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

A simple but tough-to-beat baseline for fMRI time-series classification

Current neuroimaging studies frequently use complex machine learning models to classify human fMRI data, distinguishing healthy and disordered brains, often to validate new methods or enhance prediction accuracy. Yet, where prediction accuracy is a concern, our results suggest that precision in prediction does not always require such sophistication. When a classifier as simple as logistic regression is applied to feature-engineered fMRI data, it can match or even outperform more sophisticated recent models. Classification of the raw time series fMRI data generally benefits from complex parameter-rich models. However, this complexity often pushes them into the class of black-box models. Yet, we found that a relatively simple model can consistently outperform much more complex classifiers in both accuracy and speed. This model applies the same multi-layer perceptron repeatedly across time and averages the results. Thus, the complexity and black-box nature of the parameter rich models, often perceived as a necessary trade-off for higher performance, do not invariably yield superior results on fMRI. Given the success of straightforward approaches, we challenge the merit of research that concentrates solely on complex model development driven by classification. Instead, we advocate for increased focus on designing models that prioritize the explainability of fMRI data or pursue applicable objectives beyond mere classification accuracy, unless they significantly outperform logistic regression or our proposed model. To validate our claim, we explore possible reasons for the superior performance of our straightforward model by examining the innate characteristics of fMRI time series data. Our findings suggest that the sequential information hidden in the temporal order may be far less important for the accurate fMRI classification than the stand-alone pieces of information scattered across the frames of the time series.

Bilinear Perceptual Fusion Algorithm Based on Brain Functional and Structural Data for ASD Diagnosis and Regions of Interest Identification

Autism spectrum disorder (ASD) is a serious mental disorder with a complex pathogenesis mechanism and variable presentation among individuals. Although many deep learning algorithms have been used to diagnose ASD, most of them focus on a single modality of data, resulting in limited information extraction and poor stability. In this paper, we propose a bilinear perceptual fusion (BPF) algorithm that leverages data from multiple modalities. In our algorithm, different schemes are used to extract features according to the characteristics of functional and structural data. Through bilinear operations, the associations between the functional and structural features of each region of interest (ROI) are captured. Then the associations are used to integrate the feature representation. Graph convolutional neural networks (GCNs) can effectively utilize topology and node features in brain network analysis. Therefore, we design a deep learning framework called BPF-GCN and conduct experiments on publicly available ASD dataset. The results show that the classification accuracy of BPF-GCN reached 82.35%, surpassing existing methods. This demonstrates the superiority of its classification performance, and the framework can extract ROIs related to ASD. Our work provides a valuable reference for the timely diagnosis and treatment of ASD.

Advancements in automated diagnosis of autism spectrum disorder through deep learning and resting-state functional mri biomarkers: a systematic review

Autism Spectrum Disorder(ASD) is a type of neurological disorder that is common among children. The diagnosis of this disorder at an early stage is the key to reducing its effects. The major symptoms include anxiety, lack of communication, and less social interaction. This paper presents a systematic review conducted based on PRISMA guidelines for automated diagnosis of ASD. With rapid development in the field of Data Science, numerous methods have been proposed that can diagnose the disease at an early stage which can minimize the effects of the disorder. Machine learning and deep learning have proven suitable techniques for the automated diagnosis of ASD. These models have been developed on various datasets such as ABIDE I and ABIDE II, a frequently used dataset based on rs-fMRI images. Approximately 26 articles have been reviewed after the screening process. The paper highlights a comparison between different algorithms used and their accuracy as well. It was observed that most researchers used DL algorithms to develop the ASD detection model. Different accuracies were recorded with a maximum accuracy close to 0.99. Recommendations for future work have also been discussed in a later section. This analysis derived a conclusion that AI-emerged DL and ML technologies can diagnose ASD through rs-fMRI images with maximum accuracy. The comparative analysis has been included to show the accuracy range.

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.

Functional Connectivity Differences in the Resting-state of the Amygdala in Alcohol-dependent Patients with Depression

RATIONALE AND OBJECTIVES

The mechanism of comorbidity between alcohol dependence and depressive disorders are not well understood. This study investigated differences in the brain function of alcohol-dependent patients with and without depression by performing functional connectivity analysis using resting-state functional magnetic resonance imaging.

