Multiparametric MRI characterization and prediction in autism spectrum disorder using graph theory and machine learning

Utilizing deep learning models in an intelligent eye-tracking system for autism spectrum disorder diagnosis

Timely and unbiased evaluation of Autism Spectrum Disorder (ASD) is essential for providing lasting benefits to affected individuals. However, conventional ASD assessment heavily relies on subjective criteria, lacking objectivity. Recent advancements propose the integration of modern processes, including artificial intelligence-based eye-tracking technology, for early ASD assessment. Nonetheless, the current diagnostic procedures for ASD often involve specialized investigations that are both time-consuming and costly, heavily reliant on the proficiency of specialists and employed techniques. To address the pressing need for prompt, efficient, and precise ASD diagnosis, an exploration of sophisticated intelligent techniques capable of automating disease categorization was presented. This study has utilized a freely accessible dataset comprising 547 eye-tracking systems that can be used to scan pathways obtained from 328 characteristically emerging children and 219 children with autism. To counter overfitting, state-of-the-art image resampling approaches to expand the training dataset were employed. Leveraging deep learning algorithms, specifically MobileNet, VGG19, DenseNet169, and a hybrid of MobileNet-VGG19, automated classifiers, that hold promise for enhancing diagnostic precision and effectiveness, was developed. The MobileNet model demonstrated superior performance compared to existing systems, achieving an impressive accuracy of 100%, while the VGG19 model achieved 92% accuracy. These findings demonstrate the potential of eye-tracking data to aid physicians in efficiently and accurately screening for autism. Moreover, the reported results suggest that deep learning approaches outperform existing event detection algorithms, achieving a similar level of accuracy as manual coding. Users and healthcare professionals can utilize these classifiers to enhance the accuracy rate of ASD diagnosis. The development of these automated classifiers based on deep learning algorithms holds promise for enhancing the diagnostic precision and effectiveness of ASD assessment, addressing the pressing need for prompt, efficient, and precise ASD diagnosis.

Rich-club organization of whole-brain spatio-temporal multilayer functional connectivity networks

Objective

In this work, we propose a novel method for constructing whole-brain spatio-temporal multilayer functional connectivity networks (FCNs) and four innovative rich-club metrics.

Methods

Spatio-temporal multilayer FCNs achieve a high-order representation of the spatio-temporal dynamic characteristics of brain networks by combining the sliding time window method with graph theory and hypergraph theory. The four proposed rich-club scales are based on the dynamic changes in rich-club node identity, providing a parameterized description of the topological dynamic characteristics of brain networks from both temporal and spatial perspectives. The proposed method was validated in three independent differential analysis experiments: male-female gender difference analysis, analysis of abnormality in patients with autism spectrum disorders (ASD), and individual difference analysis.

Results

The proposed method yielded results consistent with previous relevant studies and revealed some innovative findings. For instance, the dynamic topological characteristics of specific white matter regions effectively reflected individual differences. The increased abnormality in internal functional connectivity within the basal ganglia may be a contributing factor to the occurrence of repetitive or restrictive behaviors in ASD patients.

Conclusion

The proposed methodology provides an efficacious approach for constructing whole-brain spatio-temporal multilayer FCNs and conducting analysis of their dynamic topological structures. The dynamic topological characteristics of spatio-temporal multilayer FCNs may offer new insights into physiological variations and pathological abnormalities in neuroscience.

Whole-brain structural connectome asymmetry in autism

Autism spectrum disorder is a common neurodevelopmental condition that manifests as a disruption in sensory and social skills. Although it has been shown that the brain morphology of individuals with autism is asymmetric, how this differentially affects the structural connectome organization of each hemisphere remains under-investigated. We studied whole-brain structural connectivity-based brain asymmetry in individuals with autism using diffusion magnetic resonance imaging obtained from the Autism Brain Imaging Data Exchange initiative. By leveraging dimensionality reduction techniques, we constructed low-dimensional representations of structural connectivity and calculated their asymmetry index. Comparing the asymmetry index between individuals with autism and neurotypical controls, we found atypical structural connectome asymmetry in the sensory and default-mode regions, particularly showing weaker asymmetry towards the right hemisphere in autism. Network communication provided topological underpinnings by demonstrating that the inferior temporal cortex and limbic and frontoparietal regions showed reduced global network communication efficiency and decreased send-receive network navigation in the inferior temporal and lateral visual cortices in individuals with autism. Finally, supervised machine learning revealed that structural connectome asymmetry could be used as a measure for predicting communication-related autistic symptoms and nonverbal intelligence. Our findings provide insights into macroscale structural connectome alterations in autism and their topological underpinnings.

Brain Topological Reorganization Associated with Visual Neglect After Stroke

Background/Purpose: To identify brain hubs that are behaviorally relevant for neglect after stroke as well as to characterize their functional architecture of communication. Methods: Twenty acute right hemisphere damaged patients underwent neuropsychological and resting-state functional magnetic resonance imaging sessions. Spatial neglect was assessed by means of the Center of Cancellation on the Bells Cancellation Test. For each patient, resting-state functional connectivity matrices were derived by adopting a brain parcellation scheme consisting of 153 nodes. For every node, we extracted its betweenness centrality (BC) defined as the portion of all shortest paths in the connectome involving such node. Then, neglect hubs were identified as those regions showing a high correlation between their BC and neglect scores. Results: A first set of neglect hubs was identified in multiple systems including dorsal attention and ventral attention, default mode, and frontoparietal executive-control networks within the damaged hemisphere as well as in the posterior and anterior cingulate cortex. Such cortical regions exhibited a loss of BC and increased (i.e., less efficient) weighted shortest path length (WSPL) related to severe neglect. Conversely, a second group of neglect hubs found in visual and motor networks, in the undamaged hemisphere, exhibited a pathological increase of BC and reduction of WSPL associated with severe neglect. Conclusion: The topological reorganization of the brain in neglect patients might reflect a maladaptive shift in processing spatial information from higher level associative-control systems to lower level visual and sensory-motor processing areas after a right hemisphere lesion.

Classification of Preschoolers with Low-Functioning Autism Spectrum Disorder Using Multimodal MRI Data

Multimodal imaging studies targeting preschoolers and low-functioning autism spectrum disorder (ASD) patients are scarce. We applied machine learning classifiers to parameters from T1-weighted MRI and DTI data of 58 children with ASD (age 3-6 years) and 48 typically developing controls (TDC). Classification performance reached an accuracy, sensitivity, and specificity of 88.8%, 93.0%, and 83.8%, respectively. The most prominent features were the cortical thickness of the right inferior occipital gyrus, mean diffusivity of the middle cerebellar peduncle, and nodal efficiency of the left posterior cingulate gyrus. Machine learning-based analysis of MRI data was useful in distinguishing low-functioning ASD preschoolers from TDCs. Combination of T1 and DTI improved classification accuracy about 10%, and large-scale multi-modal MRI studies are warranted for external validation.

