ASD-DiagNet: A Hybrid Learning Approach for Detection of Autism Spectrum Disorder Using fMRI Data

Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing

Purpose

The main aim of our study was to explore the utility of artificial intelligence (AI) in diagnosing autism spectrum disorder (ASD). The study primarily focused on using machine learning (ML) and deep learning (DL) models to detect ASD potential cases by analyzing text inputs, especially from social media platforms like Twitter. This is to overcome the ongoing challenges in ASD diagnosis, such as the requirement for specialized professionals and extensive resources. Timely identification, particularly in children, is essential to provide immediate intervention and support, thereby improving the quality of life for affected individuals.

Methods

We employed natural language processing (NLP) techniques along with ML models like decision trees, extreme gradient boosting (XGB), k-nearest neighbors algorithm (KNN), and DL models such as recurrent neural networks (RNN), long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), bidirectional encoder representations from transformers (BERT and BERTweet). We extracted a dataset of 404,627 tweets from Twitter users using the platform's API and classified them based on whether they were written by individuals claiming to have ASD (ASD users) or by those without ASD (non-ASD users). From this dataset, we used a subset of 90,000 tweets (45,000 from each classification group) for the training and testing of these models.

Results

The application of our AI models yielded promising results, with the predictive model reaching an accuracy of almost 88% when classifying texts that potentially originated from individuals with ASD.

Conclusion

Our research demonstrated the potential of using AI, particularly DL models, in enhancing the accuracy of ASD detection and diagnosis. This innovative approach signifies the critical role AI can play in advancing early diagnostic techniques, enabling better patient outcomes and underlining the importance of early identification of ASD, especially in children.

A Multiview Brain Network Transformer Fusing Individualized Information for Autism Spectrum Disorder Diagnosis

Functional connectivity (FC) networks, built from analyses of resting-state magnetic resonance imaging (rs-fMRI), serve as efficacious biomarkers for identifying Autism Spectrum Disorders (ASD) patients. Given the neurobiological heterogeneity across individuals and the unique presentation of ASD symptoms, the fusion of individualized information into diagnosis becomes essential. However, this aspect is overlooked in most methods. Furthermore, the existing methods typically focus on studying direct pairwise connections between brain ROIs, while disregarding interactions between indirectly connected neighbors. To overcome above challenges, we build common FC and individualized FC by tangent pearson embedding (TP) and common orthogonal basis extraction (COBE) respectively, and present a novel multiview brain transformer (MBT) aimed at effectively fusing common and indivinformation of subjects. MBT is mainly constructed by transformer layers with diffusion kernel (DK), fusion quality-inspired weighting module (FQW), similarity loss and orthonormal clustering fusion readout module (OCFRead). DK transformer can incorporate higher-order random walk methods to capture wider interactions among indirectly connected brain regions. FQW promotes adaptive fusion of features between views, and similarity loss and OCFRead are placed on the last layer to accomplish the ultimate integration of information. In our method, TP, DK and FQW modules all help to model wider connectivity in the brain that make up for the shortcomings of traditional methods. We conducted experiments on the public ABIDE dataset based on AAL and CC200 respectively. Our framework has shown promising results, outperforming state-of-the-art methods on both templates. This suggests its potential as a valuable approach for clinical ASD diagnosis.

Spatial-Temporal Co-Attention Learning for Diagnosis of Mental Disorders From Resting-State fMRI Data

Neuroimaging techniques have been widely adopted to detect the neurological brain structures and functions of the nervous system. As an effective noninvasive neuroimaging technique, functional magnetic resonance imaging (fMRI) has been extensively used in computer-aided diagnosis (CAD) of mental disorders, e.g., autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). In this study, we propose a spatial-temporal co-attention learning (STCAL) model for diagnosing ASD and ADHD from fMRI data. In particular, a guided co-attention (GCA) module is developed to model the intermodal interactions of spatial and temporal signal patterns. A novel sliding cluster attention module is designed to address global feature dependency of self-attention mechanism in fMRI time series. Comprehensive experimental results demonstrate that our STCAL model can achieve competitive accuracies of 73.0 ± 4.5%, 72.0 ± 3.8%, and 72.5 ± 4.2% on the ABIDE I, ABIDE II, and ADHD-200 datasets, respectively. Moreover, the potential for feature pruning based on the co-attention scores is validated by the simulation experiment. The clinical interpretation analysis of STCAL can allow medical professionals to concentrate on the discriminative regions of interest and key time frames from fMRI data.

Advancing ASD identification with neuroimaging: a novel GARL methodology integrating Deep Q-Learning and generative adversarial networks

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects an individual's behavior, speech, and social interaction. Early and accurate diagnosis of ASD is pivotal for successful intervention. The limited availability of large datasets for neuroimaging investigations, however, poses a significant challenge to the timely and precise identification of ASD. To address this problem, we propose a breakthrough approach, GARL, for ASD diagnosis using neuroimaging data. GARL innovatively integrates the power of GANs and Deep Q-Learning to augment limited datasets and enhance diagnostic precision. We utilized the Autistic Brain Imaging Data Exchange (ABIDE) I and II datasets and employed a GAN to expand these datasets, creating a more robust and diversified dataset for analysis. This approach not only captures the underlying sample distribution within ABIDE I and II but also employs deep reinforcement learning for continuous self-improvement, significantly enhancing the capability of the model to generalize and adapt. Our experimental results confirmed that GAN-based data augmentation effectively improved the performance of all prediction models on both datasets, with the combination of InfoGAN and DQN's GARL yielding the most notable improvement.

Identification of autism spectrum disorder using multiple functional connectivity-based graph convolutional network

Presently, the combination of graph convolutional networks (GCN) with resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising approach for early diagnosis of autism spectrum disorder (ASD). However, the prevalent approach involves exclusively full-brain functional connectivity data for disease classification using GCN, while overlooking the prior information related to the functional connectivity of brain subnetworks associated with ASD. Therefore, in this study, the multiple functional connectivity-based graph convolutional network (MFC-GCN) framework is proposed, using not only full brain functional connectivity data but also the established functional connectivity data from networks of key brain subnetworks associated with ASD, and the GCN is adopted to acquire complementary feature information for the final classification task. Given the heterogeneity within the Autism Brain Imaging Data Exchange (ABIDE) dataset, a novel External Attention Network Readout (EANReadout) is introduced. This design enables the exploration of potential subject associations, effectively addressing the dataset's heterogeneity. Experiments were conducted on the ABIDE dataset using the proposed framework, involving 714 subjects, and the average accuracy of the framework was 70.31%. The experimental results show that the proposed EANReadout outperforms the best traditional readout layer and improves the average accuracy of the framework by 4.32%.

