A systematic review of structural MRI biomarkers in autism spectrum disorder: A machine learning perspective

Autism spectrum disorder detection with kNN imputer and machine learning classifiers via questionnaire mode of screening

Autism spectrum disorder (ASD) is a neurodevelopmental disorder. ASD cannot be fully cured, but early-stage diagnosis followed by therapies and rehabilitation helps an autistic person to live a quality life. Clinical diagnosis of ASD symptoms via questionnaire and screening tests such as Autism Spectrum Quotient-10 (AQ-10) and Quantitative Check-list for Autism in Toddlers (Q-chat) are expensive, inaccessible, and time-consuming processes. Machine learning (ML) techniques are beneficial to predict ASD easily at the initial stage of diagnosis. The main aim of this work is to classify ASD and typical developed (TD) class data using ML classifiers. In our work, we have used different ASD data sets of all age groups (toddlers, adults, children, and adolescents) to classify ASD and TD cases. We implemented One-Hot encoding to translate categorical data into numerical data during preprocessing. We then used kNN Imputer with MinMaxScaler feature transformation to handle missing values and data normalization. ASD and TD class data is classified using Support vector machine, k-nearest-neighbor (KNN), random forest (RF), and artificial neural network classifiers. RF gives the best performance in terms of the accuracy of 100% with different training and testing data split for all four types of data sets and has no over-fitting issue. We have also examined our results with already published work, including recent methods like Deep Neural Network (DNN) and Convolution Neural Network (CNN). Even using complex architectures like DNN and CNN, our proposed methods provide the best results with low-complexity models. In contrast, existing methods have shown accuracy upto 98% with log-loss upto 15%. Our proposed methodology demonstrates the improved generalization for real-time ASD detection during clinical trials.

Review of structural neuroimaging and genetic findings in autism spectrum disorder - a clinical perspective

Autism spectrum disorders (ASDs) are neurodevelopmental conditions characterized by deficits in social relationships and communication and restrictive, repetitive behaviors and interests. ASDs form a heterogeneous group from a clinical and genetic perspective. Currently, ASDs diagnosis is based on the clinical observation of the individual's behavior. The subjective nature of behavioral diagnoses, in the context of ASDs heterogeneity, contributes to significant variation in the age at ASD diagnosis. Early detection has been proved to be critical in ASDs, as early start of appropriate therapeutic interventions greatly improve the outcome for some children. Structural magnetic resonance imaging (MRI) is widely used in the diagnostic work-up of neurodevelopmental conditions, including ASDs, mostly for brain malformations detection. Recently, the focus of brain imaging shifted towards quantitative MRI parameters, aiming to identify subtle changes that may establish early detection biomarkers. ASDs have a strong genetic component; deletions and duplications of several genomic loci have been strongly associated with ASDs risk. Consequently, a multitude of neuroimaging and genetic findings emerged in ASDs in the recent years. The association of gross or subtle changes in brain morphometry and volumes with different genetic defects has the potential to bring new insights regarding normal development and pathomechanisms of various disorders affecting the brain. Still, the clinical implications of these discoveries and the impact of genetic abnormalities on brain structure and function are unclear. Here we review the literature on brain imaging correlated with the most prevalent genomic imbalances in ASD, and discuss the potential clinical impact.

Enhancing Autism Spectrum Disorder identification in multi-site MRI imaging: A multi-head cross-attention and multi-context approach for addressing variability in un-harmonized data

Multi-site MRI imaging poses a significant challenge due to the potential variations in images across different scanners at different sites. This variability can introduce ambiguity in further image analysis. Consequently, the image analysis techniques become site-dependent and scanner-dependent, implying that adjustments in the analysis methodologies are necessary for each scanner configuration. Further, implementing real-time modifications becomes intricate, particularly when incorporating a new type of scanner, as it requires adapting the analysis methods accordingly. Taking into account the aforementioned challenge, we have considered its implications for an Autism spectrum disorder (ASD) application. Our objective is to minimize the impact of site and scanner variability in the analysis, aiming to develop a model that remains effective across different scanners and sites. This entails devising a methodology that allows the same model to function seamlessly across multiple scanner configurations and sites. ASD, a behavioral disorder affecting child development, requires early detection. Clinical observation is time-consuming, prompting the use of fMRI with machine/deep learning for expedited diagnosis. Previous methods leverage fMRI's functional connectivity but often rely on less generalized feature extractors and classifiers. Hence, there is significant room for improvement in the generalizability of detection methods across multi-site data, which is acquired from multiple scanners with different settings. In this study, we propose a Cross-Combination Multi-Scale Multi-Context Framework (CCMSMCF) capable of performing neuroimaging-based diagnostic classification of mental disorders for a multi-site dataset. Thus, this framework attains a degree of internal data harmonization, rendering it to some extent site and scanner-agnostic. Our proposed network, CCMSMCF, is constructed by integrating two sub-modules: the Multi-Head Attention Cross-Scale Module (MHACSM) and the Residual Multi-Context Module (RMCN). We also employ multiple loss functions in a novel manner for training the model, which includes Binary Cross Entropy, Dice loss, and Embedding Coupling loss. The model is validated on the Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, which includes data from multiple scanners across different sites, and achieves promising results.

Machine-learning based prediction of future outcome using multimodal MRI during early childhood

The human brain undergoes rapid changes from the fetal stage to two years postnatally, during which proper structural and functional maturation lays the foundation for later cognitive and behavioral development. Multimodal magnetic resonance imaging (MRI) techniques, especially structural MRI (sMRI), diffusion MRI (dMRI), functional MRI (fMRI), and perfusion MRI (pMRI), provide unprecedented opportunities to non-invasively quantify these early brain changes at whole brain and regional levels. Each modality offers unique insights into the complex processes of both typical neurodevelopment and the pathological mechanisms underlying psychiatric and neurological disorders. Compared to a single modality, multimodal MRI enhances discriminative power and provides more comprehensive insights for understanding and improving neurodevelopmental and mental health outcomes, particularly in high-risk populations. Machine learning- and deep learning-based methods have demonstrated significant potential for predicting future outcomes using multimodal brain MRI acquired during early childhood. Here, we review the unique characteristics of various MRI techniques for imaging early brain development and describe the common approaches to analyze these modalities. We then discuss machine learning approaches in predicting future neurodevelopmental and clinical outcomes using multimodal MRI information during early childhood, highlighting the potential of identifying biomarkers for early detection and personalized interventions in atypical development.

The Cerebellum-Ventral Tegmental Area Microcircuit and Its Implications for Autism Spectrum Disorder: A Narrative Review

The cerebellum has long been implicated in the etiopathogenesis of autism spectrum disorder (ASD), and emerging evidence suggests a significant contribution by reciprocal neural circuits between the cerebellum and ventral tegmental area (VTA) in symptom expression. This review provides a concise overview of morphological and functional alterations in the cerebellum and VTA associated with ASD symptoms, primarily focusing on human studies while also integrating mechanistic insights from animal models. We propose that cerebello-VTA circuit dysfunctional is a major contributor to ASD symptoms and that these circuits are promising targets for drugs and therapeutic brain stimulation methods.