Amplitude of low frequency fluctuations during resting state fMRI in autistic children

Resting state fMRI (rs-fMRI) provides an excellent platform for examining the amplitude of low frequency fluctuations (ALFF) and fractional amplitude of low frequency fluctuations (fALFF), which are key indices of brain functioning. However, ALFF and fALFF have been used only sporadically to study autism. rs-fMRI data from 69 children (40 autistic, mean age = 8.47 ± 2.20 years; age range: 5.2 to 13.2; and 29 non-autistic, mean age = 9.02 ± 1.97 years; age range 5.9 to 12.9) were obtained from the Autism Brain Imaging Data Exchange (ABIDE II). ALFF and fALFF were measured using CONN connectivity toolbox and SPM12, at whole-brain & network-levels. A two-sampled t-test and a 2 Group (autistic, non-autistic) × 7 Networks ANOVA were conducted to test group differences in ALFF and fALFF. The whole-brain analysis identified significantly reduced ALFF values for autistic participants in left parietal opercular cortex, precuneus, and right insula. At the network level, there was a significant effect of diagnostic group and brain network on ALFF values, and only significant effect of network, not group, on fALFF values. Regression analyses indicated a significant effect of age on ALFF values of certain networks in autistic participants. Such intrinsically different network-level responses in autistic participants may have implications for task-level recruitment and synchronization of brain areas, which may in turn impact optimal cognitive functioning. Moreover, differences in low frequency fluctuations of key networks, such as the DMN and SN, may underlie alterations in brain responses in autism that are frequently reported in the literature.

Structural filtering of functional data offered discriminative features for autism spectrum disorder

This study attempted to answer the question, "Can filtering the functional data through the frequency bands of the structural graph provide data with valuable features which are not valuable in unfiltered data"?. The valuable features discriminate between autism spectrum disorder (ASD) and typically control (TC) groups. The resting-state fMRI data was passed through the structural graph's low, middle, and high-frequency band (LFB, MFB, and HFB) filters to answer the posed question. The structural graph was computed using the diffusion tensor imaging data. Then, the global metrics of functional graphs and metrics of functional triadic interactions were computed for filtered and unfiltered rfMRI data. Compared to TCs, ASDs had significantly higher clustering coefficients in the MFB, higher efficiencies and strengths in the MFB and HFB, and lower small-world propensity in the HFB. These results show over-connectivity, more global integration, and decreased local specialization in ASDs compared to TCs. Triadic analysis showed that the numbers of unbalanced triads were significantly lower for ASDs in the MFB. This finding may indicate the reason for restricted and repetitive behavior in ASDs. Also, in the MFB and HFB, the numbers of balanced triads and the energies of triadic interactions were significantly higher and lower for ASDs, respectively. These findings may reflect the disruption of the optimum balance between functional integration and specialization. There was no significant difference between ASDs and TCs when using the unfiltered data. All of these results demonstrated that significant differences between ASDs and TCs existed in the MFB and HFB of the structural graph when analyzing the global metrics of the functional graph and triadic interaction metrics. Also, these results demonstrated that frequency bands of the structural graph could offer significant findings which were not found in the unfiltered data. In conclusion, the results demonstrated the promising perspective of using structural graph frequency bands for attaining discriminative features and new knowledge, especially in the case of ASD.

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

Identifying Visual Attention Features Accurately Discerning Between Autism and Typically Developing: a Deep Learning Framework

Atypical visual attention is a hallmark of autism spectrum disorder (ASD). Identifying the attention features accurately discerning between people with ASD and typically developing (TD) at the individual level remains a challenge. In this study, we developed a new systematic framework combining high accuracy deep learning classification, deep learning segmentation, image ablation and a direct measurement of classification ability to identify the discriminative features for autism identification. Our two-stream model achieved the state-of-the-art performance with a classification accuracy of 0.95. Using this framework, two new categories of features, Food & drink and Outdoor-objects, were identified as discriminative attention features, in addition to the previously reported features including Center-object and Human-faces, etc. Altered attention to the new categories helps to understand related atypical behaviors in ASD. Importantly, the area under curve (AUC) based on the combined top-9 features identified in this study was 0.92, allowing an accurate classification at the individual level. We also obtained a small but informative dataset of 12 images with an AUC of 0.86, suggesting a potentially efficient approach for the clinical diagnosis of ASD. Together, our deep learning framework based on VGG-16 provides a novel and powerful tool to recognize and understand abnormal visual attention in ASD, which will, in turn, facilitate the identification of biomarkers for ASD.

rs-fMRI and machine learning for ASD diagnosis: a systematic review and meta-analysis

Autism Spectrum Disorder (ASD) diagnosis is still based on behavioral criteria through a lengthy and time-consuming process. Much effort is being made to identify brain imaging biomarkers and develop tools that could facilitate its diagnosis. In particular, using Machine Learning classifiers based on resting-state fMRI (rs-fMRI) data is promising, but there is an ongoing need for further research on their accuracy and reliability. Therefore, we conducted a systematic review and meta-analysis to summarize the available evidence in the literature so far. A bivariate random-effects meta-analytic model was implemented to investigate the sensitivity and specificity across the 55 studies that offered sufficient information for quantitative analysis. Our results indicated overall summary sensitivity and specificity estimates of 73.8% and 74.8%, respectively. SVM stood out as the most used classifier, presenting summary estimates above 76%. Studies with bigger samples tended to obtain worse accuracies, except in the subgroup analysis for ANN classifiers. The use of other brain imaging or phenotypic data to complement rs-fMRI information seems promising, achieving higher sensitivities when compared to rs-fMRI data alone (84.7% versus 72.8%). Finally, our analysis showed AUC values between acceptable and excellent. Still, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of those classification algorithms to clinical settings.

Individual-specific networks for prediction modelling – A scoping review of methods

Background

Recent advances in biotechnology enable the acquisition of high-dimensional data on individuals, posing challenges for prediction models which traditionally use covariates such as clinical patient characteristics. Alternative forms of covariate representations for the features derived from these modern data modalities should be considered that can utilize their intrinsic interconnection. The connectivity information between these features can be represented as an individual-specific network defined by a set of nodes and edges, the strength of which can vary from individual to individual. Global or local graph-theoretical features describing the network may constitute potential prognostic biomarkers instead of or in addition to traditional covariates and may replace the often unsuccessful search for individual biomarkers in a high-dimensional predictor space.

