Predicting individual autistic symptoms for patients with autism spectrum disorder using interregional morphological connectivity.

Intelligent predictive models for autistic symptoms based on neuroimaging datasets were beneficial for the precise intervention of patients with ASD. The goals of this study were twofold: investigating predictive models for autistic symptoms and discovering the brain connectivity patterns for ASD-related behaviors. To achieve these goals, we obtained a cohort of patients with ASD from the ABIDE project. The autistic symptoms were measured using the Autism Diagnostic Observation Schedule (ADOS). The anatomical MRI datasets were preprocessed using the Freesurfer package, resulting in regional morphological features. For each individual, the interregional morphological network was constructed using a novel feature distance-based method. The predictive models for autistic symptoms were built using the support vector regression (SVR) algorithm with feature selection method. The predicted autistic symptoms (i.e., ADOS social score, ADOS behavior) were significantly correlated to the original measures. The most predictive features for ADOS social scores were located in the bilateral fusiform. The most predictive features for ADOS behavior scores were located in the temporal pole and the lingual gyrus. In summary, the autistic symptoms could be predicted using the interregional morphological connectivity and machine learning. The interregional morphological connectivity could be a potential biomarker for autistic symptoms.

Aberrant dynamic and static functional connectivity of the striatum across specific low-frequency bands in patients with autism spectrum disorder.

BACKGROUND: Dysfunctions of the striatum have been repeatedly observed in autism spectrum disorder (ASD). However, previous studies have explored the static functional connectivity (sFC) of the striatum in a single frequency band, ignoring the dynamics and frequency specificity of brain FC. Therefore, we investigated the dynamic FC (dFC) and sFC of the striatum in the slow-4 (0.027-0.073 Hz) and slow-5 (0.01-0.027 Hz) frequency bands. METHODS: Data of 47 ASD patients and 47 typically developing (TD) controls were obtained from the Autism Brain Imaging Data Exchange (ABIDE) database. A seed-based approach was used to compute the dFC and sFC. Then, a two-sample t-test was performed. For regions showing abnormal sFC and dFC, we performed clinical correlation analysis and constructed support vector machine (SVM) models. RESULTS: The middle frontal gyrus (MFG), precuneus, and medial superior frontal gyrus (mPFC) showed both dynamic and static alterations. The reduced striatal dFC in the right MFG was associated with autism symptoms. The dynamic‒static FC model had a great performance in ASD classification, with 95.83 % accuracy. CONCLUSIONS: The striatal dFC and sFC were altered in ASD, which were frequency specific. Examining brain activity using dynamic and static FC provides a comprehensive view of brain activity.

Frequency characteristics of temporal and spatial concordance among dynamic indices in inattentive and combined subtypes of attention deficit hyperactivity disorder.

Numerous voxel-based resting-state functional magnetic resonance imaging (rs-fMRI) measurements have been used to characterize spontaneous brain activity in attention deficit hyperactivity disorder (ADHD). However, the practical distinctions and commonalities among these intrinsic brain activity measures remain to be fully explored, and whether the functional concordance is related to frequency is still unknown. The study included 25 ADHD, combined type (ADHD-C); 26 ADHD, inattentive type (ADHD-I); and 28 typically developing (TD) children. We calculated the voxel-wise (temporal) and volume-wise (spatial) concordance among dynamic rs-fMRI indices in the slow-5 (0.01-0.027 Hz) and slow-4 (0.027-0.073 Hz) frequency bands, respectively. The spatiotemporal concordance within the slow-4 and slow-5 bands among the ADHD-C, ADHD-I, and TD groups was compared. Although the ADHD-C and ADHD-I groups showed similar volume-wise concordance, comparison analysis revealed that compared with ADHD-C patients, ADHD-I patients exhibited decreased voxel-wise concordance in the right median cingulate and paracingulate gyrus (MCC) and right supplementary motor area (SMA) in the slow-5 band. In addition, the voxel-wise concordance was negatively correlated with the diagnostic scores of ADHD subtypes. Our results suggest that functional concordance is frequency dependent, and dynamic concordance analysis based on specific frequency bands may provide a novel approach for investigating the pathophysiological differences among ADHD subtypes.

Corrigendum: Frequency characteristics of temporal and spatial concordance among dynamic indices in inattentive and combined subtypes of attention deficit hyperactivity disorder.

[This corrects the article DOI: 10.3389/fnins.2023.1196290.].

Mapping white matter structural covariance connectivity for single subject using wavelet transform with T1-weighted anatomical brain MRI.

