Spatio-temporal deep learning method for ADHD fMRI classification

Enhanced ADHD classification through deep learning and dynamic resting state fMRI analysis

Attention Deficit Hyperactivity Disorder (ADHD) is characterized by deficits in attention, hyperactivity, and/or impulsivity. Resting-state functional connectivity analysis has emerged as a promising approach for ADHD classification using resting-state functional magnetic resonance imaging (rs-fMRI), although with limited accuracy. Recent studies have highlighted dynamic changes in functional connectivity patterns among ADHD children. In this study, we introduce Skip-Vote-Net, a novel deep learning-based network designed for classifying ADHD from typically developing children (TDC) by leveraging dynamic connectivity analysis on rs-fMRI data collected from 222 participants included in the NYU dataset within the ADHD-200 database. Initially, for each subject, functional connectivity matrices were constructed from overlapping segments using Pearson's correlation between mean time series of 116 regions of interest defined by the Automated Anatomical Labeling (AAL) 116 atlas. Skip-Vote-Net was then developed, employing a majority voting mechanism to classify ADHD/TDC children, as well as distinguishing between the two main subtypes: the inattentive subtype (ADHDI) and the predominantly combined subtype (ADHDC). The proposed method was evaluated across four classification scenarios: (1) two-class classification of ADHD from TD children using balanced data, (2) two-class classification between ADHD and TD children using unbalanced data, (3) two-class classification between ADHDI and ADHDC, and (4) three-class classification among ADHDI, ADHDC, and TD children. Using Skip-Vote-Net, we achieved mean classification accuracies of 97% ± 1.87 and 97.7% ± 2.2 for the balanced and unbalanced classification cases, respectively. Furthermore, the mean classification accuracy for discriminating between ADHDI and ADHDC reached 99.4% ± 1.21. Finally, the proposed method demonstrated an average accuracy of 98.86% ± 1.03 in classifying ADHDI, ADHDC, and TD children collectively. Our findings highlight the superior performance of Skip-Vote-Net over existing methods in the classification of ADHD, showcasing its potential as an effective diagnostic tool for identifying ADHD subtypes and distinguishing ADHD from typically developing children.

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.

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

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

Enhancing Major Depressive Disorder Diagnosis With Dynamic-Static Fusion Graph Neural Networks

Major Depressive Disorder (MDD) is a debilitating, complex mental condition with unclear mechanisms hindering diagnostic progress. Research links MDD to abnormal brain connectivity using functional magnetic resonance imaging (fMRI). Yet, existing fMRI-based MDD models suffer from limitations, including neglecting dynamic network traits, lacking interpretability, and struggling with small datasets. We present DSFGNN, a novel graph neural network framework addressing these issues for improved MDD diagnosis. DSFGNN employs a graph isomorphism encoder to model static and dynamic brain networks, achieving effective fusion of temporal and spatial information through a spatiotemporal attention mechanism, thereby enhancing interpretability. Furthermore, we incorporate a causal disentangling module and orthogonal regularization module to augment the model's expressiveness. We evaluate DSFGNN on the Rest-meta-MDD dataset, yielding superior results compared to the best baseline. Besides, extensive ablation studies and interpretability analysis confirm DSFGNN's effectiveness and potential for biomarker discovery.

Structural or/and functional MRI-based machine learning techniques for attention-deficit/hyperactivity disorder diagnosis: A systematic review and meta-analysis

BACKGROUND

The aim of this study was to investigate the diagnostic value of ML techniques based on sMRI or/and fMRI for ADHD.

METHODS

We conducted a comprehensive search (from database creation date to March 2024) for relevant English articles on sMRI or/and fMRI-based ML techniques for diagnosing ADHD. The pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), summary receiver operating characteristic (SROC) curve and area under the curve (AUC) were calculated to assess the diagnostic value of sMRI or/and fMRI-based ML techniques. The I2 test was used to assess heterogeneity and the source of heterogeneity was investigated by performing a meta-regression analysis. Publication bias was assessed using the Deeks funnel plot asymmetry test.

RESULTS

Forty-three studies were included in the systematic review, 27 of which were included in our meta-analysis. The pooled sensitivity and specificity of sMRI or/and fMRI-based ML techniques for the diagnosis of ADHD were 0.74 (95 % CI 0.65-0.81) and 0.75 (95 % CI 0.67-0.81), respectively. SROC curve showed that AUC was 0.81 (95 % CI 0.77-0.84). Based on these findings, the sMRI or/and fMRI-based ML techniques have relatively good diagnostic value for ADHD.

