaging and transcriptomic data enhances our understanding of how genetic factors contribute to brain structural changes in ASD.

Sex Differences in Spatiotemporal Consistency and Effective Connectivity of the Precuneus in Autism Spectrum Disorder

Autism spectrum disorder (ASD) has been reported to exhibit altered local functional consistency. However, previous studies mainly focused on male samples and explored the temporal consistency in the ASD brain ignoring the spatial consistency. In this study, FOur-dimensional Consistency of local neural Activities (FOCA) analysis was used to investigate the sex differences of local spatiotemporal consistency of spontaneous brain activity in ASD. This study used resting-state functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange database, including 64 males/64 females with ASD and 64 male/64 female neurotypical controls (NCs). Two-way analysis of variance was performed to ascertain diagnosis-by-sex interaction effects on whole brain FOCA maps. Moreover, granger causal analysis was used to investigate effective connectivity between the brain regions with interaction effects and the whole-brain in ASD. Significant diagnosis-by-sex interaction effects on FOCA were observed in the bilateral precuneus (PCUN), bilateral medial prefrontal cortex and right dorsolateral superior frontal gyrus. Specifically, FOCA was significantly increased in males with ASD but decreased in females with ASD in the PCUN compared with the sex-matched NC group. In addition, the lack of sex differences in the causal influences from the bilateral anterior cingulate cortex/medial prefrontal cortex to the PCUN was observed in ASD. Our results reveal altered sex differences in the spatiotemporal consistency of spontaneous brain activity and functional interaction of the anterior and posterior default mode network (DMN) in ASD, highlighting the critical role of the DMN in the sex heterogeneity of ASD.

Multi-modal cross-domain self-supervised pre-training for fMRI and EEG fusion

Neuroimaging techniques including functional magnetic resonance imaging (fMRI) and electroencephalogram (EEG) have shown promise in detecting functional abnormalities in various brain disorders. However, existing studies often focus on a single domain or modality, neglecting the valuable complementary information offered by multiple domains from both fMRI and EEG, which is crucial for a comprehensive representation of disorder pathology. This limitation poses a challenge in effectively leveraging the synergistic information derived from these modalities. To address this, we propose a Multi-modal Cross-domain Self-supervised Pre-training Model (MCSP), a novel approach that leverages self-supervised learning to synergize multi-modal information across spatial, temporal, and spectral domains. Our model employs cross-domain self-supervised loss that bridges domain differences by implementing domain-specific data augmentation and contrastive loss, enhancing feature discrimination. Furthermore, MCSP introduces cross-modal self-supervised loss to capitalize on the complementary information of fMRI and EEG, facilitating knowledge distillation within domains and maximizing cross-modal feature convergence. We constructed a large-scale pre-training dataset and pretrained MCSP model by leveraging proposed self-supervised paradigms to fully harness multimodal neuroimaging data. Through comprehensive experiments, we have demonstrated the superior performance and generalizability of our model on multiple classification tasks. Our study contributes a significant advancement in the fusion of fMRI and EEG, marking a novel integration of cross-domain features, which enriches the existing landscape of neuroimaging research, particularly within the context of mental disorder studies.

Altered Temporospatial Variability of Dynamic Amplitude of Low-Frequency Fluctuation in Children with Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with altered brain activity. However, little is known about the integrated temporospatial variation of dynamic spontaneous brain activity in ASD. In the present study, resting-state functional magnetic resonance imaging data were analyzed for 105 ASD and 102 demographically-matched typically developmental controls (TC) children obtained from the Autism Brain Imaging Data Exchange database. Using the sliding-window approach, temporal, spatial, and temporospatial variability of dynamic amplitude of low-frequency fluctuation (tvALFF, svALFF, and tsvALFF) were calculated for each participant. Group-comparisons were further performed at global, network, and brain region levels to quantify differences between ASD and TC groups. The relationship between temporospatial dynamic amplitude of low-frequency fluctuation variation alterations and clinical symptoms of ASD was finally explored by a support vector regression model. Relative to TC, we found enhanced tvALFF in visual network (Vis), somatomotor network (SMT), and salience/ventral attention network (SVA) of ASD, and weakened tvALFF in dorsal attention network (DAN) of ASD. Besides, ASD showed decreased svALFF in Vis, SVA, and limbic network (Limbic), and increased svALFF in DAN and default mode network (DMN). Elevated tsvALFF was found in the Vis, SMT, and DMN of ASD. More importantly, the altered tsvALFF from the DMN can predict the symptom severity of ASD. These findings demonstrate altered temporospatial dynamics of the spontaneous brain activity in ASD and provide novel insights into the neural mechanism underlying ASD.

Age-related unstable transient states and imbalanced activation proportion of brain networks in people with autism spectrum disorder: A resting-state fMRI study using coactivation pattern analyses

The atypical static brain functions related to the executive control network (ECN), default mode network (DMN), and salience network (SN) in people with autism spectrum disorder (ASD) has been widely reported. However, their transient functions in ASD are not clear. We aim to identify transient network states (TNSs) using coactivation pattern (CAP) analysis to characterize the age-related atypical transient functions in ASD. CAP analysis was performed on a resting-state fMRI dataset (78 ASD and 78 healthy control (CON) juveniles, 54 ASD and 54 CON adults). Six TNSs were divided into the DMN-TNSs, ECN-TNSs, and SN-TNSs. The DMN-TNSs were major states with the highest stability and proportion, and the ECN-TNSs and SN-TNSs were minor states. Age-related abnormalities on spatial stability and TNS proportion were found in ASD. The spatial stability of DMN-TNSs was found increasing with age in CON, but was not found in ASD. A lower proportion of DMN-TNSs was found in ASD compared with CON of the same age, and ASD juveniles had a higher proportion of SN-TNSs while ASD adults had a higher proportion of ECN-TNSs. The abnormalities on spatial stability and TNS proportion were related to social deficits. Our results provided new evidence for atypical transient brain functions in people with ASD.

Comparison of different group-level templates in gradient-based multimodal connectivity analysis

The study of large-scale brain connectivity is increasingly adopting unsupervised approaches that derive low-dimensional spatial representations from high-dimensional connectomes, referred to as gradient analysis. When translating this approach to study interindividual variations in connectivity, one technical issue pertains to the selection of an appropriate group-level template to which individual gradients are aligned. Here, we compared different group-level template construction strategies using functional and structural connectome data from neurotypical controls and individuals with autism spectrum disorder (ASD) to identify between-group differences. We studied multimodal magnetic resonance imaging data obtained from the Autism Brain Imaging Data Exchange (ABIDE) Initiative II and the Human Connectome Project (HCP). We designed six template construction strategies that varied in whether (1) they included typical controls in addition to ASD; or (2) they mapped from one dataset onto another. We found that aligning a combined subject template of the ASD and control subjects from the ABIDE Initiative onto the HCP template exhibited the most pronounced effect size. This strategy showed robust identification of ASD-related brain regions for both functional and structural gradients across different study settings. Replicating the findings on focal epilepsy demonstrated the generalizability of our approach. Our findings will contribute to improving gradient-based connectivity research.