Methods

We conducted a scoping review to identify, collate and critically appraise the state-of-art in the use of individual-specific networks for prediction modelling in medicine and applied health research, published during 2000–2020 in the electronic databases PubMed, Scopus and Embase.

Results

Our scoping review revealed the main application areas namely neurology and pathopsychology, followed by cancer research, cardiology and pathology (N = 148). Network construction was mainly based on Pearson correlation coefficients of repeated measurements, but also alternative approaches (e.g. partial correlation, visibility graphs) were found. For covariates measured only once per individual, network construction was mostly based on quantifying an individual’s contribution to the overall group-level structure. Despite the multitude of identified methodological approaches for individual-specific network inference, the number of studies that were intended to enable the prediction of clinical outcomes for future individuals was quite limited, and most of the models served as proof of concept that network characteristics can in principle be useful for prediction.

Conclusion

The current body of research clearly demonstrates the value of individual-specific network analysis for prediction modelling, but it has not yet been considered as a general tool outside the current areas of application. More methodological research is still needed on well-founded strategies for network inference, especially on adequate network sparsification and outcome-guided graph-theoretical feature extraction and selection, and on how networks can be exploited efficiently for prediction modelling.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-022-01544-6.

Cortical Thickness and Clinical Findings in Prescholar Children With Autism Spectrum Disorder

The term autism spectrum disorder (ASD) includes a wide variability of clinical presentation, and this clinical heterogeneity seems to reflect a still unclear multifactorial etiopathogenesis, encompassing different genetic risk factors and susceptibility to environmental factors. Several studies and many theories recognize as mechanisms of autism a disruption of brain development and maturation time course, suggesting the existence of common neurobiological substrates, such as defective synaptic structure and aberrant brain connectivity. Magnetic resonance imaging (MRI) plays an important role in both assessment of region-specific structural changes and quantification of specific alterations in gray or white matter, which could lead to the identification of an MRI biomarker. In this study, we performed measurement of cortical thickness in a selected well-known group of preschool ASD subjects with the aim of finding correlation between cortical metrics and clinical scores to understand the underlying mechanism of symptoms and to support early clinical diagnosis. Our results confirm that recent brain MRI techniques combined with clinical data can provide some useful information in defining the cerebral regions involved in ASD although large sample studies with homogeneous analytical and multisite approaches are needed.

Abnormalities of Gray Matter Volume and Its Correlation with Clinical Symptoms in Adolescents with High-Functioning Autism Spectrum Disorder

BACKGROUND

Previous studies have indicated abnormal gray matter volume (GMV) in individuals with autism spectrum disorder (ASD); however, there is little consistency across the findings within these studies, partly due to small sample size and great heterogeneity among participants between studies. Additionally, few studies have explored the correlation between clinical symptoms and GMV abnormalities in individuals with ASD. Here, the current study examined GMV alterations in whole brain and their correlations with clinical symptoms in a relatively large and homogeneous sample of participants with ASD matched typically developing (TD) controls.

METHODS

Forty-eight adolescents with high-functioning ASD and 29 group-matched TD controls underwent structural magnetic resonance images. Voxel-based morphometry was applied to investigate regional GMV alterations. The participants with ASD were examined for the severity of clinical symptoms with Autism Behavior Checklist (ABC). The relationship between GMV abnormalities and clinical symptoms was explored in ASD group using voxel-wise correlation analysis within brain regions that showed significant GMV alterations in individuals with ASD compared with TD controls.

RESULTS

We found increased GMV in multiple brain regions, including the inferior frontal gyrus, medial frontal gyrus, superior frontal gyrus, superior temporal gyrus, occipital pole, anterior cingulate, cerebellum anterior lobe, cerebellum posterior lobe, and midbrain, as well as decreased GMV in cerebellum posterior lobe in individuals with ASD. The correlation analysis showed the GMV in the left fusiform was negatively associated with the scores of sensory factor, and the GMV in the right cerebellum anterior lobe was positively associated with the scores of social self-help factor.

CONCLUSION

Our results indicated that widespread GMV abnormalities of brain regions occurred in individuals with ASD, suggesting a potential neural basis for the pathogenesis and symptomatology of ASD.

Effect of data leakage in brain MRI classification using 2D convolutional neural networks

In recent years, 2D convolutional neural networks (CNNs) have been extensively used to diagnose neurological diseases from magnetic resonance imaging (MRI) data due to their potential to discern subtle and intricate patterns. Despite the high performances reported in numerous studies, developing CNN models with good generalization abilities is still a challenging task due to possible data leakage introduced during cross-validation (CV). In this study, we quantitatively assessed the effect of a data leakage caused by 3D MRI data splitting based on a 2D slice-level using three 2D CNN models to classify patients with Alzheimer's disease (AD) and Parkinson's disease (PD). Our experiments showed that slice-level CV erroneously boosted the average slice level accuracy on the test set by 30% on Open Access Series of Imaging Studies (OASIS), 29% on Alzheimer's Disease Neuroimaging Initiative (ADNI), 48% on Parkinson's Progression Markers Initiative (PPMI) and 55% on a local de-novo PD Versilia dataset. Further tests on a randomly labeled OASIS-derived dataset produced about 96% of (erroneous) accuracy (slice-level split) and 50% accuracy (subject-level split), as expected from a randomized experiment. Overall, the extent of the effect of an erroneous slice-based CV is severe, especially for small datasets.

Discriminative Dictionary Learning for Autism Spectrum Disorder Identification

Autism Spectrum Disorder (ASD) is a group of lifelong neurodevelopmental disorders with complicated causes. A key symptom of ASD patients is their impaired interpersonal communication ability. Recent study shows that face scanning patterns of individuals with ASD are often different from those of typical developing (TD) ones. Such abnormality motivates us to study the feasibility of identifying ASD children based on their face scanning patterns with machine learning methods. In this paper, we consider using the bag-of-words (BoW) model to encode the face scanning patterns, and propose a novel dictionary learning method based on dual mode seeking for better BoW representation. Unlike k-means which is broadly used in conventional BoW models to learn dictionaries, the proposed method captures discriminative information by finding atoms which maximizes both the purity and coverage of belonging samples within one class. Compared to the rich literature of ASD studies from psychology and neural science, our work marks one of the relatively few attempts to directly identify high-functioning ASD children with machine learning methods. Experiments demonstrate the superior performance of our method with considerable gain over several baselines. Although the proposed work is yet too preliminary to directly replace existing autism diagnostic observation schedules in the clinical practice, it shed light on future applications of machine learning methods in early screening of ASD.