3D CNN for neuropsychiatry: Predicting Autism with interpretable Deep Learning applied to minimally preprocessed structural MRI data

Predictive modeling approaches are enabling progress toward robust and reproducible brain-based markers of neuropsychiatric conditions by leveraging the power of multivariate analyses of large datasets. While deep learning (DL) offers another promising avenue to further advance progress, there are challenges related to implementation in 3D (best for MRI) and interpretability. Here, we address these challenges and describe an interpretable predictive pipeline for inferring Autism diagnosis using 3D DL applied to minimally processed structural MRI scans. We trained 3D DL models to predict Autism diagnosis using the openly available ABIDE I and II datasets (n = 1329, split into training, validation, and test sets). Importantly, we did not perform transformation to template space, to reduce bias and maximize sensitivity to structural alterations associated with Autism. Our models attained predictive accuracies equivalent to those of previous machine learning (ML) studies, while side-stepping the time- and resource-demanding requirement to first normalize data to a template. Our interpretation step, which identified brain regions that contributed most to accurate inference, revealed regional Autism-related alterations that were highly consistent with the literature, encompassing a left-lateralized network of regions supporting language processing. We have openly shared our code and models to enable further progress towards remaining challenges, such as the clinical heterogeneity of Autism and site effects, and to enable the extension of our method to other neuropsychiatric conditions.

Association of polygenic scores for autism with volumetric MRI phenotypes in cerebellum and brainstem in adults

Previous research on autism spectrum disorders (ASD) have showed important volumetric alterations in the cerebellum and brainstem. Most of these studies are however limited to case-control studies with small clinical samples and including mainly children or adolescents. Herein, we aimed to explore the association between the cumulative genetic load (polygenic risk score, PRS) for ASD and volumetric alterations in the cerebellum and brainstem, as well as global brain tissue volumes of the brain among adults at the population level. We utilized the latest genome-wide association study of ASD by the Psychiatric Genetics Consortium (18,381 cases, 27,969 controls) and constructed the ASD PRS in an independent cohort, the UK Biobank. Regression analyses controlled for multiple comparisons with the false-discovery rate (FDR) at 5% were performed to investigate the association between ASD PRS and forty-four brain magnetic resonance imaging (MRI) phenotypes among ~ 31,000 participants. Primary analyses included sixteen MRI phenotypes: total volumes of the brain, cerebrospinal fluid (CSF), grey matter (GM), white matter (WM), GM of whole cerebellum, brainstem, and ten regions of the cerebellum (I_IV, V, VI, VIIb, VIIIa, VIIIb, IX, X, CrusI and CrusII). Secondary analyses included twenty-eight MRI phenotypes: the sub-regional volumes of cerebellum including the GM of the vermis and both left and right lobules of each cerebellar region. ASD PRS were significantly associated with the volumes of seven brain areas, whereby higher PRS were associated to reduced volumes of the whole brain, WM, brainstem, and cerebellar regions I-IV, IX, and X, and an increased volume of the CSF. Three sub-regional volumes including the left cerebellar lobule I-IV, cerebellar vermes VIIIb, and X were significantly and negatively associated with ASD PRS. The study highlights a substantial connection between susceptibility to ASD, its underlying genetic etiology, and neuroanatomical alterations of the adult brain.

Cortical similarities in psychiatric and mood disorders identified in federated VBM analysis via COINSTAC

Structural neuroimaging studies have identified a combination of shared and disorder-specific patterns of gray matter (GM) deficits across psychiatric disorders. Pooling large data allows for examination of a possible common neuroanatomical basis that may identify a certain vulnerability for mental illness. Large-scale collaborative research is already facilitated by data repositories, institutionally supported databases, and data archives. However, these data-sharing methodologies can suffer from significant barriers. Federated approaches augment these approaches by enabling access or more sophisticated, shareable and scaled-up analyses of large-scale data. We examined GM alterations using Collaborative Informatics and Neuroimaging Suite Toolkit for Anonymous Computation, an open-source, decentralized analysis application. Through federated analysis of eight sites, we identified significant overlap in the GM patterns (n = 4,102) of individuals with schizophrenia, major depressive disorder, and autism spectrum disorder. These results show cortical and subcortical regions that may indicate a shared vulnerability to psychiatric disorders.

Autism spectrum disorders detection based on multi-task transformer neural network

Autism Spectrum Disorders (ASD) are neurodevelopmental disorders that cause people difficulties in social interaction and communication. Identifying ASD patients based on resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising diagnostic tool, but challenging due to the complex and unclear etiology of autism. And it is difficult to effectively identify ASD patients with a single data source (single task). Therefore, to address this challenge, we propose a novel multi-task learning framework for ASD identification based on rs-fMRI data, which can leverage useful information from multiple related tasks to improve the generalization performance of the model. Meanwhile, we adopt an attention mechanism to extract ASD-related features from each rs-fMRI dataset, which can enhance the feature representation and interpretability of the model. The results show that our method outperforms state-of-the-art methods in terms of accuracy, sensitivity and specificity. This work provides a new perspective and solution for ASD identification based on rs-fMRI data using multi-task learning. It also demonstrates the potential and value of machine learning for advancing neuroscience research and clinical practice.

Deep Canonical Correlation Fusion Algorithm Based on Denoising Autoencoder for ASD Diagnosis and Pathogenic Brain Region Identification

Autism Spectrum Disorder (ASD) is defined as a neurodevelopmental condition distinguished by unconventional neural activities. Early intervention is key to managing the progress of ASD, and current research primarily focuses on the use of structural magnetic resonance imaging (sMRI) or resting-state functional magnetic resonance imaging (rs-fMRI) for diagnosis. Moreover, the use of autoencoders for disease classification has not been sufficiently explored. In this study, we introduce a new framework based on autoencoder, the Deep Canonical Correlation Fusion algorithm based on Denoising Autoencoder (DCCF-DAE), which proves to be effective in handling high-dimensional data. This framework involves efficient feature extraction from different types of data with an advanced autoencoder, followed by the fusion of these features through the DCCF model. Then we utilize the fused features for disease classification. DCCF integrates functional and structural data to help accurately diagnose ASD and identify critical Regions of Interest (ROIs) in disease mechanisms. We compare the proposed framework with other methods by the Autism Brain Imaging Data Exchange (ABIDE) database and the results demonstrate its outstanding performance in ASD diagnosis. The superiority of DCCF-DAE highlights its potential as a crucial tool for early ASD diagnosis and monitoring.

Brain functional connectivity alterations of Wernicke's area in individuals with autism spectrum conditions in multi-frequency bands: A mega-analysis

Characterized by severe deficits in communication, most individuals with autism spectrum conditions (ASC) experience significant language dysfunctions, thereby impacting their overall quality of life. Wernicke's area, a classical and traditional brain region associated with language processing, plays a substantial role in the manifestation of language impairments. The current study carried out a mega-analysis to attain a comprehensive understanding of the neural mechanisms underpinning ASC, particularly in the context of language processing. The study employed the Autism Brain Image Data Exchange (ABIDE) dataset, which encompasses data from 443 typically developing (TD) individuals and 362 individuals with ASC. The objective was to detect abnormal functional connectivity (FC) between Wernicke's area and other language-related functional regions, and identify frequency-specific altered FC using Wernicke's area as the seed region in ASC. The findings revealed that increased FC in individuals with ASC has frequency-specific characteristics. Further, in the conventional frequency band (0.01-0.08 Hz), individuals with ASC exhibited increased FC between Wernicke's area and the right thalamus compared with TD individuals. In the slow-5 frequency band (0.01-0.027 Hz), increased FC values were observed in the left cerebellum Crus II and the right lenticular nucleus, pallidum. These results provide novel insights into the potential neural mechanisms underlying communication deficits in ASC from the perspective of language impairments.