ASD-SWNet: a novel shared-weight feature extraction and classification network for autism spectrum disorder diagnosis

The traditional diagnostic process for autism spectrum disorder (ASD) is subjective, where early and accurate diagnosis significantly affects treatment outcomes and life quality. Thus, improving ASD diagnostic methods is critical. This paper proposes ASD-SWNet, a new shared-weight feature extraction and classification network. It resolves the issue found in previous studies of inefficiently integrating unsupervised and supervised learning, thereby enhancing diagnostic precision. The approach utilizes functional magnetic resonance imaging to improve diagnostic accuracy, featuring an autoencoder (AE) with Gaussian noise for robust feature extraction and a tailored convolutional neural network (CNN) for classification. The shared-weight mechanism utilizes features learned by the AE to initialize the convolutional layer weights of the CNN, thereby integrating AE and CNN for joint training. A novel data augmentation strategy for time-series medical data is also introduced, tackling the problem of small sample sizes. Tested on the ABIDE-I dataset through nested ten-fold cross-validation, the method achieved an accuracy of 76.52% and an AUC of 0.81. This approach surpasses existing methods, showing significant enhancements in diagnostic accuracy and robustness. The contribution of this paper lies not only in proposing new methods for ASD diagnosis but also in offering new approaches for other neurological brain diseases.

Multitask Learning for Joint Diagnosis of Multiple Mental Disorders in Resting-State fMRI

Facing the increasing worldwide prevalence of mental disorders, the symptom-based diagnostic criteria struggle to address the urgent public health concern due to the global shortfall in well-qualified professionals. Thanks to the recent advances in neuroimaging techniques, functional magnetic resonance imaging (fMRI) has surfaced as a new solution to characterize neuropathological biomarkers for detecting functional connectivity (FC) anomalies in mental disorders. However, the existing computer-aided diagnosis models for fMRI analysis suffer from unstable performance on large datasets. To address this issue, we propose an efficient multitask learning (MTL) framework for joint diagnosis of multiple mental disorders using resting-state fMRI data. A novel multiobjective evolutionary clustering algorithm is presented to group regions of interests (ROIs) into different clusters for FC pattern analysis. On the optimal clustering solution, the multicluster multigate mixture-of-expert model is used for the final classification by capturing the highly consistent feature patterns among related diagnostic tasks. Extensive simulation experiments demonstrate that the performance of the proposed framework is superior to that of the other state-of-the-art methods. Moreover, the potential for practical application of the framework is also validated in terms of limited computational resources, real-time analysis, and insufficient training data. The proposed model can identify the remarkable interpretative biomarkers associated with specific mental disorders for clinical interpretation analysis.

Identification of Autism Spectrum Disorder Using Topological Data Analysis

Autism spectrum disorder (ASD) is a pervasive brain development disease. Recently, the incidence rate of ASD has increased year by year and posed a great threat to the lives and families of individuals with ASD. Therefore, the study of ASD has become very important. A suitable feature representation that preserves the data intrinsic information and also reduces data complexity is very vital to the performance of established models. Topological data analysis (TDA) is an emerging and powerful mathematical tool for characterizing shapes and describing intrinsic information in complex data. In TDA, persistence barcodes or diagrams are usually regarded as visual representations of topological features of data. In this paper, the Regional Homogeneity (ReHo) data of subjects obtained from Autism Brain Imaging Data Exchange (ABIDE) database were used to extract features by using TDA. The average accuracy of cross validation on ABIDE I database was 95.6% that was higher than any other existing methods (the highest accuracy among existing methods was 93.59%). The average accuracy for sampling with the same resolutions with the ABIDE I on the ABIDE II database was 96.5% that was also higher than any other existing methods (the highest accuracy among existing methods was 75.17%).

Adversarial Learning Based Node-Edge Graph Attention Networks for Autism Spectrum Disorder Identification

Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.

Autism spectrum disorder diagnosis with EEG signals using time series maps of brain functional connectivity and a combined CNN-LSTM model

BACKGROUND AND OBJECTIVE

People with autism spectrum disorder (ASD) often have cognitive impairments. Effective connectivity between different areas of the brain is essential for normal cognition. Electroencephalography (EEG) has been widely used in the detection of neurological diseases. Previous studies on detecting ASD with EEG data have focused on frequency-related features. Most of these studies have augmented data by splitting the dataset into time slices or sliding windows. However, such approaches to data augmentation may cause the testing data to be contaminated by the training data. To solve this problem, this study developed a novel method for detecting ASD with EEG data.

METHODS

This study quantified the functional connectivity of the subject's brain from EEG signals and defined the individual to be the unit of analysis. Publicly available EEG data were gathered from 97 and 92 subjects with ASD and typical development (TD), respectively, while they were at rest or performing a task. Time-series maps of brain functional connectivity were constructed, and the data were augmented using a deep convolutional generative adversarial network. In addition, a combined network for ASD detection, based on convolutional neural network (CNN) and long short-term memory (LSTM), was designed and implemented.

RESULTS

Based on functional connectivity, the network achieved classification accuracies of 81.08% and 74.55% on resting state and task state data, respectively. In addition, we found that the functional connectivity of ASD differed from TD primarily in the short-distance functional connectivity of the parietal and occipital lobes and in the distant connections from the right temporoparietal junction region to the left posterior temporal lobe.

CONCLUSIONS

This paper provides a new perspective for better utilizing EEG to understand ASD. The method proposed in our study is expected to be a reliable tool to assist in the diagnosis of ASD.