A foundation model for enhancing magnetic resonance images and downstream segmentation, registration and diagnostic tasks

In structural magnetic resonance (MR) imaging, motion artefacts, low resolution, imaging noise and variability in acquisition protocols frequently degrade image quality and confound downstream analyses. Here we report a foundation model for the motion correction, resolution enhancement, denoising and harmonization of MR images. Specifically, we trained a tissue-classification neural network to predict tissue labels, which are then leveraged by a 'tissue-aware' enhancement network to generate high-quality MR images. We validated the model's effectiveness on a large and diverse dataset comprising 2,448 deliberately corrupted images and 10,963 images spanning a wide age range (from foetuses to elderly individuals) acquired using a variety of clinical scanners across 19 public datasets. The model consistently outperformed state-of-the-art algorithms in improving the quality of MR images, handling pathological brains with multiple sclerosis or gliomas, generating 7-T-like images from 3 T scans and harmonizing images acquired from different scanners. The high-quality, high-resolution and harmonized images generated by the model can be used to enhance the performance of models for tissue segmentation, registration, diagnosis and other downstream tasks.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.

Resting-State Functional Connectivity of the Amygdala in Autism: A Preregistered Large-Scale Study

OBJECTIVE

Three leading neurobiological hypotheses about autism spectrum disorder (ASD) propose underconnectivity between brain regions, atypical function of the amygdala, and generally higher variability between individuals with ASD than between neurotypical individuals. Past work has often failed to generalize, because of small sample sizes, unquantified data quality, and analytic flexibility. This study addressed these limitations while testing the above three hypotheses, applied to amygdala functional connectivity.

METHODS

In a comprehensive preregistered study, the three hypotheses were tested in a subset (N=488 after exclusions; N=212 with ASD) of the Autism Brain Imaging Data Exchange data sets. The authors analyzed resting-state functional connectivity (FC) from functional MRI data from two anatomically defined amygdala subdivisions, in three hypotheses with respect to magnitude, pattern similarity, and variability, across different anatomical scales ranging from whole brain to specific regions and networks.

RESULTS

A Bayesian approach to hypothesis evaluation produced inconsistent evidence in ASD for atypical amygdala FC magnitude, strong evidence that the multivariate pattern of FC was typical, and no consistent evidence of increased interindividual variability in FC. The results strongly depended on analytic choices, including preprocessing pipeline for the neuroimaging data, anatomical specificity, and subject exclusions.

CONCLUSIONS

A preregistered set of analyses found no reliable evidence for atypical functional connectivity of the amygdala in autism, contrary to leading hypotheses. Future studies should test an expanded set of hypotheses across multiple processing pipelines, collect deeper data per individual, and include a greater diversity of participants to ensure robust generalizability of findings on amygdala FC in ASD.

Segmental MRI pituitary and hypothalamus volumes post Fontan: An analysis of the Australian and New Zealand Fontan registry

Objective

Short stature, central hypothyroidism and infertility are common in those with a Fontan circulation. Given that the Fontan circulation often results in hepatic portal venous congestion, we hypothesize that the hypothalamic-pituitary portal circulation is also affected, contributing to subsequent hypothalamic-pituitary axis dysfunction.

Methods

MRI data from the Australian and New Zealand Fontan Registry (86 cases) was compared to 86 age- and sex-matched normal published controls. Total pituitary volumes (both anterior and posterior glands) were measured using a manual tracing segmentation method, and hypothalamic (and subunit) volumes using an automated segmentation tool. Measured gland volume was normalized to total brain volumes. A generalized linear model was used for statistical analysis.

Results

Normalized total pituitary volumes (nTPV) were increased in Fontan patients compared to controls (p < 0.0001), due to an increase in anterior pituitary volumes (nAPV) (p < 0.0001), with no difference in normalized posterior pituitary volumes (p = 0.7). Furthermore, normalized anterior and tubular hypothalamic subunit groups) were increased in Fontan patients compared to the controls (p < 0.01 and p < 0.0001, respectively).The time between Fontan and MRI was positively related to nTPV, nAPV and bilateral hypothalamic volumes. nTPV increased with age, and the increase in nAPV was greater in Fontan patients.

Conclusions

Segmental MRI Pituitary and Hypothalamus volumes post Fontan are increased and are related to the time since Fontan procedure. These findings are consistent with venous congestion of the anterior hypothalamic-pituitary portal venous system and may explain the high frequency of endocrine dysfunction in this patient group.

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.

Volumetric Analysis of Motor Cortex and Basal Ganglia in Pediatric Celiac Disease Patients Using volBrain: Implications for Neurological Dysfunction-Preliminary Results

BACKGROUND/OBJECTIVES

Celiac disease (CD) is a common immune-mediated, chronic systemic disorder that is treated with a strict, life-long gluten-free diet (GFD). In addition to gastrointestinal manifestations, CD also presents with a variety of extraintestinal symptoms, including significant neurological and neuropsychiatric symptoms. Among these neurological manifestations, motor dysfunctions are particularly notable. The aim of this study is to investigate the potential volumetric differences in brain structures, particularly the motor cortex and basal ganglia, between pediatric CD patients and healthy controls using the volBrain software AssemblyNet version 1.0.

METHODS

This prospective study included pediatric patients with CD who complained of neurological symptoms and were scheduled for brain magnetic resonance imaging (MRI). All children had been previously diagnosed with CD and their adherence to GFD was evaluated using the Biagi score. Brain MRIs were performed on all included patients to obtain volumetry at the onset of the disease. For volumetric and segmentation data, the volBrain software was used.

RESULTS

In total, 12 pediatric patients with CD were included, with a median duration of a GFD of 5.3 years at the time of the MRI examination. There were no statistically significant differences between patients compliant with the GFD and those non-compliant in terms of age or duration of GFD. Volumetric analysis revealed deviations in all patients analyzed, which involved either a decrease or increase in the volume of the structures studied.