Margin-Maximized Norm-Mixed Representation Learning for Autism Spectrum Disorder Diagnosis With Multi-Level Flux Features

Early diagnosis and timely intervention are significantly beneficial to patients with autism spectrum disorder (ASD). Although structural magnetic resonance imaging (sMRI) has become an essential tool to facilitate the diagnosis of ASD, these sMRI-based approaches still have the following issues. The heterogeneity and subtle anatomical changes place higher demands for effective feature descriptors. Additionally, the original features are usually high-dimensional, while most existing methods prefer to select feature subsets in the original space, in which noises and outliers may hinder the discriminative ability of selected features. In this article, we propose a margin-maximized norm-mixed representation learning framework for ASD diagnosis with multi-level flux features extracted from sMRI. Specifically, a flux feature descriptor is devised to quantify comprehensive gradient information of brain structures on both local and global levels. For the multi-level flux features, we learn latent representations in an assumed low-dimensional space, in which a self-representation term is incorporated to characterize the relationships among features. We also introduce mixed norms to finely select original flux features for the construction of latent representations while preserving the low-rankness of latent representations. Furthermore, a margin maximization strategy is applied to enlarge the inter-class distance of samples, thereby increasing the discriminative ability of latent representations. The extensive experiments on several datasets show that our proposed method can achieve promising classification performance (the average area under curve, accuracy, specificity, and sensitivity on the studied ASD datasets are 0.907, 0.896, 0.892, and 0.908, respectively) and also find potential biomarkers for ASD diagnosis.

ANKS1B encoded AIDA-1 regulates social behaviors by controlling oligodendrocyte function

Heterozygous deletions in the ANKS1B gene cause ANKS1B neurodevelopmental syndrome (ANDS), a rare genetic disease characterized by autism spectrum disorder (ASD), attention deficit/hyperactivity disorder, and speech and motor deficits. The ANKS1B gene encodes for AIDA-1, a protein that is enriched at neuronal synapses and regulates synaptic plasticity. Here we report an unexpected role for oligodendroglial deficits in ANDS pathophysiology. We show that Anks1b-deficient mouse models display deficits in oligodendrocyte maturation, myelination, and Rac1 function, and recapitulate white matter abnormalities observed in ANDS patients. Selective loss of Anks1b from the oligodendrocyte lineage, but not from neuronal populations, leads to deficits in social preference and sensory reactivity previously observed in a brain-wide Anks1b haploinsufficiency model. Furthermore, we find that clemastine, an antihistamine shown to increase oligodendrocyte precursor cell maturation and central nervous system myelination, rescues deficits in social preference in 7-month-old Anks1b-deficient mice. Our work shows that deficits in social behaviors present in ANDS may originate from abnormal Rac1 activity within oligodendrocytes.

APPlications of amyloid-β precursor protein metabolites in macrocephaly and autism spectrum disorder

Metabolites of the Amyloid-β precursor protein (APP) proteolysis may underlie brain overgrowth in Autism Spectrum Disorder (ASD). We have found elevated APP metabolites (total APP, secreted (s) APPα, and α-secretase adamalysins in the plasma and brain tissue of children with ASD). In this review, we highlight several lines of evidence supporting APP metabolites' potential contribution to macrocephaly in ASD. First, APP appears early in corticogenesis, placing APP in a prime position to accelerate growth in neurons and glia. APP metabolites are upregulated in neuroinflammation, another potential contributor to excessive brain growth in ASD. APP metabolites appear to directly affect translational signaling pathways, which have been linked to single gene forms of syndromic ASD (Fragile X Syndrome, PTEN, Tuberous Sclerosis Complex). Finally, APP metabolites, and microRNA, which regulates APP expression, may contribute to ASD brain overgrowth, particularly increased white matter, through ERK receptor activation on the PI3K/Akt/mTOR/Rho GTPase pathway, favoring myelination.

Bidirectional genetic overlap between autism spectrum disorder and cognitive traits

Autism spectrum disorder (ASD) is a highly heritable condition with a large variation in cognitive function. Here we investigated the shared genetic architecture between cognitive traits (intelligence (INT) and educational attainment (EDU)), and risk loci jointly associated with ASD and the cognitive traits. We analyzed data from genome-wide association studies (GWAS) of INT (n = 269,867), EDU (n = 766,345) and ASD (cases n = 18,381, controls n = 27,969). We used the bivariate causal mixture model (MiXeR) to estimate the total number of shared genetic variants, local analysis of co-variant annotation (LAVA) to estimate local genetic correlations, conditional false discovery rate (cond/conjFDR) to identify specific overlapping loci. The MiXeR analyses showed that 12.7k genetic variants are associated with ASD, of which 12.0k variants are shared with EDU, and 11.1k are shared with INT with both positive and negative relationships within overlapping variants. The majority (59-68%) of estimated shared loci have concordant effect directions, with a positive, albeit modest, genetic correlation between ASD and EDU (rg = 0.21, p = 2e-13) and INT (rg = 0.22, p = 4e-12). We discovered 43 loci jointly associated with ASD and cognitive traits (conjFDR<0.05), of which 27 were novel for ASD. Functional analysis revealed significant differential expression of candidate genes in the cerebellum and frontal cortex. To conclude, we quantified the genetic architecture shared between ASD and cognitive traits, demonstrated mixed effect directions, and identified the associated genetic loci and molecular pathways. The findings suggest that common genetic risk factors for ASD can underlie both better and worse cognitive functioning across the ASD spectrum, with different underlying biology.

A Review of and Roadmap for Data Science and Machine Learning for the Neuropsychiatric Phenotype of Autism

Autism spectrum disorder (autism) is a neurodevelopmental delay that affects at least 1 in 44 children. Like many neurological disorder phenotypes, the diagnostic features are observable, can be tracked over time, and can be managed or even eliminated through proper therapy and treatments. However, there are major bottlenecks in the diagnostic, therapeutic, and longitudinal tracking pipelines for autism and related neurodevelopmental delays, creating an opportunity for novel data science solutions to augment and transform existing workflows and provide increased access to services for affected families. Several efforts previously conducted by a multitude of research labs have spawned great progress toward improved digital diagnostics and digital therapies for children with autism. We review the literature on digital health methods for autism behavior quantification and beneficial therapies using data science. We describe both case-control studies and classification systems for digital phenotyping. We then discuss digital diagnostics and therapeutics that integrate machine learning models of autism-related behaviors, including the factors that must be addressed for translational use. Finally, we describe ongoing challenges and potential opportunities for the field of autism data science. Given the heterogeneous nature of autism and the complexities of the relevant behaviors, this review contains insights that are relevant to neurological behavior analysis and digital psychiatry more broadly.