Adaptive spatial-temporal neural network for ADHD identification using functional fMRI

Computer aided diagnosis methods play an important role in Attention Deficit Hyperactivity Disorder (ADHD) identification. Dynamic functional connectivity (dFC) analysis has been widely used for ADHD diagnosis based on resting-state functional magnetic resonance imaging (rs-fMRI), which can help capture abnormalities of brain activity. However, most existing dFC-based methods only focus on dependencies between two adjacent timestamps, ignoring global dynamic evolution patterns. Furthermore, the majority of these methods fail to adaptively learn dFCs. In this paper, we propose an adaptive spatial-temporal neural network (ASTNet) comprising three modules for ADHD identification based on rs-fMRI time series. Specifically, we first partition rs-fMRI time series into multiple segments using non-overlapping sliding windows. Then, adaptive functional connectivity generation (AFCG) is used to model spatial relationships among regions-of-interest (ROIs) with adaptive dFCs as input. Finally, we employ a temporal dependency mining (TDM) module which combines local and global branches to capture global temporal dependencies from the spatially-dependent pattern sequences. Experimental results on the ADHD-200 dataset demonstrate the superiority of the proposed ASTNet over competing approaches in automated ADHD classification.

Early autism diagnosis based on path signature and Siamese unsupervised feature compressor

Autism spectrum disorder has been emerging as a growing public health threat. Early diagnosis of autism spectrum disorder is crucial for timely, effective intervention and treatment. However, conventional diagnosis methods based on communications and behavioral patterns are unreliable for children younger than 2 years of age. Given evidences of neurodevelopmental abnormalities in autism spectrum disorder infants, we resort to a novel deep learning-based method to extract key features from the inherently scarce, class-imbalanced, and heterogeneous structural MR images for early autism diagnosis. Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features. We also proposed weight constraints to cope with sample heterogeneity by giving different samples different voting weights during validation, and used Path Signature to unravel meaningful developmental features from the two-time point data longitudinally. We further extracted machine learning focused brain regions for autism diagnosis. Extensive experiments have shown that our method performed well under practical scenarios, transcending existing machine learning methods and providing anatomical insights for autism early diagnosis.

Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.

Decoding Autism: Uncovering patterns in brain connectivity through sparsity analysis with rs-fMRI data

BACKGROUND

In the realm of neuro-disorders, precise diagnosis and treatment rely heavily on objective imaging-based biomarker identification. This study employs a sparsity approach on resting-state fMRI to discern relevant brain region connectivity for predicting Autism.

NEW METHOD

The proposed methodology involves four key steps: (1) Utilizing three probabilistic brain atlases to extract functionally homogeneous brain regions from fMRI data. (2) Employing a hybrid approach of Graphical Lasso and Akaike Information Criteria to optimize sparse inverse covariance matrices for representing the brain functional connectivity. (3) Employing statistical techniques to scrutinize functional brain structures in Autism and Control subjects. (4) Implementing both autoencoder-based feature extraction and entire feature-based approach coupled with AI-based learning classifiers to predict Autism.

RESULTS

The ensemble classifier with the extracted feature set achieves a classification accuracy of 84.7% ± 0.3% using the MSDL atlas. Meanwhile, the 1D-CNN model, employing all features, exhibits superior classification accuracy of 88.6% ± 1.7% with the Smith 2009 (rsn70) atlas.

COMPARISON WITH EXISTING METHOD (S)

The proposed methodology outperforms the conventional correlation-based functional connectivity approach with a notably high prediction accuracy of more than 88%, whereas considering all direct and noisy indirect region-based functional connectivity, the traditional methods bound the prediction accuracy within 70% to 79%.

CONCLUSIONS

This study underscores the potential of sparsity-based FC analysis using rs-fMRI data as a prognostic biomarker for detecting Autism.

A review of the applications of generative adversarial networks to structural and functional MRI based diagnostic classification of brain disorders

Structural and functional MRI (magnetic resonance imaging) based diagnostic classification using machine learning has long held promise, but there are many roadblocks to achieving their potential. While traditional machine learning models suffered from their inability to capture the complex non-linear mapping, deep learning models tend to overfit the model. This is because there is data scarcity and imbalanced classes in neuroimaging; it is expensive to acquire data from human subjects and even more so in clinical populations. Due to their ability to augment data by learning underlying distributions, generative adversarial networks (GAN) provide a potential solution to this problem. Here, we provide a methodological primer on GANs and review the applications of GANs to classification of mental health disorders from neuroimaging data such as functional MRI and showcase the progress made thus far. We also highlight gaps in methodology as well as interpretability that are yet to be addressed. This provides directions about how the field can move forward. We suggest that since there are a range of methodological choices available to users, it is critical for users to interact with method developers so that the latter can tailor their development according to the users' needs. The field can be enriched by such synthesis between method developers and users in neuroimaging.

Residual graph transformer for autism spectrum disorder prediction

Brain functional connectivity (FC) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been in vogue to predict Autism Spectrum Disorder (ASD), which is a neuropsychiatric disease up the plight of locating latent biomarkers for clinical diagnosis. Albeit massive endeavors have been made, most studies are fed up with several chronic issues, such as the intractability of harnessing the interaction flourishing within brain regions, the astriction of representation due to vanishing gradient within deeper network architecture, and the poor interpretability leading to unpersuasive diagnosis. To ameliorate these issues, a FC-learned Residual Graph Transformer Network, namely RGTNet, is proposed. Specifically, we design a Graph Encoder to extract temporal-related features with long-range dependencies, from which interpretable FC matrices would be modeled. Besides, the residual trick is introduced to deepen the GCN architecture, thereby learning the higher-level information. Moreover, a novel Graph Sparse Fitting followed by weighted aggregation is proposed to ease dimensionality explosion. Empirically, the results on two types of ABIDE data sets demonstrate the meliority of RGTNet. Notably, the achieved ACC metric reaches 73.4%, overwhelming most competitors with merely 70.9% on the AAL atlas using a five-fold cross-validation policy. Moreover, the investigated biomarkers concord closely with the authoritative medical knowledge, paving a viable way for ASD-clinical diagnosis. Our code is available at https://github.com/CodeGoat24/RGTNet.

EAG-RS: A Novel Explainability-Guided ROI-Selection Framework for ASD Diagnosis via Inter-Regional Relation Learning

Deep learning models based on resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used to diagnose brain diseases, particularly autism spectrum disorder (ASD). Existing studies have leveraged the functional connectivity (FC) of rs-fMRI, achieving notable classification performance. However, they have significant limitations, including the lack of adequate information while using linear low-order FC as inputs to the model, not considering individual characteristics (i.e., different symptoms or varying stages of severity) among patients with ASD, and the non-explainability of the decision process. To cover these limitations, we propose a novel explainability-guided region of interest (ROI) selection (EAG-RS) framework that identifies non-linear high-order functional associations among brain regions by leveraging an explainable artificial intelligence technique and selects class-discriminative regions for brain disease identification. The proposed framework includes three steps: (i) inter-regional relation learning to estimate non-linear relations through random seed-based network masking, (ii) explainable connection-wise relevance score estimation to explore high-order relations between functional connections, and (iii) non-linear high-order FC-based diagnosis-informative ROI selection and classifier learning to identify ASD. We validated the effectiveness of our proposed method by conducting experiments using the Autism Brain Imaging Database Exchange (ABIDE) dataset, demonstrating that the proposed method outperforms other comparative methods in terms of various evaluation metrics. Furthermore, we qualitatively analyzed the selected ROIs and identified ASD subtypes linked to previous neuroscientific studies.

