Learning Generalizable Recurrent Neural Networks from Small Task-fMRI Datasets

Spatiotemporal Data Processing with Memristor Crossbar-Array-Based Graph Reservoir

Memristor-based physical reservoir computing (RC) is a robust framework for processing complex spatiotemporal data parallelly. However, conventional memristor-based reservoirs cannot capture the spatial relationship between the time-varying inputs due to the specific mapping scheme assigning one input signal to one memristor conductance. Here, a physical "graph reservoir" is introduced using a metal cell at the diagonal-crossbar array (mCBA) with dynamic self-rectifying memristors. Input and inverted input signals are applied to the word and bit lines of the mCBA, respectively, storing the correlation information between input signals in the memristors. In this way, the mCBA graph reservoirs can map the spatiotemporal correlation of the input data in a high-dimensional feature space. The high-dimensional mapping characteristics of the graph reservoir achieve notable results, including a normalized root-mean-square error of 0.09 in Mackey-Glass time series prediction, a 97.21% accuracy in MNIST recognition, and an 80.0% diagnostic accuracy in human connectome classification.

Copy Number Variation Informs fMRI-based Prediction of Autism Spectrum Disorder

The multifactorial etiology of autism spectrum disorder (ASD) suggests that its study would benefit greatly from multimodal approaches that combine data from widely varying platforms, e.g., neuroimaging, genetics, and clinical characterization. Prior neuroimaging-genetic analyses often apply naive feature concatenation approaches in data-driven work or use the findings from one modality to guide posthoc analysis of another, missing the opportunity to analyze the paired multimodal data in a truly unified approach. In this paper, we develop a more integrative model for combining genetic, demographic, and neuroimaging data. Inspired by the influence of genotype on phenotype, we propose using an attention-based approach where the genetic data guides attention to neuroimaging features of importance for model prediction. The genetic data is derived from copy number variation parameters, while the neuroimaging data is from functional magnetic resonance imaging. We evaluate the proposed approach on ASD classification and severity prediction tasks, using a sex-balanced dataset of 228 ASD and typically developing subjects in a 10-fold cross-validation framework. We demonstrate that our attention-based model combining genetic information, demographic data, and functional magnetic resonance imaging results in superior prediction performance compared to other multimodal approaches.

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.

An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification

Autism Spectrum Disorder (ASD) is one common developmental disorder with great variations in symptoms and severity, making the diagnosis of ASD a challenging task. Existing deep learning models using brain connectivity features to classify ASD still suffer from degraded performance for multi-center data due to limited feature representation ability and insufficient interpretability. Given that Graph Convolutional Network (GCN) has demonstrated superiority in learning discriminative representations of brain connectivity networks, in this paper, we propose an invertible dynamic GCN model to identify ASD and investigate the alterations of connectivity patterns associated with the disease. In order to select explainable features from the model, invertible blocks are introduced in the whole network, and we are able to reconstruct the input dynamic features from the network's output. A pre-screening of connectivity features is adopted to reduce the redundancy of the input information, and a fully-connected layer is added to perform classification. The experimental results on 867 subjects show that our proposed method achieves superior disease classification performance. It provides an interpretable deep learning model for brain connectivity analysis and is of great potential in studying brain-related disorders.

Identifying Methamphetamine Abstainers With Convolutional Neural Networks and Short-Time Fourier Transform

Few studies have investigated the functional patterns of methamphetamine abstainers. A better understanding of the underlying neurobiological mechanism in the brains of methamphetamine abstainers will help to explain their abnormal behaviors. Forty-two male methamphetamine abstainers, currently in a long-term abstinence status (for at least 14 months), and 32 male healthy controls were recruited. All subjects underwent functional MRI while responding to drug-associated cues. This study proposes to combine a convolutional neural network with a short-time Fourier transform to identify different brain patterns between methamphetamine abstainers and controls. The short-time Fourier transformation provides time-localized frequency information, while the convolutional neural network extracts the structural features of the time-frequency spectrograms. The results showed that the classifier achieved a satisfactory performance (98.9% accuracy) and could extract robust brain voxel information. The highly discriminative power voxels were mainly concentrated in the left inferior orbital frontal gyrus, the bilateral postcentral gyri, and the bilateral paracentral lobules. This study provides a novel insight into the different functional patterns between methamphetamine abstainers and healthy controls. It also elucidates the pathological mechanism of methamphetamine abstainers from the view of time-frequency spectrograms.