MATERIALS AND METHODS

A total of 29 alcohol-dependent patients with depression, 31 alcohol-dependent patients without depression and 31 healthy control subjects were included in this study. The resting-state functional connectivity between the amygdala and the whole brain was compared among the three groups. Additionally, we examined the correlation between functional connectivity values in significantly different brain regions and levels of alcohol dependence and depression.

RESULTS

The resting-state functional connectivity between the left amygdala and the right caudate nucleus was decreased in alcohol-dependent patients. Additionally, the resting-state functional connectivity of the right amygdala with the right caudate nucleus, right transverse temporal gyrus, right temporal pole: superior temporal gyrus were also decreased. In alcohol-dependent patients with depression, not only was functional connectivity between the above brain regions significantly decreased, but so was functional connectivity between the right amygdala and the left middle temporal gyrus. Also, there was no significant correlation between the resting-state functional connectivity values in statistically significant brain regions and the levels of alcohol dependence and depression.

CONCLUSION

The impairment of the functional connectivity of the amygdala with caudate nucleus and partial temporal lobe may be involved in the neural mechanism of alcohol dependence comorbidity depressive disorders.

A machine learning model based on CHAT-23 for early screening of autism in Chinese children

Introduction

Autism spectrum disorder (ASD) is a neurodevelopmental condition that significantly impacts the mental, emotional, and social development of children. Early screening for ASD typically involves the use of a series of questionnaires. With answers to these questionnaires, healthcare professionals can identify whether a child is at risk for developing ASD and refer them for further evaluation and diagnosis. CHAT-23 is an effective and widely used screening test in China for the early screening of ASD, which contains 23 different kinds of questions.

Methods

We have collected clinical data from Wuxi, China. All the questions of CHAT-23 are regarded as different kinds of features for building machine learning models. We introduce machine learning methods into ASD screening, using the Max-Relevance and Min-Redundancy (mRMR) feature selection method to analyze the most important questions among all 23 from the collected CHAT-23 questionnaires. Seven mainstream supervised machine learning models were built and experiments were conducted.

Results

Among the seven supervised machine learning models evaluated, the best-performing model achieved a sensitivity of 0.909 and a specificity of 0.922 when the number of features was reduced to 9. This demonstrates the model's ability to accurately identify children for ASD with high precision, even with a more concise set of features.

Discussion

Our study focuses on the health of Chinese children, introducing machine learning methods to provide more accurate and effective early screening tests for autism. This approach not only enhances the early detection of ASD but also helps in refining the CHAT-23 questionnaire by identifying the most relevant questions for the diagnosis process.

A review of ADHD detection studies with machine learning methods using rsfMRI data

Attention deficit hyperactivity disorder (ADHD) is a common mental health condition that significantly affects school-age children, causing difficulties with learning and daily functioning. Early identification is crucial, and reliable and objective diagnostic tools are necessary. However, current clinical evaluations of behavioral symptoms can be inconsistent and subjective. Functional magnetic resonance imaging (fMRI) is a non-invasive technique that has proven effective in detecting brain abnormalities in individuals with ADHD. Recent studies have shown promising outcomes in using resting state fMRI (rsfMRI)-based brain functional networks to diagnose various brain disorders, including ADHD. Several review papers have examined the detection of other diseases using fMRI data and machine learning or deep learning methods. However, no review paper has specifically addressed ADHD. Therefore, this study aims to contribute to the literature by reviewing the use of rsfMRI data and machine learning methods for detection of ADHD. The study provides general information about fMRI databases and detailed knowledge of the ADHD-200 database, which is commonly used for ADHD detection. It also emphasizes the importance of examining all stages of the process, including network and atlas selection, feature extraction, and feature selection, before the classification stage. The study compares the performance, advantages, and disadvantages of previous studies in detail. This comprehensive approach may be a useful starting point for new researchers in this area.

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

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

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.