Classification of recurrent major depressive disorder using a residual denoising autoencoder framework: Insights from large-scale multisite fMRI data

BACKGROUND AND OBJECTIVE

Recurrent major depressive disorder (rMDD) has a high recurrence rate, and symptoms often worsen with each episode. Classifying rMDD using functional magnetic resonance imaging (fMRI) can enhance understanding of brain activity and aid diagnosis and treatment of this disorder.

METHODS

We developed a Residual Denoising Autoencoder (Res-DAE) framework for the classification of rMDD. The functional connectivity (FC) was extracted from fMRI data as features. The framework addresses site heterogeneity by employing the Combat method to harmonize feature distribution differences. A feature selection method based on Fisher scores was used to reduce redundant information in the features. A data augmentation strategy using a Synthetic Minority Over-sampling Technique algorithm based on Extended Frobenius Norm measure was incorporated to increase the sample size. Furthermore, a residual module was integrated into the autoencoder network to preserve important features and improve the classification accuracy.

RESULTS

We tested our framework on a large-scale, multisite fMRI dataset, which includes 189 rMDD patients and 427 healthy controls. The Res-DAE achieved an average accuracy of 75.1 % (sensitivity = 69 %, specificity = 77.8 %) in cross-validation, thereby outperforming comparison methods. In a larger dataset that also includes first-episode depression (comprising 832 MDD patients and 779 healthy controls), the accuracy reached 70 %.

CONCLUSIONS

We proposed a deep learning framework that can effectively classify rMDD and 33 identify the altered FC associated with rMDD. Our study may reveal changes in brain function 34 associated with rMDD and provide assistance for the diagnosis and treatment of rMDD.

The Dynamical Biomarkers in Functional Connectivity of Autism Spectrum Disorder Based on Dynamic Graph Embedding

Autism spectrum disorder (ASD) is a neurological and developmental disorder and its early diagnosis is a challenging task. The dynamic brain network (DBN) offers a wealth of information for the diagnosis and treatment of ASD. Mining the spatio-temporal characteristics of DBN is critical for finding dynamic communication across brain regions and, ultimately, identifying the ASD diagnostic biomarker. We proposed the dgEmbed-KNN and the Aggregation-SVM diagnostic models, which use the spatio-temporal information from DBN and interactive information among brain regions represented by dynamic graph embedding. The classification accuracies show that dgEmbed-KNN model performs slightly better than traditional machine learning and deep learning methods, while the Aggregation-SVM model has a very good capacity to diagnose ASD using aggregation brain network connections as features. We discovered over- and under-connections in ASD at the level of dynamic connections, involving brain regions of the postcentral gyrus, the insula, the cerebellum, the caudate nucleus, and the temporal pole. We also found abnormal dynamic interactions associated with ASD within/between the functional subnetworks, including default mode network, visual network, auditory network and saliency network. These can provide potential DBN biomarkers for ASD identification.

Autism Spectrum Disorder Detection by Hybrid Convolutional Recurrent Neural Networks from Structural and Resting State Functional MRI Images

This study aims to increase the accuracy of autism spectrum disorder (ASD) diagnosis based on cognitive and behavioral phenotypes through multiple neuroimaging modalities. We apply machine learning (ML) algorithms to classify ASD patients and healthy control (HC) participants using structural magnetic resonance imaging (s-MRI) together with resting state functional MRI (rs-f-MRI and f-MRI) data from the large multisite data repository ABIDE (autism brain imaging data exchange) and identify important brain connectivity features. The 2D f-MRI images were converted into 3D s-MRI images, and datasets were preprocessed using the Montreal Neurological Institute (MNI) atlas. The data were then denoised to remove any confounding factors. We show, by using three fusion strategies such as early fusion, late fusion, and cross fusion, that, in this implementation, hybrid convolutional recurrent neural networks achieve better performance in comparison to either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). The proposed model classifies subjects as autistic or not according to how functional and anatomical connectivity metrics provide an overall diagnosis based on the autism diagnostic observation schedule (ADOS) standard. Our hybrid network achieved an accuracy of 96% by fusing s-MRI and f-MRI together, which outperforms the methods used in previous studies.

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.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium

BACKGROUND

Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group.

METHODS

We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality.

RESULTS

We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance.

CONCLUSION

These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

A-GCL: Adversarial graph contrastive learning for fMRI analysis to diagnose neurodevelopmental disorders

Accurate diagnosis of neurodevelopmental disorders is a challenging task due to the time-consuming cognitive tests and potential human bias in clinics. To address this challenge, we propose a novel adversarial self-supervised graph neural network (GNN) based on graph contrastive learning, named A-GCL, for diagnosing neurodevelopmental disorders using functional magnetic resonance imaging (fMRI) data. Taking advantage of the success of GNNs in psychiatric disease diagnosis using fMRI, our proposed A-GCL model is expected to improve the performance of diagnosis and provide more robust results. A-GCL takes graphs constructed from the fMRI images as input and uses contrastive learning to extract features for classification. The graphs are constructed with 3 bands of the amplitude of low-frequency fluctuation (ALFF) as node features and Pearson's correlation coefficients (PCC) of the average fMRI time series in different brain regions as edge weights. The contrastive learning creates an edge-dropped graph from a trainable Bernoulli mask to extract features that are invariant to small variations of the graph. Experiment results on three datasets - Autism Brain Imaging Data Exchange (ABIDE) I, ABIDE II, and attention deficit hyperactivity disorder (ADHD) - with 3 atlases - AAL1, AAL3, Shen268 - demonstrate the superiority and generalizability of A-GCL compared to the other GNN-based models. Extensive ablation studies verify the robustness of the proposed approach to atlas selection and model variation. Explanatory results reveal key functional connections and brain regions associated with neurodevelopmental disorders.

