Impact of Machine Learning Pipeline Choices in Autism Prediction From Functional Connectivity Data

Randomizing Human Brain Function Representation for Brain Disease Diagnosis

Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject's brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.

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.

Effect of Action Units, Viewpoint and Immersion on Emotion Recognition Using Dynamic Virtual Faces

Facial affect recognition is a critical skill in human interactions that is often impaired in psychiatric disorders. To address this challenge, tests have been developed to measure and train this skill. Recently, virtual human (VH) and virtual reality (VR) technologies have emerged as novel tools for this purpose. This study investigates the unique contributions of different factors in the communication and perception of emotions conveyed by VHs. Specifically, it examines the effects of the use of action units (AUs) in virtual faces, the positioning of the VH (frontal or mid-profile), and the level of immersion in the VR environment (desktop screen versus immersive VR). Thirty-six healthy subjects participated in each condition. Dynamic virtual faces (DVFs), VHs with facial animations, were used to represent the six basic emotions and the neutral expression. The results highlight the important role of the accurate implementation of AUs in virtual faces for emotion recognition. Furthermore, it is observed that frontal views outperform mid-profile views in both test conditions, while immersive VR shows a slight improvement in emotion recognition. This study provides novel insights into the influence of these factors on emotion perception and advances the understanding and application of these technologies for effective facial emotion recognition training.

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.

Masked features of task states found in individual brain networks

Completing complex tasks requires that we flexibly integrate information across brain areas. While studies have shown how functional networks are altered during different tasks, this work has generally focused on a cross-subject approach, emphasizing features that are common across people. Here we used extended sampling "precision" fMRI data to test the extent to which task states generalize across people or are individually specific. We trained classifiers to decode state using functional network data in single-person datasets across 5 diverse task states. Classifiers were then tested on either independent data from the same person or new individuals. Individualized classifiers were able to generalize to new participants. However, classification performance was significantly higher within a person, a pattern consistent across model types, people, tasks, feature subsets, and even for decoding very similar task conditions. Notably, these findings also replicated in a new independent dataset. These results suggest that individual-focused approaches can uncover robust features of brain states, including features obscured in cross-subject analyses. Individual-focused approaches have the potential to deepen our understanding of brain interactions during complex cognition.

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

CNNG: A Convolutional Neural Networks With Gated Recurrent Units for Autism Spectrum Disorder Classification

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data—autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%.

Quantifying Differences Between Affine and Nonlinear Spatial Normalization of FP-CIT Spect Images

Spatial normalization helps us to compare quantitatively two or more input brain scans. Although using an affine normalization approach preserves the anatomical structures, the neuroimaging field is more common to find works that make use of nonlinear transformations. The main reason is that they facilitate a voxel-wise comparison, not only when studying functional images but also when comparing MRI scans given that they fit better to a reference template. However, the amount of bias introduced by the nonlinear transformations can potentially alter the final outcome of a diagnosis especially when studying functional scans for neurological disorders like Parkinson's Disease. In this context, we have tried to quantify the bias introduced by the affine and the nonlinear spatial registration of FP-CIT SPECT volumes of healthy control subjects and patients with PD. For that purpose, we calculated the deformation fields of each participant and applied these deformation fields to a 3D-grid. As the space between the edges of small cubes comprising the grid change, we can quantify which parts from the brain have been enlarged, compressed or just remain the same. When the nonlinear approach is applied, scans from PD patients show a region near their striatum very similar in shape to that of healthy subjects. This artificially increases the interclass separation between patients with PD and healthy subjects as the local intensity is decreased in the latter region, and leads machine learning systems to biased results due to the artificial information introduced by these deformations.

Classification of Low and High Schizotypy Levels via Evaluation of Brain Connectivity

Schizotypy is a latent cluster of personality traits that denote a vulnerability for schizophrenia or a type of spectrum disorder. The aim of the study is to investigate parametric effective brain connectivity features for classifying high versus low schizotypy (LS) status. Electroencephalography (EEG) signals are recorded from 13 high schizotypy (HS) and 11 LS participants during an emotional auditory odd-ball task. The brain connectivity signals for machine learning are taken after the settlement of event-related potentials. A multivariate autoregressive (MVAR)-based connectivity measure is estimated from the EEG signals using the directed transfer functions (DTFs) method. The values of DTF power in five standard frequency bands are used as features. The support vector machines (SVMs) revealed significant differences between HS and LS. The accuracy, specificity, and sensitivity of the results using SVM are as high as 89.21%, 90.3%, and 88.2%, respectively. Our results demonstrate that the effective brain connectivity in prefrontal/parietal and prefrontal/frontal brain regions considerably changes according to schizotypal status. These findings prove that the brain connectivity indices offer valuable biomarkers for detecting schizotypal personality. Further monitoring of the changes in DTF following the diagnosis of schizotypy may lead to the early identification of schizophrenia and other spectrum disorders.

