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

Hierarchical feature extraction on functional brain networks for autism spectrum disorder identification with resting-state fMRI data

Autism Spectrum Disorder (ASD) is a pervasive developmental disorder of the central nervous system, primarily manifesting in childhood. It is characterized by atypical and repetitive behaviors. Conventional diagnostic methods mainly rely on questionnaire surveys and behavioral observations, which are prone to misdiagnosis due to their subjective nature. With advancements in medical imaging, MR imaging-based diagnostics have emerged as a more objective alternative. In this paper, we propose a Hierarchical Neural Network model for ASD identification, termed ASD-HNet, which hierarchically extracts features from functional brain networks based on resting-state functional magnetic resonance imaging (rs-fMRI) data. This hierarchical approach enhances the extraction of brain representations, improving diagnostic accuracy and aiding in the identification of brain regions associated with ASD. Specifically, features are extracted at three levels, i.e., the local region of interest (ROI) scale, the community scale, and the global representation scale. At the ROI scale, graph convolution is employed to transfer features between ROIs. At the community scale, functional gradients are introduced, and a K-Means clustering algorithm is applied to group ROIs with similar functional gradients into communities. Features from ROIs within the same community are then extracted to characterize the communities. At the global representation scale, we extract global features from the whole community-scale brain networks to represent the entire brain. We validate the effectiveness of the ASD-HNet model using the publicly available Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, ADHD-200,dataset and ABIDE-II dataset. Extensive experimental results demonstrate that ASD-HNet outperforms existing baseline methods. The code is available at https://github.com/LYQbyte/ASD-HNet.

Neuroimaging endophenotypes reveal underlying mechanisms and genetic factors contributing to progression and development of four brain disorders

Recent work leveraging artificial intelligence has offered promise to dissect disease heterogeneity by identifying complex intermediate brain phenotypes, 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 DNEs derived from independent yet harmonized studies on Alzheimer's disease, autism spectrum disorder, late-life depression and schizophrenia in the UK Biobank study. Phenome-wide associations align with genome-wide associations, revealing 31 genomic loci (P < 5 × 10-8/9) associated with the nine DNEs. 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.

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.

Atypical brain function hierarchy in autism spectrum disorder: insights from a novel analytical approach based on neuronal oscillation pattern

Hierarchy is the basic character of the human brain. Neuronal oscillation is one of the fundamental features of brain function, revealing abnormal hierarchical structures in psychiatric disorders from a system-level perspective. However, to date, no research has yet quantified the normal and abnormal brain functional hierarchy based on oscillation patterns. Therefore, this study aimed to quantify brain hierarchy based on neuronal oscillation patterns using the wide-scale information across multiple frequency bands of functional magnetic resonance imaging (fMRI) data and further investigate atypical oscillation patterns in autism spectrum disorder (ASD) at the system level. We analyzed resting-state fMRI data from the Autism Brain Imaging Data Exchange II, including 132 participants with ASD and 132 healthy controls. The energy distribution patterns (EDPs) across frequency bands were calculated for different brain networks using multivariate empirical mode decomposition and Hilbert Transform to represent oscillation patterns. The gradient analysis was applied to quantify the EDP segregation among networks, and the network median distance of gradients was compared between the two groups. The k-means clustering was applied to intuitively verify the atypical EDP in ASD. Across all participants, we observed that the EDPs of different brain regions were spatially coupled to the brain hierarchy. Compared to healthy controls, the ASD exhibited reduced segregation between unimodal and transmodal regions on both energy gradient and clustering analyses, correlating with social deficits. Our results quantitatively confirm that oscillation patterns can reflect the functional segregation among networks and provide novel evidence of the system-level imbalances in neuronal oscillations in ASD.

Enhancing brain age estimation under uncertainty: A spectral-normalized neural gaussian process approach utilizing 2.5D slicing

Brain age gap, the difference between estimated brain age and chronological age via magnetic resonance imaging, has emerged as a pivotal biomarker in the detection of brain abnormalities. While deep learning is accurate in estimating brain age, the absence of uncertainty estimation may pose risks in clinical use. Moreover, current 3D brain age models are intricate, and using 2D slices hinders comprehensive dimensional data integration. Here, we introduced Spectral-normalized Neural Gaussian Process (SNGP) accompanied by 2.5D slice approach for seamless uncertainty integration in a single network with low computational expenses, and extra dimensional data integration without added model complexity. Subsequently, we compared different deep learning methods for estimating brain age uncertainty via the Pearson correlation coefficient, a metric that helps circumvent systematic underestimation of uncertainty during training. SNGP shows excellent uncertainty estimation and generalization on a dataset of 11 public datasets (N = 6327), with competitive predictive performance (MAE=2.95). Besides, SNGP demonstrates superior generalization performance (MAE=3.47) on an independent validation set (N = 301). Additionally, we conducted five controlled experiments to validate our method. Firstly, uncertainty adjustment in brain age estimation improved the detection of accelerated brain aging in adolescents with ADHD, with a 38% increase in effect size after adjustment. Secondly, the SNGP model exhibited OOD detection capabilities, showing significant differences in uncertainty across Asian and non-Asian datasets. Thirdly, the performance of DenseNet as a backbone for SNGP was slightly better than ResNeXt, attributed to DenseNet's feature reuse capability, with robust generalization on an independent validation set. Fourthly, site effect harmonization led to a decline in model performance, consistent with previous studies. Finally, the 2.5D slice approach significantly outperformed 2D methods, improving model performance without increasing network complexity. In conclusion, we present a cost-effective method for estimating brain age with uncertainty, utilizing 2.5D slicing for enhanced performance, showcasing promise for clinical applications.