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Autism-spectrum disorders (ASDs) are developmental disabilities that manifest in early childhood and are characterized by qualitative abnormalities in social behaviors, communication skills, and restrictive or repetitive behaviors. To explore the neurobiological mechanisms in ASD, extensive research has been done to identify potential diagnostic biomarkers through a neuroimaging genetics approach. Neuroimaging genetics helps to identify ASD-risk genes that contribute to structural and functional variations in brain circuitry and validate biological changes by elucidating the mechanisms and pathways that confer genetic risk. Integrating artificial intelligence models with neuroimaging data lays the groundwork for accurate diagnosis and facilitates the identification of early diagnostic biomarkers for ASD. This review discusses the significance of neuroimaging genetics approaches to gaining a better understanding of the perturbed neurochemical system and molecular pathways in ASD and how these approaches can detect structural, functional, and metabolic changes and lead to the discovery of novel biomarkers for the early diagnosis of ASD.

ASD-GResTM: Deep Learning Framework for ASD classification using Gramian Angular Field

Autism Spectrum Disorder (ASD) is a heterogeneous disorder in children, and the current clinical diagnosis is accomplished using behavioral, cognitive, developmental, and language metrics. These clinical metrics can be imperfect measures as they are subject to high test-retest variability, and are influenced by assessment factors such as environment, social structure, or comorbid disorders. Advances in neuroimaging coupled with machine-learning provides an opportunity to develop methods that are more quantifiable, and reliable than existing clinical techniques. In this paper, we design and develop a deep-learning model that operates on functional magnetic resonance imaging (fMRI) data, and can classify between ASD and neurotypical brains. We introduce a novel strategy to transform time-series data extracted from fMRI signals into Gramian Angular Field (GAF) while locking in the temporal and spatial patterns in the data. Our motivation is to design and develop a novel framework that could encode the time-series, acquired from fMRI data, into images that can be used by deep-learning architectures that have been successful in computer vision. In our proposed framework called ASD-GResTM, we used a Convolutional Neural Network (CNN) to extract useful features from GAF images. We then used a Long Short-Term Memory (LSTM) layer to learn the activities between the regions. Finally, the output representations of the last LSTM layer are applied to a single-layer perceptron (SPL) to get the final classification. Our extensive experimentation demonstrates high accuracy across 4 centers, and outperforms state-of-the-art models on two centers with an increase in the accuracy of 17.58% and 6.7%, respectively as compared to the state of the art. Our model achieved the maximum accuracy of 81.78% with high degree of sensitivity and specificity. All training, validation, and testing was accomplished using openly available ABIDE-I benchmarking dataset.

Automatic diagnosis of schizophrenia and attention deficit hyperactivity disorder in rs-fMRI modality using convolutional autoencoder model and interval type-2 fuzzy regression

Nowadays, many people worldwide suffer from brain disorders, and their health is in danger. So far, numerous methods have been proposed for the diagnosis of Schizophrenia (SZ) and attention deficit hyperactivity disorder (ADHD), among which functional magnetic resonance imaging (fMRI) modalities are known as a popular method among physicians. This paper presents an SZ and ADHD intelligent detection method of resting-state fMRI (rs-fMRI) modality using a new deep learning method. The University of California Los Angeles dataset, which contains the rs-fMRI modalities of SZ and ADHD patients, has been used for experiments. The FMRIB software library toolbox first performed preprocessing on rs-fMRI data. Then, a convolutional Autoencoder model with the proposed number of layers is used to extract features from rs-fMRI data. In the classification step, a new fuzzy method called interval type-2 fuzzy regression (IT2FR) is introduced and then optimized by genetic algorithm, particle swarm optimization, and gray wolf optimization (GWO) techniques. Also, the results of IT2FR methods are compared with multilayer perceptron, k-nearest neighbors, support vector machine, random forest, and decision tree, and adaptive neuro-fuzzy inference system methods. The experiment results show that the IT2FR method with the GWO optimization algorithm has achieved satisfactory results compared to other classifier methods. Finally, the proposed classification technique was able to provide 72.71% accuracy.

[Alzheimer's disease classification based on nonlinear high-order features and hypergraph convolutional neural network]

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder that damages patients' memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.

Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from rs-fMRI Multi-site Data

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive imaging technique widely used in neuroscience to understand the functional connectivity of the human brain. While rs-fMRI multi-site data can help to understand the inner working of the brain, the data acquisition and processing of this data has many challenges. One of the challenges is the variability of the data associated with different acquisitions sites, and different MRI machines vendors. Other factors such as population heterogeneity among different sites, with variables such as age and gender of the subjects, must also be considered. Given that most of the machine-learning models are developed using these rs-fMRI multi-site data sets, the intrinsic confounding effects can adversely affect the generalizability and reliability of these computational methods, as well as the imposition of upper limits on the classification scores. This work aims to identify the phenotypic and imaging variables producing the confounding effects, as well as to control these effects. Our goal is to maximize the classification scores obtained from the machine learning analysis of the Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI multi-site data. To achieve this goal, we propose novel methods of stratification to produce homogeneous sub-samples of the 17 ABIDE sites, as well as the generation of new features from the static functional connectivity values, using multiple linear regression models, ComBat harmonization models, and normalization methods. The main results obtained with our statistical models and methods are an accuracy of 76.4%, sensitivity of 82.9%, and specificity of 77.0%, which are 8.8%, 20.5%, and 7.5% above the baseline classification scores obtained from the machine learning analysis of the static functional connectivity computed from the ABIDE rs-fMRI multi-site data.

A heterogeneous graph convolutional attention network method for classification of autism spectrum disorder

BACKGROUND

Autism spectrum disorder (ASD) is a serious developmental disorder of the brain. Recently, various deep learning methods based on functional magnetic resonance imaging (fMRI) data have been developed for the classification of ASD. Among them, graph neural networks, which generalize deep neural network models to graph structured data, have shown great advantages. However, in graph neural methods, because the graphs constructed are homogeneous, the phenotype information of the subjects cannot be fully utilized. This affects the improvement of the classification performance.

METHODS

To fully utilize the phenotype information, this paper proposes a heterogeneous graph convolutional attention network (HCAN) model to classify ASD. By combining an attention mechanism and a heterogeneous graph convolutional network, important aggregated features can be extracted in the HCAN. The model consists of a multilayer HCAN feature extractor and a multilayer perceptron (MLP) classifier. First, a heterogeneous population graph was constructed based on the fMRI and phenotypic data. Then, a multilayer HCAN is used to mine graph-based features from the heterogeneous graph. Finally, the extracted features are fed into an MLP for the final classification.