LIMITATIONS

Our meta-analysis specifically focused on ML techniques based on sMRI or/and fMRI studies. Since EEG-based ML techniques are also used for diagnosing ADHD, further systematic analyses are necessary to explore ML methods based on multimodal medical data.

CONCLUSION

sMRI or/and fMRI-based ML technique is a promising objective diagnostic method for ADHD.

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.

Attention-Like Multimodality Fusion With Data Augmentation for Diagnosis of Mental Disorders Using MRI

The globally rising prevalence of mental disorders leads to shortfalls in timely diagnosis and therapy to reduce patients' suffering. Facing such an urgent public health problem, professional efforts based on symptom criteria are seriously overstretched. Recently, the successful applications of computer-aided diagnosis approaches have provided timely opportunities to relieve the tension in healthcare services. Particularly, multimodal representation learning gains increasing attention thanks to the high temporal and spatial resolution information extracted from neuroimaging fusion. In this work, we propose an efficient multimodality fusion framework to identify multiple mental disorders based on the combination of functional and structural magnetic resonance imaging. A multioutput conditional generative adversarial network (GAN) is developed to address the scarcity of multimodal data for augmentation. Based on the augmented training data, the multiheaded gating fusion model is proposed for classification by extracting the complementary features across different modalities. The experiments demonstrate that the proposed model can achieve robust accuracies of 75.1 ± 1.5 %, 72.9 ± 1.1 %, and 87.2 ± 1.5 % for autism spectrum disorder (ASD), attention deficit/hyperactivity disorder, and schizophrenia, respectively. In addition, the interpretability of our model is expected to enable the identification of remarkable neuropathology diagnostic biomarkers, leading to well-informed therapeutic decisions.

Individualized prediction models in ADHD: a systematic review and meta-regression

There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.

Unveiling critical ADHD biomarkers in limbic system and cerebellum using a binary hypothesis testing approach

Attention deficit hyperactivity disorder (ADHD) is a common childhood developmental disorder. In recent years, pattern recognition methods have been increasingly applied to neuroimaging studies of ADHD. However, these methods often suffer from limited accuracy and interpretability, impeding their contribution to the identification of ADHD-related biomarkers. To address these limitations, we applied the amplitude of low-frequency fluctuation (ALFF) results for the limbic system and cerebellar network as input data and conducted a binary hypothesis testing framework for ADHD biomarker detection. Our study on the ADHD-200 dataset at multiple sites resulted in an average classification accuracy of 93%, indicating strong discriminative power of the input brain regions between the ADHD and control groups. Moreover, our approach identified critical brain regions, including the thalamus, hippocampal gyrus, and cerebellum Crus 2, as biomarkers. Overall, this investigation uncovered potential ADHD biomarkers in the limbic system and cerebellar network through the use of ALFF realizing highly credible results, which can provide new insights for ADHD diagnosis and treatment.

Deep social neuroscience: the promise and peril of using artificial neural networks to study the social brain

This review offers an accessible primer to social neuroscientists interested in neural networks. It begins by providing an overview of key concepts in deep learning. It then discusses three ways neural networks can be useful to social neuroscientists: (i) building statistical models to predict behavior from brain activity; (ii) quantifying naturalistic stimuli and social interactions; and (iii) generating cognitive models of social brain function. These applications have the potential to enhance the clinical value of neuroimaging and improve the generalizability of social neuroscience research. We also discuss the significant practical challenges, theoretical limitations and ethical issues faced by deep learning. If the field can successfully navigate these hazards, we believe that artificial neural networks may prove indispensable for the next stage of the field's development: deep social neuroscience.

Unsupervised contrastive graph learning for resting-state functional MRI analysis and brain disorder detection

Resting-state functional magnetic resonance imaging (rs-fMRI) helps characterize regional interactions that occur in the human brain at a resting state. Existing research often attempts to explore fMRI biomarkers that best predict brain disease progression using machine/deep learning techniques. Previous fMRI studies have shown that learning-based methods usually require a large amount of labeled training data, limiting their utility in clinical practice where annotating data is often time-consuming and labor-intensive. To this end, we propose an unsupervised contrastive graph learning (UCGL) framework for fMRI-based brain disease analysis, in which a pretext model is designed to generate informative fMRI representations using unlabeled training data, followed by model fine-tuning to perform downstream disease identification tasks. Specifically, in the pretext model, we first design a bi-level fMRI augmentation strategy to increase the sample size by augmenting blood-oxygen-level-dependent (BOLD) signals, and then employ two parallel graph convolutional networks for fMRI feature extraction in an unsupervised contrastive learning manner. This pretext model can be optimized on large-scale fMRI datasets, without requiring labeled training data. This model is further fine-tuned on to-be-analyzed fMRI data for downstream disease detection in a task-oriented learning manner. We evaluate the proposed method on three rs-fMRI datasets for cross-site and cross-dataset learning tasks. Experimental results suggest that the UCGL outperforms several state-of-the-art approaches in automated diagnosis of three brain diseases (i.e., major depressive disorder, autism spectrum disorder, and Alzheimer's disease) with rs-fMRI data.

