Predictive models of autism spectrum disorder based on brain regional cortical thickness

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.

A Nomogram for Predicting ADHD and ASD in Child and Adolescent Mental Health Services (CAMHS)

Objectives: To enhance the early detection of Attention Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) by leveraging clinical variables collected at child and adolescent mental health services (CAMHS). Methods: This study included children diagnosed with ADHD and/or ASD (n = 857). Three logistic regression models were developed to predict the presence of ADHD, its subtypes, and ASD. The analysis began with univariate logistic regression, followed by a multicollinearity diagnostic. A backward logistic regression selection strategy was then employed to retain variables with p < 0.05. Ethical approval was obtained from the local ethics committee. The models' internal validity was evaluated based on their calibration and discriminative abilities. Results: The study produced models that are well-calibrated and validated for predicting ADHD (incorporating variables such as physical activity, history of bone fractures, and admissions to pediatric/psychiatric services) and ASD (including disability, gender, special education needs, and Axis V diagnoses, among others). Conclusions: Clinical variables can play a significant role in enhancing the early identification of ADHD and ASD.

Syndrome-Specific Neuroanatomical Phenotypes in Girls With Turner and Noonan Syndromes

BACKGROUND

Turner syndrome (TS) and Noonan syndrome (NS) are distinct genetic conditions with highly similar physical and neurodevelopmental phenotypes. TS is caused by X chromosome absence, whereas NS results from genetic mutations activating the Ras-mitogen-activated protein kinase signaling pathway. Previous neuroimaging studies in individuals with TS and NS have shown neuroanatomical variations relative to typically developing individuals, a standard comparison group when initially examining a clinical group of interest. However, none of these studies included a second clinical comparison group, limiting their ability to identify syndrome-specific neuroanatomical phenotypes.

METHODS

In this study, we compared the behavioral and brain phenotypes of 37 girls with TS, 26 girls with NS, and 37 typically developing girls, all ages 5 to 12 years, using univariate and multivariate data-driven analyses.

RESULTS

We found divergent neuroanatomical phenotypes between groups, despite high behavioral similarities. Relative to the typically developing group, TS was associated with smaller whole-brain cortical surface area (p ≤ .0001), whereas NS was associated with smaller whole-brain cortical thickness (p = .013). TS was associated with larger subcortical volumes (left amygdala, p = .002; right hippocampus, p = .002), whereas NS was associated with smaller subcortical volumes (bilateral caudate, p ≤ .003; putamen, p < .001; pallidum, p < .001; right hippocampus, p = .015). Multivariate analyses also showed diverging brain phenotypes in terms of surface area and cortical thickness, with surface area outperforming cortical thickness at group separation.

CONCLUSIONS

TS and NS have syndrome-specific brain phenotypes, despite their behavioral similarities. Our observations suggest that neuroanatomical phenotypes better reflect the different genetic etiologies of TS and NS and may be superior biomarkers relative to behavioral phenotypes.

Comprehensive exploration of multi-modal and multi-branch imaging markers for autism diagnosis and interpretation: insights from an advanced deep learning model

Autism spectrum disorder is a complex neurodevelopmental condition with diverse genetic and brain involvement. Despite magnetic resonance imaging advances, autism spectrum disorder diagnosis and understanding its neurogenetic factors remain challenging. We propose a dual-branch graph neural network that effectively extracts and fuses features from bimodalities, achieving 73.9% diagnostic accuracy. To explain the mechanism distinguishing autism spectrum disorder from healthy controls, we establish a perturbation model for brain imaging markers and perform a neuro-transcriptomic joint analysis using partial least squares regression and enrichment to identify potential genetic biomarkers. The perturbation model identifies brain imaging markers related to structural magnetic resonance imaging in the frontal, temporal, parietal, and occipital lobes, while functional magnetic resonance imaging markers primarily reside in the frontal, temporal, occipital lobes, and cerebellum. The neuro-transcriptomic joint analysis highlights genes associated with biological processes, such as "presynapse," "behavior," and "modulation of chemical synaptic transmission" in autism spectrum disorder's brain development. Different magnetic resonance imaging modalities offer complementary information for autism spectrum disorder diagnosis. Our dual-branch graph neural network achieves high accuracy and identifies abnormal brain regions and the neuro-transcriptomic analysis uncovers important genetic biomarkers. Overall, our study presents an effective approach for assisting in autism spectrum disorder diagnosis and identifying genetic biomarkers, showing potential for enhancing the diagnosis and treatment of this condition.

Volume-based and Surface-Based Methods in Autism Compared with Healthy Controls Are Free surfer and CAT12 in Agreement?

Objectives

Autism Spectrum Disorder (ASD) encompasses a range of neurodevelopmental disorders, and early detection is crucial. This study aims to identify the Regions of Interest (ROIs) with significant differences between healthy controls and individuals with autism, as well as evaluate the agreement between FreeSurfer 6 (FS6) and Computational Anatomy Toolbox (CAT12) methods.

Materials & Methods

Surface-based and volume-based features were extracted from FS software and CAT12 toolbox for Statistical Parametric Mapping (SPM) software to estimate ROI-wise biomarkers. These biomarkers were compared between 18 males Typically Developing Controls (TDCs) and 40 male subjects with ASD to assess group differences for each method. Finally, agreement and regression analyses were performed between the two methods for TDCs and ASD groups.

Results

Both methods revealed ROIs with significant differences for each parameter. The Analysis of Covariance (ANCOVA) showed that both TDCs and ASD groups indicated a significant relationship between the two methods (p<0.001). The R2 values for TDCs and ASD groups were 0.692 and 0.680, respectively, demonstrating a moderate correlation between CAT12 and FS6. Bland-Altman graphs showed a moderate level of agreement between the two methods.