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

Objective

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

Methods

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

Results

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

Conclusion

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

Automated diagnosis of autism with artificial intelligence: State of the art

Autism spectrum disorder (ASD) represents a panel of conditions that begin during the developmental period and result in impairments of personal, social, academic, or occupational functioning. Early diagnosis is directly related to a better prognosis. Unfortunately, the diagnosis of ASD requires a long and exhausting subjective process. We aimed to review the state of the art for automated autism diagnosis and recognition in this research. In February 2022, we searched multiple databases and sources of gray literature for eligible studies. We used an adapted version of the QUADAS-2 tool to assess the risk of bias in the studies. A brief report of the methods and results of each study is presented. Data were synthesized for each modality separately using the Split Component Synthesis (SCS) method. We assessed heterogeneity using the I 2 statistics and evaluated publication bias using trim and fill tests combined with ln DOR. Confidence in cumulative evidence was assessed using the GRADE approach for diagnostic studies. We included 344 studies from 186,020 participants (51,129 are estimated to be unique) for nine different modalities in this review, from which 232 reported sufficient data for meta-analysis. The area under the curve was in the range of 0.71-0.90 for all the modalities. The studies on EEG data provided the best accuracy, with the area under the curve ranging between 0.85 and 0.93. We found that the literature is rife with bias and methodological/reporting flaws. Recommendations are provided for future research to provide better studies and fill in the current knowledge gaps.

Delineating a Pathway for the Discovery of Functional Connectome Biomarkers of Autism

The promise of individually tailored care for autism has driven efforts to establish biomarkers. This chapter appraises the state of precision-medicine research focused on biomarkers based on the functional brain connectome. This work is grounded on abundant evidence supporting the brain dysconnection model of autism and the advantages of resting-state functional MRI (R-fMRI) for studying the brain in vivo. After considering biomarker requirements of consistency and clinical relevance, we provide a scoping review of R-fMRI studies of individual prediction in autism. In the past 10 years, responding to the availability of open data through the Autism Brain Imaging Data Exchange, machine learning studies have surged. Nearly all have focused on diagnostic label classification. These efforts have shown that autism prediction is feasible using functional connectome markers, with accuracy reported well above chance. In parallel, emerging approaches more directly addressing autism heterogeneity are paving the way for much-needed biomarkers of longitudinal outcome and treatment response. We conclude with key challenges to be addressed by the next generation of studies.

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.

Relationship between abnormal intrinsic functional connectivity of subcortices and autism symptoms in high-functioning adults with autism spectrum disorder

PURPOSE

This study explores subcortices and their intrinsic functional connectivity (iFC) in autism spectrum disorder (ASD) adults and investigates their relationship with clinical severity.

METHODS

Resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 74 ASD patients, and 63 gender and age-matched typically developing (TD) adults. Independent component analysis (ICA) was conducted to evaluate subcortical patterns of basal ganglia (BG) and thalamus. These two brain areas were treated as regions of interest to further calculate whole-brain FC. In addition, we employed multivariate machine learning to identify subcortices-based FC brain patterns and clinical scores to classify ASD adults from those TD subjects.

RESULTS

In ASD individuals, autism diagnostic observation schedule (ADOS) was negatively correlated with the BG network. Similarly, social responsiveness scale (SRS) was negatively correlated with the thalamus network. The BG-based iFC analysis revealed adults with ASD versus TD had lower FC, and its FC with the right medial temporal lobe (MTL), was positively correlated with SRS and ADOS separately. ASD could be predicted with a balanced accuracy of around 60.0 % using brain patterns and 84.7 % using clinical variables.

CONCLUSION

Our results revealed the abnormal subcortical iFC may be related to autism symptoms.

Breaking Barriers-The Intersection of AI and Assistive Technology in Autism Care: A Narrative Review

(Background) Autism increasingly requires a multidisciplinary approach that can effectively harmonize the realms of diagnosis and therapy, tailoring both to the individual. Assistive technologies (ATs) play an important role in this context and hold significant potential when integrated with artificial intelligence (AI). (Objective) The objective of this study is to analyze the state of integration of AI with ATs in autism through a review. (Methods) A review was conducted on PubMed and Scopus, applying a standard checklist and a qualification process. The outcome reported 22 studies, including 7 reviews. (Key Content and Findings) The results reveal an early yet promising interest in integrating AI into autism assistive technologies. Exciting developments are currently underway at the intersection of AI and robotics, as well as in the creation of wearable automated devices like smart glasses. These innovations offer substantial potential for enhancing communication, interaction, and social engagement for individuals with autism. Presently, researchers are prioritizing innovation over establishing a solid presence within the healthcare domain, where issues such as regulation and acceptance demand increased attention. (Conclusions) As the field continues to evolve, it becomes increasingly clear that AI will play a pivotal role in bridging various domains, and integrated ATs with AI are positioned to act as crucial connectors.

