The Neuro Bureau ADHD-200 Preprocessed repository

Hierarchical feature extraction on functional brain networks for autism spectrum disorder identification with resting-state fMRI data

Autism Spectrum Disorder (ASD) is a pervasive developmental disorder of the central nervous system, primarily manifesting in childhood. It is characterized by atypical and repetitive behaviors. Conventional diagnostic methods mainly rely on questionnaire surveys and behavioral observations, which are prone to misdiagnosis due to their subjective nature. With advancements in medical imaging, MR imaging-based diagnostics have emerged as a more objective alternative. In this paper, we propose a Hierarchical Neural Network model for ASD identification, termed ASD-HNet, which hierarchically extracts features from functional brain networks based on resting-state functional magnetic resonance imaging (rs-fMRI) data. This hierarchical approach enhances the extraction of brain representations, improving diagnostic accuracy and aiding in the identification of brain regions associated with ASD. Specifically, features are extracted at three levels, i.e., the local region of interest (ROI) scale, the community scale, and the global representation scale. At the ROI scale, graph convolution is employed to transfer features between ROIs. At the community scale, functional gradients are introduced, and a K-Means clustering algorithm is applied to group ROIs with similar functional gradients into communities. Features from ROIs within the same community are then extracted to characterize the communities. At the global representation scale, we extract global features from the whole community-scale brain networks to represent the entire brain. We validate the effectiveness of the ASD-HNet model using the publicly available Autism Brain Imaging Data Exchange I (ABIDE-I) dataset, ADHD-200,dataset and ABIDE-II dataset. Extensive experimental results demonstrate that ASD-HNet outperforms existing baseline methods. The code is available at https://github.com/LYQbyte/ASD-HNet.

Deformable image registration with strategic integration pyramid framework for brain MRI

Medical image registration plays a crucial role in medical imaging, with a wide range of clinical applications. In this context, brain MRI registration is commonly used in clinical practice for accurate diagnosis and treatment planning. In recent years, deep learning-based deformable registration methods have achieved remarkable results. However, existing methods have not been flexible and efficient in handling the feature relationships of anatomical structures at different levels when dealing with large deformations. To address this limitation, we propose a novel strategic integration registration network based on the pyramid structure. Our strategy mainly includes two aspects of integration: fusion of features at different scales, and integration of different neural network structures. Specifically, we design a CNN encoder and a Transformer decoder to efficiently extract and enhance both global and local features. Moreover, to overcome the error accumulation issue inherent in pyramid structures, we introduce progressive optimization iterations at the lowest scale for deformation field generation. This approach more efficiently handles the spatial relationships of images while improving accuracy. We conduct extensive evaluations across multiple brain MRI datasets, and experimental results show that our method outperforms other deep learning-based methods in terms of registration accuracy and robustness.

Analysis of experiments with high frequency time series responses and the implications for power and sample size

Given more accessible non-invasive measuring devices, experimental response can now be observed as high-dimensional and high-frequency time series. Amidst the complex dependence structure in the data analysis, sample size determination and power analysis remain to be the key thematic focus of statistical inference. The issue is confounded with the complexity of time lag structure and phase shift usually observed in a non-uniform but normal process typically present in medical imaging data. To address these issues in case-control studies, responses can be analyzed to obtain evidence of group differences through time series clustering based on dynamic time warping. The warping of multiple time series provides a flexible distance measure robust to time point concurrence. Time series clustering partitions experimental units into groups, enabling the computation of distances to measure effect size through sum of squares of pairwise distances in warped time series.Time series clustering provides an alternative to analysis of variance when experimental responses are high-frequency time series data. Kernel regression is formulated to link sample size, effect size, power of the test, and level of significance accounting for the structure of the data generating process of the time series responses. This provides a strategy for clinicians to optimize the power of the test that can be achieved with a minimal sample size for this experimental setup. Time series clustering method is able to differentiate case and control groups in the simulated data and in the ADHD-200 fMRI dataset. The distance measured between two or more groups of time series can be used to determine sample size for a target power.

Transforming 3D MRI to 2D Feature Maps Using Pre-Trained Models for Diagnosis of Attention Deficit Hyperactivity Disorder

Background: According to the World Health Organization (WHO), approximately 5% of children and 2.5% of adults suffer from attention deficit hyperactivity disorder (ADHD). This disorder can have significant negative consequences on people's lives, particularly children. In recent years, methods based on artificial intelligence and neuroimaging techniques, such as MRI, have made significant progress, paving the way for development of more reliable diagnostic tools. In this proof of concept study, our aim was to investigate the potential utility of neuroimaging data and clinical information in combination with a deep learning-based analytical approach, more precisely, a novel feature extraction technique for the diagnosis of ADHD with high accuracy. Methods: Leveraging the ADHD200 dataset, which encompasses demographic information and anatomical MRI scans collected from a diverse ADHD population, our study focused on developing modern deep learning-based diagnostic models. The data preprocessing employed a pre-trained Visual Geometry Group16 (VGG16) network to extract two-dimensional (2D) feature maps from three-dimensional (3D) anatomical MRI data to reduce computational complexity and enhance diagnostic power. The inclusion of personal attributes, such as age, gender, intelligence quotient, and handedness, strengthens the diagnostic models. Four deep-learning architectures-convolutional neural network 2D (CNN2D), CNN1D, long short-term memory (LSTM), and gated recurrent units (GRU)-were employed for analysis of the MRI data, with and without the inclusion of clinical characteristics. Results: A 10-fold cross-validation test revealed that the LSTM model, which incorporated both MRI data and personal attributes, had the best diagnostic performance among all tested models in the diagnosis of ADHD with an accuracy of 0.86 and area under the receiver operating characteristic (ROC) curve (AUC) score of 0.90. Conclusions: Our findings demonstrate that the proposed approach of extracting 2D features from 3D MRI images and integrating these features with clinical characteristics may be useful in the diagnosis of ADHD with high accuracy.

Topology-Guided Graph Masked Autoencoder Learning for Population-Based Neurodevelopmental Disorder Diagnosis

Exploring the pathogenic mechanisms of brain disorders within population is an important research in the field of neuroscience. Existing methods either combine clinical information to assist analysis or use data augmentation for sample expansion, ignoring the mining of individual information and the exploration of inter-individual associations in population. To solve these problems, this work proposes a novel approach for detecting abnormal neural circuits associated with brain diseases, named Topology-guided Graph Masked autoencoder Learning method (TGML), which focuses on individual representation and intra-population association, to achieve the effective diagnosis of brain diseases within the population. Concretely, the TGML comprises 1) the topology-guided group association module (T ${G}^{{2}}$ AM) that reconstructs the edges and update the initial population graph, 2) the intra-population interaction masked autoencoder network (IPI_MAE) captures the discriminative characteristics of subjects based on the novel Masked Autoencoder, which incorporates traditional masked autoencoders into a task-related process. The proposed method is evaluated on two neurodevelopmental disorder diagnosis tasks of Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD). The results show that the proposed TGML achieves significant improvements and surpasses the state-of-the-art methods.