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.

Differences in Head Motion During Functional Magnetic Resonance Imaging Across Pediatric Neuropsychiatric Disorders

Background

Robust correction for head motion during functional magnetic resonance imaging is critical to avoid artifact-driven findings. Despite head motion differences across neuropsychiatric disorders, pediatric head motion across a range of diagnoses and covariates has not yet been evaluated. We tested 4 preregistered hypotheses: 1) externalizing disorder diagnoses will associate with more head motion during scanning; 2) internalizing disorder diagnoses will associate with less motion; 3) among children without attention-deficit/hyperactivity disorder, externalizing disorders will associate with more motion; and 4) among children with attention-deficit/hyperactivity disorder, comorbid internalizing disorders will associate with less motion.

Methods

Healthy Brain Network data releases 1.0-7.0 (n = 971) were analyzed in a discovery phase, and additional data released by February 29, 2024 (n = 437) were used in confirmatory analyses. Linear mixed-effects models were fitted with in-scanner head motion as the dependent variable. Binary independent variables of interest assessed for the presence or absence of externalizing or internalizing disorders.

Results

The confirmatory sample did not show significant associations between head motion and externalizing or internalizing disorders or support for the preregistered hypotheses. Across samples, there was a consistent interaction between age and neurodevelopmental diagnoses such that age-related decreases in head motion were attenuated in children with neurodevelopmental disorders.

Conclusions

Head motion remains an important confound in pediatric neuroimaging that may be associated with many factors, including neuropsychiatric symptoms, age, cognitive and physical attributes, and interactions among these variables. This work takes a step toward parsing these complex associations, focusing on neuropsychiatric diagnoses, age, and their interaction.

Disentangling the Switching Behavior in Functional Connectivity Dynamics in Autism Spectrum Disorder: Insights from Developmental Cohort Analysis and Molecular-Cellular Associations

Characterizing the transition or switching behavior between multistable brain states in functional connectivity dynamics (FCD) holds promise for uncovering the underlying neuropathology of Autism Spectrum Disorder (ASD). However, whether and how switching behaviors in FCD change in patients with developmental ASD, as well as their cellular and molecular basis, remains unexplored. This study develops a region-wise FCD switching index (RFSI) to investigate the drivers of FCD. This work finds that brain regions within the salience, default mode, and frontoparietal networks serve as abnormal drivers of FCD in ASD across different developmental stages. Additionally, changes in RFSI at different developmental stages of ASD correlated with transcriptomic profiles and neurotransmitter density maps. Importantly, the abnormal RFSI identifies in humans has also been observed in genetically edited ASD monkeys. Finally, single-nucleus RNA sequencing data from patients with developmental ASD are analyzed and aberrant switching behaviors in FCD may be mediated by somatostatin-expressing interneurons and altered differentiation patterns in astrocyte State2. In conclusion, this study provides the first evidence of abnormal drivers of FCD across different stages of ASD and their associated cellular and molecular mechanisms. These findings deepen the understanding of ASD neuropathology and offer valuable insights into treatment strategies.

Advancements in Medical Radiology Through Multimodal Machine Learning: A Comprehensive Overview

The majority of data collected and obtained from various sources over a patient's lifetime can be assumed to comprise pertinent information for delivering the best possible treatment. Medical data, such as radiographic and histopathology images, electrocardiograms, and medical records, all guide a physician's diagnostic approach. Nevertheless, most machine learning techniques in the healthcare field emphasize data analysis from a single modality, which is insufficiently reliable. This is especially evident in radiology, which has long been an essential topic of machine learning in healthcare because of its high data density, availability, and interpretation capability. In the future, computer-assisted diagnostic systems must be intelligent to process a variety of data simultaneously, similar to how doctors examine various resources while diagnosing patients. By extracting novel characteristics from diverse medical data sources, advanced identification techniques known as multimodal learning may be applied, enabling algorithms to analyze data from various sources and eliminating the need to train each modality. This approach enhances the flexibility of algorithms by incorporating diverse data. A growing quantity of current research has focused on the exploration of extracting data from multiple sources and constructing precise multimodal machine/deep learning models for medical examinations. A comprehensive analysis and synthesis of recent publications focusing on multimodal machine learning in detecting diseases is provided. Potential future research directions are also identified. This review presents an overview of multimodal machine learning (MMML) in radiology, a field at the cutting edge of integrating artificial intelligence into medical imaging. As radiological practices continue to evolve, the combination of various imaging and non-imaging data modalities is gaining increasing significance. This paper analyzes current methodologies, applications, and trends in MMML while outlining challenges and predicting upcoming research directions. Beginning with an overview of the different data modalities involved in radiology, namely, imaging, text, and structured medical data, this review explains the processes of modality fusion, representation learning, and modality translation, showing how they boost diagnosis efficacy and improve patient care. Additionally, this review discusses key datasets that have been instrumental in advancing MMML research. This review may help clinicians and researchers comprehend the spatial distribution of the field, outline the current level of advancement, and identify areas of research that need to be explored regarding MMML in radiology.