Conclusion

The moderate correlation and agreement between CAT12 and FS6 suggest that while some consistency is observed in the results, CAT12 is not a superior substitute for FS6 software. Further research is needed to identify a potential replacement for this method.

Revealing the Selectivity of Neuroanatomical Alteration in Autism Spectrum Disorder via Reverse Inference

BACKGROUND

Although neuroimaging research has identified atypical neuroanatomical substrates in individuals with autism spectrum disorder (ASD), it is at present unclear whether and to what extent disorder-selective gray matter alterations occur in this spectrum of conditions. In fact, a growing body of evidence shows a substantial overlap between the pathomorphological changes across different brain diseases, which may complicate identification of reliable neural markers and differentiation of the anatomical substrates of distinct psychopathologies.

METHODS

Using a novel data-driven and Bayesian methodology with published voxel-based morphometry data (849 peer-reviewed experiments and 22,304 clinical subjects), this study performs the first reverse inference investigation to explore the selective structural brain alteration profile of ASD.

RESULTS

We found that specific brain areas exhibit a >90% probability of gray matter alteration selectivity for ASD: the bilateral precuneus (Brodmann area 7), right inferior occipital gyrus (Brodmann area 18), left cerebellar lobule IX and Crus II, right cerebellar lobule VIIIA, and right Crus I. Of note, many brain voxels that are selective for ASD include areas that are posterior components of the default mode network.

CONCLUSIONS

The identification of these spatial gray matter alteration patterns offers new insights into understanding the complex neurobiological underpinnings of ASD and opens attractive prospects for future neuroimaging-based interventions.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Insulin and Disorders of Behavioural Flexibility

Behavioural inflexibility is a symptom of neuropsychiatric and neurodegenerative disorders such as Obsessive-Compulsive Disorder, Autism Spectrum Disorder and Alzheimer's Disease, encompassing the maintenance of a behaviour even when no longer appropriate. Recent evidence suggests that insulin signalling has roles apart from its regulation of peripheral metabolism and mediates behaviourally-relevant central nervous system (CNS) functions including behavioural flexibility. Indeed, insulin resistance is reported to generate anxious, perseverative phenotypes in animal models, with the Type 2 diabetes medication metformin proving to be beneficial for disorders including Alzheimer's Disease. Structural and functional neuroimaging studies of Type 2 diabetes patients have highlighted aberrant connectivity in regions governing salience detection, attention, inhibition and memory. As currently available therapeutic strategies feature high rates of resistance, there is an urgent need to better understand the complex aetiology of behaviour and develop improved therapeutics. In this review, we explore the circuitry underlying behavioural flexibility, changes in Type 2 diabetes, the role of insulin in CNS outcomes and mechanisms of insulin involvement across disorders of behavioural inflexibility.

Review of Progress in Diagnostic Studies of Autism Spectrum Disorder Using Neuroimaging

This review article summarizes the recent advances in the diagnostic studies of autism spectrum disorders (ASDs) considering some of the most influential research articles from the last two decades. ASD is a heterogeneous neurodevelopmental disorder characterized by abnormalities in social interaction, communication, and behavioral patterns as well as some unique strengths and differences. The current diagnosis systems are based on autism diagnostic observation schedule (ADOS) or autism diagnostic interview-revised (ADI-R), but biological markers are also important for an effective diagnosis of ASDs. The amalgamation of neuroimaging techniques, such as structural and functional magnetic resonance imaging (sMRI and fMRI), with machine-learning and deep-learning approaches helps throw new light on typical biological markers of ASDs at the early stage of life. To assess the performance of a deep neural network, we develop a light-weighted CNN model for ASD classification. The overall accuracy, precision, and F1-score of the proposed model are 99.92%, 99.93% and 99.92%, respectively. All the neuroimaging studies we have reviewed can be divided into 3 categories, viz. thickness, volume and functional connectivity-based studies. We conclude with a discussion of the major findings of considered studies and promising directions for future research in this field.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Structural brain abnormalities and their association with language impairment in school-aged children with Autism Spectrum Disorder

Language impairment is comorbid in most children with Autism Spectrum Disorder (ASD) but its neural basis is poorly understood. Using structural magnetic resonance imaging (MRI), the present study provides the whole-brain comparison of both volume- and surface-based characteristics between groups of children with and without ASD and investigates the relationships between these characteristics in language-related areas and the language abilities of children with ASD measured with standardized tools. A total of 36 school-aged children participated in the study: 18 children with ASD and 18 age- and sex-matched typically developing controls. The results revealed that multiple regions differed between groups of children in gray matter volume, gray matter thickness, gyrification, and cortical complexity (fractal dimension). White matter volume and sulcus depth did not differ between groups of children in any region. Importantly, gray matter thickness and gyrification of language-related areas were related to language functioning in children with ASD. Thus, the results of the present study shed some light on the structural brain abnormalities associated with language impairment in ASD.

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.

Automatic detection of autism spectrum disorder (ASD) in children using structural magnetic resonance imaging with machine vision system

Background

Autism spectrum disorder (ASD) is a group of developmental disorders of the nervous system whose main manifestations are defects in social interactions, communication, repetitive behaviors, and limited interests. Over the years, the use of magnetic resonance imaging (MRI) to help identify patterns that are common in people with autism has increased for classification purposes. This study propose a method for classifying ASD patients versus controls using structural MRI information. In order to increase the accuracy of this method, the volume and surface features of the structural images are used simultaneously.

Results

The accuracy of diagnosis respectively was 86.29%, 71.15%, 86.53%, and 88.46% with SVM, RF, KNN, and ANN classifiers. The highest accuracy of diagnosis was obtained using ANN.

Conclusions

Since clinical evaluations for the diagnosis of autism are extremely time-consuming and depend on the expertise of a specialist, the importance of intelligent diagnosis of this disorder becomes clear. The aim of this study was to design an intelligent system to diagnose autism spectrum disorder.