Introduction: Current studies of structural covariance networks were focused on the gray matter in the human brain. The structural covariance connectivity in the white matter remains largely unexplored. This paper aimed to build novel metrics that can infer white matter structural covariance connectivity, and to explore the predictive power of the proposed features. Methods: To this end, a cohort of 315 adult subjects with the anatomical brain MRI datasets were obtained from the publicly available Dallas Lifespan Brain Study (DLBS) project. The 3D wavelet transform was applied on the individual voxel-based morphology (VBM) volume to obtain the white matter structural covariance connectivity. The predictive models for cognitive functions were built using support vector regression (SVR). Results: The predictive models exhibited comparable performance with previous studies. The novel features successfully predicted the individual ability of digit comparison (DC) (r = 0.41 ± 0.01, p < 0.01) and digit symbol (DSYM) (r = 0.5 ± 0.01, p < 0.01). The sensorimotor-related white matter system exhibited as the most predictive network node. Furthermore, the node strengths of sensorimotor mode were significantly correlated to cognitive scores. Discussion: The results suggested that the white matter structural covariance connectivity was informative and had potential for predictive tasks of brain-behavior research.

A Unified Framework for Inattention Estimation From Resting State Phase Synchrony Using Machine Learning.

Inattention is one of the most significant clinical symptoms for evaluating attention deficit hyperactivity disorder (ADHD). Previous inattention estimations were performed using clinical scales. Recently, predictive models for inattention have been established for brain-behavior estimation using neuroimaging features. However, the performance of inattention estimation could be improved for conventional brain-behavior models with additional feature selection, machine learning algorithms, and validation procedures. This paper aimed to propose a unified framework for inattention estimation from resting state fMRI to improve the classical brain-behavior models. Phase synchrony was derived as raw features, which were selected with minimum-redundancy maximum-relevancy (mRMR) method. Six machine learning algorithms were applied as regression methods. 100 runs of 10-fold cross-validations were performed on the ADHD-200 datasets. The relevance vector machines (RVMs) based on the mRMR features for the brain-behavior models significantly improve the performance of inattention estimation. The mRMR-RVM models could achieve a total accuracy of 0.53. Furthermore, predictive patterns for inattention were discovered by the mRMR technique. We found that the bilateral subcortical-cerebellum networks exhibited the most predictive phase synchrony patterns for inattention. Together, an optimized strategy named mRMR-RVM for brain-behavior models was found for inattention estimation. The predictive patterns might help better understand the phase synchrony mechanisms for inattention.

Identifying individuals with autism spectrum disorder based on the principal components of whole-brain phase synchrony.

Autism spectrum disorder (ASD) is a brain disorder that develops during an early stage of childhood. Previous neuroimaging-based diagnostic models for ASD were based on static functional connectivity (FC). The nonlinear complexity of brain connectivity remains unexplored for ASD diagnosis. This study aimed to build intelligent discriminative models for ASD based on phase synchrony (PS). To this end, data from 49 patients with ASD and 41 healthy controls were obtained from the Autism Brain Imaging Data Exchange (ABIDE) project. PS between brain regions was determined using Hilbert transform. Principal component analysis (PCA) and support vector machines (SVMs) were used to build the discriminative models. PS-based models (AUC = 0.81) outperformed static FC-based models (AUC = 0.71). Furthermore, embedded functional biomarkers were discovered. Moreover, significant correlations were found between PCA-PS and the clinical severity of ASD. Together, intelligent discriminative models based on PS were established for ASD identification. The performance of the diagnostic models suggested the potential benefits of PS for clinical applications. The discriminative patterns indicated that PCA-PS features could be additional biomarkers for ASD research. Furthermore, the significant relationships between the PCA-PS features and clinical scores implied their potential use for personalized medication strategies.

Estimating individual scores of inattention and impulsivity based on dynamic features of intrinsic connectivity network.

Inattention and impulsivity are the two most important indices for evaluations of ADHD. Currently, inattention and impulsivity were evaluated by clinical scales. The intelligent evaluation of the two indices using machine learning remains largely unexplored. This paper aimed to build regression modes for inattention and impulsivity based on resting state fMRI and additional measures, and discover the associating features for the two indices. To achieve these goals, a cohort of 95 children with ADHD as well as 105 healthy controls were selected from the ADHD-200 database. The raw features were consisted of univariate dynamic estimators of intrinsic connectivity network (ICNs), head motion, and additional measures. The regression models were solved using support vector regression (SVR). The performance of the regression models was evaluated by cross-validations. The performance of regression models based on ICNs outperformed that based on regional measures. The estimated clinical scores were significantly correlated to inattention (r = 0.4 ± 0.02, p < 0.01) and impulsivity (r = 0.31 ± 0.02, p < 0.01). The most associating ICNs are sensorimotor network (SMN) for inattention and executive control network (ECN) for impulsivity. The results suggested that inattention and impulsivity could be estimated using machine learning, and the intra-ICN dynamics could be supplementary features for regression models of clinical scores of ADHD.