Self-supervised learning for graph-structured data in healthcare applications: A comprehensive review

The increasing complexity and interconnectedness of healthcare data present numerous opportunities to improve prediction, diagnosis, and treatment. Graph-structured data, which represents entities and their relationships, is well-suited for modeling these complex connections. However, effectively utilizing this data often requires strong and efficient learning algorithms, especially when dealing with limited labeled data. Self-supervised learning (SSL) has emerged as a powerful paradigm for leveraging unlabeled data to learn effective representations. This paper presents a comprehensive review of SSL approaches specifically designed for graph-structured data in healthcare applications. We explore the challenges and opportunities associated with healthcare data and assess the effectiveness of SSL techniques in real-world healthcare applications. Our discussion encompasses various healthcare settings, such as disease prediction, medical image analysis, and drug discovery. We critically evaluate the performance of different SSL methods across these tasks, highlighting their strengths, limitations, and potential future research directions. To the best of our knowledge, this is the first comprehensive review of SSL applied to graph data in healthcare, providing valuable guidance for researchers and practitioners looking to leverage these techniques to enhance outcomes and drive progress in the field.

SFM-Net: Semantic Feature-Based Multi-Stage Network for Unsupervised Image Registration

It is difficult for general registration methods to establish the fine correspondence between images with complex anatomical structures. To overcome the above problem, this work presents SFM-Net, an unsupervised multi-stage semantic feature-based network. In addition to using the pixel-based similarity metrics, we propose a feature operator and emphasize a feature registration to improve the alignment of semantic related areas. Specifically, we design a two-stage training strategy, the intensity image registration stage and the semantic feature registration stage. The former is for valid semantic features learning and intensity-based coarse registration, while the latter is for semantic areas alignment, achieving fine transformation of anatomical structure. The same structure of both stages is composed of a dual-stream feature extraction module (DFEM) and a refined deformation field generation module (RDGM). Unlike the deep learning-based approaches that utilizing down-sampled encoder to extract features, DFEM constructed by dual-stream U-Net structure can capture semantic information in decoder feature for structural alignment. Different with approaches applying cascaded networks to learn deformation field, our proposed RDGM generates multi-scale deformation fields by performing a coarse-to-fine registration within a single network. Experiments on 3D brain MRI and liver CT datasets confirm that the proposed SFM-Net achieves accurate and diffeomorphic registration results, outperforming other state-of-the-art methods.

Reproducible Brain Charts: An open data resource for mapping brain development and its associations with mental health

Major mental disorders are increasingly understood as disorders of brain development. Large and heterogeneous samples are required to define generalizable links between brain development and psychopathology. To this end, we introduce the Reproducible Brain Charts (RBC), an open data resource that integrates data from 5 large studies of brain development in youth from three continents (N=6,346; 45% Female). Confirmatory bifactor models were used to create harmonized psychiatric phenotypes that capture major dimensions of psychopathology. Following rigorous quality assurance, neuroimaging data were carefully curated and processed using consistent pipelines in a reproducible manner with DataLad, the Configurable Pipeline for the Analysis of Connectomes (C-PAC), and FreeSurfer. Initial analyses of RBC data emphasize the benefit of careful quality assurance and data harmonization in delineating developmental effects and associations with psychopathology. Critically, all RBC data - including harmonized psychiatric phenotypes, unprocessed images, and fully processed imaging derivatives - are openly shared without a data use agreement via the International Neuroimaging Data-sharing Initiative. Together, RBC facilitates large-scale, reproducible, and generalizable research in developmental and psychiatric neuroscience.

Interpretable machine learning approaches for children's ADHD detection using clinical assessment data: an online web application deployment

BACKGROUND

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent mental disorder characterized by hyperactivity, impulsivity, and inattention. This study aims to develop a verifiable and interpretable machine learning model to identify ADHD and its subtypes in children using clinical assessment scales data.

METHODS

This study utilized the ADHD-200 dataset, including demographic data, Behavioral Rating Scale, and Wechsler Intelligence Scale assessments, to train and validate our models. The model's performance was evaluated using 10-fold cross-validation within the internal dataset, and the best model will be used for external validation. Seven machine learning models were evaluated. The SHapley Additive exPlanations (SHAP) method was employed for model interpretation. Finally, a web application will deploy the prediction model to provide ADHD probabilities based on user input.

RESULTS

The Random Forest (RF) model performing best in identifying ADHD and the Support Vector Machine (SVM) model excelling in distinguishing ADHD subtypes. The RF model achieved an AUC of 0.99 in 10-fold cross-validation and an AUC of 0.99 in external validation, and the SVM model achieved a micro-average AUC of 0.96 and an accuracy of 0.83 in internal validation and a micro-average AUC of 0.96 and an accuracy of 0.85 in external validation. We used SHAP to interpret the models, revealing that higher ADHD Index pushed the model towards ADHD classification. Additionally, lower IQ scores were correlated with a higher likelihood of ADHD, consistent with previous studies. The dependency analysis found that the model can identify different behavioral scales. We deployed the final model online using a web application and showed users how the model made decisions.

CONCLUSIONS

Our findings highlight the potential of using machine learning and clinical assessment scales to support the diagnosis and subtype identification of ADHD in children, offering a practical solution for improving diagnostic accuracy and efficiency in clinical settings.

Effective connectivity alterations of the triple network model in the co-occurrence of autism spectrum disorder and attention deficit hyperactivity disorder

Autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) are both highly prevalent disorders and frequently co-occur. The underlying neurological mechanisms of the co-occurrence of ASD and ADHD (ASD + ADHD) remain unknown. This study focuses on investigating the effective connectivity (EC) alterations within the triple network model in individuals with ASD + ADHD. Resting-state functional magnetic resonance imaging data were obtained from 44 individuals with ASD + ADHD, 60 individuals with ASD without ADHD (ASD-only), 35 individuals with ADHD without ASD (ADHD-only), and 81 healthy controls (HC) from the Autism Brain Imaging Data Exchange II and the ADHD-200 Sample database. Spectral dynamic causal modeling was employed to explore the EC alterations within and between the default mode network, salience network, and central executive network. Our analysis showed that compared to HC, ASD + ADHD, ASD-only, and ADHD-only exhibited both shared and disorder-specific EC alterations within the triple-network model. These results have potential clinical implications for identifying ASD + ADHD, facilitating diagnostic accuracy, guiding targeted treatment approaches, and informing etiological studies.