CONCLUSION

Despite the limited number of patients in this study, the initial findings support previously described neurological manifestations in patients with CD. Newly developed MRI tools have the potential to enable a more detailed analysis of disease progression and its impact on the motor cortex.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Enhancing Autism Spectrum Disorder identification in multi-site MRI imaging: A multi-head cross-attention and multi-context approach for addressing variability in un-harmonized data

Multi-site MRI imaging poses a significant challenge due to the potential variations in images across different scanners at different sites. This variability can introduce ambiguity in further image analysis. Consequently, the image analysis techniques become site-dependent and scanner-dependent, implying that adjustments in the analysis methodologies are necessary for each scanner configuration. Further, implementing real-time modifications becomes intricate, particularly when incorporating a new type of scanner, as it requires adapting the analysis methods accordingly. Taking into account the aforementioned challenge, we have considered its implications for an Autism spectrum disorder (ASD) application. Our objective is to minimize the impact of site and scanner variability in the analysis, aiming to develop a model that remains effective across different scanners and sites. This entails devising a methodology that allows the same model to function seamlessly across multiple scanner configurations and sites. ASD, a behavioral disorder affecting child development, requires early detection. Clinical observation is time-consuming, prompting the use of fMRI with machine/deep learning for expedited diagnosis. Previous methods leverage fMRI's functional connectivity but often rely on less generalized feature extractors and classifiers. Hence, there is significant room for improvement in the generalizability of detection methods across multi-site data, which is acquired from multiple scanners with different settings. In this study, we propose a Cross-Combination Multi-Scale Multi-Context Framework (CCMSMCF) capable of performing neuroimaging-based diagnostic classification of mental disorders for a multi-site dataset. Thus, this framework attains a degree of internal data harmonization, rendering it to some extent site and scanner-agnostic. Our proposed network, CCMSMCF, is constructed by integrating two sub-modules: the Multi-Head Attention Cross-Scale Module (MHACSM) and the Residual Multi-Context Module (RMCN). We also employ multiple loss functions in a novel manner for training the model, which includes Binary Cross Entropy, Dice loss, and Embedding Coupling loss. The model is validated on the Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, which includes data from multiple scanners across different sites, and achieves promising results.

Quantitative Expression of Latent Disease Factors in Individuals Associated with Psychopathology Dimensions and Treatment Response

Psychiatric comorbidity is common in symptom-based diagnoses like autism spectrum disorder (ASD), attention/deficit hyper-activity disorder (ADHD), and obsessive-compulsive disorder (OCD). However, these co-occurring symptoms mediated by shared and/or distinct neural mechanisms are difficult to profile at the individual level. Capitalizing on unsupervised machine learning with a hierarchical Bayesian framework, we derived latent disease factors from resting-state functional connectivity data in a hybrid cohort of ASD and ADHD and delineated individual associations with dimensional symptoms based on canonical correlation analysis. Models based on the same factors generalized to previously unseen individuals in a subclinical cohort and one local OCD database with a subset of patients undergoing neurosurgical intervention. Four factors, identified as variably co-expressed in each patient, were significantly correlated with distinct symptom domains (r = -0.26-0.53, P < 0.05): behavioral regulation (Factor-1), communication (Factor-2), anxiety (Factor-3), adaptive behaviors (Factor-4). Moreover, we demonstrated Factor-1 expressed in patients with OCD and Factor-3 expressed in participants with anxiety, at the degree to which factor expression was significantly predictive of individual symptom scores (r = 0.18-0.5, P < 0.01). Importantly, peri-intervention changes in Factor-1 of OCD were associated with variable treatment outcomes (r = 0.39, P < 0.05). Our results indicate that these data-derived latent disease factors quantify individual factor expression to inform dimensional symptom and treatment outcomes across cohorts, which may promote quantitative psychiatric diagnosis and personalized intervention.

MADE-for-ASD: A multi-atlas deep ensemble network for diagnosing Autism Spectrum Disorder

In response to the global need for efficient early diagnosis of Autism Spectrum Disorder (ASD), this paper bridges the gap between traditional, time-consuming diagnostic methods and potential automated solutions. We propose a multi-atlas deep ensemble network, MADE-for-ASD, that integrates multiple atlases of the brain's functional magnetic resonance imaging (fMRI) data through a weighted deep ensemble network. Our approach integrates demographic information into the prediction workflow, which enhances ASD diagnosis performance and offers a more holistic perspective on patient profiling. We experiment with the well-known publicly available ABIDE (Autism Brain Imaging Data Exchange) I dataset, consisting of resting state fMRI data from 17 different laboratories around the globe. Our proposed system achieves 75.20% accuracy on the entire dataset and 96.40% on a specific subset - both surpassing reported ASD diagnosis accuracy in ABIDE I fMRI studies. Specifically, our model improves by 4.4 percentage points over prior works on the same amount of data. The model exhibits a sensitivity of 82.90% and a specificity of 69.70% on the entire dataset, and 91.00% and 99.50%, respectively, on the specific subset. We leverage the F-score to pinpoint the top 10 ROI in ASD diagnosis, such as precuneus and anterior cingulate/ventromedial. The proposed system can potentially pave the way for more cost-effective, efficient and scalable strategies in ASD diagnosis. Codes and evaluations are publicly available at https://github.com/hasan-rakibul/MADE-for-ASD.

Gray Matter Volume Correlates of Co-Occurring Depression in Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) involves neurodevelopmental syndromes with significant deficits in communication, motor behaviors, emotional and social comprehension. Often, individuals with ASD exhibit co-occurring depression characterized by a change in mood and diminished interest in previously enjoyable activities. Due to communicative challenges and a lack of appropriate assessments in this cohort, co-occurring depression can often go undiagnosed during routine clinical examinations and, thus, its management neglected. The literature on co-occurring depression in adults with ASD is limited. Therefore, understanding the neural basis of the co-occurring psychopathology of depression in ASD is crucial for identifying brain-based markers for its timely and effective management. Using structural MRI and phenotypic data from the Autism Brain Imaging Data Exchange (ABIDE II) repository, we examined the pattern of relationship regional grey matter volume (rGMV) has with co-occurring depression and autism severity within regions of a priori interest in adults with ASD (n = 44; age = 17-28 years). Further, we performed an exploratory analysis of the rGMV differences between ASD and matched typically developed (TD, n = 39; age = 18-31 years) samples. The severity of co-occurring depression correlated negatively with the rGMV of the right thalamus. Additionally, a significant interaction was evident between the severity of co-occurring depression and core ASD symptoms towards explaining the rGMV in the left cerebellum crus II. The results further the understanding of the neurobiological underpinnings of co-occurring depression in adults with ASD towards exploring neuroimaging-based biomarkers in the same cohort.

3D CNN for neuropsychiatry: Predicting Autism with interpretable Deep Learning applied to minimally preprocessed structural MRI data

Predictive modeling approaches are enabling progress toward robust and reproducible brain-based markers of neuropsychiatric conditions by leveraging the power of multivariate analyses of large datasets. While deep learning (DL) offers another promising avenue to further advance progress, there are challenges related to implementation in 3D (best for MRI) and interpretability. Here, we address these challenges and describe an interpretable predictive pipeline for inferring Autism diagnosis using 3D DL applied to minimally processed structural MRI scans. We trained 3D DL models to predict Autism diagnosis using the openly available ABIDE I and II datasets (n = 1329, split into training, validation, and test sets). Importantly, we did not perform transformation to template space, to reduce bias and maximize sensitivity to structural alterations associated with Autism. Our models attained predictive accuracies equivalent to those of previous machine learning (ML) studies, while side-stepping the time- and resource-demanding requirement to first normalize data to a template. Our interpretation step, which identified brain regions that contributed most to accurate inference, revealed regional Autism-related alterations that were highly consistent with the literature, encompassing a left-lateralized network of regions supporting language processing. We have openly shared our code and models to enable further progress towards remaining challenges, such as the clinical heterogeneity of Autism and site effects, and to enable the extension of our method to other neuropsychiatric conditions.