A unified framework for mapping individual interregional high-order morphological connectivity based on regional cortical features from anatomical MRI.

Building individual brain networks form the single volume of anatomical MRI is a challenging task. Furthermore, the high-order connectivity of morphological networks remains unexplored. This paper aimed to investigate the individual high-order morphological connectivity from anatomical MRI. Towards this goal, a unified framework based on six feature distances (euclidean, seuclidean, mahalanobis, cityblock, minkowski, and chebychev) was proposed to derive high-order interregional morphological features. The test-retest datasets and the healthy aging datasets were applied to analyze the reliability and the inter-subject variability of the novel features. In addition, the predictive models based on these novel features were established for age estimation. The proposed six neuroanatomical features exhibited significant high-to-excellent reliability. Certain connections were significantly correlated to biological age based on the six novel metrics (p < .05, FDR corrected). Moreover, the predicted age were significantly correlated to the original age in each regression task (r > 0.5, p < 10-6). The results suggested that the novel high-order metrics were reliable and could reflect individual differences, which could be beneficial for current methods of individual brain connectomes.

Diagnosing autism spectrum disorder using brain entropy: A fast entropy method.

BACKGROUND AND OBJECTIVE: Previous resting-state fMRI-based diagnostic models for autism spectrum disorder (ASD) were based on traditional linear features. The complexity of the ASD brain remains unexplored. METHODS: To increase our understanding of the nonlinear neural mechanisms in ASD, entropy (i.e., approximate entropy (ApEn) and sample entropy (SampEn)) method was used to analyze the resting-state fMRI datasets collected from 21 ASD patients and 26 typically developing (TD) individuals. Here, a fast entropy algorithm was proposed through matrix computation. We combined entropy with a support-vector machine and selected "important entropy" as features to diagnose ASD. The classification performance of the fast entropy method was compared to the state-of-the-art functional connectivity (FC) method. RESULTS: The area under the receiver operating characteristic curve based on FC was 0.62. The areas under the receiver operating characteristic curves based on ApEn and SampEn were 0.79 and 0.89, respectively. The results showed that the proposed fast entropy method was more efficacious than the FC method. In addition, lower entropy was found in the ASD patients. The ApEn of the left postcentral gyrus (rs = -0.556, p = 0.009) and the SampEn of the right lingual gyrus (rs = -0.526, p = 0.014) were both significantly negatively related to Autism Diagnostic Observation Schedule total scores in the ASD patients. The proposed algorithm for entropy computation was faster than the traditional entropy method. CONCLUSIONS: Our study provides a new perspective to better understand the neural mechanisms of ASD. Brain entropy based on a fast algorithm was applied to distinguish ASD patients from TD individuals. ApEn and SampEn could be potential biomarkers in ASD investigations.

Identifying individuals with attention deficit hyperactivity disorder based on temporal variability of dynamic functional connectivity.

Attention deficit hyperactivity disorder (ADHD) is a common disorder that emerges in school-age children. The diagnostic model based on neuroimaging features could be beneficial for ADHD in twofold: identifying individuals with ADHD and discovering the discriminative patterns for patients. The dynamic functional connectivity of ADHD remains unclear. Towards this end, 100 children with ADHD and 140 normal controls were obtained from the ADHD-200 Consortium. The raw features were derived from the temporal variability between intrinsic connectivity networks (ICNs) as well as the demographic and covariate variables. The diagnostic model was based on the support vector machines (SVMs). The performance of diagnostic model was analyzed using leave-one-out cross-validation (LOOCV) and 10-folds cross-validations (CVs). The diagnostic model based on inter-ICN variability outperformed that based on inter-ICN functional connectivity and inter-ICN phase synchrony. The LOOCV achieved total accuracy of 78.75%, the sensitivity of 76%, and the specificity of 80.71%. The 10-folds CVs achieved average prediction accuracy of 75.54% ± 1.34%, average sensitivity of 70.5% ± 2.34%, and average specificity of 77.44% ± 1.47%. In addition, the discriminative patterns for ADHD were discovered using SVMs. The discriminative patterns confirmed with previous findings. In summary, individuals with ADHD could be identified through inter-ICN variability, which could be potential biomarkers for diagnostic model of ADHD.