ECG Recordings as Predictors of Very Early Autism Likelihood: A Machine Learning Approach

In recent years, there has been a rise in the prevalence of autism spectrum disorder (ASD). The diagnosis of ASD requires behavioral observation and standardized testing completed by highly trained experts. Early intervention for ASD can begin as early as 1-2 years of age, but ASD diagnoses are not typically made until ages 2-5 years, thus delaying the start of intervention. There is an urgent need for non-invasive biomarkers to detect ASD in infancy. While previous research using physiological recordings has focused on brain-based biomarkers of ASD, this study investigated the potential of electrocardiogram (ECG) recordings as an ASD biomarker in 3-6-month-old infants. We recorded the heart activity of infants at typical and elevated familial likelihood for ASD during naturalistic interactions with objects and caregivers. After obtaining the ECG signals, features such as heart rate variability (HRV) and sympathetic and parasympathetic activities were extracted. Then we evaluated the effectiveness of multiple machine learning classifiers for classifying ASD likelihood. Our findings support our hypothesis that infant ECG signals contain important information about ASD familial likelihood. Amongthe various machine learning algorithms tested, KNN performed best according to sensitivity (0.70 ± 0.117), F1-score (0.689 ± 0.124), precision (0.717 ± 0.128), accuracy (0.70 ± 0.117, p-value = 0.02), and ROC (0.686 ± 0.122, p-value = 0.06). These results suggest that ECG signals contain relevant information about the likelihood of an infant developing ASD. Future studies should consider the potential of information contained in ECG, and other indices of autonomic control, for the development of biomarkers of ASD in infancy.

A Potential Biomarker of Brain Activity in Autism Spectrum Disorders: A Pilot fNIRS Study in Female Preschoolers

Autism spectrum disorder (ASD) refers to a neurodevelopmental condition whose detection still remains challenging in young females due to the heterogeneity of the behavioral phenotype and the capacity of camouflage. The availability of quantitative biomarkers to assess brain function may support in the assessment of ASD. Functional Near-infrared Spectroscopy (fNIRS) is a non-invasive and flexible tool that quantifies cortical hemodynamic responses (HDR) that can be easily employed to describe brain activity. Since the study of the visual phenotype is a paradigmatic model to evaluate cerebral processing in many neurodevelopmental conditions, we hypothesized that visually-evoked HDR (vHDR) might represent a potential biomarker in ASD females. We performed a case-control study comparing vHDR in a cohort of high-functioning preschooler females with ASD (fASD) and sex/age matched peers. We demonstrated the feasibility of visual fNIRS measurements in fASD, and the possibility to discriminate between fASD and typical subjects using different signal features, such as the amplitude and lateralization of vHDR. Moreover, the level of response lateralization was correlated to the severity of autistic traits. These results corroborate the cruciality of sensory symptoms in ASD, paving the way for the validation of the fNIRS analytical tool for diagnosis and treatment outcome monitoring in the ASD population.

Generalizability of 3D CNN models for age estimation in diverse youth populations using structural MRI

Recently, several studies have investigated the neurodevelopment of psychiatric disorders using brain data acquired via structural magnetic resonance imaging (sMRI). These analyses have shown the potential of sMRI data to provide a relatively precise characterization of brain structural biomarkers. Despite these advances, a relatively unexplored question is how reliable and consistent a model is when assessing subjects from other independent datasets. In this study, we investigate the performance and generalizability of the same model architecture trained from distinct datasets comprising youths in diverse stages of neurodevelopment and with different mental health conditions. We employed models with the same 3D convolutional neural network (CNN) architecture to assess autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), brain age, and a measure of dimensional psychopathology, the Child Behavior Checklist (CBCL) total score. The investigated datasets include the Autism Brain Imaging Data Exchange II (ABIDE-II, N = 580), Attention Deficit Hyperactivity Disorder (ADHD-200, N = 922), Brazilian High-Risk Cohort Study (BHRCS, N = 737), and Adolescent Brain Cognitive Development (ABCD, N = 11,031). Models' performance and interpretability were assessed within each dataset (for diagnosis tasks) and inter-datasets (for age estimation). Despite the demographic and phenotypic differences of the subjects, all models presented significant estimations for age (p value < 0.001) within and between datasets. In addition, most models showed a moderate to high correlation in age estimation. The results, including the models' brain regions of interest (ROI), were analyzed and discussed in light of the youth neurodevelopmental structural changes. Among other interesting discoveries, we found that less confounded training datasets produce models with higher generalization capacity.

The Use of the Alberta Infant Motor Scale (AIMS) as a Diagnostic Scale for Infants with Autism

Autism spectrum disorder (ASD) is a group of developmental disabilities presenting difficulties in social interaction and language and an increased occurrence of cognitive, sensory, and motor gaps. Early intervention has been reported to improve the function of children with ASD. However, motor screening for children with ASD is difficult, as there are no specific tools for identifying this specific population. This study reports the results of using the Alberta Infant Motor Scale (AIMS), which assesses gross infant motor skills from ages 0 to 18 months, as a screening tool for detecting motor developmental delay (MDD) in small children with ASD. Methods: This retrospective cohort study included all children registered at one health care organization in Israel born between 2011 and 2017 (N = 240,299). Early childhood MDD was defined as having at least one recorded developmental physiotherapy (DPT) visit before the age of 2 years. Reasons for referral to DPT and the results of using AIMS as an appropriate tool for revealing developmental delays in infants with ASD are presented. Results: ASD diagnosis was reported in 1821 children (prevalence rate 0.75%). Of those, 388 (odds ratio 4.1, 95% CI 3.6–4.6) children were referred to DPT. Children with ASD mostly received DPT for motor delays (46.19%), torticollis (19.52%), developmental delay (15.48%), and preterm birth (7.38%). The use of AIMS as an early detection tool suggests that more than 87% of children with ASD and MDD present with a developmental delay or risk for one when using this scale. Conclusions: The prevalence of ASD among children referred to DPT for MDD is higher than its prevalence within the general population. The most common reasons for a child with ASD to be referred for DPT services are MMDs. AIMS was found to be a sensitive tool to pinpoint relevant candidates for ASD screening among children treated in DPT. Possible effects of the study: The use of AIMS as a relevant assessment scale for this group of clients is recommended. Training DPTs in identifying initial ASD signs and developing their clinical reasoning abilities will increase the chance of implementing early intervention with this group of clients.

The subcortical correlates of autistic traits in school-age children: a population-based neuroimaging study

BACKGROUND

There is emerging evidence that the neuroanatomy of autism forms a spectrum which extends into the general population. However, whilst several studies have identified cortical morphology correlates of autistic traits, it is not established whether morphological differences are present in the subcortical structures of the brain. Additionally, it is not clear to what extent previously reported structural associations may be confounded by co-occurring psychopathology. To address these questions, we utilised neuroimaging data from the Adolescent Brain Cognitive Development Study to assess whether a measure of autistic traits was associated with differences in child subcortical morphology, and if any observed differences persisted after adjustment for child internalising and externalising symptoms.

METHODS

Our analyses included data from 7005 children aged 9-10 years (female: 47.19%) participating in the Adolescent Brain Cognitive Development Study. Autistic traits were assessed using scores from the Social Responsiveness Scale (SRS). Volumes of subcortical regions of interest were derived from structural magnetic resonance imaging data.