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.

Functional brain network identification and fMRI augmentation using a VAE-GAN framework

Recently, deep learning models have achieved superior performance for mapping functional brain networks from functional magnetic resonance imaging (fMRI) data compared with traditional methods. However, due to the lack of sufficient data and the high dimensionality of brain volume, deep learning models of fMRI tend to suffer from overfitting. In addition, existing methods rarely studied fMRI data augmentation and its application. To address these issues, we developed a VAE-GAN framework that combined a VAE (variational auto-encoder) with a GAN (generative adversarial net) for functional brain network identification and fMRI augmentation. As a generative model, the VAE-GAN models the distribution of fMRI so that it enables the extraction of more generalized features, and thus relieve the overfitting issue. The VAE-GAN is easier to train on fMRI than a standard GAN since it uses latent variables from VAE to generate fake data rather than relying on random noise that is used in a GAN, and it can generate higher quality of fake data than VAE since the discriminator can promote the training of the generator. In other words, the VAE-GAN inherits the advantages of VAE and GAN and avoids their limitations in modeling of fMRI data. Extensive experiments on task fMRI datasets from HCP have proved the effectiveness and superiority of the proposed VAE-GAN framework for identifying both temporal features and functional brain networks compared with existing models, and the quality of fake data is higher than those from VAE and GAN. The results on resting state fMRI of Attention Deficit Hyperactivity Disorder (ADHD)-200 dataset further demonstrated that the fake data generated by the VAE-GAN can help improve the performance of brain network modeling and ADHD classification.

Seed correlation analysis based on brain region activation for ADHD diagnosis in a large-scale resting state data set

Background

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder of multifactorial pathogenesis, which is often accompanied by dysfunction in several brain functional connectivity. Resting-state functional MRI have been used in ADHD, and they have been proposed as a possible biomarker of diagnosis information. This study's primary aim was to offer an effective seed-correlation analysis procedure to investigate the possible biomarker within resting state brain networks as diagnosis information.

Method

Resting-state functional magnetic resonance imaging (rs-fMRI) data of 149 childhood ADHD were analyzed. In this study, we proposed a two-step hierarchical analysis method to extract functional connectivity features and evaluation by linear classifiers and random sampling validation.

Result

The data-driven method-ReHo provides four brain regions (mPFC, temporal pole, motor area, and putamen) with regional homogeneity differences as second-level seeds for analyzing functional connectivity differences between distant brain regions. The procedure reduces the difficulty of seed selection (location, shape, and size) in estimations of brain interconnections, improving the search for an effective seed; The features proposed in our study achieved a success rate of 83.24% in identifying ADHD patients through random sampling (saving 25% as the test set, while the remaining data was the training set) validation (using a simple linear classifier), surpassing the use of traditional seeds.

Conclusion

This preliminary study examines the feasibility of diagnosing ADHD by analyzing the resting-state fMRI data from the ADHD-200 NYU dataset. The data-driven model provides a precise way to find reliable seeds. Data-driven models offer precise methods for finding reliable seeds and are feasible across different datasets. Moreover, this phenomenon may reveal that using a data-driven approach to build a model specific to a single data set may be better than combining several data and creating a general model.

Insight into ADHD diagnosis with deep learning on Actimetry: Quantitative interpretation of occlusion maps in age and gender subgroups

Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD.

OBJECTIVE

This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations.

METHODS

Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity.

RESULTS

Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population.

CONCLUSION

The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized.

SIGNIFICANCE

Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.