The Use of fMRI Regional Analysis to Automatically Detect ADHD Through a 3D CNN-Based Approach

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by a reduced attention span, hyperactivity, and impulsive behaviors, which typically manifest during childhood. This study employs functional magnetic resonance imaging (fMRI) to use spontaneous brain activity for classifying individuals with ADHD, focusing on a 3D convolutional neural network (CNN) architecture to facilitate the design of decision support systems. We developed a novel deep learning model based on 3D CNNs using the ADHD-200 database, which comprises datasets from NeuroImage (NI), New York University (NYU), and Peking University (PU). We used fractional amplitude of low-frequency fluctuations (fALFF) and regional homogeneity (ReHo) data in three dimensions and performed a fivefold cross-validation to address the dataset imbalance. We aimed to verify the efficacy of our proposed 3D CNN by contrasting it with a fully connected neural network (FCNN) architecture. The 3D CNN achieved accuracy rates of 76.19% (NI), 69.92% (NYU), and 70.77% (PU) for fALFF data. The FCNN model yielded lower accuracy rates across all datasets. For generalizability, we trained on NI and NYU datasets and tested on PU. The 3D CNN achieved 69.48% accuracy on fALFF outperforming the FCNN. Our results demonstrate that using 3D CNNs for classifying fALFF data is an effective approach for diagnosing ADHD. Also, FCNN confirmed the efficiency of the designed model.

MHNet: Multi-view High-Order Network for Diagnosing Neurodevelopmental Disorders Using Resting-State fMRI

Deep learning models have shown promise in diagnosing neurodevelopmental disorders (NDD) like ASD and ADHD. However, many models either use graph neural networks (GNN) to construct single-level brain functional networks (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial for NDD classification. We introduce a Multi-view High-order Network (MHNet) to capture hierarchical and high-order features from multi-view BFNs derived from rs-fMRI data for NDD prediction. MHNet has two branches: the Euclidean Space Features Extraction (ESFE) module and the Non-Euclidean Space Features Extraction (Non-ESFE) module, followed by a Feature Fusion-based Classification (FFC) module for NDD identification. ESFE includes a Functional Connectivity Generation (FCG) module and a High-order Convolutional Neural Network (HCNN) module to extract local and high-order features from BFNs in Euclidean space. Non-ESFE comprises a Generic Internet-like Brain Hierarchical Network Generation (G-IBHN-G) module and a High-order Graph Neural Network (HGNN) module to capture topological and high-order features in non-Euclidean space. Experiments on three public datasets show that MHNet outperforms state-of-the-art methods using both AAL1 and Brainnetome Atlas templates. Extensive ablation studies confirm the superiority of MHNet and the effectiveness of using multi-view fMRI information and high-order features. Our study also offers atlas options for constructing more sophisticated hierarchical networks and explains the association between key brain regions and NDD. MHNet leverages multi-view feature learning from both Euclidean and non-Euclidean spaces, incorporating high-order information from BFNs to enhance NDD classification performance.

EEG-Based ADHD Classification Using Autoencoder Feature Extraction and ResNet with Double Augmented Attention Mechanism

BACKGROUND

Attention-Deficit/Hyperactivity Disorder (ADHD) represents a widely prevalent and heterogeneous neurodevelopmental condition in pediatric populations, often exhibiting a substantial propensity to persist into adulthood. ADHD is a multifaceted disorder that resists straightforward diagnostic tests. Clinicians must invest substantial time and effort to secure an accurate diagnosis and implement effective treatment. ADHD diagnosis is primarily based on psychiatric tests, as there is currently no clinically utilized objective diagnostic tool. Nonetheless, several studies in have documented endeavors to create objective instruments designed to assist in the diagnostic process of ADHD, aiming to enhance diagnostic accuracy and reduce subjectivity.

METHOD

This research endeavor sought to establish an objective diagnostic modality for ADHD through the utilization of electroencephalography (EEG) signal analysis. With the use of innovative deep learning techniques, this research seeks to improve the diagnosis of ADHD using EEG data. To capture complex patterns in EEG data, this study proposes a double-augmented attention mechanism ResNet-based model. Using an autoencoder for feature extraction, the Reptile Search Algorithm for feature selection, and a modified ResNet architecture for model training comprise the technique.

RESULTS

AUC, F1-score, accuracy, precision, recall, and other standard classifiers like Random Forest and AdaBoost were utilized to compare the model's performance. By a wide margin, the proposed ResNet model outperforms the traditional models with a 99.42% accuracy, 99.03% precision, 99.82% recall, and 99.42% F1-score.

CONCLUSIONS

ROC AUC score of 0.99 for the model underscores its remarkable capability to differentiate between children with and without ADHD, thereby minimizing misclassification errors and improving diagnostic precision.

Abnormal brain entropy dynamics in ADHD

BACKGROUND

Brain entropy (BEN) is a novel measure for irregularity and complexity of brain activities, which has been used to characterize abnormal brain activities in many brain disorders including attention-deficit/hyperactivity disorder (ADHD). While most research assumes BEN is stationary during scan sessions, the brain in resting state is also a highly dynamic system. The BEN dynamics in ADHD has not been explored.

METHODS

We used a sliding window approach to derive the dynamical brain entropy (dBEN) from resting-state functional magnetic resonance imaging (rfMRI) dataset that includes 98 ADHD patients and 111 healthy controls (HCs). We identified 3 reoccurring BEN states. We tested whether the BEN dynamics differ between ADHD and HC, and whether they are associated with ADHD symptom severity.

RESULTS

One BEN states, characterized by low overall BEN and low within-state BEN located in SMN (sensorimotor network) and VN (visual network), its FW (fractional window) and MDT (mean dwell time) were increased in ADHD and positively correlated with ADHD severity; another state characterized by high overall BEN and low within-state BEN located in DMN (default mode network) and ECN (executive control network), its FW and MDT were decreased in ADHD and negatively correlated with ADHD severity.

LIMITATIONS

The window length of dBEN analysis can be further optimized to suit more datasets. The co-variation between dBEN and other dynamical brain metrics was not explored.

CONCLUSION

Our findings revealed abnormal BEN dynamics in ADHD, providing new insights into clinical diagnosis and neuropathology of ADHD.

Putative epicenters identified by transcriptome-neuromorphic interactions in attention-deficit/hyperactivity disorder biotypes

Attention-deficit hyperactivity disorder (ADHD) is a heterogenous behavioral disorder with inattention, hyperactivity and impulsivity symptoms, indicating the important implication of identifying biotypes and its epicenters in understanding disease's pathogenesis. The study investigated the neuromorphic heterogeneity relating to transcriptional similarity architecture in ADHD, and further analyzed the epicenters of network-spreading in each ADHD biotype and their correlations with clinical characteristics. Individuals with ADHD could be identified into two discriminative biotypes that exhibited distinct neuromorphic aberrances. As increased regional cortical thickness deviation in ADHD, the first component of partial least squares (PLS1) positively weighted genes were over-expressed, whereas PLS1 negatively weighted genes were under-expressed as its reduction. Both ADHD biotypes exhibited distinct disease epicenters that distributed in cognitive control and attention networks with significantly heterogeneous characteristics, holding promise for advancing our understanding, and ultimately the treatment, of ADHD. Overall, our findings identified two discriminative biotypes and its epicenters in ADHD, promoting the understanding of underlying transcriptome-neuroimaging relationships.