RESULTS

The proposed method is assessed on the autism brain imaging data exchange (ABIDE) repository. In total, 871 subjects in the ABIDE I dataset are used for the classification task. The best classification accuracy of 82.9% is achieved. Compared to the other methods using exactly the same subjects in the literature, the proposed method achieves superior performance to the best reported result.

CONCLUSIONS

The proposed method can effectively integrate heterogeneous graph convolutional networks with a semantic attention mechanism so that the phenotype features of the subjects can be fully utilized. Moreover, it shows great potential in the diagnosis of brain functional disorders with fMRI data.

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.

PLSNet: Position-aware GCN-based autism spectrum disorder diagnosis via FC learning and ROIs sifting

Brain function connectivity, derived from functional magnetic resonance imaging (fMRI), has enjoyed high popularity in the studies of Autism Spectrum Disorder (ASD) diagnosis. Albeit rapid progress has been made, most studies still suffer from several knotty issues: (1) the hardship of modeling the sophisticated brain neuronal connectivity; (2) the mismatch of identically graph node setup to the variations of different brain regions; (3) the dimensionality explosion resulted from excessive voxels in each fMRI sample; (4) the poor interpretability giving rise to unpersuasive diagnosis. To ameliorate these issues, we propose a position-aware graph-convolution-network-based model, namely PLSNet, with superior accuracy and compelling built-in interpretability for ASD diagnosis. Specifically, a time-series encoder is designed for context-rich feature extraction, followed by a function connectivity generator to model the correlation with long range dependencies. In addition, to discriminate the brain nodes with different locations, the position embedding technique is adopted, giving a unique identity to each graph region. We then embed a rarefying method to sift the salient nodes during message diffusion, which would also benefit the reduction of the dimensionality complexity. Extensive experiments conducted on Autism Brain Imaging Data Exchange demonstrate that our PLSNet achieves state-of-the-art performance. Notably, on CC200 atlas, PLSNet reaches an accuracy of 76.4% and a specificity of 78.6%, overwhelming the previous state-of-the-art with 2.5% and 6.5% under five-fold cross-validation policy. Moreover, the most salient brain regions predicted by PLSNet are closely consistent with the theoretical knowledge in the medical domain, providing potential biomarkers for ASD clinical diagnosis. Our code is available at https://github.com/CodeGoat24/PLSNet.

Deep Hashing Mutual Learning for Brain Network Classification

Recently, clinical phenotypic semantic information has begun to play an important role in some brain network classification methods based on deep learning. However, most current methods only consider the phenotypic semantic information of individual brain networks but ignore the potential phenotypic characteristics among group brain networks. To address this problem, we present a deep hashing mutual learning (DHML)-based brain network classification method. Specifically, we first design a separable CNN-based deep hashing learning to extract individual topological features of brain networks and map them into hash codes. Secondly, we construct a group brain network relationship graph based on the similarity of phenotypic semantic information, in which each node is a brain network, and the properties of the nodes are the individual features extracted in the previous step. Then, we adopt a GCN-based deep hashing learning to extract the group topological features of the brain network and map them to hash codes. Finally, the two deep hashing learning models perform mutual learning by measuring the distribution differences between the hash codes to achieve the interaction of individual and group features. The experimental results on the three commonly used brain atlases (AAL Atlas, Dosenbach160 Atlas, and CC200 Atlas) of the ABIDE I dataset show that our proposed DHML method achieves optimal classification performance compared with some state-of-the-art methods.

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.

A deep learning method for autism spectrum disorder identification based on interactions of hierarchical brain networks

BACKGROUND

It has been recently shown that deep learning models exhibited remarkable performance of representing functional Magnetic Resonance Imaging (fMRI) data for the understanding of brain functional activities. With hierarchical structure, deep learning models can infer hierarchical functional brain networks (FBN) from fMRI. However, the applications of the hierarchical FBNs have been rarely studied.

METHODS

In this work, we proposed a hierarchical recurrent variational auto-encoder (HRVAE) to unsupervisedly model the fMRI data. The trained HRVAE encoder can predict hierarchical temporal features from its three hidden layers, and thus can be regarded as a hierarchical feature extractor. Then LASSO (least absolute shrinkage and selection operator) regression was applied to estimate the corresponding hierarchical FBNs. Based on the hierarchical FBNs from each subject, we constructed a novel classification framework for brain disorder identification and test it on the Autism Brain Imaging Data Exchange (ABIDE) dataset, a world-wide multi-site database of autism spectrum disorder (ASD). We analyzed the hierarchy organization of FBNs, and finally used the overlaps of hierarchical FBNs as features to differentiate ASD from typically developing controls (TDC).

RESULTS

The experimental results on 871 subjects from ABIDE dataset showed that the HRVAE model can effectively derive hierarchical FBNs including many well-known resting state networks (RSN). Moreover, the classification result improved the state-of-the-art by achieving a very high accuracy of 82.1 %.

CONCLUSIONS

This work presents a novel data-driven deep learning method using fMRI data for ASD identification, which could provide valuable reference for clinical diagnosis. The classification results suggest that the interactions of hierarchical FBNs have association with brain disorder, which promotes the understanding of FBN hierarchy and could be applied to other brain disorder analysis.

Graph Self-Supervised Learning With Application to Brain Networks Analysis

The less training data and insufficient supervision limit the performance of the deep supervised models for brain disease diagnosis. It is significant to construct a learning framework that can capture more information in limited data and insufficient supervision. To address these issues, we focus on self-supervised learning and aim to generalize the self-supervised learning to the brain networks, which are non-Euclidean graph data. More specifically, we propose an ensemble masked graph self-supervised framework named BrainGSLs, which incorporates 1) a local topological-aware encoder that takes the partially visible nodes as input and learns these latent representations, 2) a node-edge bi-decoder that reconstructs the masked edges by the representations of both the masked and visible nodes, 3) a signal representation learning module for capturing temporal representations from BOLD signals and 4) a classifier used for the classification. We evaluate our model on three real medical clinical applications: diagnosis of Autism Spectrum Disorder (ASD), diagnosis of Bipolar Disorder (BD) and diagnosis of Major Depressive Disorder (MDD). The results suggest that the proposed self-supervised training has led to remarkable improvement and outperforms state-of-the-art methods. Moreover, our method is able to identify the biomarkers associated with the diseases, which is consistent with the previous studies. We also explore the correlation of these three diseases and find the strong association between ASD and BD. To the best of our knowledge, our work is the first attempt of applying the idea of self-supervised learning with masked autoencoder on the brain network analysis.