TSP-GNN: a novel neuropsychiatric disorder classification framework based on task-specific prior knowledge and graph neural network

Neuropsychiatric disorder (ND) is often accompanied by abnormal functional connectivity (FC) patterns in specific task contexts. The distinctive task-specific FC patterns can provide valuable features for ND classification models using deep learning. However, most previous studies rely solely on the whole-brain FC matrix without considering the prior knowledge of task-specific FC patterns. Insight by the decoding studies on brain-behavior relationship, we develop TSP-GNN, which extracts task-specific prior (TSP) connectome patterns and employs graph neural network (GNN) for disease classification. TSP-GNN was validated using publicly available datasets. Our results demonstrate that different ND types show distinct task-specific connectivity patterns. Compared with the whole-brain node characteristics, utilizing task-specific nodes enhances the accuracy of ND classification. TSP-GNN comprises the first attempt to incorporate prior task-specific connectome patterns and the power of deep learning. This study elucidates the association between brain dysfunction and specific cognitive processes, offering valuable insights into the cognitive mechanism of neuropsychiatric disease.

A multi-view convolutional neural network method combining attention mechanism for diagnosing autism spectrum disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose current psychiatric diagnostic process is subjective and behavior-based. In contrast, functional magnetic resonance imaging (fMRI) can objectively measure brain activity and is useful for identifying brain disorders. However, the ASD diagnostic models employed to date have not reached satisfactory levels of accuracy. This study proposes the use of MAACNN, a method that utilizes multi-view convolutional neural networks (CNNs) in conjunction with attention mechanisms for identifying ASD in multi-scale fMRI. The proposed algorithm effectively combines unsupervised and supervised learning. In the initial stage, we employ stacked denoising autoencoders, an unsupervised learning method for feature extraction, which provides different nodes to adapt to multi-scale data. In the subsequent stage, we perform supervised learning by employing multi-view CNNs for classification and obtain the final results. Finally, multi-scale data fusion is achieved by using the attention fusion mechanism. The ABIDE dataset is used to evaluate the model we proposed., and the experimental results show that MAACNN achieves superior performance with 75.12% accuracy and 0.79 AUC on ABIDE-I, and 72.88% accuracy and 0.76 AUC on ABIDE-II. The proposed method significantly contributes to the clinical diagnosis of ASD.

An Umbrella Review of the Fusion of fMRI and AI in Autism

The role of functional magnetic resonance imaging (fMRI) is assuming an increasingly central role in autism diagnosis. The integration of Artificial Intelligence (AI) into the realm of applications further contributes to its development. This study's objective is to analyze emerging themes in this domain through an umbrella review, encompassing systematic reviews. The research methodology was based on a structured process for conducting a literature narrative review, using an umbrella review in PubMed and Scopus. Rigorous criteria, a standard checklist, and a qualification process were meticulously applied. The findings include 20 systematic reviews that underscore key themes in autism research, particularly emphasizing the significance of technological integration, including the pivotal roles of fMRI and AI. This study also highlights the enigmatic role of oxytocin. While acknowledging the immense potential in this field, the outcome does not evade acknowledging the significant challenges and limitations. Intriguingly, there is a growing emphasis on research and innovation in AI, whereas aspects related to the integration of healthcare processes, such as regulation, acceptance, informed consent, and data security, receive comparatively less attention. Additionally, the integration of these findings into Personalized Medicine (PM) represents a promising yet relatively unexplored area within autism research. This study concludes by encouraging scholars to focus on the critical themes of health domain integration, vital for the routine implementation of these applications.

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.

Assessing Predictive Ability of Dynamic Time Warping Functional Connectivity for ASD Classification

Functional connectivity MRI (fcMRI) is a technique used to study the functional connectedness of distinct regions of the brain by measuring the temporal correlation between their blood oxygen level-dependent (BOLD) signals. fcMRI is typically measured with the Pearson correlation (PC), which assumes that there is no lag between time series. Dynamic time warping (DTW) is an alternative measure of similarity between time series that is robust to such time lags. We used PC fcMRI data and DTW fcMRI data as predictors in machine learning models for classifying autism spectrum disorder (ASD). When combined with dimension reduction techniques, such as principal component analysis, functional connectivity estimated with DTW showed greater predictive ability than functional connectivity estimated with PC. Our results suggest that DTW fcMRI can be a suitable alternative measure that may be characterizing fcMRI in a different, but complementary, way to PC fcMRI that is worth continued investigation. In studying different variants of cross validation (CV), our results suggest that, when it is necessary to tune model hyperparameters and assess model performance at the same time, a K-fold CV nested within leave-one-out CV may be a competitive contender in terms of performance and computational speed, especially when sample size is not large.