A multi-filter deep transfer learning framework for image-based autism spectrum disorder detection

Autism Spectrum Disorder (ASD) affects approximately [Formula: see text] of the global population and is characterized by difficulties in social communication and repetitive or obsessive behaviors. Early detection of autism is crucial, as it allows therapeutic interventions to be initiated earlier, significantly increasing the effectiveness of treatments. However, diagnosing ASD remains a challenge, as it is traditionally carried out through methods that are often subjective and based on interviews and clinical observations. With the advancement of computer vision and pattern recognition techniques, new possibilities are emerging to automate and enhance the detection of characteristics associated with ASD, particularly in the analysis of facial features. In this context, image-based computational approaches must address challenges such as low data availability, variability in image acquisition conditions, and high-dimensional feature representations generated by deep learning models. This study proposes a novel framework that integrates data augmentation, multi-filtering routines, histogram equalization, and a two-stage dimensionality reduction process to enrich the representation in pre-trained and frozen deep learning neural network models applied to image pattern recognition. The framework design is guided by practical needs specific to ASD detection scenarios: data augmentation aims to compensate for limited dataset sizes; image enhancement routines improve robustness to noise and lighting variability while potentially highlighting facial traits associated with ASD; feature scaling standardizes representations prior to classification; and dimensionality reduction compresses high-dimensional deep features while preserving discriminative power. The use of frozen pre-trained networks allows for a lightweight, deterministic pipeline without the need for fine-tuning. Experiments are conducted using eight pre-trained models on a well-established benchmark facial dataset in the literature, comprising samples of autistic and non-autistic individuals. The results show that the proposed framework improves classification accuracy by up to [Formula: see text] points when compared to baseline models using pre-trained networks without any preprocessing strategies - as evidenced by the ResNet-50 architecture, which increased from [Formula: see text] to [Formula: see text]. Moreover, Transformer-based models, such as ViTSwin, reached up to [Formula: see text] accuracy, highlighting the robustness of the proposed approach. These improvements were observed consistently across different network architectures and datasets, under varying data augmentation, filtering, and dimensionality reduction configurations. A systematic ablation study further confirms the individual and collective benefits of each component in the pipeline, reinforcing the contribution of the integrated approach. These findings suggest that the framework is a promising tool for the automated detection of autism, offering an efficient improvement in traditional deep learning-based approaches to assist in early and more accurate diagnosis.

Flexible nonlinear modeling reveals age-related differences in resting-state functional brain connectivity in autistic males from childhood to mid-adulthood

BACKGROUND

Divergent age-related functional brain connectivity in autism spectrum disorder (ASD) has been observed using resting-state fMRI, although the specific findings are inconsistent across studies. Common statistical regression approaches that fit identical models across functional brain networks may contribute to these inconsistencies. Relationships among functional networks have been reported to follow unique nonlinear developmental trajectories, suggesting the need for flexible modeling. Here we apply generalized additive models (GAMs) to flexibly adapt to distinct network trajectories and simultaneously describe divergent age-related changes from childhood into mid-adulthood in ASD.

METHODS

1107 males, aged 5-40, from the ABIDE I & II cross-sectional datasets were analyzed. Functional connectivity was extracted using a network-based template. Connectivity values were harmonized using COMBAT-GAM. Connectivity-age relationships were assessed with thin-plate spline GAMs. Post-hoc analyses defined the age-ranges of divergent aging in ASD.

RESULTS

Typically developing (TD) and ASD groups shared 15 brain connections that significantly changed with age (FDR-corrected p < 0.05). Network connectivity exhibited diverse nonlinear age-related trajectories across the functional connectome. Comparing ASD and TD groups, default mode to central executive between-network connectivity followed similar nonlinear paths with no group differences. Contrarily, the ASD group had chronic hypoconnectivity throughout default mode-ventral attentional (salience) and default mode-somatomotor aging trajectories. Within-network somatomotor connectivity was similar between groups in childhood but diverged in adolescence with the ASD group showing decreased within-network connectivity. Network connectivity between the somatomotor network and various other functional networks had fully disrupted age-related pathways in ASD compared to TD, displaying significantly different model curvatures and fits.

LIMITATIONS

The present analysis includes only male participants and has a restricted age range, limiting analysis of early development and later life aging, years 40 and beyond. Additionally, our analysis is limited to large-scale network cortical functional parcellation. To parse more specificity of brain region connectivity, a fine-grained functional parcellation including subcortical areas may be warranted.

CONCLUSION

Flexible non-linear modeling minimizes statistical assumptions and allows diagnosis-related brain connections to follow independent data-driven age-related pathways. Using GAMs, we describe complex age-related pathways throughout the human connectome and observe distinct periods of divergence in autism.

Multiscale heterogeneity of white matter morphometry in psychiatric disorders

BACKGROUND

Inter-individual variability in the neurobiological and clinical characteristics of mental illnesses are 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 69% 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.

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.

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.

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.