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.

Polyconnectomic Scoring of Functional Connectivity Patterns Across Eight Neuropsychiatric and Three Neurodegenerative Disorders

BACKGROUND

Neuropsychiatric and neurodegenerative disorders involve diverse changes in brain functional connectivity. As an alternative to approaches that search for specific mosaic patterns of affected connections and networks, we used polyconnectomic scoring to quantify disorder-related whole-brain connectivity signatures into interpretable, personalized scores.

METHODS

The polyconnectomic score (PCS) measures the extent to which an individual's functional connectivity mirrors the whole-brain circuitry characteristics of a trait. We computed PCSs for 8 neuropsychiatric conditions (attention-deficit/hyperactivity disorder, anxiety-related disorders, autism spectrum disorder, obsessive-compulsive disorder, bipolar disorder, major depressive disorder, schizoaffective disorder, and schizophrenia) and 3 neurodegenerative conditions (Alzheimer's disease, frontotemporal dementia, and Parkinson's disease) across 22 datasets with resting-state functional magnetic resonance imaging data from 10,667 individuals (5325 patients, 5342 control participants). We also examined PCSs in 26,673 individuals from the population-based UK Biobank cohort.

RESULTS

PCSs were consistently higher in out-of-sample patients across 6 of the 8 neuropsychiatric and across all 3 investigated neurodegenerative disorders ([minimum, maximum]: area under the receiver operating characteristic curve = [0.55, 0.73], false discovery rate-corrected p [pFDR] = [1.8 × 10-16, 4.5 × 10-2]). Individuals with elevated PCS levels for neuropsychiatric conditions exhibited higher neuroticism (pFDR < 9.7 × 10-5), lower cognitive performance (pFDR < 5.3 × 10-5), and lower general well-being (pFDR < 9.7 × 10-4).

CONCLUSIONS

Our findings reveal generalizable whole-brain connectivity alterations in brain disorders. Polyconnectomic scoring effectively aggregates disorder-related signatures across the entire brain into an interpretable, participant-specific metric. A toolbox is provided for PCS computation.

Multimodal evidence for cerebellar influence on cortical development in autism: structural growth amidst functional disruption

Despite perinatal damage to the cerebellum being one of the highest risk factors for later being diagnosed with autism spectrum disorder (ASD), it is not yet clear how the cerebellum might influence the development of cerebral cortex and whether this co-developmental process is distinct between neurotypical and ASD children. Leveraging a large structural brain MRI dataset of neurotypical children and those diagnosed with ASD, we examined whether structural variation in cerebellar tissue across individuals was correlated with neocortical variation during development, including the thalamus as a coupling factor. We found that the thalamus plays a distinct role in moderating cerebro-cerebellar structural coordination in ASD. Notably, structural coupling between cerebellum, thalamus, and neocortex was strongest in younger childhood and waned by early adolescence, mirroring a previously undescribed trajectory of behavioral development between ASD and neurotypical children. Complementary functional connectivity analyses likewise revealed atypical connectivity between cerebellum and neocortex in ASD. This relationship was particularly prominent in a model of cerebellar structure predicting functional connectivity, where ASD and neurotypical children showed divergent patterns. Interestingly, these functional-structural relationships became more prominent with age, while structural effects were most prominent earlier in childhood, and showed significant lateralization. This pattern may suggest a developmental sequence where early uncoordinated structural growth amongst regions is followed by increasingly atypical functional synchronization. These findings provide multimodal evidence in the living brain for a cerebellar diaschisis model of autism, where both increased cerebellar-cerebral structural coupling and altered functional connectivity in cerebro-cerebellar pathways contribute to the ontogeny of this neurodevelopmental disorder.

Structure-function coupling in white matter uncovers the hypoconnectivity in autism spectrum disorder

BACKGROUND

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder associated with alterations in structural and functional coupling in gray matter. However, despite the detectability and modulation of brain signals in white matter, the structure-function coupling in white matter in autism remains less explored.

METHODS

In this study, we investigated structural-functional coupling in white matter (WM) regions, by integrating diffusion tensor data that contain fiber orientation information from WM tracts, with functional connectivity tensor data that reflect local functional anisotropy information. Using functional and diffusion magnetic resonance images, we analyzed a cohort of 89 ASD and 63 typically developing (TD) individuals from the Autism Brain Imaging Data Exchange II (ABIDE-II). Subsequently, the associations between structural-functional coupling in WM regions and ASD severity symptoms assessed by Autism Diagnostic Observation Schedule-2 were examined via supervised machine learning in an independent test cohort of 29 ASD individuals. Furthermore, we also compared the performance of multi-model features (i.e. structural-functional coupling) with single-model features (i.e. functional or structural models alone).

RESULTS

In the discovery cohort (ABIDE-II), individuals with ASD exhibited widespread reductions in structural-functional coupling in WM regions compared to TD individuals, particularly in commissural tracts (e.g. corpus callosum), association tracts (sagittal stratum), and projection tracts (e.g. internal capsule). Notably, supervised machine learning analysis in the independent test cohort revealed a significant correlation between these alterations in structural-functional coupling and ASD severity scores. Furthermore, compared to single-model features, the integration of multi-model features (i.e., structural-functional coupling) performed best in predicting ASD severity scores.

CONCLUSION

This work provides novel evidence for atypical structural-functional coupling in ASD in white matter regions, further refining our understanding of the critical role of WM networks in the pathophysiology of ASD.

Gradients of Brain Organization: Smooth Sailing from Methods Development to User Community

Multimodal neuroimaging grants a powerful in vivo window into the structure and function of the human brain. Recent methodological and conceptual advances have enabled investigations of the interplay between large-scale spatial trends - or gradients - in brain structure and function, offering a framework to unify principles of brain organization across multiple scales. Strong community enthusiasm for these techniques has been instrumental in their widespread adoption and implementation to answer key questions in neuroscience. Following a brief review of current literature on this framework, this perspective paper will highlight how pragmatic steps aiming to make gradient methods more accessible to the community propelled these techniques to the forefront of neuroscientific inquiry. More specifically, we will emphasize how interest for gradient methods was catalyzed by data sharing, open-source software development, as well as the organization of dedicated workshops led by a diverse team of early career researchers. To this end, we argue that the growing excitement for brain gradients is the result of coordinated and consistent efforts to build an inclusive community and can serve as a case in point for future innovations and conceptual advances in neuroinformatics. We close this perspective paper by discussing challenges for the continuous refinement of neuroscientific theory, methodological innovation, and real-world translation to maintain our collective progress towards integrated models of brain organization.

