Multisite Autism Spectrum Disorder Classification Using Convolutional Neural Network Classifier and Individual Morphological Brain Networks

Gray matter volume and corresponding covariance connectivity are biomarkers for major depressive disorder

The major depressive disorder (MDD) is a common and severe mental disorder. To identify a reliable biomarker for MDD is important for early diagnosis and prevention. Given easy access and high reproducibility, the structural magnetic resonance imaging (sMRI) is an ideal method to identify the biomarker for depression. In this study, sMRI data of first episode, treatment-naïve 66 MDD patients and 54 sex-, age-, and education-matched healthy controls (HC) were used to identify the differences in gray matter volume (GMV), group-level, individual-level covariance connections. Finally, the abnormal GMV and individual covariance connections were applied to classify MDD from HC. MDD patients showed higher GMV in middle occipital gyrus (MOG) and precuneus (PCun), and higher structural covariance connections between MOG and PCun. In addition, the Allen Human Brain Atlas (AHBA) was applied and revealed the genetic basis for the changes of gray matter volume. Importantly, we reported that GMV in MOG, PCun and structural covariance connectivity between MOG and PCun are able to discriminate MDD from HC. Our results revealed structural underpinnings for MDD, which may contribute towards early discriminating for depression.

The diagnosis of ASD with MRI: a systematic review and meta-analysis

While diagnosing autism spectrum disorder (ASD) based on an objective test is desired, the current diagnostic practice involves observation-based criteria. This study is a systematic review and meta-analysis of studies that aim to diagnose ASD using magnetic resonance imaging (MRI). The main objective is to describe the state of the art of diagnosing ASD using MRI in terms of performance metrics and interpretation. Furthermore, subgroups, including different MRI modalities and statistical heterogeneity, are analyzed. Studies that dichotomously diagnose individuals with ASD and healthy controls by analyses progressing from magnetic resonance imaging obtained in a resting state were systematically selected by two independent reviewers. Studies were sought on Web of Science and PubMed, which were last accessed on February 24, 2023. The included studies were assessed on quality and risk of bias using the revised Quality Assessment of Diagnostic Accuracy Studies tool. A bivariate random-effects model was used for syntheses. One hundred and thirty-four studies were included comprising 159 eligible experiments. Despite the overlap in the studied samples, an estimated 4982 unique participants consisting of 2439 individuals with ASD and 2543 healthy controls were included. The pooled summary estimates of diagnostic performance are 76.0% sensitivity (95% CI 74.1-77.8), 75.7% specificity (95% CI 74.0-77.4), and an area under curve of 0.823, but uncertainty in the study assessments limits confidence. The main limitations are heterogeneity and uncertainty about the generalization of diagnostic performance. Therefore, comparisons between subgroups were considered inappropriate. Despite the current limitations, methods progressing from MRI approach the diagnostic performance needed for clinical practice. The state of the art has obstacles but shows potential for future clinical application.

Delineating abnormal individual structural covariance brain network organization in pediatric epilepsy with unilateral resection of visual cortex

Although several previous studies have used resting-state functional magnetic resonance imaging and diffusion tensor imaging to report topological changes in the brain in epilepsy, it remains unclear whether the individual structural covariance network (SCN) changes in epilepsy, especially in pediatric epilepsy with visual cortex resection but with normal functions. Herein, individual SCNs were mapped and analyzed for seven pediatric patients with epilepsy after surgery and 15 age-matched healthy controls. A whole-brain individual SCN was constructed based on an automated anatomical labeling template, and global and nodal network metrics were calculated for statistical analyses. Small-world properties were exhibited by pediatric patients after brain surgery and by healthy controls. After brain surgery, pediatric patients with epilepsy exhibited a higher shortest path length, lower global efficiency, and higher nodal efficiency in the cuneus than those in healthy controls. These results revealed that pediatric epilepsy after brain surgery, even with normal functions, showed altered topological organization of the individual SCNs, which revealed residual network topological abnormalities and may provide initial evidence for the underlying functional impairments in the brain of pediatric patients with epilepsy after surgery that can occur in the future.