Source-free collaborative domain adaptation via multi-perspective feature enrichment for functional MRI analysis

Resting-state functional MRI (rs-fMRI) is increasingly employed in multi-site research to analyze neurological disorders, but there exists cross-site/domain data heterogeneity caused by site effects such as differences in scanners/protocols. Existing domain adaptation methods that reduce fMRI heterogeneity generally require accessing source domain data, which is challenging due to privacy concerns and/or data storage burdens. To this end, we propose a source-free collaborative domain adaptation (SCDA) framework using only a pretrained source model and unlabeled target data. Specifically, a multi-perspective feature enrichment method (MFE) is developed to dynamically exploit target fMRIs from multiple views. To facilitate efficient source-to-target knowledge transfer without accessing source data, we initialize MFE using parameters of a pretrained source model. We also introduce an unsupervised pretraining strategy using 3,806 unlabeled fMRIs from three large-scale auxiliary databases. Experimental results on three public and one private datasets show the efficacy of our method in cross-scanner and cross-study prediction.

Portable, low-field magnetic resonance imaging for evaluation of Alzheimer's disease

Portable, low-field magnetic resonance imaging (LF-MRI) of the brain may facilitate point-of-care assessment of patients with Alzheimer's disease (AD) in settings where conventional MRI cannot. However, image quality is limited by a lower signal-to-noise ratio. Here, we optimize LF-MRI acquisition and develop a freely available machine learning pipeline to quantify brain morphometry and white matter hyperintensities (WMH). We validate the pipeline and apply it to outpatients presenting with mild cognitive impairment or dementia due to AD. We find hippocampal volumes from ≤ 3 mm isotropic LF-MRI scans have agreement with conventional MRI and are more accurate than anisotropic counterparts. We also show WMH volume has agreement between manual segmentation and the automated pipeline. The increased availability and reduced cost of LF-MRI, in combination with our machine learning pipeline, has the potential to increase access to neuroimaging for dementia.

Exploring potential ADHD biomarkers through advanced machine learning: An examination of audiovisual integration networks

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental condition marked by inattention and impulsivity, linked to disruptions in functional brain connectivity and structural alterations in large-scale brain networks. Although sensory pathway anomalies have been implicated in ADHD, the exploration of sensory integration regions remains limited. In this study, we adopted an exploratory approach to investigate the connectivity profile of auditory-visual integration networks (AVIN) in children with ADHD and neurotypical controls using the ADHD-200 rs-fMRI dataset. We expanded our exploration beyond network-based statistics (NBS) by extracting a diverse range of graph theoretical features. These features formed the basis for applying machine learning (ML) techniques to discern distinguishing patterns between the control group and children with ADHD. To address class imbalance and sample heterogeneity, we employed ensemble learning models, including balanced random forest (BRF), XGBoost, and EasyEnsemble classifier (EEC). Our findings revealed significant differences in AVIN between ADHD individuals and neurotypical controls, enabling automated diagnosis with moderate accuracy (74.30%). Notably, the EEC model demonstrated balanced sensitivity and specificity metrics, crucial for diagnostic applications, offering valuable insights for potential clinical use. These results contribute to understanding ADHD's neural underpinnings and highlight the diagnostic potential of AVIN measures. However, the exploratory nature of this study underscores the need for future research to confirm and refine these findings with specific hypotheses and rigorous statistical controls.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

Introduction

Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age.

Methods

The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords "pediatric," "artificial intelligence," and "brain age" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.

Results

Fifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.

Discussion

Further research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Prediction of individual performance and verbal intelligence scores from resting-state fMRI in children and adolescents

The neuroimaging basis of intelligence remains elusive; however, there is a growing body of research employing connectome-based predictive modeling to estimate individual intelligence scores, aiming to identify the optimal set of neuroimaging features for accurately predicting an individual's cognitive abilities. Compared to adults, the disparities in cognitive performance among children and adolescents are more likely to captivate individuals' interest and attention. Limited research has been dedicated to exploring neuroimaging markers of intelligence specifically in the pediatric population. In this study, we utilized resting-state functional magnetic resonance imaging (fMRI) and intelligence quotient (IQ) scores of 170 healthy children and adolescents obtained from a public database to identify brain functional connectivity markers associated with individual intellectual behavior. Initially, we extracted and summarized relevant resting-state features from whole-brain or functional network connectivity that were most pertinent to IQ scores. Subsequently, these features were employed to establish prediction models for both performance and verbal IQ scores. Within a 10-fold cross-validation framework, our findings revealed that prediction models based on whole-brain functional connectivity effectively predicted performance IQ scores( R = 0.35 , P = 2.2 × 10 - 4 ) but not verbal IQ scores( R = 0.12 , P = 0.20 ). Results of prediction models based on brain functional network connectivity further demonstrated the exceptional predictive ability of the default mode network (DMN) and fronto-parietal task control network (FTPN) for performance IQ scores ( R = 0.71 , P = 2.2 × 10 - 18 ). The above findings have also been validated using an independent dataset. Our findings suggest that the performance IQ of children and adolescents primarily relies on the connectivity of brain regions associated with DMN and FTPN. Moreover, variations in intellectual performance during childhood and adolescences are closely linked to alterations in brain functional network connectivity.

3D CNN for neuropsychiatry: Predicting Autism with interpretable Deep Learning applied to minimally preprocessed structural MRI data

Predictive modeling approaches are enabling progress toward robust and reproducible brain-based markers of neuropsychiatric conditions by leveraging the power of multivariate analyses of large datasets. While deep learning (DL) offers another promising avenue to further advance progress, there are challenges related to implementation in 3D (best for MRI) and interpretability. Here, we address these challenges and describe an interpretable predictive pipeline for inferring Autism diagnosis using 3D DL applied to minimally processed structural MRI scans. We trained 3D DL models to predict Autism diagnosis using the openly available ABIDE I and II datasets (n = 1329, split into training, validation, and test sets). Importantly, we did not perform transformation to template space, to reduce bias and maximize sensitivity to structural alterations associated with Autism. Our models attained predictive accuracies equivalent to those of previous machine learning (ML) studies, while side-stepping the time- and resource-demanding requirement to first normalize data to a template. Our interpretation step, which identified brain regions that contributed most to accurate inference, revealed regional Autism-related alterations that were highly consistent with the literature, encompassing a left-lateralized network of regions supporting language processing. We have openly shared our code and models to enable further progress towards remaining challenges, such as the clinical heterogeneity of Autism and site effects, and to enable the extension of our method to other neuropsychiatric conditions.

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.