Diffusion tensor imaging brain structural clustering patterns in major depressive disorder

Using magnetic resonance diffusion tensor imaging data from 45 patients with major depressive disorder (MDD) and 41 healthy controls (HCs), network indices based on a 246-region Brainnetcome Atlas were investigated in the two groups, and in the MDD subgroups that were subgrouped based on their duration of the disease. Correlation between the network indices and the duration of illness was also examined. Differences were observed between the MDDS subgroup (short disease duration) and the HC group, but not between the MDD and HC groups. Compared with the HCs, the clustering coefficient (CC) values of MDDS were higher in precentral gyrus, and caudal lingual gyrus; the CC of MDDL subgroup (long disease duration) was higher in postcentral gyrus and dorsal granular insula in the right hemisphere. Network resilience analyses showed that the MDDS group was higher than the HC group, representing relatively more randomized networks in the diseased brains. The correlation analyses showed that the caudal lingual gyrus in the right hemisphere and the rostral lingual gyrus in the left hemisphere were particularly correlated with disease duration. The analyses showed that duration of the illness appears to have an impact on the networking patterns. Networking abnormalities in MDD patients could be blurred or hidden by the heterogeneity of the MDD clinical subgroups. Brain plasticity may introduce a recovery effect to the abnormal network patterns seen in patients with a relative short term of the illness, as the abnormalities may disappear in MDDL .

Autism Spectrum Disorder Studies Using fMRI Data and Machine Learning: A Review

Machine learning methods have been frequently applied in the field of cognitive neuroscience in the last decade. A great deal of attention has been attracted to introduce machine learning methods to study the autism spectrum disorder (ASD) in order to find out its neurophysiological underpinnings. In this paper, we presented a comprehensive review about the previous studies since 2011, which applied machine learning methods to analyze the functional magnetic resonance imaging (fMRI) data of autistic individuals and the typical controls (TCs). The all-round process was covered, including feature construction from raw fMRI data, feature selection methods, machine learning methods, factors for high classification accuracy, and critical conclusions. Applying different machine learning methods and fMRI data acquired from different sites, classification accuracies were obtained ranging from 48.3% up to 97%, and informative brain regions and networks were located. Through thorough analysis, high classification accuracies were found to usually occur in the studies which involved task-based fMRI data, single dataset for some selection principle, effective feature selection methods, or advanced machine learning methods. Advanced deep learning together with the multi-site Autism Brain Imaging Data Exchange (ABIDE) dataset became research trends especially in the recent 4 years. In the future, advanced feature selection and machine learning methods combined with multi-site dataset or easily operated task-based fMRI data may appear to have the potentiality to serve as a promising diagnostic tool for ASD.

Automatic classification of children with autism spectrum disorder by using a computerized visual-orienting task

Early screening and diagnosis of autism spectrum disorder (ASD) primarily rely on behavioral observations by qualified clinicians whose decision process can benefit from the combination of machine learning algorithms and sensor data. We designed a computerized visual-orienting task with gaze-related or non-gaze-related directional cues, which triggered participants' gaze-following behavior. Based on their eye-movement data registered by an eye tracker, we applied the machine learning algorithms to classify high-functioning children with ASD (HFA), low-functioning children with ASD (LFA), and typically developing children (TD). We found that TD children had higher success rates in obtaining rewards than HFA children, and HFA children had higher rates than LFA children. Based on raw eye-tracking data, our machine learning algorithm could classify the three groups with an accuracy of 81.1% and relatively high sensitivity and specificity. Classification became worse if only data from the gaze or nongaze conditions were used, suggesting that "less-social" directional cues also carry useful information for distinguishing these groups. Our findings not only provide insights about visual-orienting deficits among children with ASD but also demonstrate the promise of combining classical behavioral paradigms with machine learning algorithms for aiding the screening for individuals with ASD.

Resting-State Functional Connectivity in Mathematical Expertise

To what extent are different levels of expertise reflected in the functional connectivity of the brain? We addressed this question by using resting-state functional magnetic resonance imaging (fMRI) in mathematicians versus non-mathematicians. To this end, we investigated how the two groups of participants differ in the correlation of their spontaneous blood oxygen level-dependent fluctuations across the whole brain regions during resting state. Moreover, by using the classification algorithm in machine learning, we investigated whether the resting-state fMRI networks between mathematicians and non-mathematicians were distinguished depending on features of functional connectivity. We showed diverging involvement of the frontal-thalamic-temporal connections for mathematicians and the medial-frontal areas to precuneus and the lateral orbital gyrus to thalamus connections for non-mathematicians. Moreover, mathematicians who had higher scores in mathematical knowledge showed a weaker connection strength between the left and right caudate nucleus, demonstrating the connections' characteristics related to mathematical expertise. Separate functional networks between the two groups were validated with a maximum classification accuracy of 91.19% using the distinct resting-state fMRI-based functional connectivity features. We suggest the advantageous role of preconfigured resting-state functional connectivity, as well as the neural efficiency for experts' successful performance.

Autism classified by magnetic resonance imaging: A pilot study of a potential diagnostic tool

OBJECTIVES

Individual anatomical biomarkers have limited power for the classification of autism. The present study introduces a multivariate classification approach using structural magnetic resonance imaging data from individuals with and without autism.

METHODS

The classifier utilizes z-normalization, parameter weighting, and interindividual comparison on brain segmentation data, for estimation of an individual summed total index (TI). The TI indicates whether the gross morphological pattern of each individual's brain is in the direction of cases or controls.

RESULTS

Morphometric analysis found significant differences within subcortical gray matter structures and limbic areas. There was no significant difference in total brain volume. A case-control pilot-study of TIs in normally intelligent individuals with autism (24) and without (21) yielded a maximal accuracy of 78.9% following cross-validation. It showed a high accuracy compared with machine learning methods when tested on the same dataset. The TI correlated well with the autism quotient (R = 0.51) across groups.

CONCLUSION

These results are on par with studies on autism using machine learning. The main contributions are its transparency and simplicity. The possibility of including additional neuroimaging data further increases the potential of the classifier as a diagnostic aid for neuropsychiatric disorders, as well as a research tool for neuroscientific investigations.