A review of visual sustained attention: neural mechanisms and computational models

Sustained attention is one of the basic abilities of humans to maintain concentration on relevant information while ignoring irrelevant information over extended periods. The purpose of the review is to provide insight into how to integrate neural mechanisms of sustained attention with computational models to facilitate research and application. Although many studies have assessed attention, the evaluation of humans' sustained attention is not sufficiently comprehensive. Hence, this study provides a current review on both neural mechanisms and computational models of visual sustained attention. We first review models, measurements, and neural mechanisms of sustained attention and propose plausible neural pathways for visual sustained attention. Next, we analyze and compare the different computational models of sustained attention that the previous reviews have not systematically summarized. We then provide computational models for automatically detecting vigilance states and evaluation of sustained attention. Finally, we outline possible future trends in the research field of sustained attention.

fMRI-Based Alzheimer's Disease Detection Using the SAS Method with Multi-Layer Perceptron Network

In the present scenario, Alzheimer's Disease (AD) is one of the incurable neuro-degenerative disorders, which accounts for nearly 60% to 70% of dementia cases. Currently, several machine-learning approaches and neuroimaging modalities are utilized for diagnosing AD. Among the available neuroimaging modalities, functional Magnetic Resonance Imaging (fMRI) is extensively utilized for studying brain activities related to AD. However, analyzing complex brain structures in fMRI is a time-consuming and complex task; so, a novel automated model was proposed in this manuscript for early diagnosis of AD using fMRI images. Initially, the fMRI images are acquired from an online dataset: Alzheimer's Disease Neuroimaging Initiative (ADNI). Further, the quality of the acquired fMRI images was improved by implementing a normalization technique. Then, the Segmentation by Aggregating Superpixels (SAS) method was implemented for segmenting the brain regions (AD, Normal Controls (NC), Mild Cognitive Impairment (MCI), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI), and Significant Memory Concern (SMC)) from the denoised fMRI images. From the segmented brain regions, feature vectors were extracted by employing Gabor and Gray Level Co-Occurrence Matrix (GLCM) techniques. The obtained feature vectors were dimensionally reduced by implementing Honey Badger Optimization Algorithm (HBOA) and fed to the Multi-Layer Perceptron (MLP) model for classifying the fMRI images as AD, NC, MCI, EMCI, LMCI, and SMC. The extensive investigation indicated that the presented model attained 99.44% of classification accuracy, 88.90% of Dice Similarity Coefficient (DSC), 90.82% of Jaccard Coefficient (JC), and 88.43% of Hausdorff Distance (HD). The attained results are better compared with the conventional segmentation and classification models.

Spatial-temporal data-augmentation-based functional brain network analysis for brain disorders identification

Introduction

Due to the lack of devices and the difficulty of gathering patients, the small sample size is one of the most challenging problems in functional brain network (FBN) analysis. Previous studies have attempted to solve this problem of sample limitation through data augmentation methods, such as sample transformation and noise addition. However, these methods ignore the unique spatial-temporal information of functional magnetic resonance imaging (fMRI) data, which is essential for FBN analysis.

Methods

To address this issue, we propose a spatial-temporal data-augmentation-based classification (STDAC) scheme that can fuse the spatial-temporal information, increase the samples, while improving the classification performance. Firstly, we propose a spatial augmentation module utilizing the spatial prior knowledge, which was ignored by previous augmentation methods. Secondly, we design a temporal augmentation module by random discontinuous sampling period, which can generate more samples than former approaches. Finally, a tensor fusion method is used to combine the features from the above two modules, which can make efficient use of spatial-temporal information of fMRI simultaneously. Besides, we apply our scheme to different types of classifiers to verify the generalization performance. To evaluate the effectiveness of our proposed scheme, we conduct extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and REST-meta-MDD Project (MDD) dataset.

Results

Experimental results show that the proposed scheme achieves superior classification accuracy (ADNI: 82.942%, MDD: 63.406%) and feature interpretation on the benchmark datasets.

Discussion

The proposed STDAC scheme, utilizing both spatial and temporal information, can generate more diverse samples than former augmentation methods for brain disorder classification and analysis.

Machine Learning and MRI-based Diagnostic Models for ADHD: Are We There Yet?

OBJECTIVE

Machine learning (ML) has been applied to develop magnetic resonance imaging (MRI)-based diagnostic classifiers for attention-deficit/hyperactivity disorder (ADHD). This systematic review examines this literature to clarify its clinical significance and to assess the implications of the various analytic methods applied.

METHODS

A comprehensive literature search on MRI-based diagnostic classifiers for ADHD was performed and data regarding the utilized models and samples were gathered.

RESULTS

We found that, although most studies reported the classification accuracies, they varied in choice of MRI modalities, ML models, cross-validation and testing methods, and sample sizes. We found that the accuracies of cross-validation methods inflated the performance estimation compared with those of a held-out test, compromising the model generalizability. Test accuracies have increased with publication year but were not associated with training sample sizes. Improved test accuracy over time was likely due to the use of better ML methods along with strategies to deal with data imbalances.