A CNN Deep Local and Global ASD Classification Approach with Continuous Wavelet Transform Using Task-Based FMRI

Autism spectrum disorder (ASD) is a neurodegenerative disorder characterized by lingual and social disabilities. The autism diagnostic observation schedule is the current gold standard for ASD diagnosis. Developing objective computer aided technologies for ASD diagnosis with the utilization of brain imaging modalities and machine learning is one of main tracks in current studies to understand autism. Task-based fMRI demonstrates the functional activation in the brain by measuring blood oxygen level-dependent (BOLD) variations in response to certain tasks. It is believed to hold discriminant features for autism. A novel computer aided diagnosis (CAD) framework is proposed to classify 50 ASD and 50 typically developed toddlers with the adoption of CNN deep networks. The CAD system includes both local and global diagnosis in a response to speech task. Spatial dimensionality reduction with region of interest selection and clustering has been utilized. In addition, the proposed framework performs discriminant feature extraction with continuous wavelet transform. Local diagnosis on cingulate gyri, superior temporal gyrus, primary auditory cortex and angular gyrus achieves accuracies ranging between 71% and 80% with a four-fold cross validation technique. The fused global diagnosis achieves an accuracy of 86% with 82% sensitivity, 92% specificity. A brain map indicating ASD severity level for each brain area is created, which contributes to personalized diagnosis and treatment plans.

A robust DWT-CNN-based CAD system for early diagnosis of autism using task-based fMRI

PURPOSE

Task-based fMRI (TfMRI) is a diagnostic imaging modality for observing the effects of a disease or other condition on the functional activity of the brain. Autism spectrum disorder (ASD) is a pervasive developmental disorder associated with impairments in social and linguistic abilities. Machine learning algorithms have been widely utilized for brain imaging aiming for objective ASD diagnostics. Recently, deep learning methods have been gaining more attention for fMRI classification. The goal of this paper is to develop a convolutional neural network (CNN)-based framework to help in global diagnosis of ASD using TfMRI data that are collected from a response to speech experiment.

METHODS

To achieve this goal, the proposed framework adopts a novel imaging marker integrating both spatial and temporal information that are related to the functional activity of the brain. The developed pipeline consists of three main components. In the first step, the collected TfMRI data are preprocessed and parcellated using the Harvard-Oxford probabilistic atlas included with the fMRIB Software Library (FSL). Second, a group analysis using FSL is performed between ASD and typically developing (TD) children to identify significantly activated brain areas in response to the speech task. In order to reduce brain spatial dimensionality, a K-means clustering technique is performed on such significant brain areas. Informative blood oxygen level-dependent (BOLD) signals are extracted from each cluster. A compression step for each extracted BOLD signal using discrete wavelet transform (DWT) has been proposed. The adopted wavelets are similar to the expected hemodynamic response which enables DWT to compress the BOLD signal while highlighting its activation information. Finally, a deep learning 2D CNN network is used to classify the patients as ASD or TD based on extracted features from the previous step.

RESULTS

Preliminary results on 100 TfMRI dataset (50 ASD, 50 TD) obtain 80% correct global classification using tenfold cross validation (with sensitivity = 84%, specificity = 76%).

CONCLUSION

The experimental results show the high accuracy of the proposed framework and hold promise for the presented framework as a helpful adjunct to currently used ASD diagnostic tools.

Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification

Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed.

Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity

Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain. We propose to model heterogeneous patterns of functional network differences using a demographic-guided attention (DGA) mechanism for recurrent neural network models for prediction from functional magnetic resonance imaging (fMRI) time-series data. The context computed from the DGA head is used to help focus on the appropriate functional networks based on individual demographic information. We demonstrate improved classification on 3 subsets of the ABIDE I dataset used in published studies that have previously produced state-of-the-art results, evaluating performance under a leave-one-site-out cross-validation framework for better generalizeability to new data. Finally, we provide examples of interpreting functional network differences based on individual demographic variables.