Machine learning (ML) for the diagnosis of autism spectrum disorder (ASD) using brain imaging

Autism spectrum disorder (ASD) is a neurodevelopmental incurable disorder with a long diagnostic period encountered in the early years of life. If diagnosed early, the negative effects of this disease can be reduced by starting special education early. Machine learning (ML), an increasingly ubiquitous technology, can be applied for the early diagnosis of ASD. The aim of this study is to examine and provide a comprehensive state-of-the-art review of ML research for the diagnosis of ASD based on (a) structural magnetic resonance image (MRI), (b) functional MRI and (c) hybrid imaging techniques over the past decade. The accuracy of the studies with a large number of participants is in general lower than those with fewer participants leading to the conclusion that further large-scale studies are needed. An examination of the age of the participants shows that the accuracy of the automated diagnosis of ASD is higher at a younger age range. ML technology is expected to contribute significantly to the early and rapid diagnosis of ASD in the coming years and become available to clinicians in the near future. This review is aimed to facilitate that.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Towards a Multivariate Biomarker-Based Diagnosis of Autism Spectrum Disorder: Review and Discussion of Recent Advancements

An ever-evolving understanding of autism spectrum disorder (ASD) pathophysiology necessitates that diagnostic standards also evolve from being observation-based to include quantifiable clinical measurements. The multisystem nature of ASD motivates the use of multivariate methods of statistical analysis over common univariate approaches for discovering clinical biomarkers relevant to this goal. In addition to characterization of important behavioral patterns for improving current diagnostic instruments, multivariate analyses to date have allowed for thorough investigation of neuroimaging-based, genetic, and metabolic abnormalities in individuals with ASD. This review highlights current research using multivariate statistical analyses to quantify the value of these behavioral and physiological markers for ASD diagnosis. A detailed discussion of a blood-based diagnostic test for ASD using specific metabolite concentrations is also provided. The advancement of ASD biomarker research promises to provide earlier and more accurate diagnoses of the disorder.

Multivariate models of brain volume for identification of children and adolescents with fetal alcohol spectrum disorder

Magnetic resonance imaging (MRI) studies of fetal alcohol spectrum disorder (FASD) have shown reductions of brain volume associated with prenatal exposure to alcohol. Previous studies consider regional brain volumes independently but ignore potential relationships across numerous structures. This study aims to (a) identify a multivariate model based on regional brain volume that discriminates children/adolescents with FASD versus healthy controls, and (b) determine if FASD classification performance can be increased by building classification models separately for each sex. Three‐dimensional T1‐weighted MRI from two independent childhood/adolescent datasets were used for training (79 FASD, aged 5.7–18.9 years, 35 males; 81 controls, aged 5.8–18.5 years, 32 males) and testing (67 FASD, aged 6.0–19.6 years, 38 males; 74 controls, aged 5.2–19.5 years, 42 males) a classification model. Using FreeSurfer, 87 regional brain volumes were extracted for each subject and were used as input into a support vector machine generating a classification model from the training data. The model performed moderately well on the test data with accuracy 77%, sensitivity 64%, and specificity 88%. Regions that contributed heavily to prediction in this model included temporal lobe and subcortical gray matter. Further investigation of two separate models for males and females showed slightly decreased accuracy compared to the model including all subjects (male accuracy 70%; female accuracy 67%), but had different regional contributions suggesting sex differences. This work demonstrates the potential of multivariate analysis of brain volumes for discriminating children/adolescents with FASD and provides indication of the most affected regions.

Prediction of Autism at 3 Years from Behavioural and Developmental Measures in High-Risk Infants: A Longitudinal Cross-Domain Classifier Analysis

We integrated multiple behavioural and developmental measures from multiple time-points using machine learning to improve early prediction of individual Autism Spectrum Disorder (ASD) outcome. We examined Mullen Scales of Early Learning, Vineland Adaptive Behavior Scales, and early ASD symptoms between 8 and 36 months in high-risk siblings (HR; n = 161) and low-risk controls (LR; n = 71). Longitudinally, LR and HR-Typical showed higher developmental level and functioning, and fewer ASD symptoms than HR-Atypical and HR-ASD. At 8 months, machine learning classified HR-ASD at chance level, and broader atypical development with 69.2% Area Under the Curve (AUC). At 14 months, ASD and broader atypical development were classified with approximately 71% AUC. Thus, prediction of ASD was only possible with moderate accuracy at 14 months.

Characterizing and Predicting Autism Spectrum Disorder by Performing Resting-State Functional Network Community Pattern Analysis

Growing evidence indicates that autism spectrum disorder (ASD) is a neuropsychological disconnection syndrome that can be analyzed using various complex network metrics used as pathology biomarkers. Recently, community detection and analysis rooted in the complex network and graph theories have been introduced to investigate the changes in resting-state functional network community structure under neurological pathologies. However, the potential of hidden patterns in the modular organization of networks derived from resting-state functional magnetic resonance imaging to predict brain pathology has never been investigated. In this study, we present a novel analysis technique to identify alterations in community patterns in functional networks under ASD. In addition, we design machine learning classifiers to predict the clinical class of patients with ASD and controls by using only community pattern quality metrics as features. Analyses conducted on six publicly available datasets from 235 subjects, including patients with ASD and age-matched controls revealed that the modular structure is significantly disturbed in patients with ASD. Machine learning algorithms showed that the predictive power of our five metrics is relatively high (~85.16% peak accuracy for in-site data and ~75.00% peak accuracy for multisite data). These results lend further credence to the dysconnectivity theory of this pathology.

Innovative MRI Techniques in Neuroimaging Approaches for Cerebrovascular Diseases and Vascular Cognitive Impairment

Cognitive impairment and dementia are recognized as major threats to public health. Many studies have shown the important role played by challenges to the cerebral vasculature and the neurovascular unit. To investigate the structural and functional characteristics of the brain, MRI has proven an invaluable tool for visualizing the internal organs of patients and analyzing the parameters related to neuronal activation and blood flow in vivo. Different strategies of imaging can be combined to obtain various parameters: (i) measures of cortical and subcortical structures (cortical thickness, subcortical structures volume); (ii) evaluation of microstructural characteristics of the white matter (fractional anisotropy, mean diffusivity); (iii) neuronal activation and synchronicity to identify functional networks across different regions (functional connectivity between specific regions, graph measures of specific nodes); and (iv) structure of the cerebral vasculature and its efficacy in irrorating the brain (main vessel diameter, cerebral perfusion). The high amount of data obtainable from multi-modal sources calls for methods of advanced analysis, like machine-learning algorithms that allow the discrimination of the most informative features, to comprehensively characterize the cerebrovascular network into specific and sensitive biomarkers. By using the same techniques of human imaging in pre-clinical research, we can also investigate the mechanisms underlying the pathophysiological alterations identified in patients by imaging, with the chance of looking for molecular mechanisms to recover the pathology or hamper its progression.

Autistic traits, resting-state connectivity, and absolute pitch in professional musicians: shared and distinct neural features

Background

Recent studies indicate increased autistic traits in musicians with absolute pitch and a higher proportion of absolute pitch in people with autism. Theoretical accounts connect both of these with shared neural principles of local hyper- and global hypoconnectivity, enhanced perceptual functioning, and a detail-focused cognitive style. This is the first study to investigate absolute pitch proficiency, autistic traits, and brain correlates in the same study.