RESULTS

Overall, we did not find strong evidence for an association of autistic traits with differences in subcortical morphology in this sample of school-aged children. Whilst lower absolute volumes of the nucleus accumbens and putamen were associated with higher scores of autistic traits, these differences did not persist once a global measure of brain size was accounted for.

LIMITATIONS

It is important to note that autistic traits were assessed using the SRS, of which higher scores are associated with general behavioural problems, and therefore may not be wholly indicative of autism-specific symptoms. In addition, individuals with a moderate or severe autism diagnosis were excluded from the ABCD study, and thus, the average level of autistic traits will be lower than in the general population which may bias findings towards the null.

CONCLUSIONS

These findings from our well-powered study suggest that other metrics of brain morphology, such as cortical morphology or shape-based phenotypes, may be stronger candidates to prioritise when attempting to identify robust neuromarkers of autistic traits.

[Psychogenic non-epileptic seizures in autistic spectrum disorder]

Psychogenic non-epileptic seizures (PNES) are paroxysmal conditions that resemble epileptic seizures, but are not accompanied by epileptiform activity on the electroencephalogram and are not associated with other neurological or somatic disorders. Unrecognized PNES places a heavy burden on the patient and family, and on the health care system. Among many possible combinations of PNES with psychiatric disorders, autistic spectrum disorders are the least studied. This article presents a case of a 19-year-old female patient with autistic spectrum disorder and paroxysmal events and the presence of potentially epileptogenic changes in the brain. A multidisciplinary approach made it possible to diagnose PNEP in the patient.

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.

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.

Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects approximately 1% of the population and causes significant burdens. ASD's pathogenesis remains elusive; hence, diagnosis is based on a constellation of behaviors. Structural magnetic resonance imaging (sMRI) studies have shown several abnormalities in volumetric and geometric features of the autistic brain. However, inconsistent findings prevented most contributions from being translated into clinical practice. Establishing reliable biomarkers for ASD using sMRI is crucial for the correct diagnosis and treatment. In recent years, machine learning (ML) and specifically deep learning (DL) have quickly extended to almost every sector, notably in disease diagnosis. Thus, this has led to a shift and improvement in ASD diagnostic methods, fulfilling most clinical diagnostic requirements. However, ASD discovery remains difficult. This review examines the ML-based ASD diagnosis literature over the past 5 years. A literature-based taxonomy of the research landscape has been mapped, and the major aspects of this topic have been covered. First, we provide an overview of ML's general classification pipeline and the features of sMRI. Next, representative studies are highlighted and discussed in detail with respect to methods, and biomarkers. Finally, we highlight many common challenges and make recommendations for future directions. In short, the limited sample size was the main obstacle; Thus, comprehensive data sets and rigorous methods are necessary to check the generalizability of the results. ML technologies are expected to advance significantly in the coming years, contributing to the diagnosis of ASD and helping clinicians soon.

Examining the relationship between autistic spectrum disorder characteristics and structural brain differences seen in anorexia nervosa

Cortical differences have been reported in Anorexia Nervosa (AN) compared with healthy controls (HC); however, it is unclear if Autism Spectrum Disorder (ASD) characteristics are related to these cortical differences. The aim of this study was to examine if structural measures were correlated to ASD traits in AN. In total 184 female participants participated in the study; 57 acutely underweight AN participants (AAN), 59 weight-restored participants (WR) and 68 HC. Participants underwent structural magnetic resonance imaging as well as completing the Autism Diagnostic Observation schedule, second edition to examine ASD characteristics. Group differences in curvature, gyrification, surface area, thickness, global grey matter and white matter were measured. Correlation and regression analysis were conducted to examine the relationship between cortical measures and ASD characteristics. Two decreased gyrification clusters in the right post central and supramarginal gyrus and decreased global grey matter were observed in the AAN group compared to HC and WR. No correlations between ASD traits and structural measures existed. Our results suggest structural differences seen in individuals with AN do not appear to be related to ASD characteristics.

Granulocyte Colony-Stimulating Factor Has a Sex-Dependent Positive Effect in the Maternal Immune Activation-Induced Autism Model

OBJECTIVE

The medical intervention for autism spectrum disorder (ASD) is restricted to ameliorating comorbid situations. Granulocyte colony-stimulating factor (G-CSF) is a growth factor that enhances the proliferation, differentiation and survival of hematopoietic progenitor cells. In the present study, we aimed to investigate the effects of G-CSF in a maternal immune activation-induced autism model.

METHODS

Sixteen female and 6 male Wistar adult rats were included in the study. After 21 days, forty-eight littermates (8 male controls, 8 female controls, 16 male lipopolysaccharide (LPS)-exposed rats and 16 female LPS-exposed rats) were divided into groups. Sixteen male LPS-exposed and 16 female LPS-exposed rats were divided into saline and G-CSF treatment groups.

RESULTS

In male rats, the LPS-exposed group was found to have significantly higher levels of TNF-α, IL-2, and IL-17 than the LPS-exposed G-CSF group. Levels of nerve growth factor, brain PSD-95 and brain GAD67 were higher in the LPS-exposed G-CSF group than in the LPS-exposed group in male rats. In female rats, brain NGF levels were similar between groups. There was no difference between groups in terms of brain GAD 67 levels. Brain PSD-95 levels were higher in the control group than in both the LPS-exposed and LPS-exposed G-CSF groups in female rats. Both neuronal CA1 and neuronal CA2 levels were lower, and the GFAP immunostaining index (CA1) and GFAP immunostaining index (CA3) were higher in the LPS-exposed group than in the LPS-exposed G-CSF group in male rats. However, neuronal count CA1 and Neuronal count CA3 values were found to be similar between groups in female rats.

CONCLUSIONS

The present research is the first to demonstrate the beneficial effects of G-CSF on core symptoms of ASD experimentally depending on male sex. G-CSF can be a good candidate for ameliorating the core symptoms of ASD without serious side effects in males.

The powerful brain: Neural correlates of sense of power and hope

A sense of power refers to the perception that one can control and influence others' states by providing or withholding valued resources in an asymmetrical way, and which has been associated with greater hope. However, little is known about the neural bases underlying this association. The present study aimed to examine these phenomena in 261 healthy adolescent students by assessing resting-state brain activity (i.e., the amplitude of low-frequency fluctuations, ALFF) and connectivity (i.e., resting-state functional connectivity, RSFC). Whole-brain correlation analyses revealed that higher levels of perceived power were linked with reduced ALFF in the left thalamus and increased RSFC between the left thalamus and left superior temporal gyrus. Mediation analyses further showed that perceived power mediated the influence of the left thalamus activity on hope. Our results remained significant even after controlling for the head motion, age, and gender. Our findings contribute to the neurobiological basis of a sense of power and the neural mechanism underlying the relationship between a sense of power and hope.