A hybrid CNN-SVM model for enhanced autism diagnosis

Autism is a representative disorder of pervasive developmental disorder. It exerts influence upon an individual's behavior and performance, potentially co-occurring with other mental illnesses. Consequently, an effective diagnostic approach proves to be invaluable in both therapeutic interventions and the timely provision of medical support. Currently, most scholars' research primarily relies on neuroimaging techniques for auxiliary diagnosis and does not take into account the distinctive features of autism's social impediments. In order to address this deficiency, this paper introduces a novel convolutional neural network-support vector machine model that integrates resting state functional magnetic resonance imaging data with the social responsiveness scale metrics for the diagnostic assessment of autism. We selected 821 subjects containing the social responsiveness scale measure from the publicly available Autism Brain Imaging Data Exchange dataset, including 379 subjects with autism spectrum disorder and 442 typical controls. After preprocessing of fMRI data, we compute the static and dynamic functional connectivity for each subject. Subsequently, convolutional neural networks and attention mechanisms are utilized to extracts their respective features. The extracted features, combined with the social responsiveness scale features, are then employed as novel inputs for the support vector machine to categorize autistic patients and typical controls. The proposed model identifies salient features within the static and dynamic functional connectivity, offering a possible biological foundation for clinical diagnosis. By incorporating the behavioral assessments, the model achieves a remarkable classification accuracy of 94.30%, providing a more reliable support for auxiliary diagnosis.

Toward individualized connectomes of brain morphology

The morphological brain connectome (MBC) delineates the coordinated patterns of local morphological features (such as cortical thickness) across brain regions. While classically constructed using population-based approaches, there is a growing trend toward individualized modeling. Currently, the methods for individualized MBCs are varied, posing challenges for method selection and cross-study comparisons. Here, we summarize how individualized MBCs are modeled through low-order methods (correlation-, divergence-, distance-, and deviation-based methods) describing relations in brain morphology, as well as high-order methods capturing similarities in these low-order relations. We discuss the merits and limitations of different methods, examining them in the context of robustness, reproducibility, and reliability. We highlight the importance of elucidating the cellular and molecular mechanisms underlying the individualized connectome, and establishing normative benchmarks to assess individual variation in development, aging, and neuropsychiatric disorders.

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.

Do it the transformer way: A comprehensive review of brain and vision transformers for autism spectrum disorder diagnosis and classification

Autism spectrum disorder (ASD) is a condition observed in children who display abnormal patterns of interaction, behavior, and communication with others. Despite extensive research efforts, the underlying causes of this neurodevelopmental disorder and its biomarkers remain unknown. However, advancements in artificial intelligence and machine learning have improved clinicians' ability to diagnose ASD. This review paper investigates various MRI modalities to identify distinct features that characterize individuals with ASD compared to typical control subjects. The review then moves on to explore deep learning models for ASD diagnosis, including convolutional neural networks (CNNs), autoencoders, graph convolutions, attention networks, and other models. CNNs and their variations are particularly effective due to their capacity to learn structured image representations and identify reliable biomarkers for brain disorders. Computer vision transformers often employ CNN architectures with transfer learning techniques like fine-tuning and layer freezing to enhance image classification performance, surpassing traditional machine learning models. This review paper contributes in three main ways. Firstly, it provides a comprehensive overview of a recommended architecture for using vision transformers in the systematic ASD diagnostic process. To this end, the paper investigates various pre-trained vision architectures such as VGG, ResNet, Inception, InceptionResNet, DenseNet, and Swin models that were fine-tuned for ASD diagnosis and classification. Secondly, it discusses the vision transformers of 2020th like BiT, ViT, MobileViT, and ConvNeXt, and applying transfer learning methods in relation to their prospective practicality in ASD classification. Thirdly, it explores brain transformers that are pre-trained on medically rich data and MRI neuroimaging datasets. The paper recommends a systematic architecture for ASD diagnosis using brain transformers. It also reviews recently developed brain transformer-based models, such as METAFormer, Com-BrainTF, Brain Network, ST-Transformer, STCAL, BolT, and BrainFormer, discussing their deep transfer learning architectures and results in ASD detection. Additionally, the paper summarizes and discusses brain-related transformers for various brain disorders, such as MSGTN, STAGIN, and MedTransformer, in relation to their potential usefulness in ASD. The study suggests that developing specialized transformer-based models, following the success of natural language processing (NLP), can offer new directions for image classification problems in ASD brain biomarkers learning and classification. By incorporating the attention mechanism, treating MRI modalities as sequence prediction tasks trained on brain disorder classification problems, and fine-tuned on ASD datasets, brain transformers can show a great promise in ASD diagnosis.

