Identifying disease-related subnetwork connectome biomarkers by sparse hypergraph learning.
ABSTRACT: The functional brain network has gained increased attention in the neuroscience community because of its ability to reveal the underlying architecture of human brain. In general, majority work of functional network connectivity is built based on the correlations between discrete-time-series signals that link only two different brain regions. However, these simple region-to-region connectivity models do not capture complex connectivity patterns between three or more brain regions that form a connectivity subnetwork, or subnetwork for short. To overcome this current limitation, a hypergraph learning-based method is proposed to identify subnetwork differences between two different cohorts. To achieve our goal, a hypergraph is constructed, where each vertex represents a subject and also a hyperedge encodes a subnetwork with similar functional connectivity patterns between different subjects. Unlike previous learning-based methods, our approach is designed to jointly optimize the weights for all hyperedges such that the learned representation is in consensus with the distribution of phenotype data, i.e. clinical labels. In order to suppress the spurious subnetwork biomarkers, we further enforce a sparsity constraint on the hyperedge weights, where a larger hyperedge weight indicates the subnetwork with the capability of identifying the disorder condition. We apply our hypergraph learning-based method to identify subnetwork biomarkers in Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD). A comprehensive quantitative and qualitative analysis is performed, and the results show that our approach can correctly classify ASD and ADHD subjects from normal controls with 87.65 and 65.08% accuracies, respectively.
Project description:BACKGROUND:Children with autism spectrum disorder (ASD) and co-occurring attention-deficit/hyperactivity disorder (ADHD) symptoms have worse functional outcomes and treatment response than those without ADHD symptoms. There is limited knowledge of the neurobiology of ADHD symptoms in ASD. Here, we test the hypothesis that aberrant functional connectivity of two large-scale executive brain networks implicated in ADHD-the frontoparietal and salience/ventral attention networks-also play a role in ADHD symptoms in ASD. METHODS:We compared resting-state functional connectivity of the two executive brain networks in children with ASD (n = 77) and typically developing control children (n = 82). These two executive brain networks comprise five subnetworks (three frontoparietal, two salience/ventral attention). After identifying aberrant functional connections among subnetworks, we examined dimensional associations with parent-reported ADHD symptoms. RESULTS:Weaker functional connectivity in ASD was present within and between the frontoparietal and salience/ventral attention subnetworks. Decreased functional connectivity within a single salience/ventral attention subnetwork, as well as between two frontoparietal subnetworks, significantly correlated with ADHD symptoms. Furthermore, follow-up linear regressions demonstrated that the salience/ventral attention and frontoparietal subnetworks explain unique variance in ADHD symptoms. These executive brain network-ADHD symptom relationships remained significant after controlling for ASD symptoms. Finally, specificity was also demonstrated through the use of a control brain network (visual) and a control co-occurring symptom domain (anxiety). CONCLUSIONS:The present findings provide novel evidence that both frontoparietal and salience/ventral attention networks' weaker connectivities are linked to ADHD symptoms in ASD. Moreover, co-occurring ADHD in the context of ASD is a source of meaningful neural heterogeneity in ASD.
Project description:BACKGROUND:Both attention-deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) are neurodevelopmental disorders with a high prevalence. They are often comorbid and both exhibit abnormalities in sustained attention, yet common and distinct neural patterns of ASD and ADHD remain unidentified.AimsTo investigate shared and distinct functional connectivity patterns in a relatively large sample of boys (7- to 15-year-olds) with ADHD, ASD and typical development matched by age, gender and IQ. METHOD:We applied machine learning techniques to investigate patterns of surface-based brain resting-state connectivity in 86 boys with ASD, 83 boys with ADHD and 125 boys with typical development. RESULTS:We observed increased functional connectivity within the limbic and somatomotor networks in boys with ASD compared with boys with typical development. We also observed increased functional connectivity within the limbic, visual, default mode, somatomotor, dorsal attention, frontoparietal and ventral attention networks in boys with ADHD compared with boys with ASD. In addition, using a machine learning approach, we were able to discriminate typical development from ASD, typical development from ADHD and ASD from ADHD with accuracy rates of 76.3%, 84.1%, and 79.3%, respectively. CONCLUSIONS:Our results may shed new light on the underlying mechanisms of ASD and ADHD and facilitate the development of new diagnostic methods for these disorders.Declaration of interestJ.K. holds equity in a startup company, MNT.