Accommodating site variation in neuroimaging data using normative and hierarchical Bayesian models

The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance caused by age and sex as biological variation of interest, and with a non-linear version of ComBat. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90% of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modeling where the primary interest is in accurate modeling of inter-subject variation and statistical quantification of deviations from a reference model.

Accommodating site variation in neuroimaging data using normative and hierarchical Bayesian models

The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance caused by age and sex as biological variation of interest, and with a non-linear version of ComBat. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90% of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modeling where the primary interest is in accurate modeling of inter-subject variation and statistical quantification of deviations from a reference model.

Evaluation of brain structure abnormalities in children with autism spectrum disorder (ASD) using structural magnetic resonance imaging

Background

Autism spectrum disorder (ASD) is a group of developmental disorders of the nervous system. Since the core cause of many of the symptoms of autism spectrum disorder is due to changes in the structure of the brain, the importance of examining the structural abnormalities of the brain in these disorder becomes apparent. The aim of this study is evaluation of brain structure abnormalities in children with autism spectrum disorder (ASD) using structural magnetic resonance imaging (sMRI). sMRI images of 26 autistic and 26 Healthy control subjects in the range of 5–10 years are selected from the ABIDE database. For a better assessment of structural abnormalities, the surface and volume features are extracted together from this images. Then, the extracted features from both groups were compared with the sample t test and the features with significant differences between the two groups were identified.

Results

The results of volume-based features indicate an increase in total brain volume and white matter and a change in white and gray matter volume in brain regions of Hammers atlas in the autism group. In addition, the results of surface-based features indicate an increase in mean and standard deviation of cerebral cortex thickness and changes in cerebral cortex thickness, sulcus depth, surface complexity and gyrification index in the brain regions of the Desikan–Killany cortical atlas.

Conclusions

Identifying structurally abnormal areas of the brain and examining their relationship to the clinical features of Autism Spectrum Disorder can pave the way for the correct and early detection of this disorder using structural magnetic resonance imaging. It is also possible to design treatment for autistic people based on the abnormal areas of the brain, and to see the effectiveness of the treatment using imaging.

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.

Cortical and subcortical grey matter atrophy in Amyotrophic Lateral Sclerosis correlates with measures of disease accumulation independent of disease aggressiveness

There is a growing demand for reliable biomarkers to monitor disease progression in Amyotrophic Lateral Sclerosis (ALS) that also take the heterogeneity of ALS into account. In this study, we explored the association between Magnetic Resonance Imaging (MRI)-derived measures of cortical thickness (CT) and subcortical grey matter (GM) volume with D50 model parameters. T1-weighted MRI images of 72 Healthy Controls (HC) and 100 patients with ALS were analyzed using Surface-based Morphometry for cortical structures and Voxel-based Morphometry for subcortical Region-Of-Interest analyses using the Computational Anatomy Toolbox (CAT12). In Inter-group contrasts, these parameters were compared between patients and HC. Further, the D50 model was used to conduct subgroup-analyses, dividing patients by a) Phase of disease covered at the time of MRI-scan and b) individual overall disease aggressiveness. Finally, correlations between GM and D50 model-derived parameters were examined. Inter-group analyses revealed ALS-related cortical thinning compared to HC located mainly in frontotemporal regions and a decrease in GM volume in the left hippocampus and amygdala. A comparison of patients in different phases showed further cortical and subcortical GM atrophy along with disease progression. Correspondingly, regression analyses identified negative correlations between cortical thickness and individual disease covered. However, there were no differences in CT and subcortical GM between patients with low and high disease aggressiveness. By application of the D50 model, we identified correlations between cortical and subcortical GM atrophy and ALS-related functional disability, but not with disease aggressiveness. This qualifies CT and subcortical GM volume as biomarkers representing individual disease covered to monitor therapeutic interventions in ALS.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Small Nucleus Accumbens and Large Cerebral Ventricles in Infants and Toddlers Prior to Receiving Diagnoses of Autism Spectrum Disorder

Early interventions for autism spectrum disorder (ASD) are increasingly available, while only 42-50% of ASD children are diagnosed before 3 years old (YO). To identify neuroimaging biomarkers for early ASD diagnosis, we evaluated surface- and voxel-based brain morphometry in participants under 3YO who were later diagnosed with ASD. Magnetic resonance imaging data were retrospectively obtained from patients later diagnosed with ASD at Boston Children's Hospital. The ASD participants with comorbidities such as congenital disorder, epilepsy, and global developmental delay/intellectual disability were excluded from statistical analyses. Eighty-five structural brain magnetic resonance imaging images were collected from 81 participants under 3YO and compared with 45 images from 45 gender- and age-matched nonautistic controls (non-ASD). Using an Infant FreeSurfer pipeline, 236 regionally distributed measurements were extracted from each scan. By t-tests and linear mixed models, the smaller nucleus accumbens and larger bilateral lateral, third, and fourth ventricles were identified in the ASD group. Vertex-wise t-statistical maps showed decreased thickness in the caudal anterior cingulate cortex and increased thickness in the right medial orbitofrontal cortex in ASD. The smaller bilateral accumbens nuclei and larger cerebral ventricles were independent of age, gender, or gestational age at birth, suggesting that there are MRI-based biomarkers in prospective ASD patients before they receive the diagnosis and that the volume of the nucleus accumbens and cerebral ventricles can be key MRI-based early biomarkers to predict the emergence of ASD.

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.