Sample and methods

Graph theoretical analysis was conducted on resting-state (eyes closed and eyes open) EEG connectivity (wPLI, weighted phase lag index) matrices obtained from 31 absolute pitch (AP) and 33 relative pitch (RP) professional musicians. Small-worldness, global clustering coefficient, and average path length were related to autistic traits, passive (tone identification) and active (pitch adjustment) absolute pitch proficiency, and onset of musical training using Welch two-sample tests, correlations, and general linear models.

Results

Analyses revealed increased path length (delta 2–4 Hz), reduced clustering (beta 13–18 Hz), reduced small-worldness (gamma 30–60 Hz), and increased autistic traits for AP compared to RP. Only clustering values (beta 13–18 Hz) were predicted by both AP proficiency and autistic traits. Post hoc single connection permutation tests among raw wPLI matrices in the beta band (13–18 Hz) revealed widely reduced interhemispheric connectivity between bilateral auditory-related electrode positions along with higher connectivity between F7–F8 and F8–P9 for AP. Pitch-naming ability and pitch adjustment ability were predicted by path length, clustering, autistic traits, and onset of musical training (for pitch adjustment) explaining 44% and 38% of variance, respectively.

Conclusions

Results show both shared and distinct neural features between AP and autistic traits. Differences in the beta range were associated with higher autistic traits in the same population. In general, AP musicians exhibit a widely underconnected brain with reduced functional integration and reduced small-world property during resting state. This might be partly related to autism-specific brain connectivity, while differences in path length and small-worldness reflect other ability-specific influences. This is further evidenced for different pathways in the acquisition and development of absolute pitch, likely influenced by both genetic and environmental factors and their interaction.

Transient increased thalamic-sensory connectivity and decreased whole-brain dynamism in autism

Autism spectrum disorder (ASD) is a neurodevelopmental disorder associated with social communication deficits and restricted/repetitive behaviors and is characterized by large-scale atypical subcortical-cortical connectivity, including impaired resting-state functional connectivity between thalamic and sensory regions. Previous studies have typically focused on the abnormal static connectivity in ASD and overlooked potential valuable dynamic patterns in brain connectivity. However, resting-state brain connectivity is indeed highly dynamic, and abnormalities in dynamic brain connectivity have been widely identified in psychiatric disorders. In this study, we investigated the dynamic functional network connectivity (dFNC) between 51 intrinsic connectivity networks in 170 individuals with ASD and 195 age-matched typically developing (TD) controls using independent component analysis and a sliding window approach. A hard clustering state analysis and a fuzzy meta-state analysis were conducted respectively, for the exploration of local and global aberrant dynamic connectivity patterns in ASD. We examined the group difference in dFNC between thalamic and sensory networks in each functional state and group differences in four high-dimensional dynamic measures. The results showed that compared with TD controls, individuals with ASD show an increase in transient connectivity between hypothalamus/subthalamus and some sensory networks (right postcentral gyrus, bi paracentral lobule, and lingual gyrus) in certain functional states, and diminished global meta-state dynamics of the whole-brain functional network. In addition, these atypical dynamic patterns are significantly associated with autistic symptoms indexed by the Autism Diagnostic Observation Schedule. These converging results support and extend previous observations regarding hyperconnectivity between thalamic and sensory regions and stable whole-brain functional configuration in ASD. Dynamic brain connectivity may serve as a potential biomarker of ASD and further investigation of these dynamic patterns might help to advance our understanding of behavioral differences in this complex neurodevelopmental disorder.

Mutual Information Better Quantifies Brain Network Architecture in Children with Epilepsy

Purpose

Metrics of the brain network architecture derived from resting-state fMRI have been shown to provide physiologically meaningful markers of IQ in children with epilepsy. However, traditional measures of functional connectivity (FC), specifically the Pearson correlation, assume a dominant linear relationship between BOLD time courses; this assumption may not be valid. Mutual information is an alternative measure of FC which has shown promise in the study of complex networks due to its ability to flexibly capture association of diverse forms. We aimed to compare network metrics derived from mutual information-defined FC to those derived from traditional correlation in terms of their capacity to predict patient-level IQ.

Materials and Methods

Patients were retrospectively identified with the following: (1) focal epilepsy; (2) resting-state fMRI; and (3) full-scale IQ by a neuropsychologist. Brain network nodes were defined by anatomic parcellation. Parcellation was performed at the size threshold of 350 mm², resulting in networks containing 780 nodes. Whole-brain, weighted graphs were then constructed according to the pairwise connectivity between nodes. In the traditional condition, edges (connections) between each pair of nodes were defined as the absolute value of the Pearson correlation coefficient between their BOLD time courses. In the mutual information condition, edges were defined as the mutual information between time courses. The following metrics were then calculated for each weighted graph: clustering coefficient, modularity, characteristic path length, and global efficiency. A machine learning algorithm was used to predict the IQ of each individual based on their network metrics. Prediction accuracy was assessed as the fractional variation explained for each condition.

Results

Twenty-four patients met the inclusion criteria (age: 8-18 years). All brain networks demonstrated expected small-world properties. Network metrics derived from mutual information-defined FC significantly outperformed the use of the Pearson correlation. Specifically, fractional variation explained was 49% (95% CI: 46%, 51%) for the mutual information method; the Pearson correlation demonstrated a variation of 17% (95% CI: 13%, 19%).

Conclusion

Mutual information-defined functional connectivity captures physiologically relevant features of the brain network better than correlation.

Clinical Relevance

Optimizing the capacity to predict cognitive phenotypes at the patient level is a necessary step toward the clinical utility of network-based biomarkers.

Structural neuroimaging as clinical predictor: A review of machine learning applications

In this paper, we provide an extensive overview of machine learning techniques applied to structural magnetic resonance imaging (MRI) data to obtain clinical classifiers. We specifically address practical problems commonly encountered in the literature, with the aim of helping researchers improve the application of these techniques in future works. Additionally, we survey how these algorithms are applied to a wide range of diseases and disorders (e.g. Alzheimer's disease (AD), Parkinson's disease (PD), autism, multiple sclerosis, traumatic brain injury, etc.) in order to provide a comprehensive view of the state of the art in different fields.

Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging

Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis methods including widely used static functional connectivity (SFC) and more recently proposed dynamic functional connectivity (DFC). Temporal correlations among regions of interest (ROIs), data-driven spatial network and functional network connectivity (FNC) are often computed to reflect SFC from different angles. SFC can be extended to DFC using a sliding-window framework, and intrinsic connectivity states along the time-varying connectivity patterns are typically extracted using clustering or decomposition approaches. We also briefly summarize window-less DFC approaches. Subsequently, we highlight various strategies for feature selection including the filter, wrapper and embedded methods. In terms of model building, we include traditional classifiers as well as more recently applied deep learning methods. Moreover, we review representative applications with remarkable classification accuracy for psychosis and mood disorders, neurodevelopmental disorder, and neurological disorders using fMRI data. Schizophrenia, bipolar disorder, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease and mild cognitive impairment (MCI) are discussed. Finally, challenges in the field are pointed out with respect to the inaccurate diagnosis labeling, the abundant number of possible features and the difficulty in validation. Some suggestions for future work are also provided.