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

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

Learning to Fuse Multiple Brain Functional Networks for Automated Autism Identification

Functional connectivity network (FCN) has become a popular tool to identify potential biomarkers for brain dysfunction, such as autism spectrum disorder (ASD). Due to its importance, researchers have proposed many methods to estimate FCNs from resting-state functional MRI (rs-fMRI) data. However, the existing FCN estimation methods usually only capture a single relationship between brain regions of interest (ROIs), e.g., linear correlation, nonlinear correlation, or higher-order correlation, thus failing to model the complex interaction among ROIs in the brain. Additionally, such traditional methods estimate FCNs in an unsupervised way, and the estimation process is independent of the downstream tasks, which makes it difficult to guarantee the optimal performance for ASD identification. To address these issues, in this paper, we propose a multi-FCN fusion framework for rs-fMRI-based ASD classification. Specifically, for each subject, we first estimate multiple FCNs using different methods to encode rich interactions among ROIs from different perspectives. Then, we use the label information (ASD vs. healthy control (HC)) to learn a set of fusion weights for measuring the importance/discrimination of those estimated FCNs. Finally, we apply the adaptively weighted fused FCN on the ABIDE dataset to identify subjects with ASD from HCs. The proposed FCN fusion framework is straightforward to implement and can significantly improve diagnostic accuracy compared to traditional and state-of-the-art methods.

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.

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.

Role of Artificial Intelligence for Autism Diagnosis Using DTI and fMRI: A Survey

Autism spectrum disorder (ASD) is a wide range of diseases characterized by difficulties with social skills, repetitive activities, speech, and nonverbal communication. The Centers for Disease Control (CDC) estimates that 1 in 44 American children currently suffer from ASD. The current gold standard for ASD diagnosis is based on behavior observational tests by clinicians, which suffer from being subjective and time-consuming and afford only late detection (a child must have a mental age of at least two to apply for an observation report). Alternatively, brain imaging-more specifically, magnetic resonance imaging (MRI)-has proven its ability to assist in fast, objective, and early ASD diagnosis and detection. With the recent advances in artificial intelligence (AI) and machine learning (ML) techniques, sufficient tools have been developed for both automated ASD diagnosis and early detection. More recently, the development of deep learning (DL), a young subfield of AI based on artificial neural networks (ANNs), has successfully enabled the processing of brain MRI data with improved ASD diagnostic abilities. This survey focuses on the role of AI in autism diagnostics and detection based on two basic MRI modalities: diffusion tensor imaging (DTI) and functional MRI (fMRI). In addition, the survey outlines the basic findings of DTI and fMRI in autism. Furthermore, recent techniques for ASD detection using DTI and fMRI are summarized and discussed. Finally, emerging tendencies are described. The results of this study show how useful AI is for early, subjective ASD detection and diagnosis. More AI solutions that have the potential to be used in healthcare settings will be introduced in the future.

Exploring interpretable graph convolutional networks for autism spectrum disorder diagnosis

PURPOSE

Finding the biomarkers associated with autism spectrum disorder (ASD) is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatments. In essence, we are faced with two challenges (i) how to learn a node representation and a clean graph structure from original graph data with high dimensionality and (ii) how to jointly model the procedure of node representation learning, structure learning and graph classification.

METHODS

We propose FSL-BrainNet, an interpretable graph convolution network (GCN) model for jointly Learning of node Features and clean Structures in brain networks for automatic brain network classification and interpretation. We formulate an end-to-end trainable and interpretable framework for graph classification and biomarkers (salient brain regions and potential subnetworks) identification.

RESULTS

The experimental results on the ABIDE dataset show that our proposed methods not only achieve improved prediction performance compared with the state-of-the-art methods, but also find a compact set of highly suggestive biomarkers including relevant brain regions and subnetworks to ASD.

CONCLUSION

Through node feature learning and structure learning, our model can simultaneously select important brain regions and identify subnetworks.

A Model for Diagnosing Autism Patients Using Spatial and Statistical Measures Using rs-fMRI and sMRI by Adopting Graphical Neural Networks

This article proposes a model to diagnose autism patients using graphical neural networks. A graphical neural network relates the subjects (nodes) using the features (edges). In our model, radiomic features obtained from sMRI are used as edges, and spatial-temporal data obtained through rs-fMRI are used as nodes. The similarity between first-order and texture features from the sMRI data of subjects are derived using radiomics to construct the edges of a graph. The features from brain summaries are assembled and learned using 3DCNN to represent the features of each node of the graph. Using the structural similarities of the brain rather than phenotypic data or graph kernel functions provides better accuracy. The proposed model was applied to a standard dataset, ABIDE, and it was shown that the classification results improved with the use of both spatial (sMRI) and statistical measures (brain summaries of rs-fMRI) instead of using only medical images.

Dynamic multi-site graph convolutional network for autism spectrum disorder identification

Multi-site learning has attracted increasing interests in autism spectrum disorder (ASD) identification tasks by its efficacy on capturing data heterogeneity of neuroimaging taken from different medical sites. However, existing multi-site graph convolutional network (MSGCN) often ignores the correlations between different sites, and may obtain suboptimal identification results. Moreover, current feature extraction methods characterizing temporal variations of functional magnetic resonance imaging (fMRI) signals require the time series to be of the same length and cannot be directly applied to multi-site fMRI datasets. To address these problems, we propose a dual graph based dynamic multi-site graph convolutional network (DG-DMSGCN) for multi-site ASD identification. First, a sliding-window dual-graph convolutional network (SW-DGCN) is introduced for feature extraction, simultaneously capturing temporal and spatial features of fMRI data with different series lengths. Then we aggregate the features extracted from multiple medical sites through a novel dynamic multi-site graph convolutional network (DMSGCN), which effectively considers the correlations between different sites and is beneficial to improve identification performance. We evaluate the proposed DG-DMSGCN on public ABIDE I dataset containing data from 17 medical sites. The promising results obtained by our framework outperforms the state-of-the-art methods with increase in identification accuracy, indicating that it has a potential clinical prospect for practical ASD diagnosis. Our codes are available on https://github.com/Junling-Du/DG-DMSGCN.