The Role of Structure MRI in Diagnosing Autism

This study proposes a Computer-Aided Diagnostic (CAD) system to diagnose subjects with autism spectrum disorder (ASD). The CAD system identifies morphological anomalies within the brain regions of ASD subjects. Cortical features are scored according to their contribution in diagnosing a subject to be ASD or typically developed (TD) based on a trained machine-learning (ML) model. This approach opens the hope for developing a new CAD system for early personalized diagnosis of ASD. We propose a framework to extract the cerebral cortex from structural MRI as well as identifying the altered areas in the cerebral cortex. This framework consists of the following five main steps: (i) extraction of cerebral cortex from structural MRI; (ii) cortical parcellation to a standard atlas; (iii) identifying ASD associated cortical markers; (iv) adjusting feature values according to sex and age; (v) building tailored neuro-atlases to identify ASD; and (vi) artificial neural networks (NN) are trained to classify ASD. The system is tested on the Autism Brain Imaging Data Exchange (ABIDE I) sites achieving an average balanced accuracy score of 97±2%. This paper demonstrates the ability to develop an objective CAD system using structure MRI and tailored neuro-atlases describing specific developmental patterns of the brain in autism.

Multi-site harmonization of MRI data uncovers machine-learning discrimination capability in barely separable populations: An example from the ABIDE dataset

•

Multi-site MRI data encode confounding information which may mask case-control differences.

•

The impact of the NeuroHarmonize method is evaluated in the ASD-control classification.

•

We verified the successful removal of the site effect by the harmonization protocol.

•

The increment in the classification performance is quantified after data harmonization.

•

We identified the anatomical features that contributed to the two-class separation.

Machine Learning (ML) techniques have been widely used in Neuroimaging studies of Autism Spectrum Disorders (ASD) both to identify possible brain alterations related to this condition and to evaluate the predictive power of brain imaging modalities. The collection and public sharing of large imaging samples has favored an even greater diffusion of the use of ML-based analyses. However, multi-center data collections may suffer the batch effect, which, especially in case of Magnetic Resonance Imaging (MRI) studies, should be curated to avoid confounding effects for ML classifiers and masking biases. This is particularly important in the study of barely separable populations according to MRI data, such as subjects with ASD compared to controls with typical development (TD). Here, we show how the implementation of a harmo- nization protocol on brain structural features unlocks the case-control ML separation capability in the analysis of a multi-center MRI dataset. This effect is demonstrated on the ABIDE data collection, involving subjects encompassing a wide age range. After data harmonization, the overall ASD vs. TD discrimination capability by a Random Forest (RF) classifier improves from a very low performance (AUC = 0.58 ± 0.04) to a still low, but reasonably significant AUC = 0.67 ± 0.03. The performances of the RF classifier have been evaluated also in the age-specific subgroups of children, adolescents and adults, obtaining AUC = 0.62 ± 0.02, AUC = 0.65 ± 0.03 and AUC = 0.69 ± 0.06, respectively. Specific and consistent patterns of anatomical differences related to the ASD condition have been identified for the three different age subgroups.

Brain structural correlates of autistic traits across the diagnostic divide: A grey matter and white matter microstructure study

Autism Spectrum Disorders (ASD) are a set of neurodevelopmental conditions characterised by difficulties in social interaction and communication as well as stereotyped and restricted patterns of interest. Autistic traits exist in a continuum across the general population, whilst the extreme end of this distribution is diagnosed as clinical ASD. While many studies have investigated brain structure in autism using a case-control design, few have used a dimensional approach. To add to this growing body of literature, we investigated the structural brain correlates of autistic traits in a mixed sample of adult participants (25 ASD and 66 neurotypicals; age: 18-60 years). We examined the relationship between regional brain volumes (using voxel-based morphometry and surface-based morphometry) and white matter microstructure properties (using Diffusion Tensor Imaging) and autistic traits (using Autism Spectrum Quotient). Our findings show grey matter differences in regions including the orbitofrontal cortex and lingual gyrus, and suggestive evidence for white matter microstructure differences in tracts including the superior longitudinal fasciculus being related to higher autistic traits. These grey matter and white matter microstructure findings from our study are consistent with previous reports and support the brain structural differences in ASD. These findings provide further support for shared aetiology for autistic traits across the diagnostic divide.

Autistic Spectrum Disorder Detection and Structural Biomarker Identification Using Self-Attention Model and Individual-Level Morphological Covariance Brain Networks

Autism spectrum disorder (ASD) is a range of neurodevelopmental disorders, which brings enormous burdens to the families of patients and society. However, due to the lack of representation of variance for diseases and the absence of biomarkers for diagnosis, the early detection and intervention of ASD are remarkably challenging. In this study, we proposed a self-attention deep learning framework based on the transformer model on structural MR images from the ABIDE consortium to classify ASD patients from normal controls and simultaneously identify the structural biomarkers. In our work, the individual structural covariance networks are used to perform ASD/NC classification via a self-attention deep learning framework, instead of the original structural MR data, to take full advantage of the coordination patterns of morphological features between brain regions. The self-attention deep learning framework based on the transformer model can extract both local and global information from the input data, making it more suitable for the brain network data than the CNN- structural model. Meanwhile, the potential diagnosis structural biomarkers are identified by the self-attention coefficients map. The experimental results showed that our proposed method outperforms most of the current methods for classifying ASD patients with the ABIDE data and achieves a classification accuracy of 72.5% across different sites. Furthermore, the potential diagnosis biomarkers were found mainly located in the prefrontal cortex, temporal cortex, and cerebellum, which may be treated as the early biomarkers for the ASD diagnosis. Our study demonstrated that the self-attention deep learning framework is an effective way to diagnose ASD and establish the potential biomarkers for ASD.

Machine learning with neuroimaging data to identify autism spectrum disorder: a systematic review and meta-analysis

PURPOSE

Autism Spectrum Disorder (ASD) is diagnosed through observation or interview assessments, which is time-consuming, subjective, and with questionable validity and reliability. Thus, we aimed to evaluate the role of machine learning (ML) with neuroimaging data to provide a reliable classification of ASD.