The Impact of Atlas Parcellation on Functional Connectivity Analysis Across Six Psychiatric Disorders

Neuropsychiatric disorders are associated with altered functional connectivity (FC); however, the reported regional patterns of functional alterations suffered from low replicability and high variability. This is partly because of differences in the atlas and delineation techniques used to measure FC-related deficits within/across disorders. We systematically investigated the impact of the brain parcellation approach on the FC-based brain network analysis. We focused on identifying the replicable FCs using three structural brain atlases, including Automated Anatomical Labeling (AAL), Brainnetome atlas (BNA) and HCP_MMP_1.0, and four functional brain parcellation approaches: Yeo-Networks (Yeo), Gordon parcel (Gordon) and two Schaefer parcelletions, among correlation, group difference, and classification tasks in six neuropsychiatric disorders: attention deficit and hyperactivity disorder (ADHD, n = 340), autism spectrum disorder (ASD, n = 513), schizophrenia (SZ, n = 200), schizoaffective disorder (SAD, n = 142), bipolar disorder (BP, n = 172), and major depression disorder (MDD, n = 282). Our cross-atlas/disorder analyses demonstrated that frontal-related FC deficits were reproducible in all disorders, independent of the atlasing approach; however, replicable FC extraction in other areas and the classification accuracy were affected by the parcellation schema. Overall, functional atlases with finer granularity performed better in classification tasks. Specifically, the Schaefer atlases generated the most repeatable FC deficit patterns across six illnesses. These results indicate that frontal-related FCs may serve as potential common and robust neuro-abnormalities across 6 psychiatric disorders. Furthermore, in order to improve the replicability of rsfMRI-based FC analyses, this study suggests the use of functional templates at larger granularity.

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.

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.

Differentiating Functional Connectivity Patterns in ADHD and Autism Among the Young People: A Machine Learning Solution

OBJECTIVE

ADHD and autism are complex and frequently co-occurring neurodevelopmental conditions with shared etiological and pathophysiological elements. In this paper, we attempt to differentiate these conditions among the young people in terms of intrinsic patterns of brain connectivity revealed during resting state using machine learning approaches. We had two key objectives: (a) to determine the extent to which ADHD and autism could be effectively distinguished via machine learning from one another on this basis and (b) to identify the brain networks differentially implicated in the two conditions.

METHOD

Data from two publicly available resting-state functional magnetic resonance imaging (fMRI) resources-Autism Brain Imaging Data Exchange (ABIDE) and the ADHD-200 Consortium-were analyzed. A total of 330 participants (65 females and 265 males; mean age = 11.6 years), comprising equal subgroups of 110 participants each for ADHD, autism, and healthy controls (HC), were selected from the data sets ensuring data quality and the exclusion of comorbidities. We identified region-to-region connectivity values, which were subsequently employed as inputs to the linear discriminant analysis algorithm.

RESULTS

Machine learning models provided strong differentiation between connectivity patterns in participants with ADHD and autism-with the highest accuracy of 85%. Predominantly frontoparietal network alterations in connectivity discriminate ADHD individuals from autism and neurotypical group. Networks contributing to discrimination of autistic individuals from neurotypical group were more heterogeneous. These included language, salience, and frontoparietal networks.

CONCLUSION

These results contribute to our understanding of the distinct neural signatures underlying ADHD and autism in terms of intrinsic patterns of brain connectivity. The high level of discriminability between ADHD and autism, highlights the potential role of brain based metrics in supporting differential diagnostics.

Parsing the heterogeneity of brain structure and function in male children with autism spectrum disorder: a multimodal MRI study

Autism spectrum disorder (ASD) is a neurodevelopmental condition with high structural and functional heterogeneity. Multimodal fusion of structural and functional magnetic resonance imaging (MRI) allows better integration of ASD features from multiple perspectives. This study aimed to uncover the potential ASD subtypes by fusing the features of brain structure and function. An unsupervised learning method, similarity network fusion (SNF), was used. Resting-state functional MRI and structural MRI from the Autism Brain Imaging Data Exchange database of 207 male children were included in this study (105 ASD; 102 healthy controls (HC)). Gray matter volume (GMV) and amplitude of low-frequency fluctuation (ALFF) were utilized to represent structural and functional features separately. Structural and functional distance networks were constructed and fused by SNF. Then spectral clustering was carried out on the fused network. At last, the multivariate support vector regression analysis was used to investigate the relationship between the multimodal alterations and symptom severity of ASD subtypes. Two ASD subtypes were identified. Compared to HC, the two ASD subtypes demonstrated opposite GMV changes and distinct ALFF alterations. Furthermore, the alterations of ALFF predicted the severity of social communication impairments in ASD subtype 1. However, no significant associations were found between the multimodal alterations and symptoms in ASD subtype 2. These findings demonstrate the existence of heterogeneity with distinct structural and functional patterns in ASD and highlight the crucial role of combining multimodal features in investigating the neural mechanism underlying ASD.

Revealing the Multivariate Associations Between Autistic Traits and Principal Functional Connectome

Autism Spectrum Disorder (ASD) is a multifaceted neurodevelopmental condition characterized by a spectrum of behavioral and cognitive traits. As the characteristics of ASD are highly heterogeneous across individuals, a dimensional approach that overcomes the limitation of the categorical approach is preferred to reveal the symptomatology of ASD. Previous neuroimaging studies demonstrated strong links between large-scale brain networks and autism phenotypes. However, the existing studies have primarily focused on univariate association analysis, which limits our understanding of autism connectopathy. Using resting-state functional magnetic resonance imaging data from 309 participants (168 individuals with ASD and 141 typically developing controls) across a discovery dataset and two independent validation datasets, we identified multivariate associations between high-dimensional neuroimaging features and diverse phenotypic measures (20 or 7 measures). We generated low-dimensional representations of functional connectivity (i.e., gradients) and assessed their multivariate associations with autism-related phenotypes of social, behavioral, and cognitive problems using sparse canonical correlation analysis (SCCA). We selected three functional gradients that represented the cortical axes of the sensory-transmodal, motor-visual, and multiple demand-rests of the brain. The SCCA revealed multivariate associations between gradients and phenotypic measures, which were noted as linked dimensions. We identified three linked dimensions: the links between (1) the first gradient and social impairment, (2) the second and internalizing/externalizing problems, and (3) the third and metacognitive problems. Our findings were partially replicated in two independent validation datasets, indicating robustness. Multivariate association analysis linking high-dimensional neuroimaging and phenotypic features may offer promising avenues for establishing a dimensional approach to autism diagnosis.