Sex differences in the flexibility of dynamic network reconfiguration of autism spectrum disorder based on multilayer network

Dynamic network reconfiguration alterations in the autism spectrum disorder (ASD) brain have been frequently reported. However, since the prevalence of ASD in males is approximately 3.8 times higher than that in females, and previous studies of dynamic network reconfiguration of ASD have predominantly used male samples, it is unclear whether sex differences exist in dynamic network reconfiguration in ASD. This study used resting-state functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange database, which included balanced samples of 64 males and 64 females with ASD, along with 64 demographically-matched typically developing control (TC) males and 64 TC females. The multilayer network analysis was used to explore the flexibility of dynamic network reconfiguration. The two-way analysis of variance was further performed to examine the sex-related changes in ASD in flexibility of dynamic network reconfiguration. A diagnosis-by-sex interaction effect was identified in the cingulo-opercular network (CON), central executive network (CEN), salience network (SN), and subcortical network (SUB). Compared with TC females, females with ASD showed lower flexibility in CON, CEN, SN, and SUB. The flexibility of CEN and SUB in males with ASD was higher than that in females with ASD. In addition, the flexibility of CON, CEN, SN, and SUB predicted the severity of social communication impairments and stereotyped behaviors and restricted interests only in females with ASD. These findings highlight significant sex differences in the flexibility of dynamic network reconfiguration in ASD and emphasize the importance of further study of sex differences in future ASD research.

Moving beyond processing- and analysis-related variation in resting-state functional brain imaging

When fields lack consensus standard methods and accessible ground truths, reproducibility can be more of an ideal than a reality. Such has been the case for functional neuroimaging, where there exists a sprawling space of tools and processing pipelines. We provide a critical evaluation of the impact of differences across five independently developed minimal preprocessing pipelines for functional magnetic resonance imaging. We show that, even when handling identical data, interpipeline agreement was only moderate, critically shedding light on a factor that limits cross-study reproducibility. We show that low interpipeline agreement can go unrecognized until the reliability of the underlying data is high, which is increasingly the case as the field progresses. Crucially we show that, when interpipeline agreement is compromised, so too is the consistency of insights from brain-wide association studies. We highlight the importance of comparing analytic configurations, because both widely discussed and commonly overlooked decisions can lead to marked variation.

Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning

Machine learning has been increasingly used to obtain individualized neuroimaging signatures for disease diagnosis, prognosis, and response to treatment in neuropsychiatric and neurodegenerative disorders. Therefore, it has contributed to a better understanding of disease heterogeneity by identifying disease subtypes with different brain phenotypic measures. In this review, we first present a systematic literature overview of studies using machine learning and multimodal magnetic resonance imaging to unravel disease heterogeneity in various neuropsychiatric and neurodegenerative disorders, including Alzheimer's disease, schizophrenia, major depressive disorder, autism spectrum disorder, and multiple sclerosis, as well as their potential in a transdiagnostic framework, where neuroanatomical and neurobiological commonalities were assessed across diagnostic boundaries. Subsequently, we summarize relevant machine learning methodologies and their clinical interpretability. We discuss the potential clinical implications of the current findings and envision future research avenues. Finally, we discuss an emerging paradigm called dimensional neuroimaging endophenotypes. Dimensional neuroimaging endophenotypes dissects the neurobiological heterogeneity of neuropsychiatric and neurodegenerative disorders into low-dimensional yet informative, quantitative brain phenotypic representations, serving as robust intermediate phenotypes (i.e., endophenotypes), presumably reflecting the interplay of underlying genetic, lifestyle, and environmental processes associated with disease etiology.

A functional parcellation of the whole brain in high-functioning individuals with autism spectrum disorder reveals atypical patterns of network organization

Researchers studying autism spectrum disorder (ASD) lack a comprehensive map of the functional network topography in the ASD brain. We used high-quality resting state functional MRI (rs-fMRI) connectivity data and a robust parcellation routine to provide a whole-brain map of functional networks in a group of seventy high-functioning individuals with ASD and a group of seventy typically developing (TD) individuals. The rs-fMRI data were collected using an imaging sequence optimized to achieve high temporal signal-to-noise ratio (tSNR) across the whole-brain. We identified functional networks using a parcellation routine that intrinsically incorporates internal consistency and repeatability of the networks by keeping only network distinctions that agree across halves of the data over multiple random iterations in each group. The groups were tightly matched on tSNR, in-scanner motion, age, and IQ. We compared the maps from each group and found that functional networks in the ASD group are atypical in three seemingly related ways: (1) whole-brain connectivity patterns are less stable across voxels within multiple functional networks, (2) the cerebellum, subcortex, and hippocampus show weaker differentiation of functional subnetworks, and (3) subcortical structures and the hippocampus are atypically integrated with the neocortex. These results were statistically robust and suggest that patterns of network connectivity between the neocortex and the cerebellum, subcortical structures, and hippocampus are atypical in ASD individuals.

Generalizable and transportable resting-state neural signatures characterized by functional networks, neurotransmitters, and clinical symptoms in autism

Autism spectrum disorder (ASD) is a lifelong condition with elusive biological mechanisms. The complexity of factors, including inter-site and developmental differences, hinders the development of a generalizable neuroimaging classifier for ASD. Here, we developed a classifier for ASD using a large-scale, multisite resting-state fMRI dataset of 730 Japanese adults, aiming to capture neural signatures that reflect pathophysiology at the functional network level, neurotransmitters, and clinical symptoms of the autistic brain. Our adult ASD classifier was successfully generalized to adults in the United States, Belgium, and Japan. The classifier further demonstrated its successful transportability to children and adolescents. The classifier contained 141 functional connections (FCs) that were important for discriminating individuals with ASD from typically developing controls. These FCs and their terminal brain regions were associated with difficulties in social interaction and dopamine and serotonin, respectively. Finally, we mapped attention-deficit/hyperactivity disorder (ADHD), schizophrenia (SCZ), and major depressive disorder (MDD) onto the biological axis defined by the ASD classifier. ADHD and SCZ, but not MDD, were located proximate to ASD on the biological dimensions. Our results revealed functional signatures of the ASD brain, grounded in molecular characteristics and clinical symptoms, achieving generalizability and transportability applicable to the evaluation of the biological continuity of related diseases.