Diametrical relationship between gray and white matter volumes in autism spectrum disorder and schizophrenia

Autism spectrum disorders and schizophrenia have been variously characterized as separate nosological entities with overlapping deficits in social cognition or diametrical extremes of a phenotypic continuum. This study aimed to determine how these models apply to comparative morphometric data. MRI scans of the brain were obtained in 49 subjects with schizophrenia, 20 subjects with autism and 39 healthy controls. Images were parcellated into 40 Brodmann areas and entered into repeated-measures ANOVA for between-group comparison of global and localized gray and white matter volumes. A pattern of lower gray mater volumes and greater white matter volumes was found in subjects with schizophrenia in comparison to subjects with autism. For both gray and white matter, this pattern was most pronounced in regions associated with motor-premotor and anterior frontal cortex, anterior cingulate, fusiform, superior and middle temporal gyri. Patient groups tended to diverge from healthy controls in opposite directions, with greater-than-normal gray matter volumes and lower-than-normal white matter volumes in subjects with autism and reversed patterns in subjects with schizophrenia. White matter reductions in subjects with autism were seen in posterior frontal lobe and along the cingulate arch. Normal hemispheric asymmetry in the temporal lobe was effaced in subjects with autism and schizophrenia, especially in the latter. Nearly identical distribution of changes and diametrically divergent volumetry suggest that autism and schizophrenia may occupy opposite extremes of the same cognitive continuum.

Pattern recognition of magnetic resonance imaging-based gray matter volume measurements classifies bipolar disorder and major depressive disorder

BACKGROUND

Bipolar Disorder (BD) cannot be reliably distinguished from Major Depressive Disorder (MDD) until the first manic or hypomanic episode. Consequently, many patients with BD are treated with antidepressants without mood stabilizers, a strategy that is often ineffective and carries a risk of inducing a manic episode. We previously reported reduced cortical thickness in right precuneus, right caudal middle-frontal cortex and left inferior parietal cortex in BD compared with MDD.

METHODS

This study extends our previous work by performing individual level classification of BD or MDD in an expanded, currently unmedicated, cohort using gray matter volume (GMV) based on Magnetic Resonance Imaging and a Support Vector Machine. All patients were in a Major Depressive Episode and a leave-two-out analysis was performed.

RESULTS

Nineteen out of 26 BD subjects and 20 out of 26 MDD subjects were correctly identified, for a combined accuracy of 75%. The three brain regions contributing to the classification were higher GMV in bilateral supramarginal gyrus and occipital cortex indicating MDD, and higher GMV in right dorsolateral prefrontal cortex indicating BD.

LIMITATIONS

This analysis included scans performed with two different headcoils and scan sequences, which limited the interpretability of results in an independent cohort analysis.

CONCLUSIONS

Our results add to previously published data which suggest that regional gray matter volume should be investigated further as a clinical diagnostic tool to predict BD before the appearance of a manic or hypomanic episode.

Graph Theoretic Analysis of Resting State Functional MR Imaging

Graph theoretic analyses applied to examine the brain at rest have played a critical role in clarifying the foundations of the brain's intrinsic and task-related activity. There are many opportunities for clinical scientists to describe and predict dysfunction using a network perspective. This primer describes the theoretic basis and practical application of graph theoretic analysis to resting state functional MR imaging data. Major practices, concepts, and findings are concisely reviewed. The theoretic and practical frontiers of resting state functional MR imaging are highlighted with observations about major avenues for conceptual advances and clinical translation.

Progress and roadblocks in the search for brain-based biomarkers of autism and attention-deficit/hyperactivity disorder

Children with neurodevelopmental disorders benefit most from early interventions and treatments. The development and validation of brain-based biomarkers to aid in objective diagnosis can facilitate this important clinical aim. The objective of this review is to provide an overview of current progress in the use of neuroimaging to identify brain-based biomarkers for autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD), two prevalent neurodevelopmental disorders. We summarize empirical work that has laid the foundation for using neuroimaging to objectively quantify brain structure and function in ways that are beginning to be used in biomarker development, noting limitations of the data currently available. The most successful machine learning methods that have been developed and applied to date are discussed. Overall, there is increasing evidence that specific features (for example, functional connectivity, gray matter volume) of brain regions comprising the salience and default mode networks can be used to discriminate ASD from typical development. Brain regions contributing to successful discrimination of ADHD from typical development appear to be more widespread, however there is initial evidence that features derived from frontal and cerebellar regions are most informative for classification. The identification of brain-based biomarkers for ASD and ADHD could potentially assist in objective diagnosis, monitoring of treatment response and prediction of outcomes for children with these neurodevelopmental disorders. At present, however, the field has yet to identify reliable and reproducible biomarkers for these disorders, and must address issues related to clinical heterogeneity, methodological standardization and cross-site validation before further progress can be achieved.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Network organization is globally atypical in autism: A graph theory study of intrinsic functional connectivity

BACKGROUND

Despite abundant evidence of brain network anomalies in autism spectrum disorder (ASD), findings have varied from broad functional underconnectivity to broad overconnectivity. Rather than pursuing overly simplifying general hypotheses ('under' vs. 'over'), we tested the hypothesis of atypical network distribution in ASD (i.e., participation of unusual loci in distributed functional networks).

METHODS

We used a selective high-quality data subset from the ABIDE datashare (including 111 ASD and 174 typically developing [TD] participants) and several graph theory metrics. Resting state functional MRI data were preprocessed and analyzed for detection of low-frequency intrinsic signal correlations. Groups were tightly matched for available demographics and head motion.

RESULTS

As hypothesized, the Rand Index (reflecting how similar network organization was to a normative set of networks) was significantly lower in ASD than TD participants. This was accounted for by globally reduced cohesion and density, but increased dispersion of networks. While differences in hub architecture did not survive correction, rich club connectivity (among the hubs) was increased in the ASD group.

CONCLUSIONS

Our findings support the model of reduced network integration (connectivity with networks) and differentiation (or segregation; based on connectivity outside network boundaries) in ASD. While the findings applied at the global level, they were not equally robust across all networks and in one case (greater cohesion within ventral attention network in ASD) even reversed.