Comparative analysis of group information-guided independent component analysis and independent vector analysis for assessing brain functional network characteristics in autism spectrum disorder

Introduction

Group information-guided independent component analysis (GIG-ICA) and independent vector analysis (IVA) are two methods that improve estimation of subject-specific independent components in neuroimaging studies. These methods have shown better performance than traditional group independent component analysis (GICA) with respect to intersubject variability (ISV).

Methods

In this study, we compared the patterns of community structure, spatial variance, and prediction performance of GIG-ICA and IVA-GL, respectively. The dataset was obtained from the publicly available Autism Brain Imaging Data Exchange (ABIDE) database, comprising 75 healthy controls (HC) and 102 Autism Spectrum Disorder (ASD) participants. The greedy rule was used to match components from IVA-GL and GIG-ICA in order to compare the similarities between the two methods.

Results

Robust correspondence was observed between the two methods the following networks: cerebellum network (CRN; |r| = 0.7813), default mode network (DMN; |r| = 0.7263), self-reference network (SRN; |r| = 0.7818), ventral attention network (VAN; |r| = 0.7574), and visual network (VSN; |r| = 0.7503). Additionally, the Sensorimotor Network demonstrated the highest similarity between IVA-GL and GIG-ICA (SOM: |r| = 0.8125). Our findings revealed a significant difference in the number of modules identified by the two methods (HC: p < 0.001; ASD: p < 0.001). GIG-ICA identified significant differences in FNC between HC and ASD compared to IVA-GL. However, in correlation analysis, IVA-GL identified a statistically negative correlation between FNC of ASD and the social total subscore of the classic Autism Diagnostic Observation Schedule (ADOS: pi = -0.26, p = 0.0489). Moreover, both methods demonstrated similar prediction performances on age within specific networks, as indicated by GIG-ICA-CRN (R2 = 0.91, RMSE = 3.05) and IVA-VAN (R2 = 0.87, RMSE = 3.21).

Conclusion

In summary, IVA-GL demonstrated lower modularity, suggesting greater sensitivity in estimating networks with higher intersubject variability. The improved age prediction of cerebellar-attention networks underscores their importance in the developmental progression of ASD. Overall, IVA-GL may be appropriate for investigating disorders with greater variability, while GIG-ICA identifies functional networks with distinct modularity patterns.

Multimodal Autism Spectrum Disorder Diagnosis Method Based on DeepGCN

Multimodal data play an important role in the diagnosis of brain diseases. This study constructs a whole-brain functional connectivity network based on functional MRI data, uses non-imaging data with demographic information to complement the classification task for diagnosing subjects, and proposes a multimodal and across-site WL-DeepGCN-based method for classification to diagnose autism spectrum disorder (ASD). This method is used to resolve the existing problem that deep learning ASD identification cannot efficiently utilize multimodal data. In the WL-DeepGCN, a weight-learning network is used to represent the similarity of non-imaging data in the latent space, introducing a new approach for constructing population graph edge weights, and we find that it is beneficial and robust to define pairwise associations in the latent space rather than the input space. We propose a graph convolutional neural network residual connectivity approach to reduce the information loss due to convolution operations by introducing residual units to avoid gradient disappearance and gradient explosion. Furthermore, an EdgeDrop strategy makes the node connections sparser by randomly dropping edges in the raw graph, and its introduction can alleviate the overfitting and oversmoothing problems in the DeepGCN training process. We compare the WL-DeepGCN model with competitive models based on the same topics and nested 10-fold cross-validation show that our method achieves 77.27% accuracy and 0.83 AUC for ASD identification, bringing substantial performance gains.