Learning Active Multimodal Subspaces in the Brain

Here we introduce a multimodal framework to identify subspaces in the human brain that are defined by collective changes in structural and functional measures and are actively linked to demographic, biological and cognitive indicators in a population. We determine the multimodal subspaces using principles of active subspace learning (ASL) and demonstrate its application on a sample learning task (biological ageing) on a schizophrenia dataset. The proposed multimodal ASL method successfully identifies latent brain representations as subsets of brain regions and connections forming covarying subspaces in association with biological age. We show that schizophrenia is characterized by different subspace patterns compared to those in a cognitively normal brain. The multimodal features generated by projecting structural and functional MRI components onto these active subspaces perform better than several PCA-based transformations and equally well when compared to non-transformed features on the studied learning task. In essence, the proposed method successfully learns active brain subspaces associated with a specific brain condition but inferred from the brain imaging data along with the biological/cognitive traits of interest. Clinical relevance- The work introduces a novel way to create multimodal brain biomarkers based on subspaces computed in association with cognitive or biological traits of interest. These subspaces collectively covary maximally in association with a given trait and successfully retain predictive information.

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

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.

Research Progress on the Role of Vitamin D in Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that can lead to severe social behavioral difficulties, which mainly manifests as social communication and interaction disorders; narrow interests; and repetitive, stereotyped behaviors. In recent years, the prevalence of ASD has increased annually, and it has evolved from a rare disease to one with a high incidence among childhood developmental disorders. The pathogenesis of ASD is considered to be the interaction of genetic and environmental factors. There is increasing evidence that vitamin D deficiency in pregnancy and early childhood can lead to the occurrence of ASD. Studies have demonstrated that vitamin D intervention can significantly improve the symptoms of ASD, but the underlying mechanism is still unclear. Therefore, exploring the neuroprotective mechanism of vitamin D against ASD is a huge challenge currently being worked on by current basic and clinical researchers, a task which is of great significance for the clinical promotion and optimization of vitamin D in the treatment of ASD. To further clarify the relationship between vitamin D and ASD, this review summarizes the correlation between vitamin D level and ASD, the effects of vitamin D supplementation on ASD, the possible mechanism of vitamin D involved in ASD, and insights from ASD animal models.

Cai L, Roy M, Edde M, Caceres MP, Ocampo‐Pineda M, Al‐Sharif N, Karan P, Bontempi P, Obaid S, Bosticardo S, Schiavi S, Sairanen V, Daducci A, Cutting LE, Petit L, Descoteaux M, Landman BA. Tractostorm 2: Optimizing tractography dissection reproducibility with segmentation protocol dissemination

The segmentation of brain structures is a key component of many neuroimaging studies. Consistent anatomical definitions are crucial to ensure consensus on the position and shape of brain structures, but segmentations are prone to variation in their interpretation and execution. White-matter (WM) pathways are global structures of the brain defined by local landmarks, which leads to anatomical definitions being difficult to convey, learn, or teach. Moreover, the complex shape of WM pathways and their representation using tractography (streamlines) make the design and evaluation of dissection protocols difficult and time-consuming. The first iteration of Tractostorm quantified the variability of a pyramidal tract dissection protocol and compared results between experts in neuroanatomy and nonexperts. Despite virtual dissection being used for decades, in-depth investigations of how learning or practicing such protocols impact dissection results are nonexistent. To begin to fill the gap, we evaluate an online educational tractography course and investigate the impact learning and practicing a dissection protocol has on interrater (groupwise) reproducibility. To generate the required data to quantify reproducibility across raters and time, 20 independent raters performed dissections of three bundles of interest on five Human Connectome Project subjects, each with four timepoints. Our investigation shows that the dissection protocol in conjunction with an online course achieves a high level of reproducibility (between 0.85 and 0.90 for the voxel-based Dice score) for the three bundles of interest and remains stable over time (repetition of the protocol). Suggesting that once raters are familiar with the software and tasks at hand, their interpretation and execution at the group level do not drastically vary. When compared to previous work that used a different method of communication for the protocol, our results show that incorporating a virtual educational session increased reproducibility. Insights from this work may be used to improve the future design of WM pathway dissection protocols and to further inform neuroanatomical definitions.

Cortical thickness systematically varies with curvature and depth in healthy human brains

Cortical thickness varies throughout the cortex in a systematic way. However, it is challenging to investigate the patterns of cortical thickness due to the intricate geometry of the cortex. The cortex has a folded nature both in radial and tangential directions which forms not only gyri and sulci but also tangential folds and intersections. In this article, cortical curvature and depth are used to characterize the spatial distribution of the cortical thickness with much higher resolution than conventional regional atlases. To do this, a computational pipeline was developed that is capable of calculating a variety of quantitative measures such as surface area, cortical thickness, curvature (mean curvature, Gaussian curvature, shape index, intrinsic curvature index, and folding index), and sulcal depth. By analyzing 501 neurotypical adult human subjects from the ABIDE-I dataset, we show that cortex has a very organized structure and cortical thickness is strongly correlated with local shape. Our results indicate that cortical thickness consistently increases along the gyral-sulcal spectrum from concave to convex shape, encompassing the saddle shape along the way. Additionally, tangential folds influence cortical thickness in a similar way as gyral and sulcal folds; outer folds are consistently thicker than inner.

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.

Therapeutic Effects of a Novel Form of Biotin on Propionic Acid-Induced Autistic Features in Rats

Magnesium biotinate (MgB) is a novel biotin complex with superior absorption and anti-inflammatory effects in the brain than D-Biotin. This study aimed to investigate the impact of different doses of MgB on social behavior deficits, learning and memory alteration, and inflammatory markers in propionic acid (PPA)-exposed rats. In this case, 35 Wistar rats (3 weeks old) were distributed into five groups: 1, Control; 2, PPA treated group; 3, PPA+MgBI (10 mg, HED); 4, PPA+MgBII (100 mg, HED); 5, PPA+MgBIII (500 mg, HED). PPA was given subcutaneously at 500 mg/kg/day for five days, followed by MgB for two weeks. PPA-exposed rats showed poor sociability and a high level of anxiety-like behaviors and cognitive impairments (p < 0.001). In a dose-dependent manner, behavioral and learning-memory disorders were significantly improved by MgB supplementation (p < 0.05). PPA decreased both the numbers and the sizes of Purkinje cells in the cerebellum. However, MgB administration increased the sizes and the densities of Purkinje cells. MgB improved the brain and serum Mg, biotin, serotonin, and dopamine concentrations, as well as antioxidant enzymes (CAT, SOD, GPx, and GSH) (p < 0.05). In addition, MgB treatment significantly regulated the neurotoxicity-related cytokines and neurotransmission-related markers. For instance, MgB significantly decreased the expression level of TNF-α, IL-6, IL-17, CCL-3, CCL-5, and CXCL-16 in the brain, compared to the control group (p < 0.05). These data demonstrate that MgB may ameliorate dysfunctions in social behavior, learning and memory and reduce the oxidative stress and inflammation indexes of the brain in a rat model.