CONCLUSION

Ultimately, large multi-modal imaging datasets, and potentially the combination with other types of data, like cognitive data and/or genetics, will be essential to achieve the goal of developing clinically useful imaging classification tools for ADHD in the future.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

Diffusion Kernel Attention Network for Brain Disorder Classification

Constructing and analyzing functional brain networks (FBN) has become a promising approach to brain disorder classification. However, the conventional successive construct-and-analyze process would limit the performance due to the lack of interactions and adaptivity among the subtasks in the process. Recently, Transformer has demonstrated remarkable performance in various tasks, attributing to its effective attention mechanism in modeling complex feature relationships. In this paper, for the first time, we develop Transformer for integrated FBN modeling, analysis and brain disorder classification with rs-fMRI data by proposing a Diffusion Kernel Attention Network to address the specific challenges. Specifically, directly applying Transformer does not necessarily admit optimal performance in this task due to its extensive parameters in the attention module against the limited training samples usually available. Looking into this issue, we propose to use kernel attention to replace the original dot-product attention module in Transformer. This significantly reduces the number of parameters to train and thus alleviates the issue of small sample while introducing a non-linear attention mechanism to model complex functional connections. Another limit of Transformer for FBN applications is that it only considers pair-wise interactions between directly connected brain regions but ignores the important indirect connections. Therefore, we further explore diffusion process over the kernel attention to incorporate wider interactions among indirectly connected brain regions. Extensive experimental study is conducted on ADHD-200 data set for ADHD classification and on ADNI data set for Alzheimer's disease classification, and the results demonstrate the superior performance of the proposed method over the competing methods.

Towards high-accuracy classifying attention-deficit/hyperactivity disorders using CNN-LSTM model

OBJECTIVE

The neurocognitive attention functions involve the cooperation of multiple brain regions, and the defects in the cooperation will lead to attention-deficit/hyperactivity disorder (ADHD), which is one of the most common neuropsychiatric disorders for children. The current ADHD diagnosis is mainly based on a subjective evaluation that is easily biased by the experience of the clinicians and lacks the support of objective indicators. The purpose of this study is to propose a method that can effectively identify children with ADHD.

APPROACH

In this study, we proposed a CNN-LSTM model to solve the three-class problems of classifying ADHD, attention deficit disorder (ADD) and healthy children, based on a public EEG dataset that includes event-related potential (ERP) EEG signals of 144 children. The convolution visualization and saliency map methods were used to observe the features automatically extracted by the proposed model, which could intuitively explain how the model distinguished different groups.

MAIN RESULTS

The results showed that our CNN-LSTM model could achieve an accuracy as high as 98.23% in a 5-fold cross-validation method, which was significantly better than the current state-of-the-art CNN models. The features extracted by the proposed model were mainly located in the frontal and central areas, with significant differences in the time period mappings among the three different groups. The P300 and contingent negative variation (CNV) in the frontal lobe had the largest decrease in the healthy control (HC) group, and the ADD group had the smallest decrease. In the central area, only the HC group had a significant negative oscillation of CNV waves.

SIGNIFICANCE

The results of this study suggest that the CNN-LSTM model can effectively identify children with ADHD and its subtypes. The visualized features automatically extracted by this model could better explain the differences in the ERP response among different groups, which is more convincing than previous studies, and it could be used as more reliable neural biomarkers to help with more accurate diagnosis in the clinics.

A semi-supervised classification RBM with an improved fMRI representation algorithm

BACKGROUND AND OBJECTIVE

Training an effective and robust supervised learning classifier is not easy due to the limitations of acquiring and labeling considerable human functional magnetic resonance imaging (fMRI) data. Semi-supervised learning uses unlabeled data for feature learning and combines them into labeled data to build better classification models.

METHODS

Since no premises or assumptions are required, a restricted Boltzmann machine (RBM) is suitable for learning data representation of neuroimages. In our study, an improved fMRI representation algorithm with a hybrid L1/L2 regularization method (HRBM) was proposed to optimize the original model for sparsity. Different from common semi-supervised classification models that treat feature learning and classification as two separate training steps, we then constructed a new semi-supervised classification RBM based on a joint training algorithm with HRBM, named Semi-HRBM. This joint training algorithm jointly trains the objective function of feature learning and classification process, so that the learned features can effectively represent the original fMRI data and adapt to the classification tasks.