Multi-Slice Generation sMRI and fMRI for Autism Spectrum Disorder Diagnosis Using 3D-CNN and Vision Transformers

Researchers have explored various potential indicators of ASD, including changes in brain structure and activity, genetics, and immune system abnormalities, but no definitive indicator has been found yet. Therefore, this study aims to investigate ASD indicators using two types of magnetic resonance images (MRI), structural (sMRI) and functional (fMRI), and to address the issue of limited data availability. Transfer learning is a valuable technique when working with limited data, as it utilizes knowledge gained from a pre-trained model in a domain with abundant data. This study proposed the use of four vision transformers namely ConvNeXT, MobileNet, Swin, and ViT using sMRI modalities. The study also investigated the use of a 3D-CNN model with sMRI and fMRI modalities. Our experiments involved different methods of generating data and extracting slices from raw 3D sMRI and 4D fMRI scans along the axial, coronal, and sagittal brain planes. To evaluate our methods, we utilized a standard neuroimaging dataset called NYU from the ABIDE repository to classify ASD subjects from typical control subjects. The performance of our models was evaluated against several baselines including studies that implemented VGG and ResNet transfer learning models. Our experimental results validate the effectiveness of the proposed multi-slice generation with the 3D-CNN and transfer learning methods as they achieved state-of-the-art results. In particular, results from 50-middle slices from the fMRI and 3D-CNN showed a profound promise in ASD classifiability as it obtained a maximum accuracy of 0.8710 and F1-score of 0.8261 when using the mean of 4D images across the axial, coronal, and sagittal. Additionally, the use of the whole slices in fMRI except the beginnings and the ends of brain views helped to reduce irrelevant information and showed good performance of 0.8387 accuracy and 0.7727 F1-score. Lastly, the transfer learning with the ConvNeXt model achieved results higher than other transformers when using 50-middle slices sMRI along the axial, coronal, and sagittal planes.

Application of Multimodal MRI in the Early Diagnosis of Autism Spectrum Disorders: A Review

Autism spectrum disorder (ASD) is a neurodevelopmental disorder in children. Early diagnosis and intervention can remodel the neural structure of the brain and improve quality of life but may be inaccurate if based solely on clinical symptoms and assessment scales. Therefore, we aimed to analyze multimodal magnetic resonance imaging (MRI) data from the existing literature and review the abnormal changes in brain structural-functional networks, perfusion, neuronal metabolism, and the glymphatic system in children with ASD, which could help in early diagnosis and precise intervention. Structural MRI revealed morphological differences, abnormal developmental trajectories, and network connectivity changes in the brain at different ages. Functional MRI revealed disruption of functional networks, abnormal perfusion, and neurovascular decoupling associated with core ASD symptoms. Proton magnetic resonance spectroscopy revealed abnormal changes in the neuronal metabolites during different periods. Decreased diffusion tensor imaging signals along the perivascular space index reflected impaired glymphatic system function in children with ASD. Differences in age, subtype, degree of brain damage, and remodeling in children with ASD led to heterogeneity in research results. Multimodal MRI is expected to further assist in early and accurate clinical diagnosis of ASD through deep learning combined with genomics and artificial intelligence.

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.

Few-Shot Classification of Autism Spectrum Disorder using Site-Agnostic Meta-Learning and Brain MRI

For machine learning applications in medical imaging, the availability of training data is often limited, which hampers the design of radiological classifiers for subtle conditions such as autism spectrum disorder (ASD). Transfer learning is one method to counter this problem of low training data regimes. Here we explore the use of meta-learning for very low data regimes in the context of having prior data from multiple sites - an approach we term site-agnostic meta-learning. Inspired by the effectiveness of meta-learning for optimizing a model across multiple tasks, here we propose a framework to adapt it to learn across multiple sites. We tested our meta-learning model for classifying ASD versus typically developing controls in 2,201 T1-weighted (T1-w) MRI scans collected from 38 imaging sites as part of Autism Brain Imaging Data Exchange (ABIDE) [age: 5.2 -64.0 years]. The method was trained to find a good initialization state for our model that can quickly adapt to data from new unseen sites by fine-tuning on the limited data that is available. The proposed method achieved an area under the receiver operating characteristic curve (ROC-AUC)=0.857 on 370 scans from 7 unseen sites in ABIDE using a few-shot setting of 2-way 20-shot i.e., 20 training samples per site. Our results outperformed a transfer learning baseline by generalizing across a wider range of sites as well as other related prior work. We also tested our model in a zero-shot setting on an independent test site without any additional fine-tuning. Our experiments show the promise of the proposed site-agnostic meta-learning framework for challenging neuroimaging tasks involving multi-site heterogeneity with limited availability of training data.Clinical Relevance- We propose a learning framework that accommodates multi-site heterogeneity and limited data to assist in challenging neuroimaging tasks.

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.