METHODS

A systematic search of PubMed, Scopus, and Embase was conducted to identify relevant publications. Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used to assess the studies' quality. A bivariate random-effects model meta-analysis was employed to evaluate the pooled sensitivity, the pooled specificity, and the diagnostic performance through the hierarchical summary receiver operating characteristic (HSROC) curve of ML with neuroimaging data in classifying ASD. Meta-regression was also performed.

RESULTS

Forty-four studies (5697 ASD and 6013 typically developing individuals [TD] in total) were included in the quantitative analysis. The pooled sensitivity for differentiating ASD from TD individuals was 86.25 95% confidence interval [CI] (81.24, 90.08), while the pooled specificity was 83.31 95% CI (78.12, 87.48) with a combined area under the HSROC (AUC) of 0.889. Higgins I² (> 90%) and Cochran's Q (p < 0.0001) suggest a high degree of heterogeneity. In the bivariate model meta-regression, a higher pooled specificity was observed in studies not using a brain atlas (90.91 95% CI [80.67, 96.00], p = 0.032). In addition, a greater pooled sensitivity was seen in studies recruiting both males and females (89.04 95% CI [83.84, 92.72], p = 0.021), and combining imaging modalities (94.12 95% [85.43, 97.76], p = 0.036).

CONCLUSION

ML with neuroimaging data is an exciting prospect in detecting individuals with ASD but further studies are required to improve its reliability for usage in clinical practice.

The Connectivity Fingerprint of the Fusiform Gyrus Captures the Risk of Developing Autism in Infants with Tuberous Sclerosis Complex

Tuberous sclerosis complex (TSC) is a rare genetic disorder characterized by benign tumors throughout the body; it is generally diagnosed early in life and has a high prevalence of autism spectrum disorder (ASD), making it uniquely valuable in studying the early development of autism, before neuropsychiatric symptoms become apparent. One well-documented deficit in ASD is an impairment in face processing. In this work, we assessed whether anatomical connectivity patterns of the fusiform gyrus, a central structure in face processing, capture the risk of developing autism early in life. We longitudinally imaged TSC patients at 1, 2, and 3 years of age with diffusion compartment imaging. We evaluated whether the anatomical connectivity fingerprint of the fusiform gyrus was associated with the risk of developing autism measured by the Autism Observation Scale for Infants (AOSI). Our findings suggest that the fusiform gyrus connectivity captures the risk of developing autism as early as 1 year of age and provides evidence that abnormal fusiform gyrus connectivity increases with age. Moreover, the identified connections that best capture the risk of developing autism involved the fusiform gyrus and limbic and paralimbic regions that were consistent with the ASD phenotype, involving an increased number of left-lateralized structures with increasing age.

Automatic classification of autism spectrum disorder in children using cortical thickness and support vector machine

OBJECTIVE

Autism spectrum disorder (ASD) is a neurodevelopmental condition with a heterogeneous phenotype. The role of biomarkers in ASD diagnosis has been highlighted; cortical thickness has proved to be involved in the etiopathogenesis of ASD core symptoms. We apply support vector machine, a supervised machine learning method, in order to identify specific cortical thickness alterations in ASD subjects.

METHODS

A sample of 76 subjects (9.5 ± 3.4 years old) has been selected, 40 diagnosed with ASD and 36 typically developed subjects. All children underwent a magnetic resonance imaging (MRI) examination; T1-MPRAGE sequences were analyzed to extract features for the characterization and parcellation of regions of interests (ROI); average cortical thickness (CT) has been measured for each ROI. For the classification process, the extracted features were used as input for a classifier to identify ASD subjects through a "learning by example" procedure; the features with best performance was then selected by "greedy forward-feature selection." Finally, this model underwent a leave-one-out cross-validation approach.

RESULTS

From the training set of 68 ROIs, five ROIs reached accuracies of over 70%. After this phase, we used a recursive feature selection process in order to identify the eight features with the best accuracy (84.2%). CT resulted higher in ASD compared to controls in all the ROIs identified at the end of the process.

CONCLUSION

We found increased CT in various brain regions in ASD subjects, confirming their role in the pathogenesis of this condition. Considering the brain development curve during ages, these changes in CT may normalize during development. Further validation on a larger sample is required.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Altered cingulate structures and the associations with social awareness deficits and CNTNAP2 gene in autism spectrum disorder

•

ASD individuals showed thinner cortical thickness in bilateral cingulate subregions.

•

The right anterior cingulate WM volume was correlated with social awareness deficit.

•

The CNTNAP2 variant might be associated with the right middle cingulate WM volume.

•

The CNTNAP2 might interact with ASD diagnosis and age on the cortical thickness.

Backgrounds

Although evidence suggests that the activity of the anterior cingulate cortex involves social cognition, there are inconsistent findings regarding the aberrant cingulate gray matter (GM) and scanty evidence about altered cortical thickness and white matter (WM) of cingulate in individuals with autism spectrum disorder (ASD). Evidence supports the association between the genetic variants of CNTNAP2 and altered brain connectivity. This study investigated the cingulate substructure and its association with social awareness deficits and the CNTNAP2 variants in individuals with ASD and typically-developing controls (TDC).

Methods

We assessed 118 individuals with ASD and 122 TDC with MRI and clinical evaluation. The GM, WM volumes and cortical thickness of the cingulate gyrus were compared between ASD and TDC based on fine parcellation. Five SNPs of the CNTNAP2 linked to ASD and brain structural abnormality were genotyped, and rs2710102, rs2538991, rs2710126 passed quality control filters.

Results

ASD individuals showed thinner cortical thickness in bilateral cingulate subregions than TDC without significant group differences in GM and WM volumes. The WM volume of the right anterior cingulate gyrus was correlated with social awareness deficits in ASD. The CNTNAP2 variant demonstrated a main effect on the WM volumes of the right middle cingulate gyrus. Besides, the CNTNAP2 variants interacted with ASD diagnosis and age on the cortical thickness of the left anterior middle cingulate cortex.