An Experimental Study of Neural Approaches to Multi-Hop Inference in Question Answering

Question answering aims at computing the answer to a question given a context with facts. Many proposals focus on questions whose answer is explicit in the context; lately, there has been an increasing interest in questions whose answer is not explicit and requires multi-hop inference to be computed. Our analysis of the literature reveals that there is a seminal proposal with increasingly complex follow-ups. Unfortunately, they were presented without an extensive study of their hyper-parameters, the experimental studies focused exclusively on English, and no statistical analysis to sustain the conclusions was ever performed. In this paper, we report on our experience devising a very simple neural approach to address the problem, on our extensive grid search over the space of hyper-parameters, on the results attained with English, Spanish, Hindi, and Portuguese, and sustain our conclusions with statistically sound analyses. Our findings prove that it is possible to beat many of the proposals in the literature with a very simple approach that was likely overlooked due to the difficulty to perform an extensive grid search, that the language does not have a statistically significant impact on the results, and that the empirical differences found among some existing proposals are not statistically significant.

Brain Network Organization Following Post-Stroke Neurorehabilitation

Brain network analysis can offer useful information to guide the rehabilitation of post-stroke patients. We applied functional network connection models based on multiplex-multilayer network analysis (MMN) to explore functional network connectivity changes induced by robot-aided gait training (RAGT) using the Ekso, a wearable exoskeleton, and compared it to conventional overground gait training (COGT) in chronic stroke patients. We extracted the coreness of individual nodes at multiple locations in the brain from EEG recordings obtained before and after gait training in a resting state. We found that patients provided with RAGT achieved a greater motor function recovery than those receiving COGT. This difference in clinical outcome was paralleled by greater changes in connectivity patterns among different brain areas central to motor programming and execution, as well as a recruitment of other areas beyond the sensorimotor cortices and at multiple frequency ranges, contemporarily. The magnitude of these changes correlated with motor function recovery chances. Our data suggest that the use of RAGT as an add-on treatment to COGT may provide post-stroke patients with a greater modification of the functional brain network impairment following a stroke. This might have potential clinical implications if confirmed in large clinical trials.

Wavelet-Based Biphase Analysis of Brain Rhythms in Automated Wake-Sleep Classification

Many studies in the field of sleep have focused on connectivity and coherence. Still, the nonstationary nature of electroencephalography (EEG) makes many of the previous methods unsuitable for automatic sleep detection. Time-frequency representations and high-order spectra are applied to nonstationary signal analysis and nonlinearity investigation, respectively. Therefore, combining wavelet and bispectrum, wavelet-based bi-phase (Wbiph) was proposed and used as a novel feature for sleep-wake classification. The results of the statistical analysis with emphasis on the importance of the gamma rhythm in sleep detection show that the Wbiph is more potent than coherence in the wake-sleep classification. The Wbiph has not been used in sleep studies before. However, the results and inherent advantages, such as the use of wavelet and bispectrum in its definition, suggest it as an excellent alternative to coherence. In the next part of this paper, a convolutional neural network (CNN) classifier was applied for the sleep-wake classification by Wbiph. The classification accuracy was 97.17% in nonLOSO and 95.48% in LOSO cross-validation, which is the best among previous studies on sleep-wake classification.

A review of methods for classification and recognition of ASD using fMRI data

Autism spectrum disorder (ASD) is a severe neuropsychiatric brain disorder that affects people's social communication and daily routine. Considering the phenomenon of abnormal brain function in the early stage of ASD, functional magnetic resonance imaging (fMRI), an excellent technique that measures brain activity, provides effective data to study ASD. Therefore, based on fMRI data of ASD cases, this paper reviews the progress of machine learning methods and deep learning methods in ASD classification and recognition in the last three years and summarizes the different research results of fMRI data extracted from the Autism Brain Imaging Data Exchange (ABIDE). From the classification performance of classification and recognition of ASD by the two methods, comparing the important classification indicators such as accuracy, sensitivity and specificity, the current challenges and future development trends are reported, which can provide an essential reference for the early diagnosis of ASD cases.