DeepMNF: Deep Multimodal Neuroimaging Framework for Diagnosing Autism Spectrum Disorder

The growing prevalence of neurological disorders, e.g., Autism Spectrum Disorder (ASD), demands robust computer-aided diagnosis (CAD) due to the diverse symptoms which require early intervention, particularly in young children. The absence of a benchmark neuroimaging diagnostics paves the way to study transitions in the brain's anatomical structure and neurological patterns associated with ASD. The existing CADs take advantage of the large-scale baseline dataset from the Autism Brain Imaging Data Exchange (ABIDE) repository to improve diagnostic performance, but the involvement of multisite data also amplifies the variabilities and heterogeneities that hinder satisfactory results. To resolve this problem, we propose a Deep Multimodal Neuroimaging Framework (DeepMNF) that employs Functional Magnetic Resonance Imaging (fMRI) and Structural Magnetic Resonance Imaging (sMRI) to integrate cross-modality spatiotemporal information by exploiting 2-dimensional time-series data along with 3-dimensional images. The purpose is to fuse complementary information that increases group differences and homogeneities. To the best of our knowledge, our DeepMNF achieves superior validation performance than the best reported result on the ABIDE-1 repository involving datasets from all available screening sites. In this work, we also demonstrate the performance of the studied modalities in a single model as well as their possible combinations to develop the multimodal framework.

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

Introduction

Current studies of structural covariance networks were focused on the gray matter in the human brain. The structural covariance connectivity in the white matter remains largely unexplored. This paper aimed to build novel metrics that can infer white matter structural covariance connectivity, and to explore the predictive power of the proposed features.

Methods

To this end, a cohort of 315 adult subjects with the anatomical brain MRI datasets were obtained from the publicly available Dallas Lifespan Brain Study (DLBS) project. The 3D wavelet transform was applied on the individual voxel-based morphology (VBM) volume to obtain the white matter structural covariance connectivity. The predictive models for cognitive functions were built using support vector regression (SVR).

Results

The predictive models exhibited comparable performance with previous studies. The novel features successfully predicted the individual ability of digit comparison (DC) (r = 0.41 ± 0.01, p < 0.01) and digit symbol (DSYM) (r = 0.5 ± 0.01, p < 0.01). The sensorimotor-related white matter system exhibited as the most predictive network node. Furthermore, the node strengths of sensorimotor mode were significantly correlated to cognitive scores.

Discussion

The results suggested that the white matter structural covariance connectivity was informative and had potential for predictive tasks of brain-behavior research.

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.

A Deep Spatiotemporal Attention Network for Mild Cognitive Impairment Identification

Mild cognitive impairment (MCI) is a nervous system disease, and its clinical status can be used as an early warning of Alzheimer's disease (AD). Subtle and slow changes in brain structure between patients with MCI and normal controls (NCs) deprive them of effective diagnostic methods. Therefore, the identification of MCI is a challenging task. The current functional brain network (FBN) analysis to predict human brain tissue structure is a new method emerging in recent years, which provides sensitive and effective medical biomarkers for the diagnosis of neurological diseases. Therefore, to address this challenge, we propose a novel Deep Spatiotemporal Attention Network (DSTAN) framework for MCI recognition based on brain functional networks. Specifically, we first extract spatiotemporal features between brain functional signals and FBNs by designing a spatiotemporal convolution strategy (ST-CONV). Then, on this basis, we introduce a learned attention mechanism to further capture brain nodes strongly correlated with MCI. Finally, we fuse spatiotemporal features for MCI recognition. The entire network is trained in an end-to-end fashion. Extensive experiments show that our proposed method significantly outperforms current baselines and state-of-the-art methods, with a classification accuracy of 84.21%.

Individual Brain Morphological Connectome Indicator Based on Jensen-Shannon Divergence Similarity Estimation for Autism Spectrum Disorder Identification

Background

Structural magnetic resonance imaging (sMRI) reveals abnormalities in patients with autism spectrum syndrome (ASD). Previous connectome studies of ASD have failed to identify the individual neuroanatomical details in preschool-age individuals. This paper aims to establish an individual morphological connectome method to characterize the connectivity patterns and topological alterations of the individual-level brain connectome and their diagnostic value in patients with ASD.

Methods

Brain sMRI data from 24 patients with ASD and 17 normal controls (NCs) were collected; participants in both groups were aged 24-47 months. By using the Jensen-Shannon Divergence Similarity Estimation (JSSE) method, all participants's morphological brain network were ascertained. Student's t-tests were used to extract the most significant features in morphological connection values, global graph measurement, and node graph measurement.