Neuroimaging-AI endophenotypes reveal underlying mechanisms and genetic factors contributing to progression and development of four brain disorders

Recent work leveraging artificial intelligence has offered promise to dissect disease heterogeneity by identifying complex intermediate brain phenotypes, 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 DNEs derived from independent yet harmonized studies on Alzheimer's disease, autism spectrum disorder, late-life depression, and schizophrenia in the UK Biobank study. Phenome-wide associations align with genome-wide associations, revealing 31 genomic loci (P-value<5×10-8/9) associated with the nine DNEs.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.

Atypical maturation of the functional connectome hierarchy in autism

BACKGROUND

Autism spectrum disorder (ASD) is marked by disruptions in low-level sensory processing and higher-order sociocognitive functions, suggesting a complex interplay between different brain regions across the cortical hierarchy. However, the developmental trajectory of this hierarchical organization in ASD remains underexplored. Herein, we investigated the maturational abnormalities in the cortical hierarchy among individuals with ASD.

METHODS

Resting-state functional magnetic resonance imaging data from three large-scale datasets were analyzed: Autism Brain Imaging Data Exchange I and II and Lifespan Human Connectome Project Development (aged 5-22 years). The principal functional connectivity gradient representing cortical hierarchy was estimated using diffusion map embedding. By applying normative modeling with the generalized additive model for location, scale, and shape (GAMLSS), we captured the nonlinear trajectories of the developing functional gradient, as well as the individual-level deviations in ASD from typical development based on centile scores measured as deviations from the normative curves. A whole-brain summary metric, the functional hierarchy score, was derived to measure the extent of abnormal maturation in individuals with ASD. Finally, through a series of mediation analyses, we examined the potential role of network-level connectomic disruptions between the diagnoses and deviations in the cortical hierarchy.

RESULTS

The maturation of cortical hierarchy in individuals with ASD followed a non-linear trajectory, showing delayed maturation during childhood compared to that of typically developing individuals, followed by an accelerated "catch-up" phase during adolescence and a subsequent decline in young adulthood. The nature of these deviations varied across networks, with sensory and attention networks displaying the most pronounced abnormalities in childhood, while higher-order networks, particularly the default mode network (DMN), remaining impaired from childhood to adolescence. Mediation analyses revealed that the persistent reduction in DMN segregation throughout development was a key contributor to the atypical development of cortical hierarchy in ASD.

LIMITATIONS

The uneven distribution of samples across age groups, particularly in the later stages of development, limited our ability to fully capture developmental trajectories among older individuals.

CONCLUSIONS

These findings highlight the importance of understanding the developmental trajectories of cortical organization in ASD, collectively suggesting that early interventions aimed at promoting the normative development of higher-order networks may be critical for improving outcomes in individuals with ASD.

Mapping Along-Tract White Matter Microstructural Differences in Autism

Previous diffusion magnetic resonance imaging (dMRI) research has indicated altered white matter microstructure in autism, but the implicated regions are highly inconsistent across studies. Such prior work has largely used conventional dMRI analysis methods, including the traditional microstructure model, based on diffusion tensor imaging (DTI). However, these methods are limited in their ability to precisely map microstructural differences and accurately resolve complex fiber configurations. In our study, we investigated white matter microstructure alterations in autism using the refined along-tract analytic approach, BUndle ANalytics (BUAN), and an advanced microstructure model, the tensor distribution function (TDF). We analyzed dMRI data from 365 autistic and neurotypical participants (5-24 years; 34% female) from 10 cohorts to examine commissural and association tracts. Autism was associated with lower fractional anisotropy and higher diffusivity in localized portions of nearly every commissural and association tract examined; these tracts inter-connected a wide range of brain regions, including frontal, temporal, parietal, and occipital. Taken together, BUAN and TDF allow robust and spatially precise mapping of microstructural properties in autism. Our findings rigorously demonstrate that white matter microstructure alterations in autism may be greater within specific regions of individual tracts, and that the implicated tracts are distributed across the brain.

Unravelling pathological ageing with brain age gap estimation in Alzheimer's disease, diabetes and schizophrenia