RESULTS

This study uses fMRI data to identify categories of visual stimuli. In the fMRI data classification task under four visual stimuli (house, face, car, and cat), our HRBM has satisfactory feature representation capabilities and better performance for multiple classification tasks. Taking the supervised RBM (sup-RBM) as an example, our Semi-HRBM classification model improves the average accuracy of the four-classification task by 7.68%, and improves the average F1 score of each visual stimulus task by 8.90%. In addition, the generalization ability of the model was also improved.

CONCLUSION

This research might contribute to enrich solutions for insufficiently labeled neuroimaging samples, which could help to identify complex brain states under different stimuli or tasks.

Accelerated 3D myelin water imaging using joint spatio-temporal reconstruction

PURPOSE

To enable acceleration in 3D multi-echo gradient echo (mGRE) acquisition for myelin water imaging (MWI) by combining joint parallel imaging (JPI) and joint deep learning (JDL).

METHODS

We implemented a multistep reconstruction process using both advanced parallel imaging and deep learning network which can utilize joint spatiotemporal components between the multi-echo images to further accelerate 3D mGRE acquisition for MWI. In the first step, JPI was performed to estimate missing k-space lines. Next, JDL was implemented to reduce residual artifacts and produce high-fidelity reconstruction by using variable splitting optimization consisting of spatiotemporal denoiser block, data consistency block, and weighted average block. The proposed method was evaluated for MWI with 2D Cartesian uniform under-sampling for each echo, enabling scan times of up to approximately 2 min for 2 mm × 2 mm × 2 mm $2\ {\rm mm} \times 2\ {\rm mm} \times 2\ {\rm mm}$ 3D coverage.

RESULTS

The proposed method showed acceptable MWI quality with improved quantitative values compared to both JPI and JDL methods individually. The improved performance of the proposed method was demonstrated by the low normalized mean-square error and high-frequency error norm values of the reconstruction with high similarity to the fully sampled MWI.

CONCLUSION

Joint spatiotemporal reconstruction approach by combining JPI and JDL can achieve high acceleration factors for 3D mGRE-based MWI.

LARNet-STC: Spatio-temporal orthogonal region selection network for laryngeal closure detection in endoscopy videos

The vocal folds (VFs) are a pair of muscles in the larynx that play a critical role in breathing, swallowing, and speaking. VF function can be adversely affected by various medical conditions including head or neck injuries, stroke, tumor, and neurological disorders. In this paper, we propose a deep learning system for automated detection of laryngeal adductor reflex (LAR) events in laryngeal endoscopy videos to enable objective, quantitative analysis of VF function. The proposed deep learning system incorporates our novel orthogonal region selection network and temporal context. This network learns to directly map its input to a VF open/close state without first segmenting or tracking the VF region. This one-step approach drastically reduces manual annotation needs from labor-intensive segmentation masks or VF motion tracks to frame-level class labels. The proposed spatio-temporal network with an orthogonal region selection subnetwork allows integration of local image features, global image features, and VF state information in time for robust LAR event detection. The proposed network is evaluated against several network variations that incorporate temporal context and is shown to lead to better performance. The experimental results show promising performance for automated, objective, and quantitative analysis of LAR events from laryngeal endoscopy videos with over 90% and 99% F1 scores for LAR and non-LAR frames respectively.

MRI Segmentation of Brain Tissue and Course Classification in Alzheimer’s Disease

Alzheimer’s disease (AD) is one of the most common diseases causing cognitive impairment in middle-aged and elderly people, and the high cost of the disease poses a challenge for health systems to cope with the expected increasing number of cases in the future. With the advance of aging of the society, China has the largest number of Alzheimer’s disease patients in the world. Therefore, how to diagnose Alzheimer’s disease early and accurately and intervene positively is an urgent problem. In this paper, the improved MultiRes + UNet network is used to effectively segment the brain tissue in the preprocessing. This method expands the convolutional field by null convolution to integrate the global information, mitigates the differences between encoder–decoder features by using MultiRes block and Res path structure, greatly reducing the memory requirement, and improving its accuracy, applicability, and robustness. The non-local means the attention model is introduced to make the mapped organization categories free from noise interference. In the classification problem, this paper adopts the improved VoxCNN network model for binary classification of AD, EMCI, LMCI, and NC. Experiments showed that the model classification performance and the accuracy rate improved significantly with the combined effect of the improved MultiRes + UNet network and VoxCNN network, the binary classification accuracy was 98.35% for AD vs. NC, 89.46% for AD vs. LMCI, 83.95% for LMCI vs. EMCI, and 88.27% for EMCI vs. NC.