Results

The results of global metrics' analysis showed no statistical significance in the difference between two groups. Brain regions with meaningful properties for consensus connections and nodal metric features are mostly distributed in are predominantly distributed in the basal ganglia, thalamus, and cortical regions spanning the frontal, temporal, and parietal lobes. Consensus connectivity results showed an increase in most of the consensus connections in the frontal, parietal, and thalamic regions of patients with ASD, while there was a decrease in consensus connectivity in the occipital, prefrontal lobe, temporal lobe, and pale regions. The model that combined morphological connectivity, global metrics, and node metric features had optimal performance in identifying patients with ASD, with an accuracy rate of 94.59%.

Conclusion

The individual brain network indicator based on the JSSE method is an effective indicator for identifying individual-level brain network abnormalities in patients with ASD. The proposed classification method can contribute to the early clinical diagnosis of ASD.

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.

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

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.

Deep learning for neuroimaging-based diagnosis and rehabilitation of Autism Spectrum Disorder: A review

Accurate diagnosis of Autism Spectrum Disorder (ASD) followed by effective rehabilitation is essential for the management of this disorder. Artificial intelligence (AI) techniques can aid physicians to apply automatic diagnosis and rehabilitation procedures. AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques. Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally. DL methods for diagnosis of ASD have been focused on neuroimaging-based approaches. Neuroimaging techniques are non-invasive disease markers potentially useful for ASD diagnosis. Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain. Due to the intricate structure and function of the brain, proposing optimum procedures for ASD diagnosis with neuroimaging data without exploiting powerful AI techniques like DL may be challenging. In this paper, studies conducted with the aid of DL networks to distinguish ASD are investigated. Rehabilitation tools provided for supporting ASD patients utilizing DL networks are also assessed. Finally, we will present important challenges in the automated detection and rehabilitation of ASD and propose some future works.

Three-Dimensional Convolutional Autoencoder Extracts Features of Structural Brain Images With a "Diagnostic Label-Free" Approach: Application to Schizophrenia Datasets

There has been increasing interest in performing psychiatric brain imaging studies using deep learning. However, most studies in this field disregard three-dimensional (3D) spatial information and targeted disease discrimination, without considering the genetic and clinical heterogeneity of psychiatric disorders. The purpose of this study was to investigate the efficacy of a 3D convolutional autoencoder (3D-CAE) for extracting features related to psychiatric disorders without diagnostic labels. The network was trained using a Kyoto University dataset including 82 patients with schizophrenia (SZ) and 90 healthy subjects (HS) and was evaluated using Center for Biomedical Research Excellence (COBRE) datasets, including 71 SZ patients and 71 HS. We created 16 3D-CAE models with different channels and convolutions to explore the effective range of hyperparameters for psychiatric brain imaging. The number of blocks containing two convolutional layers and one pooling layer was set, ranging from 1 block to 4 blocks. The number of channels in the extraction layer varied from 1, 4, 16, and 32 channels. The proposed 3D-CAEs were successfully reproduced into 3D structural magnetic resonance imaging (MRI) scans with sufficiently low errors. In addition, the features extracted using 3D-CAE retained the relation to clinical information. We explored the appropriate hyperparameter range of 3D-CAE, and it was suggested that a model with 3 blocks may be related to extracting features for predicting the dose of medication and symptom severity in schizophrenia.

The Deficits of Individual Morphological Covariance Network Architecture in Schizophrenia Patients With and Without Violence

Background: Schizophrenia is associated with a significant increase in the risk of violence, which constitutes a public health concern and contributes to stigma associated with mental illness. Although previous studies revealed structural and functional abnormalities in individuals with violent schizophrenia (VSZ), the neural basis of psychotic violence remains controversial. Methods: In this study, high-resolution structural magnetic resonance imaging (MRI) data were acquired from 18 individuals with VSZ, 23 individuals with non-VSZ (NSZ), and 22 age- and sex-matched healthy controls (HCs). Whole-brain voxel-based morphology and individual morphological covariance networks were analysed to reveal differences in gray matter volume (GMV) and individual morphological covariance network topology. Relationships among abnormal GMV, network topology, and clinical assessments were examined using correlation analyses. Results: GMV in the hypothalamus gradually decreased from HCs and NSZ to VSZ and showed significant differences between all pairs of groups. Graph theory analyses revealed that morphological covariance networks of HCs, NSZ, and VSZ exhibited small worldness. Significant differences in network topology measures, including global efficiency, shortest path length, and nodal degree, were found. Furthermore, changes in GMV and network topology were closely related to clinical performance in the NSZ and VSZ groups. Conclusions: These findings revealed the important role of local structural abnormalities of the hypothalamus and global network topological impairments in the neuropathology of NSZ and VSZ, providing new insight into the neural basis of and markers for VSZ and NSZ to facilitate future accurate clinical diagnosis and targeted treatment.