Multiclass classification of Autism Spectrum Disorder, attention deficit hyperactivity disorder, and typically developed individuals using fMRI functional connectivity analysis

Neurodevelopmental conditions, such as Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD), present unique challenges due to overlapping symptoms, making an accurate diagnosis and targeted intervention difficult. Our study employs advanced machine learning techniques to analyze functional magnetic resonance imaging (fMRI) data from individuals with ASD, ADHD, and typically developed (TD) controls, totaling 120 subjects in the study. Leveraging multiclass classification (ML) algorithms, we achieve superior accuracy in distinguishing between ASD, ADHD, and TD groups, surpassing existing benchmarks with an area under the ROC curve near 98%. Our analysis reveals distinct neural signatures associated with ASD and ADHD: individuals with ADHD exhibit altered connectivity patterns of regions involved in attention and impulse control, whereas those with ASD show disruptions in brain regions critical for social and cognitive functions. The observed connectivity patterns, on which the ML classification rests, agree with established diagnostic approaches based on clinical symptoms. Furthermore, complex network analyses highlight differences in brain network integration and segregation among the three groups. Our findings pave the way for refined, ML-enhanced diagnostics in accordance with established practices, offering a promising avenue for developing trustworthy clinical decision-support systems.

Optimal interval and feature selection in activity data for detecting attention deficit hyperactivity disorder

Attention deficit hyperactivity disorder (ADHD) is a heterogeneous neurobehavioral disorder that is common in children and adolescents. Inattention, impulsivity, and hyperactivity are the key symptoms of ADHD patients. Traditional clinical assessments delay ADHD diagnosis and increase undiagnosed cases and costs, as well. The use of deep learning (DL) and machine learning (ML)-based objective techniques for diagnosing ADHD has grown exponentially in recent years as the efficiency of early diagnosis has improved. This research highlights the significance of utilizing feature selection techniques before constructing machine learning models on activity datasets. It also explores the distinctions between specific time-interval activity data and broader interval activity data in identifying ADHD patients from the clinical control group. Five ML models were developed and tested to assess the performance of two sets of features and different categories of activity data in predicting ADHD. The study concludes with the following findings: (i) the model's performance showed a notable improvement of 0.11 in accuracy with the adoption of a precise feature selection process; (ii) activity data recorded in the morning and at night are more significant predictors of ADHD compared to other times; (iii) the utilization of specific time interval data is crucial for ADHD prediction; (iv) the random forest performs better than the other machine learning models used in the study, with 84% accuracy, 79% precision, 85% F1-score, and 92% recall. As we move into an era where early disease prediction is possible, combining artificial intelligence methods with activity data could create a strong framework for helping doctors make decisions that can be used far beyond hospitals.

Compressed cerebro-cerebellar functional gradients in children and adolescents with attention-deficit/hyperactivity disorder

Both cortical and cerebellar developmental differences have been implicated in attention-deficit/hyperactivity disorder (ADHD). Recently accumulating neuroimaging studies have highlighted hierarchies as a fundamental principle of brain organization, suggesting the importance of assessing hierarchy abnormalities in ADHD. A novel gradient-based resting-state functional connectivity analysis was applied to investigate the cerebro-cerebellar disturbed hierarchy in children and adolescents with ADHD. We found that the interaction of functional gradient between diagnosis and age was concentrated in default mode network (DMN) and visual network (VN). At the same time, we also found that the opposite gradient changes of DMN and VN caused the compression of the cortical main gradient in ADHD patients, implicating the co-occurrence of both low- (visual processing) and high-order (self-related thought) cognitive dysfunction manifesting in abnormal cerebro-cerebellar organizational hierarchy in ADHD. Our study provides a neurobiological framework to better understand the co-occurrence and interaction of both low-level and high-level functional abnormalities in the cortex and cerebellum in ADHD.

Evaluation of potential alterations related to ADHD in the effective connectivity between the default mode network and cerebellum, hippocampus, thalamus, and primary visual cortex

Hyperactivity in children with attention-deficit/hyperactivity disorder (ADHD) leads to restlessness and impulse-control impairments. Nevertheless, the relation between ADHD symptoms and brain regions interactions remains unclear. We focused on dynamic causal modeling to study the effective connectivity in a fully connected network comprised of four regions of the default mode network (DMN) (linked to response control behaviors) and four other regions with previously-reported structural alterations due to ADHD. Then, via the parametric empirical Bayes analysis, the most significant connections, with the highest correlation to the covariates ADHD/control, age, and sex were extracted. Our results demonstrated a positive correlation between ADHD and effective connectivity between the right cerebellum and three DMN nodes (intrinsically inhibitory connections). Therefore, an increase in the effective connectivity leads to more inhibition imposition from the right cerebellum to DMN that reduces this network activation. The lower DMN activity makes leaving the resting-state easier, which may be involved in the restlessness symptom. Furthermore, our results indicated a negative correlation between age and these connections. We showed that the difference between the average of effective connectivities of ADHD and control groups in the age-range of 7-11 years disappeared after 14 years-old. Therefore, aging tends to alleviate ADHD-specific symptoms.

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.

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

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

Neuroimaging epicenters as potential sites of onset of the neuroanatomical pathology in schizophrenia

Schizophrenia lacks a clear definition at the neuroanatomical level, capturing the sites of origin and progress of this disorder. Using a network-theory approach called epicenter mapping on cross-sectional magnetic resonance imaging from 1124 individuals with schizophrenia, we identified the most likely "source of origin" of the structural pathology. Our results suggest that the Broca's area and adjacent frontoinsular cortex may be the epicenters of neuroanatomical pathophysiology in schizophrenia. These epicenters can predict an individual's response to treatment for psychosis. In addition, cross-diagnostic similarities based on epicenter mapping over of 4000 individuals diagnosed with neurological, neurodevelopmental, or psychiatric disorders appear to be limited. When present, these similarities are restricted to bipolar disorder, major depressive disorder, and obsessive-compulsive disorder. We provide a comprehensive framework linking schizophrenia-specific epicenters to multiple levels of neurobiology, including cognitive processes, neurotransmitter receptors and transporters, and human brain gene expression. Epicenter mapping may be a reliable tool for identifying the potential onset sites of neural pathophysiology in schizophrenia.

Predicting verbal and performance intelligence quotients from multimodal data in individuals with attention deficit/hyperactivity disorder

Despite the importance of understanding how intelligence is ingrained in the function and structure of the brain in some neurological disorders, the alterations of intelligence-associated neurological factors in atypical neurodevelopmental disorders, such as attention deficit/hyperactivity disorder (ADHD), are limited. Therefore, we aimed to explore the relationship between the brain functional and morphological characteristics and the intellectual performance of 139 patients with ADHD. Resting-state functional and T1-weighted structural magnetic resonance imaging (MRI) data and intellectual-performance data of the patients were collected. The MRI data were preprocessed to extract four indicators characterizing the participants' brain features: fractional amplitude of low-frequency fluctuation, regional homogeneity, and gray and white matter volumes. Then, we used a two-layer feature-selection method with support vector regression models based on three kernel functions to predict the verbal and performance intelligent quotients of the patients, along with ten fold cross-validation to evaluate the models' predictive performance. All models showed good performance; the correlation coefficients between the predicted and observed values for each predictive phenotypic variable were >0.41, with statistical significance. The brain features that could best predict the intellectual performance of the patients were concentrated in the superior and inferior frontal gyrus of the prefrontal areas, the angular gyrus and precuneus of the parietal lobe, the inferior and middle temporal gyrus of the temporal lobe, and part of the cerebellar regions. Thus, the voxel-based brain-feature indicators could adequately predict the intellectual performance of patients with ADHD, providing a foundation for future neuroimaging studies of this disorder.