Attention module improves both performance and interpretability of four-dimensional functional magnetic resonance imaging decoding neural network

Decoding brain cognitive states from neuroimaging signals is an important topic in neuroscience. In recent years, deep neural networks (DNNs) have been recruited for multiple brain state decoding and achieved good performance. However, the open question of how to interpret the DNN black box remains unanswered. Capitalizing on advances in machine learning, we integrated attention modules into brain decoders to facilitate an in‐depth interpretation of DNN channels. A four‐dimensional (4D) convolution operation was also included to extract temporo‐spatial interaction within the fMRI signal. The experiments showed that the proposed model obtains a very high accuracy (97.4%) and outperforms previous researches on the seven different task benchmarks from the Human Connectome Project (HCP) dataset. The visualization analysis further illustrated the hierarchical emergence of task‐specific masks with depth. Finally, the model was retrained to regress individual traits within the HCP and to classify viewing images from the BOLD5000 dataset, respectively. Transfer learning also achieves good performance. Further visualization analysis shows that, after transfer learning, low‐level attention masks remained similar to the source domain, whereas high‐level attention masks changed adaptively. In conclusion, the proposed 4D model with attention module performed well and facilitated interpretation of DNNs, which is helpful for subsequent research.

ADHD classification using auto-encoding neural network and binary hypothesis testing

Attention Deficit Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental disease of school-age children. Early diagnosis is crucial for ADHD treatment, wherein its neurobiological diagnosis (or classification) is helpful and provides the objective evidence to clinicians. The existing ADHD classification methods suffer two problems, i.e., insufficient data and feature noise disturbance from other associated disorders. As an attempt to overcome these difficulties, a novel deep-learning classification architecture based on a binary hypothesis testing framework and a modified auto-encoding (AE) network is proposed in this paper. The binary hypothesis testing framework is introduced to cope with insufficient data of ADHD database. Brain functional connectivities (FCs) of test data (without seeing their labels) are incorporated during feature selection along with those of training data and affect the sequential deep learning procedure under binary hypotheses. On the other hand, the modified AE network is developed to capture more effective features from training data, such that the difference of inter- and intra-class variability scores between binary hypotheses can be enlarged and effectively alleviate the disturbance of feature noise. On the test of ADHD-200 database, our method significantly outperforms the existing classification methods. The average accuracy reaches 99.6% with the leave-one-out cross validation. Our method is also more robust and practically convenient for ADHD classification due to its uniform parameter setting across various datasets.

Spatial Patterns and Development Characteristics of China's Postgraduate Education

Using four types of publicly available datasets and ArcGIS software, the authors identify the spatial characteristics of postgraduate education in China at three scales: comprehensive economic zone, provincial, and city. They also employ geographically weighted regression and ordinary least squares to study the factors influencing the spatial pattern of postgraduate education in Gin at the city scale. The findings show that the number of postgraduate education institutions increases as the longitude of a city increases, but the number decreases from coast to inland. Second, postgraduate education institutions tend to group together in provincial capitals and megacities. Finally, GDP, per capita GDP, population size, local income, and total retail sales of consumer goods significantly impact postgraduate education development. The study contributes to the literature and provides insights for practitioners in promoting urban planning and infrastructure development.

Volume Reduction Techniques for the Classification of Independent Components of rs-fMRI Data: a Study with Convolutional Neural Networks

In the last decade, neurosciences have had an increasing interest in resting state functional magnetic resonance imaging (rs-fMRI) as a result of its advantages, such as high spatial resolution, compared to other brain exploration techniques. To improve the technique, the elimination of artifacts through Independent Components Analysis (ICA) has been proposed, as this can separate neural signal and noise, opening possibilities for automatic classification. The main classification techniques have focused on processes based on typical machine learning. However, there are currently more robust approaches such as convolutional neural networks, which can deal with complex problems directly from the data without feature selection and even with data that does not have a simple interpretation, being limited by the amount of data necessary for training and its high computational cost. This research focused on studying four methods of volume reduction mitigating the computational cost for the training of 3 models based on convolutional neural networks. One of the reduction techniques is a novel approach that we call Reduction by Consecutive Binary Patterns (RCBP), which was shown to preserve the spatial features of the independent components. In addition, the RCBP showed networks in components associated with neuronal activity more clearly. The networks achieved accuracy above 98 % in classification, and one network was even found to be over 99 % accurate, outperforming most machine learning-based classification algorithms.