Project description:Individuals with autism spectrum disorders (ASD) often exhibit symptoms of attention-deficit/hyperactivity disorder (ADHD). Across both disorders, observations of distributed functional abnormalities suggest aberrant large-scale brain network connectivity. Yet, common and distinct network correlates of ASD and ADHD remain unidentified. Here, we aimed to examine patterns of dysconnection in school-age children with ASD and ADHD and typically developing children who completed a resting state functional magnetic resonance imaging scan.We measured voxelwise network centrality, functional connectivity metrics indexing local (degree centrality [DC]) and global (eigenvector centrality) functional relationships across the entire brain connectome, in resting state functional magnetic resonance imaging data from 56 children with ASD, 45 children with ADHD, and 50 typically developing children. A one-way analysis of covariance, with group as fixed factor (whole-brain corrected), was followed by post hoc pairwise comparisons.Cortical and subcortical areas exhibited centrality abnormalities, some common to both ADHD and ASD, such as in precuneus. Others were disorder-specific and included ADHD-related increases in DC in right striatum/pallidum, in contrast with ASD-related increases in bilateral temporolimbic areas. Secondary analyses differentiating children with ASD into those with or without ADHD-like comorbidity (ASD(+) and ASD(-), respectively) revealed that the ASD(+) group shared ADHD-specific abnormalities in basal ganglia. By contrast, centrality increases in temporolimbic areas characterized children with ASD regardless of ADHD-like comorbidity. At the cluster level, eigenvector centrality group patterns were similar to DC.ADHD and ASD are neurodevelopmental disorders with distinct and overlapping clinical presentations. This work provides evidence for both shared and distinct underlying mechanisms at the large-scale network level.
Project description:Previous functional connectivity studies have found both hypo- and hyper-connectivity in brains of individuals having autism spectrum disorder (ASD). Here we studied abnormalities in functional brain subnetworks in high-functioning individuals with ASD during free viewing of a movie containing social cues and interactions. Twenty-six subjects (13 with ASD) watched a 68-min movie during functional magnetic resonance imaging. For each subject, we computed Pearson's correlation between haemodynamic time-courses of each pair of 6-mm isotropic voxels. From the whole-brain functional networks, we derived individual and group-level subnetworks using graph theory. Scaled inclusivity was then calculated between all subject pairs to estimate intersubject similarity of connectivity structure of each subnetwork. Additional 54 individuals (27 with ASD) from the ABIDE resting-state database were included to test the reproducibility of the results. Between-group differences were observed in the composition of default-mode and ventro-temporal-limbic (VTL) subnetworks. The VTL subnetwork included amygdala, striatum, thalamus, parahippocampal, fusiform, and inferior temporal gyri. Further, VTL subnetwork similarity between subject pairs correlated significantly with similarity of symptom gravity measured with autism quotient. This correlation was observed also within the controls, and in the reproducibility dataset with ADI-R and ADOS scores. Our results highlight how the reorganization of functional subnetworks in individuals with ASD clarifies the mixture of hypo- and hyper-connectivity findings. Importantly, only the functional organization of the VTL subnetwork emerges as a marker of inter-individual similarities that co-vary with behavioral measures across all participants. These findings suggest a pivotal role of ventro-temporal and limbic systems in autism.
Project description:BACKGROUND:Current diagnostic systems for neurodevelopmental disorders do not have clear links to underlying neurobiology, limiting their utility in identifying targeted treatments for individuals. Here, we aimed to investigate differences in functional brain network integrity between traditional diagnostic categories (autism spectrum disorder [ASD], attention-deficit/hyperactivity disorder [ADHD], typically developing [TD]) and carefully consider the impact of comorbid ASD and ADHD on functional brain network integrity in a sample adequately powered to detect large effects. We also assess the neurobiological separability of a novel, potential alternative categorical scheme based on behavioral measures of executive function. METHOD:Five-minute resting-state fMRI data were obtained from 168 children (128 boys, 40 girls) with ASD, ADHD, comorbid ASD and ADHD, and TD children. Independent component analysis and dual regression were used to compute within- and between-network functional connectivity metrics at the individual level. RESULTS:No significant group differences in within- or between-network functional connectivity were observed between traditional diagnostic categories (ASD, ADHD, TD) even when stratified by comorbidity (ASD + ADHD, ASD, ADHD, TD). Similarly, subgroups classified by executive functioning levels showed no group differences. CONCLUSIONS:Using clinical diagnosis and behavioral measures of executive function, no differences in functional connectivity were observed among the categories examined. Despite our limited ability to detect small- to medium-sized differences between groups, this work contributes to a growing literature suggesting that traditional diagnostic categories do not define neurobiologically separable groups. Future work is necessary to ascertain the validity of the executive function-based nosology, but current results suggest that nosologies reliant on behavioral data alone may not lead to discovery of neurobiologically distinct categories.