Conclusions

Our findings suggest that aberrant cingulate structure in ASD might be associated with the social awareness deficits and genetic variants of the CNTNAP2. These novel findings need validation.

Decreased grey matter volumes in unaffected mothers of individuals with autism spectrum disorder reflect the broader autism endophenotype

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with an early onset and a strong genetic origin. Unaffected relatives may present similar but subthreshold characteristics of ASD. This broader autism phenotype is especially prevalent in the parents of individuals with ASD, suggesting that it has heritable factors. Although previous studies have demonstrated brain morphometry differences in ASD, they are poorly understood in parents of individuals with ASD. Here, we estimated grey matter volume in 45 mothers of children with ASD (mASD) and 46 age-, sex-, and handedness-matched controls using whole-brain voxel-based morphometry analysis. The mASD group had smaller grey matter volume in the right middle temporal gyrus, temporoparietal junction, cerebellum, and parahippocampal gyrus compared with the control group. Furthermore, we analysed the correlations of these brain volumes with ASD behavioural characteristics using autism spectrum quotient (AQ) and systemizing quotient (SQ) scores, which measure general autistic traits and the drive to systemize. Smaller volumes in the middle temporal gyrus and temporoparietal junction correlated with higher SQ scores, and smaller volumes in the cerebellum and parahippocampal gyrus correlated with higher AQ scores. Our findings suggest that atypical grey matter volumes in mASD may represent one of the neurostructural endophenotypes of 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.

Machine Learning Methods for Diagnosing Autism Spectrum Disorder and Attention- Deficit/Hyperactivity Disorder Using Functional and Structural MRI: A Survey

Here we summarize recent progress in machine learning model for diagnosis of Autism Spectrum Disorder (ASD) and Attention-deficit/Hyperactivity Disorder (ADHD). We outline and describe the machine-learning, especially deep-learning, techniques that are suitable for addressing research questions in this domain, pitfalls of the available methods, as well as future directions for the field. We envision a future where the diagnosis of ASD, ADHD, and other mental disorders is accomplished, and quantified using imaging techniques, such as MRI, and machine-learning models.

A novel pipeline leveraging surface-based features of small subcortical structures to classify individuals with autism spectrum disorder

Autism spectrum disorder (ASD) is accompanied with widespread impairment in social-emotional functioning. Classification of ASD using sensitive morphological features derived from structural magnetic resonance imaging (MRI) of the brain may help us to better understand ASD-related mechanisms and improve related automatic diagnosis. Previous studies using T1 MRI scans in large heterogeneous ABIDE dataset with typical development (TD) controls reported poor classification accuracies (around 60%). This may because they only considered surface-based morphometry (SBM) as scalar estimates (such as cortical thickness and surface area) and ignored the neighboring intrinsic geometry information among features. In recent years, the shape-related SBM achieves great success in discovering the disease burden and progression of other brain diseases. However, when focusing on local geometry information, its high dimensionality requires careful treatment in its application to machine learning. To address the above challenges, we propose a novel pipeline for ASD classification, which mainly includes the generation of surface-based features, patch-based surface sparse coding and dictionary learning, Max-pooling and ensemble classifiers based on adaptive optimizers. The proposed pipeline may leverage the sensitivity of brain surface morphometry statistics and the efficiency of sparse coding and Max-pooling. By introducing only the surface features of bilateral hippocampus that derived from 364 male subjects with ASD and 381 age-matched TD males, this pipeline outperformed five recent MRI-based ASD classification studies with >80% accuracy in discriminating individuals with ASD from TD controls. Our results suggest shape-related SBM features may further boost the classification performance of MRI between ASD and TD.

Cost-effectiveness of neuroimaging technologies in management of psychiatric and insomnia disorders: A meta-analysis and prospective cost analysis

BACKGROUND

The optimal diagnostic strategy for patients with psychiatric and insomnia disorders has not been established yet.

PURPOSE

The purpose of this study was to perform cost-effectiveness analysis of six neuroimaging technologies in diagnosis of patients with psychiatric and insomnia disorders.

METHODS

An economic evaluation study was conducted in three parts, including a systematic review for determining diagnostic accuracy, a descriptive cross-sectional study with Activity-Based Costing (ABC) technique for tracing resource consumption, and a cost-effectiveness analysis using a short-term decision-analytic model.

RESULTS

In the first phase, 93 diagnostic accuracy studies were included in the systematic review. The accumulated results (meta-analysis) showed that the highest diagnostic accuracy for psychiatric and insomnia disorders was attributed to PET (sensitivity of 90% and specificity of 80%) and MRI (sensitivity of 76% and specificity of 78%) respectively. In the second phase of the study, we calculated the cost of each technology. The results showed that MRI has the lowest cost. Based on the results in the model of cost-effectiveness sMRI ($ 50.08 per accurate diagnosis) and MRI ($ 58.54 per accurate diagnosis) were more cost-effective neuroimaging technologies.

CONCLUSION

In psychiatric disorders, no single strategy was characterized by both low cost and high accuracy. However, MRI and PET scan had lower cost and higher accuracy for psychiatric disorders, respectively. MRI was the least costly with the highest diagnostic accuracy in insomnia disorders. Based on our model, sMRI in psychiatric disorders and MRI in insomnia disorders were the most cost-effective technologies.

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.

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.

Imbalance of laminar-specific excitatory and inhibitory circuits of the orbitofrontal cortex in autism

BACKGROUND

The human orbitofrontal cortex (OFC) is involved in assessing the emotional significance of events and stimuli, emotion-based learning, allocation of attentional resources, and social cognition. Little is known about the structure, connectivity and excitatory/inhibitory circuit interactions underlying these diverse functions in human OFC, as well as how the circuit is disrupted in individuals with autism spectrum disorder (ASD).