Spatiotemporal trajectories in resting-state FMRI revealed by convolutional variational autoencoder

Recent resting-state fMRI studies have shown that brain activity exhibits temporal variations in functional connectivity by using various approaches including sliding window correlation, co-activation patterns, independent component analysis, quasi-periodic patterns, and hidden Markov models. These methods often model the brain activity as a discretized hopping among several brain states that are defined by the spatial configurations of network activity. However, the discretized states are merely a simplification of what is likely to be a continuous process, where each network evolves over time following its unique path. To model these characteristic spatiotemporal trajectories, we trained a variational autoencoder using rs-fMRI data and evaluated the spatiotemporal features of the latent variables obtained from the trained networks. Our results suggest that there are a relatively small number of approximately orthogonal whole-brain spatiotemporal patterns that capture the most prominent features of rs-fMRI data, which can serve as the building blocks to construct all possible spatiotemporal dynamics in resting state fMRI. These spatiotemporal patterns provide insight into how activity flows across the brain in concordance with known network structures and functional connectivity gradients.

Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors

Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method's performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.

Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review

Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer's disease (AD), Parkinson's disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

A Novel Knowledge Distillation-Based Feature Selection for the Classification of ADHD

Attention Deficit Hyperactivity Disorder (ADHD) is a brain disorder with characteristics such as lack of concentration, excessive fidgeting, outbursts of emotions, lack of patience, difficulty in organizing tasks, increased forgetfulness, and interrupting conversation, and it is affecting millions of people worldwide. There is, until now, not a gold standard test using which an ADHD expert can differentiate between an individual with ADHD and a healthy subject, making accurate diagnosis of ADHD a challenging task. We are proposing a Knowledge Distillation-based approach to search for discriminating features between the ADHD and healthy subjects. Learned embeddings from a large neural network, trained on the functional connectivity features, were fed to one hidden layer Autoencoder for reproduction of the embeddings using the same connectivity features. Finally, a forward feature selection algorithm was used to select a combination of most discriminating features between the ADHD and the Healthy Controls. We achieved promising classification results for each of the five individual sites. A combined accuracy of 81% in KKI, 60% Peking, 56% in NYU, 64% NI, and 56% OHSU and individual site wise accuracy of 72% in KKI, 60% Peking, 73% in NYU, 70% NI, and 71% OHSU were obtained using our extracted features. Our results also outperformed state-of-the-art methods in literature which validates the efficacy of our proposed approach.

Key Intrinsic Connectivity Networks for Individual Identification With Siamese Long Short-Term Memory

In functional magnetic resonance imaging (fMRI) analysis, many studies have been conducted on inter-subject variability as well as intra-subject reproducibility. These studies indicate that fMRI could have unique characteristics for individuals. In this study, we hypothesized that the dynamic information during 1 min of fMRI was unique and repetitive enough for each subject, so we applied long short-term memory (LSTM) using initial time points of dynamic resting-state fMRI for individual identification. Siamese network is used to obtain robust individual identification performance without additional learning on a new dataset. In particular, by adding a new structure called region of interest–wise average pooling (RAP), individual identification performance could be improved, and key intrinsic connectivity networks (ICNs) for individual identification were also identified. The average performance of individual identification was 97.88% using the test dataset in eightfold cross-validation analysis. Through the visualization of features learned by Siamese LSTM with RAP, ICNs spanning the parietal region were observed as the key ICNs in identifying individuals. These results suggest the key ICNs in fMRI could represent individual uniqueness.

A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity

Brain connectivity alterations associated with mental disorders have been widely reported in both functional MRI (fMRI) and diffusion MRI (dMRI). However, extracting useful information from the vast amount of information afforded by brain networks remains a great challenge. Capturing network topology, graph convolutional networks (GCNs) have demonstrated to be superior in learning network representations tailored for identifying specific brain disorders. Existing graph construction techniques generally rely on a specific brain parcellation to define regions-of-interest (ROIs) to construct networks, often limiting the analysis into a single spatial scale. In addition, most methods focus on the pairwise relationships between the ROIs and ignore high-order associations between subjects. In this letter, we propose a mutual multi-scale triplet graph convolutional network (MMTGCN) to analyze functional and structural connectivity for brain disorder diagnosis. We first employ several templates with different scales of ROI parcellation to construct coarse-to-fine brain connectivity networks for each subject. Then, a triplet GCN (TGCN) module is developed to learn functional/structural representations of brain connectivity networks at each scale, with the triplet relationship among subjects explicitly incorporated into the learning process. Finally, we propose a template mutual learning strategy to train different scale TGCNs collaboratively for disease classification. Experimental results on 1,160 subjects from three datasets with fMRI or dMRI data demonstrate that our MMTGCN outperforms several state-of-the-art methods in identifying three types of brain disorders.