Identifying temporal pathways using biomarkers in the presence of latent non-Gaussian components

Time-series data collected from a network of random variables are useful for identifying temporal pathways among the network nodes. Observed measurements may contain multiple sources of signals and noises, including Gaussian signals of interest and non-Gaussian noises, including artifacts, structured noise, and other unobserved factors (eg, genetic risk factors, disease susceptibility). Existing methods, including vector autoregression (VAR) and dynamic causal modeling do not account for unobserved non-Gaussian components. Furthermore, existing methods cannot effectively distinguish contemporaneous relationships from temporal relations. In this work, we propose a novel method to identify latent temporal pathways using time-series biomarker data collected from multiple subjects. The model adjusts for the non-Gaussian components and separates the temporal network from the contemporaneous network. Specifically, an independent component analysis (ICA) is used to extract the unobserved non-Gaussian components, and residuals are used to estimate the contemporaneous and temporal networks among the node variables based on method of moments. The algorithm is fast and can easily scale up. We derive the identifiability and the asymptotic properties of the temporal and contemporaneous networks. We demonstrate superior performance of our method by extensive simulations and an application to a study of attention-deficit/hyperactivity disorder (ADHD), where we analyze the temporal relationships between brain regional biomarkers. We find that temporal network edges were across different brain regions, while most contemporaneous network edges were bilateral between the same regions and belong to a subset of the functional connectivity network.

Mapping dynamic spatial patterns of brain function with spatial-wise attention

Objective: Using functional magnetic resonance imaging (fMRI) and deep learning to discover the spatial pattern of brain function, or functional brain networks (FBNs) has been attracted many reseachers. Most existing works focus on static FBNs or dynamic functional connectivity among fixed spatial network nodes, but ignore the potential dynamic/time-varying characteristics of the spatial networks themselves. And most of works based on the assumption of linearity and independence, that oversimplify the relationship between blood-oxygen level dependence signal changes and the heterogeneity of neuronal activity within voxels.Approach: To overcome these problems, we proposed a novel spatial-wise attention (SA) based method called Spatial and Channel-wise Attention Autoencoder (SCAAE) to discover the dynamic FBNs without the assumptions of linearity or independence. The core idea of SCAAE is to apply the SA to generate FBNs directly, relying solely on the spatial information present in fMRI volumes. Specifically, we trained the SCAAE in a self-supervised manner, using the autoencoder to guide the SA to focus on the activation regions. Experimental results show that the SA can generate multiple meaningful FBNs at each fMRI time point, which spatial similarity are close to the FBNs derived by known classical methods, such as independent component analysis.Main results: To validate the generalization of the method, we evaluate the approach on HCP-rest, HCP-task and ADHD-200 dataset. The results demonstrate that SA mechanism can be used to discover time-varying FBNs, and the identified dynamic FBNs over time clearly show the process of time-varying spatial patterns fading in and out.Significance: Thus we provide a novel method to understand human brain better. Code is available athttps://github.com/WhatAboutMyStar/SCAAE.

Acoustic and Text Features Analysis for Adult ADHD Screening: A Data-Driven Approach Utilizing DIVA Interview

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder commonly seen in childhood that leads to behavioural changes in social development and communication patterns, often continues into undiagnosed adulthood due to a global shortage of psychiatrists, resulting in delayed diagnoses with lasting consequences on individual's well-being and the societal impact. Recently, machine learning methodologies have been incorporated into healthcare systems to facilitate the diagnosis and enhance the potential prediction of treatment outcomes for mental health conditions. In ADHD detection, the previous research focused on utilizing functional magnetic resonance imaging (fMRI) or Electroencephalography (EEG) signals, which require costly equipment and trained personnel for data collection. In recent years, speech and text modalities have garnered increasing attention due to their cost-effectiveness and non-wearable sensing in data collection. In this research, conducted in collaboration with the Cumbria, Northumberland, Tyne and Wear NHS Foundation Trust, we gathered audio data from both ADHD patients and normal controls based on the clinically popular Diagnostic Interview for ADHD in adults (DIVA). Subsequently, we transformed the speech data into text modalities through the utilization of the Google Cloud Speech API. We extracted both acoustic and text features from the data, encompassing traditional acoustic features (e.g., MFCC), specialized feature sets (e.g., eGeMAPS), as well as deep-learned linguistic and semantic features derived from pre-trained deep learning models. These features are employed in conjunction with a support vector machine for ADHD classification, yielding promising outcomes in the utilization of audio and text data for effective adult ADHD screening. Clinical impact: This research introduces a transformative approach in ADHD diagnosis, employing speech and text analysis to facilitate early and more accessible detection, particularly beneficial in areas with limited psychiatric resources. Clinical and Translational Impact Statement: The successful application of machine learning techniques in analyzing audio and text data for ADHD screening represents a significant advancement in mental health diagnostics, paving the way for its integration into clinical settings and potentially improving patient outcomes on a broader scale.

A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research

Artificial intelligence (AI) has the potential to bring transformative improvements to the field of radiology; yet, there are barriers to widespread clinical adoption. One of the most important barriers has been access to large, well-annotated, widely representative medical image datasets, which can be used to accurately train AI programs. Creating such datasets requires time and expertise and runs into constraints around data security and interoperability, patient privacy, and appropriate data use. Recognizing these challenges, several institutions have started curating and providing publicly available, high-quality datasets that can be accessed by researchers to advance AI models. The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. Despite being an emerging field, a simple internet search for open MRI datasets presents an overwhelming number of results. Therefore, we decided to create a survey of the major publicly accessible MRI datasets in different subfields of radiology (brain, body, and musculoskeletal), and list the most important features of value to the AI researcher. To complete this review, we searched for publicly available MRI datasets and assessed them based on several parameters (number of subjects, demographics, area of interest, technical features, and annotations). We reviewed 110 datasets across sub-fields with 1,686,245 subjects in 12 different areas of interest ranging from spine to cardiac. This review is meant to serve as a reference for researchers to help spur advancements in the field of AI for radiology. LEVEL OF EVIDENCE: Level 4 TECHNICAL EFFICACY: Stage 6.