Region-specific associations between gamma-aminobutyric acid A receptor binding and cortical thickness in high-functioning autistic adults

The neurobiology of autism has been shown to involve alterations in cortical morphology and gamma-aminobutyric acid A (GABA_A ) receptor density. We hypothesized that GABA_A receptor binding potential (GABA_A R BP_ND ) would correlate with cortical thickness, but their correlations would differ between autistic adults and typically developing (TD) controls. We studied 50 adults (23 autism, 27 TD, mean age of 27 years) using magnetic resonance imaging to measure cortical thickness, and [¹⁸ F]flumazenil positron emission tomography imaging to measure GABA_A R BP_ND . We determined the correlations between cortical thickness and GABA_A R BP_ND by cortical lobe, region-of-interest, and diagnosis of autism spectrum disorder (ASD). We also explored potential sex differences in the relationship between cortical thickness and autism characteristics, as measured by autism spectrum quotient (AQ) scores. Comparing autism and TD groups, no significant differences were found in cortical thickness or GABA_A R BP_ND . In both autism and TD groups, a negative relationship between cortical thickness and GABA_A R BP_ND was observed in the frontal and occipital cortices, but no relationship was found in the temporal or limbic cortices. A positive correlation was seen in the parietal cortex that was only significant for the autism group. Interestingly, in an exploratory analysis, we found sex differences in the relationships between cortical thickness and GABA_A R BP_ND , and cortical thickness and AQ scores in the left postcentral gyrus. LAY SUMMARY: The thickness of the brain cortex and the density of the receptors associated with inhibitory neurotransmitter GABA have been hypothesized to underlie the neurobiology of autism. In this study, we found that these biomarkers correlate positively in the parietal cortex, but negatively in the frontal and occipital cortical regions of the brain. Furthermore, we collected preliminary evidence that the correlations between cortical thickness and GABA receptor density are sexdependent in a brain region where sensory inputs are registered.

Looking for “fNIRS Signature” in Autism Spectrum: A Systematic Review Starting From Preschoolers

Accumulating evidence suggests that functional Near-Infrared Spectroscopy (fNIRS) can provide an essential bridge between our current understanding of neural circuit organization and cortical activity in the developing brain. Indeed, fNIRS allows studying brain functions through the measurement of neurovascular coupling that links neural activity to subsequent changes in cerebral blood flow and hemoglobin oxygenation levels. While the literature offers a multitude of fNIRS applications to typical development, only recently this tool has been extended to the study of neurodevelopmental disorders (NDDs). The exponential rise of scientific publications on this topic during the last years reflects the interest to identify a “fNIRS signature” as a biomarker of high translational value to support both early clinical diagnosis and treatment outcome. The purpose of this systematic review is to describe the updating clinical applications of fNIRS in NDDs, with a specific focus on preschool population. Starting from this rationale, a systematic search was conducted for relevant studies in different scientific databases (Pubmed, Scopus, and Web of Science) resulting in 13 published articles. In these studies, fNIRS was applied in individuals with Autism Spectrum Disorder (ASD) or infants at high risk of developing ASD. Both functional connectivity in resting-state conditions and task-evoked brain activation using multiple experimental paradigms were used in the selected investigations, suggesting that fNIRS might be considered a promising method for identifying early quantitative biomarkers in the autism field.

Identifying and Predicting Autism Spectrum Disorder Based on Multi-Site Structural MRI With Machine Learning

Although emerging evidence has implicated structural/functional abnormalities of patients with Autism Spectrum Disorder(ASD), definitive neuroimaging markers remain obscured due to inconsistent or incompatible findings, especially for structural imaging. Furthermore, brain differences defined by statistical analysis are difficult to implement individual prediction. The present study has employed the machine learning techniques under the unified framework in neuroimaging to identify the neuroimaging markers of patients with ASD and distinguish them from typically developing controls(TDC). To enhance the interpretability of the machine learning model, the study has processed three levels of assessments including model-level assessment, feature-level assessment, and biology-level assessment. According to these three levels assessment, the study has identified neuroimaging markers of ASD including the opercular part of bilateral inferior frontal gyrus, the orbital part of right inferior frontal gyrus, right rolandic operculum, right olfactory cortex, right gyrus rectus, right insula, left inferior parietal gyrus, bilateral supramarginal gyrus, bilateral angular gyrus, bilateral superior temporal gyrus, bilateral middle temporal gyrus, and left inferior temporal gyrus. In addition, negative correlations between the communication skill score in the Autism Diagnostic Observation Schedule (ADOS_G) and regional gray matter (GM) volume in the gyrus rectus, left middle temporal gyrus, and inferior temporal gyrus have been detected. A significant negative correlation has been found between the communication skill score in ADOS_G and the orbital part of the left inferior frontal gyrus. A negative correlation between verbal skill score and right angular gyrus and a significant negative correlation between non-verbal communication skill and right angular gyrus have been found. These findings in the study have suggested the GM alteration of ASD and correlated with the clinical severity of ASD disease symptoms. The interpretable machine learning framework gives sight to the pathophysiological mechanism of ASD but can also be extended to other diseases.

The amplitude of fNIRS hemodynamic response in the visual cortex unmasks autistic traits in typically developing children

Autistic traits represent a continuum dimension across the population, with autism spectrum disorder (ASD) being the extreme end of the distribution. Accumulating evidence shows that neuroanatomical and neurofunctional profiles described in relatives of ASD individuals reflect an intermediate neurobiological pattern between the clinical population and healthy controls. This suggests that quantitative measures detecting autistic traits in the general population represent potential candidates for the development of biomarkers identifying early pathophysiological processes associated with ASD. Functional near-infrared spectroscopy (fNIRS) has been extensively employed to investigate neural development and function. In contrast, the potential of fNIRS to define reliable biomarkers of brain activity has been barely explored. Features of non-invasiveness, portability, ease of administration, and low-operating costs make fNIRS a suitable instrument to assess brain function for differential diagnosis, follow-up, analysis of treatment outcomes, and personalized medicine in several neurological conditions. Here, we introduce a novel standardized procedure with high entertaining value to measure hemodynamic responses (HDR) in the occipital cortex of adult subjects and children. We found that the variability of evoked HDR correlates with the autistic traits of children, assessed by the Autism-Spectrum Quotient. Interestingly, HDR amplitude was especially linked to social and communication features, representing the core symptoms of ASD. These findings establish a quick and easy strategy for measuring visually-evoked cortical activity with fNIRS that optimize the compliance of young subjects, setting the background for testing the diagnostic value of fNIRS visual measurements in the ASD clinical population.

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.

Sex/gender differences in children with autism spectrum disorder: A brief overview on epidemiology, symptom profile, and neuroanatomy

Autism spectrum disorders (ASD) are a heterogeneous group of neurodevelopmental conditions whose shared core features are impairments in social interaction and communication as well as restricted patterns of behavior, interests, and activities. The significant and consistent male preponderance in ASD prevalence has historically affected the scientific knowledge of autism in females as regards, inter alia, the clinical presentation, the genetic architecture, and the structural brain underpinnings. Indeed, females with ASD are under-investigated as samples recruited for clinical research typically reflect the strong male bias of the disorder. In the last years, the study of the various aspects of sex/gender (s/g) differences in ASD is gaining increased clinical and research interest resulting in a growing number of investigations on this topic. Here, I review and discuss evidence emerged from epidemiological, clinical, and neuroimaging studies in the last decade focusing on s/g differences in children with ASD. These studies are the prerequisites for the development of assessment and treatment practices which take into consideration s/g differences in ASD. Ultimately, a better understanding of s/g differences aims at improving healthcare for both ASD males and females.

Neuroimaging findings in children with cerebral palsy with autism and/or attention-deficit/hyperactivity disorder: a population-based study

AIM

To compare neuroimaging patterns according to the Magnetic Resonance Imaging Classification System (MRICS) in children with cerebral palsy (CP) with and without autism and/or attention-deficit/hyperactivity disorder (ADHD).