Brain age gap estimation (BrainAGE), the difference between predicted brain age and chronological age, might be a putative biomarker aiming to detect the transition from healthy to pathological brain ageing. The biomarker primarily models healthy ageing with machine learning models trained with structural magnetic resonance imaging (MRI) data. BrainAGE is expected to translate the deviations in neural ageing trajectory and has been shown to be increased in multiple pathologies, such as Alzheimer's disease (AD), schizophrenia and Type 2 diabetes (T2D). Thus, accelerated ageing seems to be a general feature of neuropathological processes. However, neurobiological constraints remain to be identified to provide specificity to this biomarker. Explainability might be the key to uncovering age predictions and understanding which brain regions lead to an elevated predicted age on a given pathology compared to healthy controls. This is highly relevant to understanding the similarities and differences in neurodegeneration in AD and T2D, which remains an outstanding biological question. Sensitivity maps explain models by computing the importance of each voxel on the final prediction, thereby contributing to the interpretability of deep learning approaches. This paper assesses whether sensitivity maps yield different results across three conditions related to pathological neural ageing: AD, schizophrenia and T2D. Five deep learning models were considered, each model trained with different MRI data types: minimally processed T1-weighted brain scans, and corresponding grey matter, white matter, cerebrospinal fluid tissue segmentation and deformation fields (after spatial normalization). Our results revealed an increased BrainAGE in all pathologies, with a different mean, which is the smallest in schizophrenia; this is in line with the observation that neural loss is secondary in this early-onset condition. Importantly, our findings suggest that the sensitivity, indexing regional weights, for all models varies with age. A set of regions were shown to yield statistical differences across conditions. These sensitivity results suggest that mechanisms of neurodegeneration are quite distinct in AD and T2D. For further validation, the sensitivity and the morphometric maps were compared. The findings outlined a high congruence between the sensitivity and morphometry maps for age and clinical group conditions. Our evidence outlines that the biological explanation of model predictions is vital in adding specificity to the BrainAGE and understanding the pathophysiology of chronic conditions affecting the brain.

Structural pathways related to the subventricular zone are decreased in volume with altered microstructure in young adult males with autism spectrum disorder

Autism spectrum disorder is a neurodevelopmental condition characterized by reduced social communication and repetitive behaviors. Altered neurogenesis, including disturbed neuronal migration, has been implicated in autism spectrum disorder. Using diffusion MRI, we previously identified neuronal migration pathways in the human fetal brain and hypothesized that similar pathways persist into adulthood, with differences in volume and microstructural characteristics between individuals with autism spectrum disorder and controls. We analyzed diffusion MRI-based tractography of subventricular zone-related pathways in 15 young adult men with autism spectrum disorder and 18 controls at Massachusetts General Hospital, with validation through the Autism Imaging Data Exchange II dataset. Participants with autism spectrum disorder had reduced subventricular zone pathway volumes and fractional anisotropy compared to controls. Furthermore, subventricular zone pathway volume was positively correlated (r: 0.68; 95% CI: 0.25 to 0.88) with symptom severity, suggesting that individuals with more severe symptoms tended to have larger subventricular zone pathway volumes, normalized by brain size. Analysis of the Autism Imaging Data Exchange cohort confirmed these findings of reduced subventricular zone pathway volumes in autism spectrum disorder. While some of these pathways may potentially include inaccurately disconnected pathways that go through the subventricular zone, our results suggest that diffusion MRI-based tractography pathways anatomically linked to the periventricular region are associated with certain symptom types in adult males with autism spectrum disorder.

Biological subtyping of autism via cross-species fMRI

It is frequently assumed that the phenotypic heterogeneity in autism spectrum disorder reflects underlying pathobiological variation. However, direct evidence in support of this hypothesis is lacking. Here, we leverage cross-species functional neuroimaging to examine whether variability in brain functional connectivity reflects distinct biological mechanisms. We find that fMRI connectivity alterations in 20 distinct mouse models of autism (n=549 individual mice) can be clustered into two prominent hypo- and hyperconnectivity subtypes. We show that these connectivity profiles are linked to distinct signaling pathways, with hypoconnectivity being associated with synaptic dysfunction, and hyperconnectivity reflecting transcriptional and immune-related alterations. Extending these findings to humans, we identify analogous hypo- and hyperconnectivity subtypes in a large, multicenter resting state fMRI dataset of n=940 autistic and n=1036 neurotypical individuals. Remarkably, hypo- and hyperconnectivity autism subtypes are replicable across independent cohorts (accounting for 25.1% of all autism data), exhibit distinct functional network architecture, are behaviorally dissociable, and recapitulate synaptic and immune mechanisms identified in corresponding mouse subtypes. Our cross-species investigation, thus, decodes the heterogeneity of fMRI connectivity in autism into distinct pathway-specific etiologies, offering a new empirical framework for targeted subtyping of autism.

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.

AI-based non-invasive imaging technologies for early autism spectrum disorder diagnosis: A short review and future directions

Autism Spectrum Disorder (ASD) is a neurological condition, with recent statistics from the CDC indicating a rising prevalence of ASD diagnoses among infants and children. This trend emphasizes the critical importance of early detection, as timely diagnosis facilitates early intervention and enhances treatment outcomes. Consequently, there is an increasing urgency for research to develop innovative tools capable of accurately and objectively identifying ASD in its earliest stages. This paper offers a short overview of recent advancements in non-invasive technology for early ASD diagnosis, focusing on an imaging modality, structural MRI technique, which has shown promising results in early ASD diagnosis. This brief review aims to address several key questions: (i) Which imaging radiomics are associated with ASD? (ii) Is the parcellation step of the brain cortex necessary to improve the diagnostic accuracy of ASD? (iii) What databases are available to researchers interested in developing non-invasive technology for ASD? (iv) How can artificial intelligence tools contribute to improving the diagnostic accuracy of ASD? Finally, our review will highlight future trends in ASD diagnostic efforts.

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.