Project description:Attention-deficit/hyperactive disorder (ADHD) and autism spectrum disorders (ASD) are two of the most common and vexing neurodevelopmental disorders among children. Although the two disorders share many behavioral and neuropsychological characteristics, most MRI studies examine only one of the disorders at a time. Using graph theory combined with structural and functional connectivity, we examined the large-scale network organization among three groups of children: a group with ADHD (8-12 years, n = 20), a group with ASD (7-13 years, n = 16), and typically developing controls (TD) (8-12 years, n = 20). We apply the concept of the rich-club organization, whereby central, highly connected hub regions are also highly connected to themselves. We examine the brain into two different network domains: (1) inside a rich-club network phenomena and (2) outside a rich-club network phenomena. The ASD and ADHD groups had markedly different patterns of rich club and non rich-club connections in both functional and structural data. The ASD group exhibited higher connectivity in structural and functional networks but only inside the rich-club networks. These findings were replicated using the autism brain imaging data exchange dataset with ASD (n = 85) and TD (n = 101). The ADHD group exhibited a lower generalized fractional anisotropy and functional connectivity inside the rich-club networks, but a higher number of axonal fibers and correlation coefficient values outside the rich club. Despite some shared biological features and frequent comorbity, these data suggest ADHD and ASD exhibit distinct large-scale connectivity patterns in middle childhood.
Project description:Differences in cerebellar structure have been identified in autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), and developmental dyslexia. However, it is not clear if different cerebellar regions are involved in each disorder, and thus whether cerebellar anatomical differences reflect a generic developmental vulnerability or disorder-specific characteristics. To clarify this, we conducted an anatomic likelihood estimate (ALE) meta-analysis on voxel-based morphometry (VBM) studies which compared ASD (17 studies), ADHD (10 studies), and dyslexic (10 studies) participants with age-matched typically-developing (TD) controls. A second ALE analysis included studies in which the cerebellum was a region of interest (ROI). There were no regions of significantly increased gray matter (GM) in the cerebellum in ASD, ADHD, or dyslexia. Data from ASD studies revealed reduced GM in the inferior cerebellar vermis (lobule IX), left lobule VIIIB, and right Crus I. In ADHD, significantly decreased GM was found bilaterally in lobule IX, whereas participants with developmental dyslexia showed GM decreases in left lobule VI. There was no overlap between the cerebellar clusters identified in each disorder. We evaluated the functional significance of the regions revealed in both whole-brain and cerebellar ROI ALE analyses using Buckner and colleagues' 7-network functional connectivity map available in the SUIT cerebellar atlas. The cerebellar regions identified in ASD showed functional connectivity with frontoparietal, default mode, somatomotor, and limbic networks; in ADHD, the clusters were part of dorsal and ventral attention networks; and in dyslexia, the clusters involved ventral attention, frontoparietal, and default mode networks. The results suggest that different cerebellar regions are affected in ASD, ADHD, and dyslexia, and these cerebellar regions participate in functional networks that are consistent with the characteristic symptoms of each disorder.