A face image classification method of autistic children based on the two-phase transfer learning

Autism spectrum disorder (ASD) is a neurodevelopmental disorder, which seriously affects children's normal life. Screening potential autistic children before professional diagnose is helpful to early detection and early intervention. Autistic children have some different facial features from non-autistic children, so the potential autistic children can be screened by taking children's facial images and analyzing them with a mobile phone. The area under curve (AUC) is a more robust metrics than accuracy in evaluating the performance of a model used to carry out the two-category classification, and the AUC of the deep learning model suitable for the mobile terminal in the existing research can be further improved. Moreover, the size of an input image is large, which is not fit for a mobile phone. A deep transfer learning method is proposed in this research, which can use images with smaller size and improve the AUC of existing studies. The proposed transfer method uses the two-phase transfer learning mode and the multi-classifier integration mode. For MobileNetV2 and MobileNetV3-Large that are suitable for a mobile phone, the two-phase transfer learning mode is used to improve their classification performance, and then the multi-classifier integration mode is used to integrate them to further improve the classification performance. A multi-classifier integrating calculation method is also proposed to calculate the final classification results according to the classifying results of the participating models. The experimental results show that compared with the one-phase transfer learning, the two-phase transfer learning can significantly improve the classification performance of MobileNetV2 and MobileNetV3-Large, and the classification performance of the integrated classifier is better than that of any participating classifiers. The accuracy of the integrated classifier in this research is 90.5%, and the AUC is 96.32%, which is 3.51% greater than the AUC (92.81%) of the previous studies.

Brain disease research based on functional magnetic resonance imaging data and machine learning: a review

Brain diseases, including neurodegenerative diseases and neuropsychiatric diseases, have long plagued the lives of the affected populations and caused a huge burden on public health. Functional magnetic resonance imaging (fMRI) is an excellent neuroimaging technology for measuring brain activity, which provides new insight for clinicians to help diagnose brain diseases. In recent years, machine learning methods have displayed superior performance in diagnosing brain diseases compared to conventional methods, attracting great attention from researchers. This paper reviews the representative research of machine learning methods in brain disease diagnosis based on fMRI data in the recent three years, focusing on the most frequent four active brain disease studies, including Alzheimer's disease/mild cognitive impairment, autism spectrum disorders, schizophrenia, and Parkinson's disease. We summarize these 55 articles from multiple perspectives, including the effect of the size of subjects, extracted features, feature selection methods, classification models, validation methods, and corresponding accuracies. Finally, we analyze these articles and introduce future research directions to provide neuroimaging scientists and researchers in the interdisciplinary fields of computing and medicine with new ideas for AI-aided brain disease diagnosis.

ALERT: Atlas-Based Low Estimation Rank Tensor Approach to Detect Autism Spectrum Disorder. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023;2023:1-4. [PMID: 38083014 DOI: 10.1109/embc40787.2023.10340610] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

In response to a stimulus, distinct areas of the human brain are activated. Also, it is known that the regions interact with one another. This functional connectivity is helpful to diagnose any neurological abnormality, such as autism spectrum disorder (ASD). This work proposes an approach to construct a functional connectivity network from fMRI image data. For obtaining a functional connectivity network, the time series component of fMRI data is used and from it correlation matrix is calculated showing the degree of interaction among the brain regions. To map the different regions of a brain, the brain atlas is considered. This essentially yields a low-rank tensor approximation of the functional connectivity matrix. A 2D convolutional deep neural network model is built to categorize topological similarity in the functional connectivity matrices related to ASD and typically developing control. The proposed approach has been tested with ABIDE dataset of fMRI data for autism spectrum disorder. Several brain atlases have been considered in the experiment. With a majority voting concept on the results from the atlases, the proposed technique reveals an ASD detection accuracy of 84.79%, which is significantly comparable to the state of the art techniques.Clinical Relevance- ASD is one of the least understood neurological disorders that has been recently recognized to have major sociological consequences on an affected individual's life. A symptom-based diagnosis is in practice. However, this requires prolonged behavioural examinations under the supervision of a highly skilled multidisciplinary team. An early and cost-effective detection using an fMRI image is considered an appropriate, comprehensive, and advanced treatment plan.

Application of TBSS-based machine learning models in the diagnosis of pediatric autism

Objective

To explore the microstructural changes of white matter in children with pediatric autism by using diffusion kurtosis imaging (DKI), and evaluate whether the combination of tract-based spatial statistics (TBSS) and back-propagation neural network (BPNN)/support vector machine (SVM)/logistic regression (LR) was feasible for the classification of pediatric autism.