METHOD

This population-based study assessed 184 children (97 males, 87 females) with CP born from 1999 to 2006 from the CP register of western Sweden, who had completed comprehensive screening and clinical assessment for neuropsychiatric disorders and undergone neuroimaging.

RESULTS

Autism (total prevalence 30%) and ADHD (31%) were common in all neuroimaging patterns, including normal. Autism and ADHD were not more prevalent in children with bilateral than unilateral lesions, contrary to other associated impairments. Children with predominant white matter injury, related to insults in the late second or early third trimester, had the highest prevalence of autism (40%). Children who had sustained a middle cerebral artery infarction had the highest prevalence of ADHD (62%).

INTERPRETATION

Although autism and ADHD are common regardless of neuroimaging patterns, timing and localization of insult appear to be of importance for the occurrence of autism and ADHD in children with CP. Neuroimaging may be of prognostic value for these associated impairments. Further in-depth neuroimaging studies may lead to a better understanding of the association between CP and neuropsychiatric disorders.

iPSC toolbox for understanding and repairing disrupted brain circuits in autism

Over the past decade, tremendous progress has been made in defining autism spectrum disorder (ASD) as a disorder of brain connectivity. Indeed, whole-brain imaging studies revealed altered connectivity in the brains of individuals with ASD, and genetic studies identified rare ASD-associated mutations in genes that regulate synaptic development and function. However, it remains unclear how specific mutations alter the development of neuronal connections in different brain regions and whether altered connections can be restored therapeutically. The main challenge is the lack of preclinical models that recapitulate important aspects of human development for studying connectivity. Through recent technological innovations, it is now possible to generate patient- or mutation-specific human neurons or organoids from induced pluripotent stem cells (iPSCs) and to study altered connectivity in vitro or in vivo upon xenotransplantation into an intact rodent brain. Here, we discuss how deficits in neurodevelopmental processes may lead to abnormal brain connectivity and how iPSC-based models can be used to identify abnormal connections and to gain insights into underlying cellular and molecular mechanisms to develop novel therapeutics.

Brain structural alterations in autism and criminal psychopathy

•

Autism and psychopathy are both disorders of social cognition and share numerous of their features but still differ distinctively in their clinical phenotype.

•

The lower grey matter volumes in the right temporal pole and the left inferior frontal gyrus are the most prominent findings distinguishing violent offenders with high psychopatic from ASD individuals.

•

Violent offenders with high psychopatic traits and individuals with ASD both present similar lower grey matter volumes in the right precentral cortex compared to controls.

The goal of this study was to elucidate the anatomical brain basis of social cognition through two disorders with distinctively different phenotypes of social interaction. We compared structural MR images of 20 individuals with autism spectrum disorder (ASD), 19 violent offenders with high psychopathic traits, and 19 control participants using voxel-based morphometry (VBM). Our earlier study showed lower grey matter volume (GMV) values in the insula, frontal cortex, and sensorimotor cortex of the offender group compared to controls. In the present study, the images of the ASD group revealed lower GMV in the left precuneus, right cerebellum, and right precentral gyrus in comparison with controls. The comparison between the offender and ASD groups showed lower GMV values for the right temporal pole and left inferior frontal gyrus in the offender group. There was also an overlap of both disorders in the right pre-central cortex, showing lower GMV compared to controls. Our findings suggest structural differences between violent offenders with high psychopathy traits and ASD individuals in the frontotemporal social brain network areas, previously associated with empathy. We also provide evidence of similar abnormal structures in the motor cortex for both of these disorders, possibly related to uniting issues of social cognition.

Learning Active Multimodal Subspaces in the Brain.. [DOI: 10.1101/2021.12.06.471396] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Here we introduce a multimodal framework to identify subspaces in the human brain that are defined by collective changes in structural and functional measures and are actively linked to demographic, biological and cognitive indicators in a population. We determine the multimodal subspaces using principles of active subspace learning (ASL) and demonstrate its application on a sample learning task (biological ageing) on a Schizophrenia dataset. The proposed multimodal ASL method successfully identifies latent brain representations as subsets of brain regions and connections forming co-varying subspaces in association with biological age. We show that Schizophrenia is characterized by different subspace patterns compared to those in a cognitively normal brain. The multimodal features generated by projecting structural and functional MRI components onto these active subspaces perform better than several PCA-based transformations and equally well when compared to non-transformed features on the studied learning task. In essence, the proposed method successfully learns active brain subspaces associated with a specific brain condition but inferred from the brain imaging data along with the biological/cognitive traits of interest.

An Enhanced Deep Recurrent Neural Network for Autism Spectrum Disorder Diagnosis

Autism Spectrum Disorder is one of the major investigation area in current era. There are many research works introduced earlier for handling the Autism Spectrum Disorders. However those research works doesn’t achieve the expected accuracy level. The accuracy and prediction efficiency can be increased by building a better classification system using Deep Learning. This paper focuses on the deep learning technique for Autism Diagnosis and the domain identification. In the proposed work, an Enhanced Deep Recurrent Neural Network has been developed for the detection of ASD at all ages. It attempts to predict the autism spectrum in the children along with prediction of areas which can predict the autism in the prior level. The main advantage of EDRNN is to provide higher accuracy in classification and domain identification. Here Artificial Algal Algorithm is used for identifying the most relevant features from the existing feature set. This model was evaluated for the data that followed Indian Scale for Assessment of Autism. The results obtained for the proposed EDRNN has better accuracy, sensitivity, specificity, recall and precision.

Functional Connectivity-Based Prediction of Autism on Site Harmonized ABIDE Dataset

OBJECTIVE

The larger sample sizes available from multi-site publicly available neuroimaging data repositories makes machine-learning based diagnostic classification of mental disorders more feasible by alleviating the curse of dimensionality. However, since multi-site data are aggregated post-hoc, i.e. they were acquired from different scanners with different acquisition parameters, non-neural inter-site variability may mask inter-group differences that are at least in part neural in origin. Hence, the advantages gained by the larger sample size in the context of machine-learning based diagnostic classification may not be realized.

METHODS

We address this issue using harmonization of multi-site neuroimaging data using the ComBat technique, which is based on an empirical Bayes formulation to remove inter-site differences in data distributions, to improve diagnostic classification accuracy. Specifically, we demonstrate this using ABIDE (Autism Brain Imaging Data Exchange) multi-site data for classifying individuals with Autism from healthy controls using resting state fMRI-based functional connectivity data.

RESULTS

Our results show that higher classification accuracies across multiple classification models can be obtained (especially for models based on artificial neural networks) from multi-site data post harmonization with the ComBat technique as compared to without harmonization, outperforming earlier results from existing studies using ABIDE. Furthermore, our network ablation analysis facilitated important insights into autism spectrum disorder pathology and the connectivity in networks shown to be important for classification covaried with verbal communication impairments in Autism.

CONCLUSION

Multi-site data harmonization using ComBat improves neuroimaging-based diagnostic classification of mental disorders.

SIGNIFICANCE

ComBat has the potential to make AI-based clinical decision-support systems more feasible in psychiatry.