Nine Neuroimaging-AI Endophenotypes Unravel Disease Heterogeneity and Partial Overlap across Four Brain Disorders: A Dimensional Neuroanatomical Representation

Disease heterogeneity poses a significant challenge for precision diagnostics. Recent work leveraging artificial intelligence has offered promise to dissect this heterogeneity by identifying complex intermediate brain phenotypes, herein called dimensional neuroimaging endophenotypes (DNEs). We advance the argument that these DNEs capture the degree of expression of respective neuroanatomical patterns measured, offering a dimensional neuroanatomical representation for studying disease heterogeneity and similarities of neurologic and neuropsychiatric diseases. We investigate the presence of nine such DNEs derived from independent yet harmonized studies on Alzheimer's disease (AD1-2)1, autism spectrum disorder (ASD1-3)2, late-life depression (LLD1-2)3, and schizophrenia (SCZ1-2)4, in the general population of 39,178 participants in the UK Biobank study. Phenome-wide associations revealed prominent associations between the nine DNEs and phenotypes related to the brain and other human organ systems. This phenotypic landscape aligns with the SNP-phenotype genome-wide associations, revealing 31 genomic loci associated with the nine DNEs (Bonferroni corrected P-value < 5×10-8/9). The DNEs exhibited significant genetic correlations, colocalization, and causal relationships with multiple human organ systems and chronic diseases. A causal effect (odds ratio=1.25 [1.11, 1.40], P-value=8.72×10-4) was established from AD2, characterized by focal medial temporal lobe atrophy, to AD. The nine DNEs, along with their polygenic risk scores, significantly enhanced the predictive accuracy for 14 systemic disease categories, particularly for conditions related to mental health and the central nervous system, as well as mortality outcomes. These findings underscore the potential of the nine DNEs to capture the expression of disease-related brain phenotypes in individuals of the general population and to relate such measures with genetics, lifestyle factors, and chronic diseases. All results are publicly available at https://labs-laboratory.com/medicine/.

Behavioral and brain morphological changes before and after hemispherotomy

Hemispherotomy is an effective surgery for treating refractory epilepsy from diffuse unihemispheric lesions. To date, postsurgery neuroplastic changes supporting behavioral recovery after left or right hemispherotomy remain unclear. In the present study, we systematically investigated changes in gray matter volume (GMV) before and after surgery and further analyzed their relationships with behavioral scores in two large groups of pediatric patients with left and right hemispherotomy (29 left and 28 right). To control for the dramatic developmental effect during this stage, age-adjusted GMV within unaffected brain regions was derived voxel by voxel using a normative modeling approach with an age-matched reference cohort of 2115 healthy children. Widespread GMV increases in the contralateral cerebrum and ipsilateral cerebellum and GMV decreases in the contralateral cerebellum were consistently observed in both patient groups, but only the left hemispherotomy patients showed GMV decreases in the contralateral cingulate gyrus. Intriguingly, the GMV decrease in the contralateral cerebellum was significantly correlated with improvement in behavioral scores in the right but not the left hemispherotomy patients. Importantly, the preoperative voxelwise GMV features can be used to significantly predict postoperative behavioral scores in both patient groups. These findings indicate an important role of the contralateral cerebellum in the behavioral recovery following right hemispherotomy and highlight the predictive potential of preoperative imaging features in postoperative behavioral performance.

Resolving autism spectrum disorder (ASD) through brain topologies using fMRI dataset with multi-layer perceptron (MLP)

Autism is a neurodevelopmental disorder that manifests in individuals during childhood and has enduring consequences for their social interactions and communication. The prediction of Autism Spectrum Disorder (ASD) in individuals based on the differences in brain networks and activities have been studied extensively in the recent past, however, with lower accuracies. Therefore in this research, identification at the early stage through computer-aided algorithms to differentiate between ASD and TD patients is proposed. In order to identify features, a Multi-Layer Perceptron (MLP) model is developed which utilizes logistic regression on characteristics extracted from connectivity matrices of subjects derived from fMRI images. The features that significantly contribute to the classification of individuals as having Autism Spectrum Disorder (ASD) or typically developing (TD) are identified by the logistic regression model. To enhance emphasis on essential attributes, an AND operation is integrated. This involves selecting features demonstrating statistical significance across diverse logistic regression analyses conducted on various random distributions. The iterative approach contributes to a comprehensive understanding of relevant features for accurate classification. By implementing this methodology, the estimation of feature importance became more dependable, and the potential for overfitting is moderated through the evaluation of model performance on various subsets of data. It is observed from the experimentation that the highly correlated Left Lateral Occipital Cortex and Right Lateral Occipital Cortex ROIs are only found in ASD. Also, it is noticed that the highly correlated Left Cerebellum Tonsil and Right Cerebellum Tonsil are only found in TD participants. Among the MLP classifier, a recall of 82.61 % is achieved followed by Logistic Regression with an accuracy of 72.46 %. MLP also stands out with a commendable accuracy of 83.57 % and AUC of 0.978.

Sex heterogeneity of dynamic brain activity and functional connectivity in autism spectrum disorder

Sex heterogeneity has been frequently reported in autism spectrum disorders (ASD) and has been linked to static differences in brain function. However, given the complexity of ASD and diagnosis-by-sex interactions, dynamic characteristics of brain activity and functional connectivity may provide important information for distinguishing ASD phenotypes between females and males. The aim of this study was to explore sex heterogeneity of functional networks in the ASD brain from a dynamic perspective. Resting-state functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange database were analyzed in 128 ASD subjects (64 males/64 females) and 128 typically developing control (TC) subjects (64 males/64 females). A sliding-window approach was adopted for the estimation of dynamic amplitude of low-frequency fluctuation (dALFF) and dynamic functional connectivity (dFC) to characterize time-varying brain activity and functional connectivity respectively. We then examined the sex-related changes in ASD using two-way analysis of variance. Significant diagnosis-by-sex interaction effects were identified in the left anterior cingulate cortex/medial prefrontal cortex (ACC/mPFC) and left precuneus in the dALFF analysis. Furthermore, there were significant diagnosis-by-sex interaction effects of dFC variance between the left ACC/mPFC and right ACC, left postcentral gyrus, left precuneus, right middle temporal gyrus and left inferior frontal gyrus, triangular part. These findings reveal the sex heterogeneity in brain activity and functional connectivity in ASD from a dynamic perspective, and provide new evidence for further exploring sex heterogeneity in ASD.

The Future of Disentangling the Heterogeneity of Autism With Neuroimaging Studies

Autism spectrum disorder (ASD) is a lifelong neurodevelopmental condition. Over the past decade, a considerable number of approaches have been developed to identify potential neuroimaging-based biomarkers of ASD that have uncovered specific neural mechanisms that underlie behaviors associated with ASD. However, the substantial heterogeneity among individuals who are diagnosed with ASD hinders the development of biomarkers. Disentangling the heterogeneity of ASD is pivotal to improving the quality of life for individuals with ASD by facilitating early diagnosis and individualized interventions for those who need support. In this review, we discuss recent advances in neuroimaging that have facilitated the characterization of the heterogeneity of this condition using 3 frameworks: neurosubtyping, dimensional models, and normative models. We also discuss the challenges, possible solutions, and clinical utility of these 3 frameworks. We argue that several factors need to be considered when parsing heterogeneity using neuroimaging, including co-occurring conditions, neurodevelopment, heredity and environment, and multisite and multimodal data. We close with a discussion of future directions for achieving a better understanding of the neural mechanisms that underlie neurodevelopmental heterogeneity and the future of precision medicine in ASD.

Brain-Charting Autism and Attention-Deficit/Hyperactivity Disorder Reveals Distinct and Overlapping Neurobiology

BACKGROUND

Autism and attention-deficit/hyperactivity disorder (ADHD) are heterogeneous neurodevelopmental conditions with complex underlying neurobiology that is still poorly understood. Despite overlapping presentation and sex-biased prevalence, autism and ADHD are rarely studied together and sex differences are often overlooked. Population modeling, often referred to as normative modeling, provides a unified framework for studying age-specific and sex-specific divergences in brain development.