Methods

DKI data were retrospectively collected from 32 children with autism and 27 healthy controls (HCs). Kurtosis fractional anisotropy (FAK), mean kurtosis (MK), axial kurtosis (KA), radial kurtosis (RK), fractional anisotropy (FA), axial diffusivity (DA), mean diffusivity (MD) and Radial diffusivity (DR) were generated by iQuant workstation. TBSS was used to detect the regions of parameters values abnormalities and for the comparison between these two groups. In addition, we also introduced the lateralization indices (LI) to study brain lateralization in children with pediatric autism, using TBSS for additional analysis. The parameters values of the differentiated regions from TBSS were then calculated for each participant and used as the features in SVM/BPNN/LR. All models were trained and tested with leave-one-out cross validation (LOOCV).

Results

Compared to the HCs group, the FAK, DA, and KA values of multi-fibers [such as the bilateral superior longitudinal fasciculus (SLF), corticospinal tract (CST) and anterior thalamic radiation (ATR)] were lower in pediatric autism group (p < 0.05, TFCE corrected). And we also found DA lateralization abnormality in Superior longitudinal fasciculus (SLF) (the LI in HCs group was higher than that in pediatric autism group). However, there were no significant differences in FA, MD, MK, DR, and KR values between HCs and pediatric autism group (P > 0.05, TFCE corrected). After performing LOOCV to train and test three model (SVM/BPNN/LR), we found the accuracy of BPNN (accuracy = 86.44%) was higher than that of LR (accuracy = 76.27%), but no different from SVM (RBF, accuracy = 81.36%; linear, accuracy = 84.75%).

Conclusion

Our proposed method combining TBSS findings with machine learning (LR/SVM/BPNN), was applicable in the classification of pediatric autism with high accuracy. Furthermore, the FAK, DA, and KA values and Lateralization index (LI) value could be used as neuroimaging biomarkers to discriminate the children with pediatric autism or not.

Inductively coupled plasma mass spectrometry based urine metallome to construct clinical decision models for autism spectrum disorder

BACKGROUND

The global prevalence of autism spectrum disorder (ASD) is on the rise, and high levels of exposure to toxic heavy metals may be associated with this increase. Urine analysis is a noninvasive method for investigating the accumulation and excretion of heavy metals. The aim of this study was to identify ASD-associated urinary metal markers.

METHODS

Overall, 70 children with ASD and 71 children with typical development (TD) were enrolled in this retrospective case-control study. In this metallomics investigation, inductively coupled plasma mass spectrometry was performed to obtain the urine profile of 27 metals.

RESULTS

Children with ASD could be distinguished from children with TD based on the urine metal profile, with ASD children showing an increased urine metal Shannon diversity. A metallome-wide association analysis was used to identify seven ASD-related metals in urine, with cobalt, aluminum, selenium, and lithium significantly higher, and manganese, mercury, and titanium significantly lower in the urine of children with ASD than in children with TD. The least absolute shrinkage and selection operator (LASSO) machine learning method was used to rank the seven urine metals in terms of their effect on ASD. On the basis of these seven urine metals, we constructed a LASSO regression model for ASD classification and found an area under the receiver operating characteristic curve of 0.913. We also constructed a clinical prediction model for ASD based on the seven metals that were different in the urine of children with ASD and found that the model would be useful for the clinical prediction of ASD risk.

CONCLUSIONS

The study findings suggest that altered urine metal concentrations may be an important risk factor for ASD, and we recommend further exploration of the mechanisms and clinical treatment measures for such alterations.

Functional Connectome-Based Predictive Modeling in Autism

Autism is a heterogeneous neurodevelopmental condition, and functional magnetic resonance imaging-based studies have helped advance our understanding of its effects on brain network activity. We review how predictive modeling, using measures of functional connectivity and symptoms, has helped reveal key insights into this condition. We discuss how different prediction frameworks can further our understanding of the brain-based features that underlie complex autism symptomatology and consider how predictive models may be used in clinical settings. Throughout, we highlight aspects of study interpretation, such as data decay and sampling biases, that require consideration within the context of this condition. We close by suggesting exciting future directions for predictive modeling in autism.