GAN-Based Motion Artifact Correction of 3D MR Volumes Using an Image-to-Image Translation Algorithm

The quality of brain MRI volumes is often compromised by motion artifacts arising from intricate respiratory patterns and involuntary head movements, manifesting as blurring and ghosting that markedly degrade imaging quality. In this study, we introduce an innovative approach employing a 3D deep learning framework to restore brain MR volumes afflicted by motion artifacts. The framework integrates a densely connected 3D U-net architecture augmented by generative adversarial network (GAN)-informed training with a novel volumetric reconstruction loss function tailored to 3D GAN to enhance the quality of the volumes. Our methodology is substantiated through comprehensive experimentation involving a diverse set of motion artifact-affected MR volumes. The generated high-quality MR volumes have similar volumetric signatures comparable to motion-free MR volumes after motion correction. This underscores the significant potential of harnessing this 3D deep learning system to aid in the rectification of motion artifacts in brain MR volumes, highlighting a promising avenue for advanced clinical applications.

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

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

Nonparametric Statistical Inference via Metric Distribution Function in Metric Spaces

The distribution function is essential in statistical inference and connected with samples to form a directed closed loop by the correspondence theorem in measure theory and the Glivenko-Cantelli and Donsker properties. This connection creates a paradigm for statistical inference. However, existing distribution functions are defined in Euclidean spaces and are no longer convenient to use in rapidly evolving data objects of complex nature. It is imperative to develop the concept of the distribution function in a more general space to meet emerging needs. Note that the linearity allows us to use hypercubes to define the distribution function in a Euclidean space. Still, without the linearity in a metric space, we must work with the metric to investigate the probability measure. We introduce a class of metric distribution functions through the metric only. We overcome this challenging step by proving the correspondence theorem and the Glivenko-Cantelli theorem for metric distribution functions in metric spaces, laying the foundation for conducting rational statistical inference for metric space-valued data. Then, we develop a homogeneity test and a mutual independence test for non-Euclidean random objects and present comprehensive empirical evidence to support the performance of our proposed methods.

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

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

A stochastic block Ising model for multi-layer networks with inter-layer dependence

Community detection has attracted tremendous interests in network analysis, which aims at finding group of nodes with similar characteristics. Various detection methods have been developed to detect homogeneous communities in multi-layer networks, where inter-layer dependence is a widely acknowledged but severely under-investigated issue. In this paper, we propose a novel stochastic block Ising model (SBIM) to incorporate the inter-layer dependence to help with community detection in multi-layer networks. The community structure is modeled by the stochastic block model (SBM) and the inter-layer dependence is incorporated via the popular Ising model. Furthermore, we develop an efficient variational EM algorithm to tackle the resultant optimization task and establish the asymptotic consistency of the proposed method. Extensive simulated examples and a real example on gene co-expression multi-layer network data are also provided to demonstrate the advantage of the proposed method.

Brain Growth Charts for Quantitative Analysis of Pediatric Clinical Brain MRI Scans with Limited Imaging Pathology

Background Clinically acquired brain MRI scans represent a valuable but underused resource for investigating neurodevelopment due to their technical heterogeneity and lack of appropriate controls. These barriers have curtailed retrospective studies of clinical brain MRI scans compared with more costly prospectively acquired research-quality brain MRI scans. Purpose To provide a benchmark for neuroanatomic variability in clinically acquired brain MRI scans with limited imaging pathology (SLIPs) and to evaluate if growth charts from curated clinical MRI scans differed from research-quality MRI scans or were influenced by clinical indication for the scan. Materials and Methods In this secondary analysis of preexisting data, clinical brain MRI SLIPs from an urban pediatric health care system (individuals aged ≤22 years) were scanned across nine 3.0-T MRI scanners. The curation process included manual review of signed radiology reports and automated and manual quality review of images without gross pathology. Global and regional volumetric imaging phenotypes were measured using two image segmentation pipelines, and clinical brain growth charts were quantitatively compared with charts derived from a large set of research controls in the same age range by means of Pearson correlation and age at peak volume. Results The curated clinical data set included 532 patients (277 male; median age, 10 years [IQR, 5-14 years]; age range, 28 days after birth to 22 years) scanned between 2005 and 2020. Clinical brain growth charts were highly correlated with growth charts derived from research data sets (22 studies, 8346 individuals [4947 male]; age range, 152 days after birth to 22 years) in terms of normative developmental trajectories predicted by the models (median r = 0.979). Conclusion The clinical indication of the scans did not significantly bias the output of clinical brain charts. Brain growth charts derived from clinical controls with limited imaging pathology were highly correlated with brain charts from research controls, suggesting the potential of curated clinical MRI scans to supplement research data sets. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Ertl-Wagner and Pai in this issue.

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.

The robustness of persistent homology of brain networks to data acquisition-related non-neural variability in resting state fMRI

There is increasing interest in investigating brain function based on functional connectivity networks (FCN) obtained from resting-state functional magnetic resonance imaging (fMRI). FCNs, typically obtained using measures of time series association such as Pearson's correlation, are sensitive to data acquisition parameters such as sampling period. This introduces non-neural variability in data pooled from different acquisition protocols and MRI scanners, negating the advantages of larger sample sizes in pooled data. To address this, we hypothesize that the topology or shape of brain networks must be preserved irrespective of how densely it is sampled, and metrics which capture this topology may be statistically similar across sampling periods, thereby alleviating this source of non-neural variability. Accordingly, we present an end-to-end pipeline that uses persistent homology (PH), a branch of topological data analysis, to demonstrate similarity across FCNs acquired at different temporal sampling periods. PH, as a technique, extracts topological features by capturing the network organization across all continuous threshold values, as opposed to graph theoretic methods, which fix a discrete network topology by thresholding the connectivity matrix. The extracted topological features are encoded in the form of persistent diagrams that can be compared against one another using the earth-moving metric, also popularly known as the Wasserstein distance. We extract topological features from three data cohorts, each acquired at different temporal sampling periods and demonstrate that these features are statistically the same, hence, empirically showing that PH may be robust to changes in data acquisition parameters such as sampling period.

Consistent estimation of the number of communities via regularized network embedding

The network analysis plays an important role in numerous application domains including biomedicine. Estimation of the number of communities is a fundamental and critical issue in network analysis. Most existing studies assume that the number of communities is known a priori, or lack of rigorous theoretical guarantee on the estimation consistency. In this paper, we propose a regularized network embedding model to simultaneously estimate the community structure and the number of communities in a unified formulation. The proposed model equips network embedding with a novel composite regularization term, which pushes the embedding vector toward its center and pushes similar community centers collapsed with each other. A rigorous theoretical analysis is conducted, establishing asymptotic consistency in terms of community detection and estimation of the number of communities. Extensive numerical experiments have also been conducted on both synthetic networks and brain functional connectivity network, which demonstrate the superior performance of the proposed method compared with existing alternatives.

Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives

Transformer, one of the latest technological advances of deep learning, has gained prevalence in natural language processing or computer vision. Since medical imaging bear some resemblance to computer vision, it is natural to inquire about the status quo of Transformers in medical imaging and ask the question: can the Transformer models transform medical imaging? In this paper, we attempt to make a response to the inquiry. After a brief introduction of the fundamentals of Transformers, especially in comparison with convolutional neural networks (CNNs), and highlighting key defining properties that characterize the Transformers, we offer a comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging and exhibit current research progresses made in the areas of medical image segmentation, recognition, detection, registration, reconstruction, enhancement, etc. In particular, what distinguishes our review lies in its organization based on the Transformer's key defining properties, which are mostly derived from comparing the Transformer and CNN, and its type of architecture, which specifies the manner in which the Transformer and CNN are combined, all helping the readers to best understand the rationale behind the reviewed approaches. We conclude with discussions of future perspectives.

Brain regional homogeneity and its association with age and intelligence in typically developing youth

Accelerated synaptic pruning and weakening of short-range functional connectivity are characteristic of adolescent brain development. Based on these structural microscopic and system-level functional changes, it was hypothesized that regional homogeneity (ReHo) may decrease with age in the developing brain, and a differential association between ReHo and cognitive performance was expected to depend on age. ReHo maps of typically developing participants were provided by the Attention-Deficit/Hyperactivity Disorder (ADHD)-200 Preprocessed repository. Intelligence quotient was evaluated using the Wechsler Intelligence Scale for Chinese Children-Revised and Wechsler Abbreviated Scale of Intelligence at Peking University and New York University, respectively. Correlations between ReHo and age were examined, along with the interaction effects of ReHo and age on intelligence quotient (IQ), in 121 typically developing youth aged 8-14 years. Of the 400 ROIs tested, ReHo in 105 brain regions was significantly correlated with age (p < 0.05, false discovery rate-corrected), among which 102 showed that ReHo decreased with age. In addition, ReHo in 18 brain regions was negatively correlated with age at Bonferroni-corrected thresholds (p < 0.05), and most associations were observed in the prefrontal cortex. The interaction analyses suggested that higher ReHo was associated with higher IQ in children, whereas this association was attenuated or reversed in adolescents (p < 0.05, uncorrected). ReHo decreased with age in the developing brain and was differentially associated with intelligence in children and adolescents.

Brain Network Analysis: A Review on Multivariate Analytical Methods

Despite the explosive growth of neuroimaging studies aimed at analyzing the brain as a complex system, critical methodological gaps remain to be addressed. Most tools currently used for analyzing network data of the brain are univariate in nature and are based on assumptions borne out of previous techniques not directly related to the big and complex data of the brain. Although graph-based methods have shown great promise, the development of principled multivariate models to address inherent limitations of graph-based methods, such as their dependence on network size and degree distributions, and to allow assessing the effects of multiple phenotypes on the brain and simulating brain networks has largely lagged behind. Although some studies have been made in developing multivariate frameworks to fill this gap, in the absence of a "gold-standard" method or guidelines, choosing the most appropriate method for each study can be another critical challenge for investigators in this multidisciplinary field. Here, we briefly introduce important multivariate methods for brain network analyses in two main categories: data-driven and model-based methods. We discuss whether/how such methods are suited for examining connectivity (edge-level), topology (system-level), or both. This review will aid in choosing an appropriate multivariate method with respect to variables such as network type, number of subjects and brain regions included, and the interest in connectivity, topology, or both. This review is aimed to be accessible to investigators from different backgrounds, with a focus on applications in brain network studies, though the methods may be applicable in other areas too. Impact statement As the U.S. National Institute of Health notes, the rich biomedical data can greatly improve our knowledge of human health if new analytical tools are developed, and their applications are broadly disseminated. A major challenge in analyzing the brain as a complex system is about developing parsimonious multivariate methods, and particularly choosing the most appropriate one among the existing methods with respect to the study variables in this multidisciplinary field. This study provides a review on the most important multivariate methods to aid in helping the most appropriate ones with respect to the desired variables for each study.

Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning

Attention Deficit Hyperactivity Disorder (ADHD) is a type of mental health disorder that can be seen from children to adults and affects patients' normal life. Accurate diagnosis of ADHD as early as possible is very important for the treatment of patients in clinical applications. Some traditional classification methods, although having been shown powerful in many other classification tasks, are not as successful in the application of ADHD classification. In this paper, we propose two novel deep learning approaches for ADHD classification based on functional magnetic resonance imaging. The first method incorporates independent component analysis with convolutional neural network. It first extracts independent components from each subject. The independent components are then fed into a convolutional neural network as input features to classify the ADHD patient from typical controls. The second method, called the correlation autoencoder method, uses correlations between regions of interest of the brain as the input of an autoencoder to learn latent features, which are then used in the classification task by a new neural network. These two methods use different ways to extract the inter-voxel information from fMRI, but both use convolutional neural networks to further extract predictive features for the classification task. Empirical experiments show that both methods are able to outperform the classical methods such as logistic regression, support vector machines, and other methods used in previous studies.

Reproducibility of cerebral perfusion measurements using BOLD delay

BOLD delay is an emerging, noninvasive method for assessing cerebral perfusion that does not require the use of intravenous contrast agents and is thus particularly suited for longitudinal monitoring. In this study, we assess the reproducibility of BOLD delay using data from 136 subjects with normal cerebral perfusion scanned on two separate occasions with scanners, sequence parameters, and intervals between scans varying between subjects. The effects of various factors on the reproducibility of BOLD delay, defined here as the differences in BOLD delay values between the scanning sessions, were investigated using a linear mixed model. Reproducibility was additionally assessed using the intraclass correlation coefficient of BOLD delay between sessions. Reproducibility was highest in the posterior cerebral artery territory. The mean BOLD delay test-retest difference after accounting for the aforementioned factors was 1.2 s (95% CI = 1.0 to 1.4 s). Overall, BOLD delay shows good reproducibility, but care should be taken when interpreting longitudinal BOLD delay changes that are either very small or are located in certain brain regions.

BrainGB: A Benchmark for Brain Network Analysis With Graph Neural Networks

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data. Despite their superior performance in many fields, there has not yet been a systematic study of how to design effective GNNs for brain network analysis. To bridge this gap, we present BrainGB, a benchmark for brain network analysis with GNNs. BrainGB standardizes the process by (1) summarizing brain network construction pipelines for both functional and structural neuroimaging modalities and (2) modularizing the implementation of GNN designs. We conduct extensive experiments on datasets across cohorts and modalities and recommend a set of general recipes for effective GNN designs on brain networks. To support open and reproducible research on GNN-based brain network analysis, we host the BrainGB website at https://braingb.us with models, tutorials, examples, as well as an out-of-box Python package. We hope that this work will provide useful empirical evidence and offer insights for future research in this novel and promising direction.