METHODS

We used post-mortem brain tissue from neurotypical adults and individuals with ASD. We examined the morphology and distribution of myelinated axons across cortical layers in OFC, at the single axon level, as a proxy of excitatory pathways. In the same regions, we also examined the laminar distribution of all neurons and neurochemically- and functionally-distinct inhibitory neurons that express the calcium-binding proteins parvalbumin (PV), calbindin (CB), and calretinin (CR).

RESULTS

We found that the density of myelinated axons increased consistently towards layer 6, while the average axon diameter did not change significantly across layers in both groups. However, both the density and diameter of myelinated axons were significantly lower in the ASD group compared with the Control group. The distribution pattern and density of the three major types of inhibitory neurons was comparable between groups, but there was a significant reduction in the density of excitatory neurons across OFC layers in ASD.

LIMITATIONS

This study is limited by the availability of human post-mortem tissue optimally processed for high-resolution microscopy and immunolabeling, especially from individuals with ASD.

CONCLUSIONS

The balance between excitation and inhibition in OFC is at the core of its function, assessing and integrating emotional and social cues with internal states and external inputs. Our preliminary results provide evidence for laminar-specific changes in the ratio of excitation/inhibition in OFC of adults with ASD, with an overall weakening and likely disorganization of excitatory signals and a relative strengthening of local inhibition. These changes likely underlie pathology of major OFC communications with limbic or other cortices and the amygdala in individuals with ASD, and may provide the anatomic basis for disrupted transmission of signals for social interactions and emotions in autism.

The Effects of COMT Polymorphism on Cortical Thickness and Surface Area Abnormalities in Children with ADHD

The catechol-O-methyltransferase (COMT) gene is associated with frontal cortex development and the pathophysiology of attention-deficit/hyperactivity disorder (ADHD). However, how the COMT gene impacts brain structure and behavior in ADHD remains unknown. In the present study, we identify the effect of COMT on cortical thickness and surface area in children with ADHD and children with typically developing (TD) using a machine learning approach. In a sample of 39 children with ADHD and 34 age- and IQ-matched TD children, we found that cortical thickness and surface area differences were predominantly observed in the frontal cortex. Furthermore, a path analysis revealed that a COMT genotype affected abnormal development of the frontal cortex in terms of both cortical thickness and surface area and was associated with working memory changes in children with ADHD. Our study confirms that the role of COMT in ADHD is not restricted to the development of behavior but may also affect the cortical thickness and surface area. Thus, our findings may help to improve the understanding of the neuroanatomic basis for the relationship between the COMT genotype and ADHD pathogenesis.

A normative modelling approach reveals age-atypical cortical thickness in a subgroup of males with autism spectrum disorder

Understanding heterogeneity is an important goal on the path to precision medicine for autism spectrum disorders (ASD). We examined how cortical thickness (CT) in ASD can be parameterized as an individualized metric of atypicality relative to typically-developing (TD) age-related norms. Across a large sample (n = 870 per group) and wide age range (5-40 years), we applied normative modelling resulting in individualized whole-brain maps of age-related CT atypicality in ASD and isolating a small subgroup with highly age-atypical CT. Age-normed CT scores also highlights on-average differentiation, and associations with behavioural symptomatology that is separate from insights gleaned from traditional case-control approaches. This work showcases an individualized approach for understanding ASD heterogeneity that could potentially further prioritize work on a subset of individuals with cortical pathophysiology represented in age-related CT atypicality. Only a small subset of ASD individuals are actually highly atypical relative to age-norms. driving small on-average case-control differences.

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.

Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis

Neuropsychiatric disorders are diagnosed based on behavioral criteria, which makes the diagnosis challenging. Objective biomarkers such as neuroimaging are needed, and when coupled with machine learning, can assist the diagnostic decision and increase its reliability. Sixty-four schizophrenia, 36 autism spectrum disorder (ASD), and 106 typically developing individuals were analyzed. FreeSurfer was used to obtain the data from the participant's brain scans. Six classifiers were utilized to classify the subjects. Subsequently, 26 ultra-high risk for psychosis (UHR) and 17 first-episode psychosis (FEP) subjects were run through the trained classifiers. Lastly, the classifiers' output of the patient groups was correlated with their clinical severity. All six classifiers performed relatively well to distinguish the subject groups, especially support vector machine (SVM) and Logistic regression (LR). Cortical thickness and subcortical volume feature groups were most useful for the classification. LR and SVM were highly consistent with clinical indices of ASD. When UHR and FEP groups were run with the trained classifiers, majority of the cases were classified as schizophrenia, none as ASD. Overall, SVM and LR were the best performing classifiers. Cortical thickness and subcortical volume were most useful for the classification, compared to surface area. LR, SVM, and DT's output were clinically informative. The trained classifiers were able to help predict the diagnostic category of both UHR and FEP Individuals.

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.

Genetics of structural and functional brain changes in autism spectrum disorder

Autism spectrum disorder (ASD) is a neurological and developmental disorder characterized by social impairment and restricted interactive and communicative behaviors. It may occur as an isolated disorder or in the context of other neurological, psychiatric, developmental, and genetic disorders. Due to rapid developments in genomics and imaging technologies, imaging genetics studies of ASD have evolved in the last few years. Increased risk for ASD diagnosis is found to be related to many specific single-nucleotide polymorphisms, and the study of genetic mechanisms and noninvasive imaging has opened various approaches that can help diagnose ASD at the nascent level. Identifying risk genes related to structural and functional changes in the brain of ASD patients provide a better understanding of the disease's neuropsychiatry and can help identify targets for therapeutic intervention that could be useful for the clinical management of ASD patients.