Diagnostic model for attention-deficit hyperactivity disorder based on interregional morphological connectivity.

Previous brain morphology-related diagnostic models for attention-deficit hyperactivity disorder (ADHD) were based on regional features. However, building a model of individual interregional morphological connectivity is a challenging task. This study aimed to identify children with ADHD utilizing a novel interregional morphological connectivity model and discover the discriminative patterns in patients. Therefore, novel interregional morphological patterns rather than regional patterns were extracted via surface-based analysis. The interregional morphological features were trained and tested using a hybrid machine learning method, which was implemented using the leave-one-out cross-validation (LOOCV) method to produce the optimized discriminative model and discriminative patterns. The inclusion of interregional morphological connectivity significantly improved the performance of the diagnostic models compared to the performance of the model constructed using regional features. The optimized discriminative model exhibited a total accuracy of 74.65%, a sensitivity of 75% and a specificity of 74.29%. The brain regions displaying altered morphological connectivity included the insula, the caudal anterior cingulate cortex, the frontal pole, and the postcentral cortex, among others. In addition, the altered connections correlated with the clinical symptoms. In summary, patients with ADHD exhibited altered morphological connectivity, which might be a potential biomarker for the classification of ADHD. The discriminative features will potentially benefit studies investigating the brain network mechanisms of ADHD.

Mapping individual voxel-wise morphological connectivity using wavelet transform of voxel-based morphology.

Mapping individual brain networks has drawn significant research interest in recent years. Most individual brain networks developed to date have been based on fMRI or diffusion MRI. Given recent concerns regarding confounding artifacts, various preprocessing steps are generally included in functional or structural brain networks. Notably, voxel-based morphometry (VBM) derived from anatomical MRI exhibits high signal-to-noise ratios and has been applied to individual interregional morphological networks. To the best of our knowledge, individual voxel-wise morphological networks remain unexplored. The goal of this research is twofold: to build novel metrics for individual voxel-wise morphological networks and to test the reliability of the proposed morphological connectivity. To this end, anatomical scans of a cohort of healthy subjects were obtained from a public database. The anatomical datasets were preprocessed and normalized to the standard brain space. For each individual, wavelet-transform was applied on the VBM measures to obtain voxel-wise hierarchical features. The voxel-wise morphological connectivity was computed based on the wavelet features. Reliable brain hubs were detected by the z-scores of degree centrality. High reliability was discovered by test-retest analysis. No effects of wavelet scale, network threshold or network type were found on hubs of group-level degree centrality. However, significant effects of wavelet scale, network threshold and network type were found on individual-level degree centrality. Significant effects of network threshold and network type were found on reliability of degree centrality. The results suggested that the voxel-wise morphological connectivity was reliable and exhibited a hub structure. Moreover, the voxel-wise morphological connectivity could reflect individual differences. In summary, individual voxel-wise wavelet-based features can probe morphological connectivity and may be beneficial for investigating the brain morphological connectomes.

Predictive models of minimal hepatic encephalopathy for cirrhotic patients based on large-scale brain intrinsic connectivity networks.

We aimed to find the most representative connectivity patterns for minimal hepatic encephalopathy (MHE) using large-scale intrinsic connectivity networks (ICNs) and machine learning methods. Resting-state fMRI was administered to 33 cirrhotic patients with MHE and 43 cirrhotic patients without MHE (NMHE). The connectivity maps of 20 ICNs for each participant were obtained by dual regression. A Bayesian machine learning technique, called Graphical Model-based Multivariate Analysis, was applied to determine ICN regions that characterized group differences. The most representative ICNs were evaluated by the performance of three machine learning methods (support vector machines (SVMs), multilayer perceptrons (MLP), and C4.5). The clinical significance of these potential biomarkers was further tested. The temporal lobe network (TLN), and subcortical network (SCN), and sensorimotor network (SMN) were selected as representative ICNs. The distinct functional integration patterns of the representative ICNs were significantly correlated with behavior criteria and Child-Pugh scores. Our findings suggest the representative ICNs based on GAMMA can distinguish MHE from NMHE and provide supplementary information to current MHE diagnostic criteria.

Predicting clinical symptoms of attention deficit hyperactivity disorder based on temporal patterns between and within intrinsic connectivity networks.