Systematic Bibliometric and Visualized Analysis of Research Hotspots and Trends on Autism Spectrum Disorder Neuroimaging

Background

Autism spectrum disorder (ASD) is a chronic developmental disability caused by differences in the brain. The gold standard for the diagnosis of this condition is based on behavioral science, but research on the application of neurological detection to diagnose the atypical nervous system of ASD is ongoing. ASD neuroimaging research involves the examination of the brain's structure, functional connections, and neurometabolic. However, limited medical resource and the unique heterogeneity of ASD have resulted in many challenges when neuroimaging is utilized.

Objective

This bibliometric study is aimed at summarizing themes and trends in research on autism spectrum disorder neuroimaging and at proposing potential directions for future inquiry.

Methods

Citations were downloaded from the Web of Science Core Collection database on neuroimaging published from January 1, 2012, to December 31, 2021. The retrieved information was analyzed using Bibliometric.com, CiteSpace.5.8. R3, and VOS viewer.

Results

A total of 1,363 papers were published across 58 regions. The United States was the leading source of publications. The League of European Research Universities published the largest number of articles (171). Burst keywords from 2018 to 2021 include identification and network. The clusters of references that continued into 2020 included graph theory, functional connectivity, and classification, which represent key research topics.

Conclusions

Imaging data is being used to identify neuro-network models with higher accuracy for ASD discrimination. Functional near-infrared imaging is advantageous compared to other neuroimaging. In the future, research on systematic and accurate computer-aided diagnosis technology should be encouraged. Moreover, the study of neuroimaging of ASD in different psychological and behavioral states can inspire new ideas about the diagnosis and intervention training of ASD and should be explored.

Retained Primitive Reflexes and Potential for Intervention in Autistic Spectrum Disorders

We provide evidence to support the contention that many aspects of Autistic Spectrum Disorder (ASD) are related to interregional brain functional disconnectivity associated with maturational delays in the development of brain networks. We think a delay in brain maturation in some networks may result in an increase in cortical maturation and development in other networks, leading to a developmental asynchrony and an unevenness of functional skills and symptoms. The paper supports the close relationship between retained primitive reflexes and cognitive and motor function in general and in ASD in particular provided to indicate that the inhibition of RPRs can effect positive change in ASD.

Application of Quantitative Magnetic Resonance Imaging in the Diagnosis of Autism in Children

Objective

To explore the application of quantitative magnetic resonance imaging in the diagnosis of autism in children.

Methods

Sixty autistic children aged 2–3 years and 60 age- and sex-matched healthy children participated in the study. All the children were scanned using head MRI conventional sequences, 3D-T1, diffusion kurtosis imaging (DKI), enhanced T2*- weighted magnetic resonance angiography (ESWAN) and 3D-pseudo continuous Arterial Spin-Labeled (3D-pcASL) sequences. The quantitative susceptibility mapping (QSM), cerebral blood flow (CBF), and brain microstructure of each brain area were compared between the groups, and correlations were analyzed.

Results

The iron content and cerebral blood flow in the frontal lobe, temporal lobe, hippocampus, caudate nucleus, substantia nigra, and red nucleus of the study group were lower than those in the corresponding brain areas of the control group (P < 0.05). The mean kurtosis (MK), radial kurtosis (RK), and axial kurtosis (AK) values of the frontal lobe, temporal lobe, putamen, hippocampus, caudate nucleus, substantia nigra, and red nucleus in the study group were lower than those of the corresponding brain areas in the control group (P < 0.05). The mean diffusivity (MD) and fractional anisotropy of kurtosis (FAK) values of the frontal lobe, temporal lobe and hippocampus in the control group were lower than those in the corresponding brain areas in the study group (P < 0.05). The values of CBF, QSM, and DKI in frontal lobe, temporal lobe and hippocampus could distinguish ASD children (AUC > 0.5, P < 0.05), among which multimodal technology (QSM, CBF, DKI) had the highest AUC (0.917) and DKI had the lowest AUC (0.642).

Conclusion

Quantitative magnetic resonance imaging (including QSM, 3D-pcASL, and DKI) can detect abnormalities in the iron content, cerebral blood flow and brain microstructure in young autistic children, multimodal technology (QSM, CBF, DKI) could be considered as the first choice of imaging diagnostic technology.

Clinical Trial Registration

[http://www.chictr.org.cn/searchprojen.aspx], identifier [ChiCTR2000029699].