METHODS

Here, we used population modeling and a large, multisite neuroimaging dataset (N = 4255 after quality control) to characterize cortical anatomy associated with autism and ADHD, benchmarked against models of average brain development based on a sample of more than 75,000 individuals. We also examined sex and age differences and relationship with autistic traits and explored the co-occurrence of autism and ADHD.

RESULTS

We observed robust neuroanatomical signatures of both autism and ADHD. Overall, autistic individuals showed greater cortical thickness and volume that was localized to the superior temporal cortex, whereas individuals with ADHD showed more global increases in cortical thickness but lower cortical volume and surface area across much of the cortex. The co-occurring autism+ADHD group showed a unique pattern of widespread increases in cortical thickness and certain decreases in surface area. We also found that sex modulated the neuroanatomy of autism but not ADHD, and there was an age-by-diagnosis interaction for ADHD only.

CONCLUSIONS

These results indicate distinct cortical differences in autism and ADHD that are differentially affected by age and sex as well as potentially unique patterns related to their co-occurrence.

Investigating the impact of lumping heterogenous conduct problems: aggression and rule-breaking rely on distinct spontaneous brain activity

Accumulating evidence suggests that aggression and rule-breaking may have distinct origins. However, grouping these heterogeneous behaviors into a single dimension labelled Conduct Problems (CP) has become the norm rather than the exception. Yet, the neurobiological features that differentiate aggression and rule-breaking remain largely unexplored. Using a large sample of children and adolescents (n = 1360, 6-18 years old), we examined the common and specific brain activity between CP, aggression, and rule-breaking behaviors. Analyses were conducted using fMRI resting-state data from a 10-minute session to explore the correlations between low frequency fluctuations and both broad and fine-grained CP dimensions. The broad CP dimension was associated with deficits in the precentral gyrus, superior temporal gyrus, and tempo-parietal junction. However, only the superior temporal gyrus was shared between aggression and rule-breaking. Activity of the precentral gyrus was mainly associated with rule-breaking, and the temporo-parietal cortex with aggression. More importantly, voxel-wise analyses on fine-grained dimensions revealed additional specific effects that were initially obscured when using a broad CP dimension. Finally, we showed that the findings specific to aggression and rule-breaking may be related to distinct brain networks and mental functions, especially ventral attention/sensorimotor processes and default mode network/social cognitions, respectively. The current study highlights that aggression and rule-breaking may be related to distinct local and distributed neurobiological markers. Overall, using fine-grained dimensions may provide a clearer picture of the role of neurobiological correlates in CP and their invariance across measurement levels. We advocate for adopting a more thorough examination of the lumping/splitting effect across neuroimaging studies on CP.

Associations of alcohol and tobacco use with psychotic, depressive and developmental disorders revealed via multimodal neuroimaging

People affected by psychotic, depressive and developmental disorders are at a higher risk for alcohol and tobacco use. However, the further associations between alcohol/tobacco use and symptoms/cognition in these disorders remain unexplored. We identified multimodal brain networks involving alcohol use (n = 707) and tobacco use (n = 281) via supervised multimodal fusion and evaluated if these networks affected symptoms and cognition in people with psychotic (schizophrenia/schizoaffective disorder/bipolar, n = 178/134/143), depressive (major depressive disorder, n = 260) and developmental (autism spectrum disorder/attention deficit hyperactivity disorder, n = 421/346) disorders. Alcohol and tobacco use scores were used as references to guide functional and structural imaging fusion to identify alcohol/tobacco use associated multimodal patterns. Correlation analyses between the extracted brain features and symptoms or cognition were performed to evaluate the relationships between alcohol/tobacco use with symptoms/cognition in 6 psychiatric disorders. Results showed that (1) the default mode network (DMN) and salience network (SN) were associated with alcohol use, whereas the DMN and fronto-limbic network (FLN) were associated with tobacco use; (2) the DMN and fronto-basal ganglia (FBG) related to alcohol/tobacco use were correlated with symptom and cognition in psychosis; (3) the middle temporal cortex related to alcohol/tobacco use was associated with cognition in depression; (4) the DMN related to alcohol/tobacco use was related to symptom, whereas the SN and limbic system (LB) were related to cognition in developmental disorders. In summary, alcohol and tobacco use were associated with structural and functional abnormalities in DMN, SN and FLN and had significant associations with cognition and symptoms in psychotic, depressive and developmental disorders likely via different brain networks. Further understanding of these relationships may assist clinicians in the development of future approaches to improve symptoms and cognition among psychotic, depressive and developmental disorders.

Multiscale heterogeneity of white matter morphometry in psychiatric disorders

Background

Inter-individual variability in neurobiological and clinical characteristics in mental illness is often overlooked by classical group-mean case-control studies. Studies using normative modelling to infer person-specific deviations of grey matter volume have indicated that group means are not representative of most individuals. The extent to which this variability is present in white matter morphometry, which is integral to brain function, remains unclear.

Methods

We applied Warped Bayesian Linear Regression normative models to T1-weighted magnetic resonance imaging data and mapped inter-individual variability in person-specific white matter volume deviations in 1,294 cases (58% male) diagnosed with one of six disorders (attention-deficit/hyperactivity, autism, bipolar, major depressive, obsessive-compulsive and schizophrenia) and 1,465 matched controls (54% male) recruited across 25 scan sites. We developed a framework to characterize deviation heterogeneity at multiple spatial scales, from individual voxels, through inter-regional connections, specific brain regions, and spatially extended brain networks.

Results

The specific locations of white matter volume deviations were highly heterogeneous across participants, affecting the same voxel in fewer than 8% of individuals with the same diagnosis. For autism and schizophrenia, negative deviations (i.e., areas where volume is lower than normative expectations) aggregated into common tracts, regions and large-scale networks in up to 35% of individuals.

Conclusions

The prevalence of white matter volume deviations was lower than previously observed in grey matter, and the specific location of these deviations was highly heterogeneous when considering voxel-wise spatial resolution. Evidence of aggregation within common pathways and networks was apparent in schizophrenia and autism but not other disorders.

BrainNPT: Pre-Training Transformer Networks for Brain Network Classification

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature learning in many domains, such as natural language processing. However, this technique is under-explored in brain network analysis. In this paper, we focused on pre-training methods with Transformer networks to leverage existing unlabeled data for brain functional network classification. First, we proposed a Transformer-based neural network, named as BrainNPT, for brain functional network classification. The proposed method leveraged token as a classification embedding vector for the Transformer model to effectively capture the representation of brain networks. Second, we proposed a pre-training framework for BrainNPT model to leverage unlabeled brain network data to learn the structure information of brain functional networks. The results of classification experiments demonstrated the BrainNPT model without pre-training achieved the best performance with the state-of-the-art models, and the BrainNPT model with pre-training strongly outperformed the state-of-the-art models. The pre-training BrainNPT model improved 8.75% of accuracy compared with the model without pre-training. We further compared the pre-training strategies and the data augmentation methods, analyzed the influence of the parameters of the model, and explained the trained model.