Attention deficit hyperactivity disorder (ADHD) is a common brain disorder with high prevalence in school-age children. Previously developed machine learning-based methods have discriminated patients with ADHD from normal controls by providing label information of the disease for individuals. Inattention and impulsivity are the two most significant clinical symptoms of ADHD. However, predicting clinical symptoms (i.e., inattention and impulsivity) is a challenging task based on neuroimaging data. The goal of this study is twofold: to build predictive models for clinical symptoms of ADHD based on resting-state fMRI and to mine brain networks for predictive patterns of inattention and impulsivity. To achieve this goal, a cohort of 74 boys with ADHD and a cohort of 69 age-matched normal controls were recruited from the ADHD-200 Consortium. Both structural and resting-state fMRI images were obtained for each participant. Temporal patterns between and within intrinsic connectivity networks (ICNs) were applied as raw features in the predictive models. Specifically, sample entropy was taken asan intra-ICN feature, and phase synchronization (PS) was used asan inter-ICN feature. The predictive models were based on the least absolute shrinkage and selectionator operator (LASSO) algorithm. The performance of the predictive model for inattention is r=0.79 (p<10-8), and the performance of the predictive model for impulsivity is r=0.48 (p<10-8). The ICN-related predictive patterns may provide valuable information for investigating the brain network mechanisms of ADHD. In summary, the predictive models for clinical symptoms could be beneficial for personalizing ADHD medications.

Investigating the Temporal Patterns within and between Intrinsic Connectivity Networks under Eyes-Open and Eyes-Closed Resting States: A Dynamical Functional Connectivity Study Based on Phase Synchronization.

The brain active patterns were organized differently under resting states of eyes open (EO) and eyes closed (EC). The altered voxel-wise and regional-wise resting state active patterns under EO/EC were found by static analysis. More importantly, dynamical spontaneous functional connectivity has been observed in the resting brain. To the best of our knowledge, the dynamical mechanisms of intrinsic connectivity networks (ICNs) under EO/EC remain largely unexplored. The goals of this paper were twofold: 1) investigating the dynamical intra-ICN and inter-ICN temporal patterns during resting state; 2) analyzing the altered dynamical temporal patterns of ICNs under EO/EC. To this end, a cohort of healthy subjects with scan conditions of EO/EC were recruited from 1000 Functional Connectomes Project. Through Hilbert transform, time-varying phase synchronization (PS) was applied to evaluate the inter-ICN synchrony. Meanwhile, time-varying amplitude was analyzed as dynamical intra-ICN temporal patterns. The results found six micro-states of inter-ICN synchrony. The medial visual network (MVN) showed decreased intra-ICN amplitude during EC relative to EO. The sensory-motor network (SMN) and auditory network (AN) exhibited enhanced intra-ICN amplitude during EC relative to EO. Altered inter-ICN PS was found between certain ICNs. Particularly, the SMN and AN exhibited enhanced PS to other ICNs during EC relative to EO. In addition, the intra-ICN amplitude might influence the inter-ICN synchrony. Moreover, default mode network (DMN) might play an important role in information processing during EO/EC. Together, the dynamical temporal patterns within and between ICNs were altered during different scan conditions of EO/EC. Overall, the dynamical intra-ICN and inter-ICN temporal patterns could benefit resting state fMRI-related research, and could be potential biomarkers for human functional connectome.

Altered temporal features of intrinsic connectivity networks in boys with combined type of attention deficit hyperactivity disorder.

PURPOSE: Investigating the altered temporal features within and between intrinsic connectivity networks (ICNs) for boys with attention-deficit/hyperactivity disorder (ADHD); and analyzing the relationships between altered temporal features within ICNs and behavior scores. MATERIALS AND METHODS: A cohort of boys with combined type of ADHD and a cohort of age-matched healthy boys were recruited from ADHD-200 Consortium. All resting-state fMRI datasets were preprocessed and normalized into standard brain space. Using general linear regression, 20 ICNs were taken as spatial templates to analyze the time-courses of ICNs for each subject. Amplitude of low frequency fluctuations (ALFFs) were computed as univariate temporal features within ICNs. Pearson correlation coefficients and node strengths were computed as bivariate temporal features between ICNs. Additional correlation analysis was performed between temporal features of ICNs and behavior scores. RESULTS: ADHD exhibited more activated network-wise ALFF than normal controls in attention and default mode-related network. Enhanced functional connectivities between ICNs were found in ADHD. The network-wise ALFF within ICNs might influence the functional connectivity between ICNs. The temporal pattern within posterior default mode network (pDMN) was positively correlated to inattentive scores. The subcortical network, fusiform-related DMN and attention-related networks were negatively correlated to Intelligence Quotient (IQ) scores. CONCLUSION: The temporal low frequency oscillations of ICNs in boys with ADHD were more activated than normal controls during resting state; the temporal features within ICNs could provide additional information to investigate the altered network patterns of ADHD.