PTEN mutations impair CSF dynamics and cortical networks by dysregulating periventricular neural progenitors

Enlargement of the cerebrospinal fluid (CSF)-filled brain ventricles (ventriculomegaly) is a defining feature of congenital hydrocephalus (CH) and an under-recognized concomitant of autism. Here, we show that de novo mutations in the autism risk gene PTEN are among the most frequent monogenic causes of CH and primary ventriculomegaly. Mouse Pten-mutant ventriculomegaly results from aqueductal stenosis due to hyperproliferation of periventricular Nkx2.1+ neural progenitor cells (NPCs) and increased CSF production from hyperplastic choroid plexus. Pten-mutant ventriculomegalic cortices exhibit network dysfunction from increased activity of Nkx2.1+ NPC-derived inhibitory interneurons. Raptor deletion or postnatal everolimus treatment corrects ventriculomegaly, rescues cortical deficits and increases survival by antagonizing mTORC1-dependent Nkx2.1+ NPC pathology. Thus, PTEN mutations concurrently alter CSF dynamics and cortical networks by dysregulating Nkx2.1+ NPCs. These results implicate a nonsurgical treatment for CH, demonstrate a genetic association of ventriculomegaly and ASD, and help explain neurodevelopmental phenotypes refractory to CSF shunting in select individuals with CH.

Reproducible Brain Charts: An open data resource for mapping brain development and its associations with mental health

Major mental disorders are increasingly understood as disorders of brain development. Large and heterogeneous samples are required to define generalizable links between brain development and psychopathology. To this end, we introduce the Reproducible Brain Charts (RBC), an open data resource that integrates data from 5 large studies of brain development in youth from three continents (N=6,346; 45% Female). Confirmatory bifactor models were used to create harmonized psychiatric phenotypes that capture major dimensions of psychopathology. Following rigorous quality assurance, neuroimaging data were carefully curated and processed using consistent pipelines in a reproducible manner with DataLad, the Configurable Pipeline for the Analysis of Connectomes (C-PAC), and FreeSurfer. Initial analyses of RBC data emphasize the benefit of careful quality assurance and data harmonization in delineating developmental effects and associations with psychopathology. Critically, all RBC data - including harmonized psychiatric phenotypes, unprocessed images, and fully processed imaging derivatives - are openly shared without a data use agreement via the International Neuroimaging Data-sharing Initiative. Together, RBC facilitates large-scale, reproducible, and generalizable research in developmental and psychiatric neuroscience.

Diffusion transformer-augmented fMRI functional connectivity for enhanced autism spectrum disorder diagnosis

Objective.Functional magnetic resonance imaging (fMRI) is often modeled as networks of Regions of Interest and their functional connectivity to study brain functions and mental disorders. Limited fMRI data due to high acquisition costs hampers recognition model performance. We aim to address this issue using generative diffusion models for data augmentation.Approach.We propose Brain-Net-Diffusion, a transformer-based latent diffusion model to generate realistic functional connectivity for augmenting fMRI datasets and evaluate its impact on classification tasks.Main results.The Brain-Net-Diffusion effectively generates connectivity patterns resembling real data and significantly enhances classification performance. Augmentation using Brain-Net-Diffusion increased downstream autism spectrum disorder classification accuracy by 4.3% compared to no augmentation. It also outperformed other augmentation methods, with accuracy improvements ranging from 1.3% to 2.2%.Significance.Our approach demonstrates the effectiveness of diffusion models for fMRI data augmentation, providing a robust solution for overcoming data scarcity in functional connectivity analysis. To facilitate further research, we have made our code publicly available athttps://github.com/JoeZhao527/brain-net-diffusion.

Age-related changes in brain signal variability in autism spectrum disorder

BACKGROUND

Brain signal variability (BSV) is an important understudied aspect of brain function linked to cognitive flexibility and adaptive behavior. Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by social communication difficulties and restricted and repetitive behaviors (RRBs). While atypical brain function has been identified in individuals with ASD using fMRI task-activation and functional connectivity approaches, little is known about age-related relationships with resting-state BSV and repetitive behaviors in ASD.

METHODS

We conducted a cross-sectional examination of resting-state BSV and its relationship with age and RRBs in a cohort of individuals with Autism Brain Imaging Data Exchange (n = 351) and typically developing (TD) individuals (n = 402) aged 5-50 years obtained from the Autism Brain Imaging Data Exchange. RRBs were assessed using the Autism Diagnostic Interview-Revised (ADI-RRB) scale. BSV was quantified using the root-mean-square successive difference (rMSSD) of the resting-state fMRI time series. We examined categorical group differences in rMSSD between ASD and TD groups, controlling for both linear and quadratic age. To identify dimensional relationships between age, group, and rMSSD, we utilized interaction regressors for group x age and group x quadratic age. Within a subset of individuals with ASD (269 subjects), we explored the relationship between rMSSD and ADI-RRB scores, both with and without age considerations. The relationship between rMSSD and ADI-RRB scores was further analyzed while accounting for linear and quadratic age. Additionally, we investigated the relationship between BSV, age, and ADI-RRB scores using interaction regressors for age x RRB and quadratic age x RRB.