Atypical age-related changes in cortical thickness in autism spectrum disorder

Recent longitudinal neuroimaging and neurophysiological studies have shown that tracking relative age-related changes in neural signals, rather than a static snapshot of a neural measure, could offer higher sensitivity for discriminating typically developing (TD) individuals from those with autism spectrum disorder (ASD). It is not clear, however, which aspects of age-related changes (trajectories) would be optimal for identifying atypical brain development in ASD. Using a large cross-sectional data set (Autism Brain Imaging Data Exchange [ABIDE] repository; releases I and II), we aimed to explore age-related changes in cortical thickness (CT) in TD and ASD populations (age range 6–30 years old). Cortical thickness was estimated from T1-weighted MRI images at three scales of spatial coarseness (three parcellations with different numbers of regions of interest). For each parcellation, three polynomial models of age-related changes in CT were tested. Specifically, to characterize alterations in CT trajectories, we compared the linear slope, curvature, and aberrancy of CT trajectories across experimental groups, which was estimated using linear, quadratic, and cubic polynomial models, respectively. Also, we explored associations between age-related changes with ASD symptomatology quantified as the Autism Diagnostic Observation Schedule (ADOS) scores. While no overall group differences in cortical thickness were observed across the entire age range, ASD and TD populations were different in terms of age-related changes, which were located primarily in frontal and tempo-parietal areas. These atypical age-related changes were also associated with ADOS scores in the ASD group and used to predict ASD from TD development. These results indicate that the curvature is the most reliable feature for localizing brain areas developmentally atypical in ASD with a more pronounced effect with symptomatology and is the most sensitive in predicting ASD development.

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.

The Development of a Practical Artificial Intelligence Tool for Diagnosing and Evaluating Autism Spectrum Disorder: Multicenter Study

Background

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder with an unknown etiology. Early diagnosis and intervention are key to improving outcomes for patients with ASD. Structural magnetic resonance imaging (sMRI) has been widely used in clinics to facilitate the diagnosis of brain diseases such as brain tumors. However, sMRI is less frequently used to investigate neurological and psychiatric disorders, such as ASD, owing to the subtle, if any, anatomical changes of the brain.

Objective

This study aimed to investigate the possibility of identifying structural patterns in the brain of patients with ASD as potential biomarkers in the diagnosis and evaluation of ASD in clinics.

Methods

We developed a novel 2-level histogram-based morphometry (HBM) classification framework in which an algorithm based on a 3D version of the histogram of oriented gradients (HOG) was used to extract features from sMRI data. We applied this framework to distinguish patients with ASD from healthy controls using 4 datasets from the second edition of the Autism Brain Imaging Data Exchange, including the ETH Zürich (ETH), NYU Langone Medical Center: Sample 1, Oregon Health and Science University, and Stanford University (SU) sites. We used a stratified 10-fold cross-validation method to evaluate the model performance, and we applied the Naive Bayes approach to identify the predictive ASD-related brain regions based on classification contributions of each HOG feature.

Results

On the basis of the 3D HOG feature extraction method, our proposed HBM framework achieved an area under the curve (AUC) of >0.75 in each dataset, with the highest AUC of 0.849 in the ETH site. We compared the 3D HOG algorithm with the original 2D HOG algorithm, which showed an accuracy improvement of >4% in each dataset, with the highest improvement of 14% (6/42) in the SU site. A comparison of the 3D HOG algorithm with the scale-invariant feature transform algorithm showed an AUC improvement of >18% in each dataset. Furthermore, we identified ASD-related brain regions based on the sMRI images. Some of these regions (eg, frontal gyrus, temporal gyrus, cingulate gyrus, postcentral gyrus, precuneus, caudate, and hippocampus) are known to be implicated in ASD in prior neuroimaging literature. We also identified less well-known regions that may play unrecognized roles in ASD and be worth further investigation.

Conclusions

Our research suggested that it is possible to identify neuroimaging biomarkers that can distinguish patients with ASD from healthy controls based on the more cost-effective sMRI images of the brain. We also demonstrated the potential of applying data-driven artificial intelligence technology in the clinical setting of neurological and psychiatric disorders, which usually harbor subtle anatomical changes in the brain that are often invisible to the human eye.

Accuracy of Machine Learning Algorithms for the Diagnosis of Autism Spectrum Disorder: Systematic Review and Meta-Analysis of Brain Magnetic Resonance Imaging Studies

BACKGROUND

In the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, their application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder (ASD). However, given their complexity and potential clinical implications, there is an ongoing need for further research on their accuracy.

OBJECTIVE

This study aimed to perform a systematic review and meta-analysis to summarize the available evidence for the accuracy of machine learning algorithms in diagnosing ASD.

METHODS

The following databases were searched on November 28, 2018: MEDLINE, EMBASE, CINAHL Complete (with Open Dissertations), PsycINFO, and Institute of Electrical and Electronics Engineers Xplore Digital Library. Studies that used a machine learning algorithm partially or fully for distinguishing individuals with ASD from control subjects and provided accuracy measures were included in our analysis. The bivariate random effects model was applied to the pooled data in a meta-analysis. A subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false-negative, and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw Summary Receiver Operating Characteristics curves, and obtain the area under the curve (AUC) and partial AUC (pAUC).

RESULTS

A total of 43 studies were included for the final analysis, of which a meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural magnetic resonance imaging (sMRI) subgroup meta-analysis (12 samples with 1776 participants) showed a sensitivity of 0.83 (95% CI 0.76-0.89), a specificity of 0.84 (95% CI 0.74-0.91), and AUC/pAUC of 0.90/0.83. A functional magnetic resonance imaging/deep neural network subgroup meta-analysis (5 samples with 1345 participants) showed a sensitivity of 0.69 (95% CI 0.62-0.75), specificity of 0.66 (95% CI 0.61-0.70), and AUC/pAUC of 0.71/0.67.

CONCLUSIONS

The accuracy of machine learning algorithms for diagnosis of ASD was considered acceptable by few accuracy measures only in cases of sMRI use; however, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of machine learning algorithms to clinical settings.

TRIAL REGISTRATION

PROSPERO CRD42018117779; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=117779.