BLENDS: Augmentation of Functional Magnetic Resonance Images for Machine Learning Using Anatomically Constrained Warping

Introduction: Data augmentation improves the accuracy of deep learning models when training data are scarce by synthesizing additional samples. This work addresses the lack of validated augmentation methods specific for synthesizing anatomically realistic four-dimensional (4D) (three-dimensional [3D] + time) images for neuroimaging, such as functional magnetic resonance imaging (fMRI), by proposing a new augmentation method. Methods: The proposed method, Brain Library Enrichment through Nonlinear Deformation Synthesis (BLENDS), generates new nonlinear warp fields by combining intersubject coregistration maps, computed using symmetric normalization, through spatial blending. These new warp fields can be applied to existing 4D fMRI to create new augmented images. BLENDS was tested on two neuroimaging problems using de-identified data sets: (1) the prediction of antidepressant response from task-based fMRI (original data set n = 163), and (2) the prediction of Parkinson's disease (PD) symptom trajectory from baseline resting-state fMRI regional homogeneity (original data set n = 43). Results: BLENDS readily generates hundreds of new fMRI from existing images, with unique anatomical variations from the source images, that significantly improve prediction performance. For antidepressant response prediction, augmenting each original image once (2 × the original training data) significantly increased prediction R2 from 0.055 to 0.098 (p < 1 e - 6 ), whereas at 10 × augmentation R2 increased to 0.103. For the prediction of PD trajectory, 10 × augmentation R2 increased from -0.044 to 0.472 (p < 1 e - 6 ). Conclusions: Augmentation of fMRI through nonlinear transformations with BLENDS significantly improved the performance of deep learning models on clinically relevant predictive tasks. This method will help neuroimaging researchers overcome data set size limitations and achieve more accurate predictive models.

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.

BrainTGL: A dynamic graph representation learning model for brain network analysis

Modeling the dynamics characteristics in functional brain networks (FBNs) is important for understanding the functional mechanism of the human brain. However, the current works do not fully consider the potential complex spatial and temporal correlations in human brain. To solve this problem, we propose a temporal graph representation learning framework for brain networks (BrainTGL). The framework involves a temporal graph pooling for eliminating the noisy edges as well as data inconsistency, and a dual temporal graph learning for capturing the spatio-temporal features of the temporal graphs. The proposed method has been evaluated in both tasks of brain disease (ASD, MDD and BD) diagnosis/gender classification (classification task) and subtype identification (clustering task) on the four datasets: Human Connectome Project (HCP), Autism Brain Imaging Data Exchange (ABIDE), NMU-MDD and NMU-BD. A large improvement is achieved for the ASD diagnosis. Specifically, our model outperforms the GroupINN and ST-GCN by an average increase of 4.2% and 8.6% on accuracy, respectively, demonstrating its advantages in comparison to the state-of-the-art methods based on functional connectivity features or learned spatio-temporal features. The results demonstrate that learning the spatial-temporal brain network representation for modeling dynamics characteristics in FBNs can improve the model's performance on both disease diagnosis and subtype identification tasks for multiple disorders. Apart from performance, the improvements of computational efficiency and convergence speed reduce training costs.

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

Background: Functional brain networks (FBNs) derived from resting-state functional MRI (rs-fMRI) have shown great potential in identifying brain disorders, such as autistic spectrum disorder (ASD). Therefore, many FBN estimation methods have been proposed in recent years. Most existing methods only model the functional connections between brain regions of interest (ROIs) from a single view (e.g., by estimating FBNs through a specific strategy), failing to capture the complex interactions among ROIs in the brain. Methods: To address this problem, we propose fusion of multiview FBNs through joint embedding, which can make full use of the common information of multiview FBNs estimated by different strategies. More specifically, we first stack the adjacency matrices of FBNs estimated by different methods into a tensor and use tensor factorization to learn the joint embedding (i.e., a common factor of all FBNs) for each ROI. Then, we use Pearson's correlation to calculate the connections between each embedded ROI in order to reconstruct a new FBN. Results: Experimental results obtained on the public ABIDE dataset with rs-fMRI data reveal that our method is superior to several state-of-the-art methods in automated ASD diagnosis. Moreover, by exploring FBN "features" that contributed most to ASD identification, we discovered potential biomarkers for ASD diagnosis. The proposed framework achieves an accuracy of 74.46%, which is generally better than the compared individual FBN methods. In addition, our method achieves the best performance compared to other multinetwork methods, i.e., an accuracy improvement of at least 2.72%. Conclusions: We present a multiview FBN fusion strategy through joint embedding for fMRI-based ASD identification. The proposed fusion method has an elegant theoretical explanation from the perspective of eigenvector centrality.

Prediction Model for Sensory Perception Abnormality in Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by heterogeneous clinical phenotypes. Patients often experience abnormal sensory perception, which may further affect the ASD core phenotype, significantly and adversely affecting their quality of life. However, biomarkers for the diagnosis of ASD sensory perception abnormality are currently elusive. We sought to identify potential biomarkers related to ASD sensory perception abnormality to construct a prediction model that could facilitate the early identification of and screening for ASD. Differentially expressed genes in ASD were obtained from the Gene Expression Omnibus database and were screened for genes related to sensory perception abnormality. After enrichment analysis, the random forest method was used to identify disease-characteristic genes. A prediction model was constructed with an artificial neural network. Finally, the results were validated using data from the dorsal root ganglion, cerebral cortex, and striatum of the BTBR T+ Itpr3tf/J (BTBR) ASD mouse model. A total of 1869 differentially expressed genes in ASD were screened, among which 16 genes related to sensory perception abnormality were identified. According to enrichment analysis, these 16 genes were mainly related to actin, cholesterol metabolism, and tight junctions. Using random forest, 15 disease-characteristic genes were screened for model construction. The area under the curve of the training set validation result was 0.999, and for the model function validation, the result was 0.711, indicating high accuracy. The validation of BTBR mice confirmed the reliability of using these disease-characteristic genes for prediction of ASD. In conclusion, we developed a highly accurate model for predicting ASD sensory perception abnormality from 15 disease-characteristic genes. This model provides a new method for the early identification and diagnosis of ASD sensory perception abnormality.