Project description:Structural neuroimaging studies suggest altered brain maturation in autism spectrum disorder (ASD) compared with typically developing controls (TDC). However, the prognostic value of whole-brain structural connectivity analysis in ASD has not been established. Diffusion magnetic imaging data were acquired in 27 high-functioning young ASD participants (2 females) and 29 age-matched TDC (12 females; age 8-18 years) at baseline and again following 3-7 years. Whole-brain structural connectomes were reconstructed from these data and analyzed using a longitudinal statistical model. We identified distinct patterns of widespread brain connections that exhibited either significant increases or decreases in connectivity over time (p < 0.001). There was a significant interaction between diagnosis and time in brain development (p < 0.001). This was expressed by a decrease in structural connectivity within the frontoparietal network-and its broader connectivity-in ASD during adolescence and early adulthood. Conversely, these connections increased with time in TDC. Crucially, stronger baseline connectivity in this subnetwork predicted a lower symptom load at follow-up (p = 0.048), independent of the expression of symptoms at baseline. Our findings suggest a clinically meaningful relationship between the atypical development of frontoparietal structural connections and the dynamics of the autism phenotype through early adulthood. These results highlight a potential marker of future outcome.
Project description:BACKGROUND:Those with autism spectrum disorder (ASD) and/or attention-deficit-hyperactivity disorder (ADHD) exhibit symptoms of hyperactivity and inattention, causing significant hardships for families and society. A potential mechanism involved in these conditions is atypical executive function (EF). Inconsistent findings highlight that EF features may be shared or distinct across ADHD and ASD. With ADHD and ASD each also being heterogeneous, we hypothesized that there may be nested subgroups across disorders with shared or unique underlying mechanisms. METHODS:Participants (N = 130) included adolescents aged 7-16 with ASD (n = 64) and ADHD (n = 66). Typically developing (TD) participants (n = 28) were included for a comparative secondary sub-group analysis. Parents completed the K-SADS and youth completed an extended battery of executive and other cognitive measures. A two stage hybrid machine learning tool called functional random forest (FRF) was applied as a classification approach and then subsequently to subgroup identification. We input 43 EF variables to the classification step, a supervised random forest procedure in which the features estimated either hyperactive or inattentive ADHD symptoms per model. The FRF then produced proximity matrices and identified optimal subgroups via the infomap algorithm (a type of community detection derived from graph theory). Resting state functional connectivity MRI (rs-fMRI) was used to evaluate the neurobiological validity of the resulting subgroups. RESULTS:Both hyperactive (Mean absolute error (MAE) = 0.72, Null model MAE = 0.8826, (t(58) = -4.9, p < .001) and inattentive (MAE = 0.7, Null model MAE = 0.85, t(58) = -4.4, p < .001) symptoms were predicted better than chance by the EF features selected. Subgroup identification was robust (Hyperactive: Q = 0.2356, p < .001; Inattentive: Q = 0.2350, p < .001). Two subgroups representing severe and mild symptomology were identified for each symptom domain. Neuroimaging data revealed that the subgroups and TD participants significantly differed within and between multiple functional brain networks, but no consistent "severity" patterns of over or under connectivity were observed between subgroups and TD. CONCLUSION:The FRF estimated hyperactive/inattentive symptoms and identified 2 distinct subgroups per model, revealing distinct neurocognitive profiles of Severe and Mild EF performance per model. Differences in functional connectivity between subgroups did not appear to follow a severity pattern based on symptom expression, suggesting a more complex mechanistic interaction that cannot be attributed to symptom presentation alone.
Project description:In spite of its importance for education, the relationship between learning behaviors (LB), attention deficit hyperactivity disorder symptoms (ADHD) and executive functioning (EF) in children with autism spectrum disorder (ASD) has hardly been explored. The first objective of the present study was to compare children with ASD without intellectual disability and children with typical development (TD) on ADHD symptoms and learning behaviors: Motivation/competence, attitude toward learning, persistence on the task, and strategy/flexibility. The second objective was to analyze the mediator role of behavioral regulation and metacognition components of EF between ADHD symptoms and learning behaviors in children with ASD. Participants were 89 children between 7 and 11 years old, 52 with ASD and 37 with TD, matched on age and intelligence. Their teachers filled out questionnaires assessing executive functioning as well as learning behaviors. Parents and teachers reported on inattention and hyperactivity/impulsivity behaviors. Compared to children with TD, children with ASD presented significantly more ADHD symptoms and poorer learning behaviors. In addition, there were significant mediation effects of the behavioral regulation index (BRI) and metacognition index (MI) of EF, indicating that both are part of the route through which ADHD symptoms impact to learning behaviors of children with ASD.