Diagnostic model generated by MRI-derived brain features in toddlers with autism spectrum disorder

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder mainly showed atypical social interaction, communication, and restricted, repetitive patterns of behavior, interests and activities. Now clinic diagnosis of ASD is mostly based on psychological evaluation, clinical observation and medical history. All these behavioral indexes could not avoid defects such as subjectivity and reporter-dependency. Therefore researchers devoted themselves to seek relatively stable biomarkers of ASD as supplementary diagnostic evidence. The goal of present study is to generate relatively stable predictive model based on anatomical brain features by using machine learning technique. Forty-six ASD children and thirty-nine development delay children aged from 18 to 37 months were evolved in. As a result, the predictive model generated by regional average cortical thickness of regions with top 20 highest importance of random forest classifier showed best diagnostic performance. And random forest was proved to be the optimal approach for neuroimaging data mining in small size set and thickness-based classification outperformed volume-based classification and surface area-based classification in ASD. The brain regions selected by the models might attract attention and the idea of considering biomarkers as a supplementary evidence of ASD diagnosis worth exploring. Autism Res 2017, 0: 000-000. © 2016 International Society for Autism Research, Wiley Periodicals, Inc. Autism Res 2017, 10: 620-630. © 2016 International Society for Autism Research, Wiley Periodicals, Inc.

One-Class Support Vector Machines Identify the Language and Default Mode Regions As Common Patterns of Structural Alterations in Young Children with Autism Spectrum Disorders

The identification of reliable brain endophenotypes of autism spectrum disorders (ASD) has been hampered to date by the heterogeneity in the neuroanatomical abnormalities detected in this condition. To handle the complexity of neuroimaging data and to convert brain images in informative biomarkers of pathology, multivariate analysis techniques based on Support Vector Machines (SVM) have been widely used in several disease conditions. They are usually trained to distinguish patients from healthy control subjects by making a binary classification. Here, we propose the use of the One-Class Classification (OCC) or Data Description method that, in contrast to two-class classification, is based on a description of one class of objects only. This approach, by defining a multivariate normative rule on one class of subjects, allows recognizing examples from a different category as outliers. We applied the OCC to 314 regional features extracted from brain structural Magnetic Resonance Imaging (MRI) scans of young children with ASD (21 males and 20 females) and control subjects (20 males and 20 females), matched on age [range: 22-72 months of age; mean = 49 months] and non-verbal intelligence quotient (NVIQ) [range: 31-123; mean = 73]. We demonstrated that a common pattern of features characterize the ASD population. The OCC SVM trained on the group of ASD subjects showed the following performances in the ASD vs. controls separation: the area under the receiver operating characteristic curve (AUC) was 0.74 for the male and 0.68 for the female population, respectively. Notably, the ASD vs. controls discrimination results were maximized when evaluated on the subsamples of subjects with NVIQ ≥ 70, leading to AUC = 0.81 for the male and AUC = 0.72 for the female populations, respectively. Language regions and regions from the default mode network-posterior cingulate cortex, pars opercularis and pars triangularis of the inferior frontal gyrus, and transverse temporal gyrus-contributed most to distinguishing individuals with ASD from controls, arguing for the crucial role of these areas in the ASD pathophysiology. The observed brain patterns associate preschoolers with ASD independently of their age, gender and NVIQ and therefore they are expected to constitute part of the ASD brain endophenotype.

Cortical thickness change in autism during early childhood

Structural magnetic resonance imaging (MRI) scans at high spatial resolution can detect potential foci of early brain dysmaturation in children with autism spectrum disorders (ASD). In addition, comparison between MRI and behavior measures over time can identify patterns of brain change accompanying specific outcomes. We report structural MRI data from two time points for a total of 84 scans in children with ASD and 30 scans in typical controls (mean age time one = 4.1 years, mean age at time two = 6.6 years). Surface-based cortical morphometry and linear mixed effects models were used to link changes in cortical anatomy to both diagnostic status and individual differences in changes in language and autism severity. Compared with controls, children with ASD showed accelerated gray matter volume gain with age, which was driven by a lack of typical age-related cortical thickness (CT) decrease within 10 cortical regions involved in language, social cognition, and behavioral control. Greater expressive communication gains with age in children with ASD were associated with greater CT gains in a set of right hemisphere homologues to dominant language cortices, potentially identifying a compensatory system for closer translational study. Hum Brain Mapp 37:2616-2629, 2016. © 2016 Wiley Periodicals, Inc.

Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework

The atypical face scanning patterns in individuals with Autism Spectrum Disorder (ASD) has been repeatedly discovered by previous research. The present study examined whether their face scanning patterns could be potentially useful to identify children with ASD by adopting the machine learning algorithm for the classification purpose. Particularly, we applied the machine learning method to analyze an eye movement dataset from a face recognition task [Yi et al., 2016], to classify children with and without ASD. We evaluated the performance of our model in terms of its accuracy, sensitivity, and specificity of classifying ASD. Results indicated promising evidence for applying the machine learning algorithm based on the face scanning patterns to identify children with ASD, with a maximum classification accuracy of 88.51%. Nevertheless, our study is still preliminary with some constraints that may apply in the clinical practice. Future research should shed light on further valuation of our method and contribute to the development of a multitask and multimodel approach to aid the process of early detection and diagnosis of ASD. Autism Res 2016, 9: 888-898. © 2016 International Society for Autism Research, Wiley Periodicals, Inc.

Reorganization of functionally connected brain subnetworks in high-functioning autism

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.

Classification of autistic individuals and controls using cross-task characterization of fMRI activity

Multivariate pattern analysis (MVPA) has been applied successfully to task-based and resting-based fMRI recordings to investigate which neural markers distinguish individuals with autistic spectrum disorders (ASD) from controls. While most studies have focused on brain connectivity during resting state episodes and regions of interest approaches (ROI), a wealth of task-based fMRI datasets have been acquired in these populations in the last decade. This calls for techniques that can leverage information not only from a single dataset, but from several existing datasets that might share some common features and biomarkers. We propose a fully data-driven (voxel-based) approach that we apply to two different fMRI experiments with social stimuli (faces and bodies). The method, based on Support Vector Machines (SVMs) and Recursive Feature Elimination (RFE), is first trained for each experiment independently and each output is then combined to obtain a final classification output. Second, this RFE output is used to determine which voxels are most often selected for classification to generate maps of significant discriminative activity. Finally, to further explore the clinical validity of the approach, we correlate phenotypic information with obtained classifier scores. The results reveal good classification accuracy (range between 69% and 92.3%). Moreover, we were able to identify discriminative activity patterns pertaining to the social brain without relying on a priori ROI definitions. Finally, social motivation was the only dimension which correlated with classifier scores, suggesting that it is the main dimension captured by the classifiers. Altogether, we believe that the present RFE method proves to be efficient and may help identifying relevant biomarkers by taking advantage of acquired task-based fMRI datasets in psychiatric populations.