RESULTS

When controlling for linear age effects, we observed significant group differences between individuals with ASD and TD individuals in the default-mode network (DMN) and visual network, with decreased BSV in ASD. Similarly, controlling for quadratic age effects revealed significant group differences in the DMN and visual network. In both cases, individuals with ASD showed decreased BSV compared with TD individuals in these brain regions. The group × age interaction demonstrated significant group differences in the DMN, and visual network brain areas, indicating that rMSSD was greater in older individuals compared with younger individuals in the ASD group, while rMSSD was greater in younger individuals compared with older individuals in the TD group. The group × quadratic age interaction showed significant differences in the brain regions included in DMN, with an inverted U-shaped rMSSD-age relationship in ASD (higher rMSSD in younger individuals that slightly increased into middle age before decreasing) and a U-shaped rMSSD-age relationship in TD (higher rMSSD in younger and older individuals compared with middle-aged individuals). When controlling for linear and quadratic age effects, we found a significant positive association between rMSSD and ADI-RRB scores in brain regions within the DMN, salience, and visual network. While no significant results were observed for the linear age × RRB interaction, a significant association between quadratic age and ADI-RRB scores emerged in the DMN, dorsal attention network, and sensorimotor network. Individuals with high ADI-RRB scores exhibited an inverted U-shaped relationship between rMSSD and age, with lower rMSSD levels observed in both younger and older individuals, and higher rMSSD in middle-aged individuals. Those with mid-range ADI-RRB scores displayed a weak inverted U-shaped rMSSD-age association. In contrast, individuals with low ADI-RRB scores showed a U-shaped rMSSD-age association, with higher rMSSD levels in younger and older individuals, but a lower rMSSD in middle-aged individuals.

CONCLUSION

These findings highlight age-related atypical BSV patterns in ASD and their association with repetitive behaviors, contributing to the growing literature on understanding alterations in functional brain maturation in ASD.

Effective connectivity alterations of the triple network model in the co-occurrence of autism spectrum disorder and attention deficit hyperactivity disorder

Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) are both highly prevalent disorders and frequently co-occur. The underlying neurological mechanisms of the co-occurrence of ASD and ADHD (ASD + ADHD) remain unknown. This study focuses on investigating the effective connectivity (EC) alterations within the triple network model in individuals with ASD + ADHD. Resting-state functional magnetic resonance imaging data were obtained from 44 individuals with ASD + ADHD, 60 individuals with ASD without ADHD (ASD-only), 35 individuals with ADHD without ASD (ADHD-only), and 81 healthy controls (HC) from the Autism Brain Imaging Data Exchange II and the ADHD-200 Sample database. Spectral dynamic causal modeling was employed to explore the EC alterations within and between the default mode network, salience network, and central executive network. Our analysis showed that compared to HC, ASD + ADHD, ASD-only, and ADHD-only exhibited both shared and disorder-specific EC alterations within the triple-network model. These results have potential clinical implications for identifying ASD + ADHD, facilitating diagnostic accuracy, guiding targeted treatment approaches, and informing etiological studies.

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.

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.

Robust Autism Spectrum Disorder-Related Spatial Covariance Gray Matter Pattern Revealed With a Large-Scale Multi-Center Dataset

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder and its underlying neuroanatomical mechanisms still remain unclear. The scaled subprofile model of principal component analysis (SSM-PCA) is a data-driven multivariate technique for capturing stable disease-related spatial covariance pattern. Here, SSM-PCA is innovatively applied to obtain robust ASD-related gray matter volume pattern associated with clinical symptoms. We utilized T1-weighted structural MRI images (sMRI) of 576 subjects (288 ASDs and 288 typically developing (TD) controls) aged 7-29 years from the Autism Brain Imaging Data Exchange II (ABIDE II) dataset. These images were analyzed with SSM-PCA to identify the ASD-related spatial covariance pattern. Subsequently, we investigated the relationship between the pattern and clinical symptoms and verified its robustness. Then, the applicability of the pattern under different age stages were further explored. The results revealed that the ASD-related pattern primarily involves the thalamus, putamen, parahippocampus, orbitofrontal cortex, and cerebellum. The expression of this pattern correlated with Social Response Scale and Social Communication Questionnaire scores. Moreover, the ASD-related pattern was robust for the ABIDE I dataset. Regarding the applicability of the pattern for different age stages, the effect sizes of its expression in ASD were medium in the children and adults, while small in adolescents. This study identified a robust ASD-related pattern based on gray matter volume that is associated with social deficits. Our findings provide new insights into the neuroanatomical mechanisms of ASD and may facilitate its future 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.

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.

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.

FastSurfer-LIT: Lesion inpainting tool for whole-brain MRI segmentation with tumors, cavities, and abnormalities

Resection cavities, tumors, and other lesions can fundamentally alter brain structure and present as abnormalities in brain MRI. Specifically, quantifying subtle neuroanatomical changes in other, not directly affected regions of the brain is essential to assess the impact of tumors, surgery, chemo/radiotherapy, or drug treatments. However, only a limited number of solutions address this important task, while many standard analysis pipelines simply do not support abnormal brain images at all. In this paper, we present a method to perform sensitive neuroanatomical analysis of healthy brain regions in the presence of large lesions and cavities. Our approach called "FastSurfer Lesion Inpainting Tool" (FastSurfer-LIT) leverages the recently emerged Denoising Diffusion Probabilistic Models (DDPM) to fill lesion areas with healthy tissue that matches and extends the surrounding tissue. This enables subsequent processing with established MRI analysis methods such as the calculation of adjusted volume and surface measurements using FastSurfer or FreeSurfer. FastSurfer-LIT significantly outperforms previously proposed solutions on a large dataset of simulated brain tumors (N = 100) and synthetic multiple sclerosis lesions (N = 39) with improved Dice and Hausdorff measures, and also on a highly heterogeneous dataset with lesions and cavities in a manual assessment (N = 100). Finally, we demonstrate increased reliability to reproduce pre-operative cortical thickness estimates from corresponding post-operative temporo-mesial resection surgery MRIs. The method is publicly available at https://github.com/Deep-MI/LIT and will be integrated into the FastSurfer toolbox.

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.

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.