Brain functional gradient and structure features in adolescent and adult autism spectrum disorders

Understanding how function and structure are organized and their coupling with clinical traits in individuals with autism spectrum disorder (ASD) is a primary goal in network neuroscience research for ASD. Atypical brain functional networks and structures in individuals with ASD have been reported, but whether these associations show heterogeneous hierarchy modeling in adolescents and adults with ASD remains to be clarified. In this study, 176 adolescent and 74 adult participants with ASD without medication or comorbidities and sex, age matched healthy controls (HCs) from 19 research groups from the openly shared Autism Brain Imaging Data Exchange II database were included. To investigate the relationship between the functional gradient, structural changes, and clinical symptoms of brain networks in adolescents and adults with ASD, functional gradient and voxel-based morphometry (VBM) analyses based on 1000 parcels defined by Schaefer mapped to Yeo's seven-network atlas were performed. Pearson's correlation was calculated between the gradient scores, gray volume and density, and clinical traits. The subsystem-level analysis showed that the second gradient scores of the default mode networks and frontoparietal network in patients with ASD were relatively compressed compared to adolescent HCs. Adult patients with ASD showed an overall compression gradient of 1 in the ventral attention networks. In addition, the gray density and volumes of the subnetworks showed no significant differences between the ASD and HC groups at the adolescent stage. However, adults with ASD showed decreased gray density in the limbic network. Moreover, numerous functional gradient parameters, but not VBM parameters, in adolescents with ASD were considerably correlated with clinical traits in contrast to those in adults with ASD. Our findings proved that the atypical changes in adolescent ASD mainly involve the brain functional network, while in adult ASD, the changes are more related to brain structure, including gray density and volume. These changes in functional gradients or structures are markedly correlated with clinical traits in patients with ASD. Our study provides a novel understanding of the pathophysiology of the structure-function hierarchy in ASD.

Gender and age related brain structural and functional alterations in children with autism spectrum disorder

To explore the effects of age and gender on the brain in children with autism spectrum disorder using magnetic resonance imaging. 185 patients with autism spectrum disorder and 110 typically developing children were enrolled. In terms of gender, boys with autism spectrum disorder had increased gray matter volumes in the insula and superior frontal gyrus and decreased gray matter volumes in the inferior frontal gyrus and thalamus. The brain regions with functional alterations are mainly distributed in the cerebellum, anterior cingulate gyrus, postcentral gyrus, and putamen. Girls with autism spectrum disorder only had increased gray matter volumes in the right cuneus and showed higher amplitude of low-frequency fluctuation in the paracentral lobule, higher regional homogeneity and degree centrality in the calcarine fissure, and greater right frontoparietal network-default mode network connectivity. In terms of age, preschool-aged children with autism spectrum disorder exhibited hypo-connectivity between and within auditory network, somatomotor network, and visual network. School-aged children with autism spectrum disorder showed increased gray matter volumes in the rectus gyrus, superior temporal gyrus, insula, and suboccipital gyrus, as well as increased amplitude of low-frequency fluctuation and regional homogeneity in the calcarine fissure and precentral gyrus and decreased in the cerebellum and anterior cingulate gyrus. The hyper-connectivity between somatomotor network and left frontoparietal network and within visual network was found. It is essential to consider the impact of age and gender on the neurophysiological alterations in autism spectrum disorder children when analyzing changes in brain structure and function.

A review of deep learning-based information fusion techniques for multimodal medical image classification

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.

Differently different?: A commentary on the emerging social cognitive neuroscience of female autism

Autism is a neurodevelopmental condition, behaviourally identified, which is generally characterised by social communication differences, and restrictive and repetitive patterns of behaviour and interests. It has long been claimed that it is more common in males. This observed preponderance of males in autistic populations has served as a focussing framework in all spheres of autism-related issues, from recognition and diagnosis through to theoretical models and research agendas. One related issue is the near total absence of females in key research areas. For example, this paper reports a review of over 120 brain-imaging studies of social brain processes in autism that reveals that nearly 70% only included male participants or minimal numbers (just one or two) of females. Authors of such studies very rarely report that their cohorts are virtually female-free and discuss their findings as though applicable to all autistic individuals. The absence of females can be linked to exclusionary consequences of autism diagnostic procedures, which have mainly been developed on male-only cohorts. There is clear evidence that disproportionately large numbers of females do not meet diagnostic criteria and are then excluded from ongoing autism research. Another issue is a long-standing assumption that the female autism phenotype is broadly equivalent to that of the male autism phenotype. Thus, models derived from male-based studies could be applicable to females. However, it is now emerging that certain patterns of social behaviour may be very different in females. This includes a specific type of social behaviour called camouflaging or masking, linked to attempts to disguise autistic characteristics. With respect to research in the field of sex/gender cognitive neuroscience, there is emerging evidence of female differences in patterns of connectivity and/or activation in the social brain that are at odds with those reported in previous, male-only studies. Decades of research have excluded or overlooked females on the autistic spectrum, resulting in the construction of inaccurate and misleading cognitive neuroscience models, and missed opportunities to explore the brain bases of this highly complex condition. A note of warning needs to be sounded about inferences drawn from past research, but if future research addresses this problem of male bias, then a deeper understanding of autism as a whole, as well as in previously overlooked females, will start to emerge.

Atypical dynamic neural configuration in autism spectrum disorder and its relationship to gene expression profiles

Although it is well recognized that autism spectrum disorder (ASD) is associated with atypical dynamic functional connectivity patterns, the dynamic changes in brain intrinsic activity over each time point and the potential molecular mechanisms associated with atypical dynamic temporal characteristics in ASD remain unclear. Here, we employed the Hidden Markov Model (HMM) to explore the atypical neural configuration at every scanning time point in ASD, based on resting-state functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange. Subsequently, partial least squares regression and pathway enrichment analysis were employed to explore the potential molecular mechanism associated with atypical neural dynamics in ASD. 8 HMM states were inferred from rs-fMRI data. Compared to typically developing, individuals on the autism spectrum showed atypical state-specific temporal characteristics, including number of states and occurrences, mean life time and transition probability between states. Moreover, these atypical temporal characteristics could predict communication difficulties of ASD, and states assoicated with negative activation in default mode network and frontoparietal network, and positive activation in somatomotor network, ventral attention network, and limbic network, had higher predictive contribution. Furthermore, a total of 321 genes was revealed to be significantly associated with atypical dynamic brain states of ASD, and these genes are mainly enriched in neurodevelopmental pathways. Our study provides new insights into characterizing the atypical neural dynamics from a moment-to-moment perspective, and indicates a linkage between atypical neural configuration and gene expression in ASD.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.