Using graph convolutional network to characterize individuals with major depressive disorder across multiple imaging sites

The impact of illness duration on brain activity in goal-directed and habit-learning systems in obsessive-compulsive disorder progression: a resting-state functional imaging study

It is increasingly evident that structural and functional changes in brain regions associated with obsessive-compulsive disorder (OCD) are often related to the development of the disease. However, limited research has been conducted on how the progression of OCD may lead to an imbalance between goal-directed and habit-learning systems. This study employs resting-state functional imaging to examine the relationship between illness duration and abnormal brain function in goal-directed/habitual-learning systems. Demographic, clinical, and multimodal fMRI data were collected from participants. Our findings suggest that, compared to healthy controls, individuals with OCD exhibit abnormal brain functional indicators in both goal-directed and habit-learning brain regions, with a more pronounced reduction observed in the goal-directed regions. Additionally, abnormal brain activity is associated with illness duration, and the abnormalities observed in goal-directed regions are more effective in distinguishing different courses of OCD patients. Patients with different durations of OCD have functional abnormalities in the goal-directed and habitual-learning brain regions. There are differences in the degree of abnormality in different brain regions, and these abnormalities may disrupt the balance between goal-directed and habitual-learning systems, leading to increasing reliance on repetitive behaviors.

Randomizing Human Brain Function Representation for Brain Disease Diagnosis

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

The power of many brains: Catalyzing neuropsychiatric discovery through open neuroimaging data and large-scale collaboration

Recent advances in open neuroimaging data are enhancing our comprehension of neuropsychiatric disorders. By pooling images from various cohorts, statistical power has increased, enabling the detection of subtle abnormalities and robust associations, and fostering new research methods. Global collaborations in imaging have furthered our knowledge of the neurobiological foundations of brain disorders and aided in imaging-based prediction for more targeted treatment. Large-scale magnetic resonance imaging initiatives are driving innovation in analytics and supporting generalizable psychiatric studies. We also emphasize the significant role of big data in understanding neural mechanisms and in the early identification and precise treatment of neuropsychiatric disorders. However, challenges such as data harmonization across different sites, privacy protection, and effective data sharing must be addressed. With proper governance and open science practices, we conclude with a projection of how large-scale imaging resources and collaborations could revolutionize diagnosis, treatment selection, and outcome prediction, contributing to optimal brain health.

Multiview hyperedge-aware hypergraph embedding learning for multisite, multiatlas fMRI based functional connectivity network analysis

Recently, functional magnetic resonance imaging (fMRI) based functional connectivity network (FCN) analysis via graph convolutional networks (GCNs) has shown promise for automated diagnosis of brain diseases by regarding the FCNs as irregular graph-structured data. However, multiview information and site influences of the FCNs in a multisite, multiatlas fMRI scenario have been understudied. In this paper, we propose a Class-consistency and Site-independence Multiview Hyperedge-Aware HyperGraph Embedding Learning (CcSi-MHAHGEL) framework to integrate FCNs constructed on multiple brain atlases in a multisite fMRI study. Specifically, for each subject, we first model brain network as a hypergraph for every brain atlas to characterize high-order relations among multiple vertexes, and then introduce a multiview hyperedge-aware hypergraph convolutional network (HGCN) to extract a multiatlas-based FCN embedding where hyperedge weights are adaptively learned rather than employing the fixed weights precalculated in traditional HGCNs. In addition, we formulate two modules to jointly learn the multiatlas-based FCN embeddings by considering the between-subject associations across classes and sites, respectively, i.e., a class-consistency module to encourage both compactness within every class and separation between classes for promoting discrimination in the embedding space, and a site-independence module to minimize the site dependence of the embeddings for mitigating undesired site influences due to differences in scanning platforms and/or protocols at multiple sites. Finally, the multiatlas-based FCN embeddings are fed into a few fully connected layers followed by the soft-max classifier for diagnosis decision. Extensive experiments on the ABIDE demonstrate the effectiveness of our method for autism spectrum disorder (ASD) identification. Furthermore, our method is interpretable by revealing ASD-relevant brain regions that are biologically significant.

Altered functional-structural coupling may predict Parkinson's patient's depression

We aimed to elucidate the neurobiological basis of depression in Parkinson's disease and identify potential imaging markers for depression in patients with Parkinson's disease. We recruited 43 normal controls (NC), 46 depressed Parkinson's disease patients (DPD) and 56 non-depressed Parkinson's disease (NDPD). All participants underwent routine T2-weighted, T2Flair, and resting-state scans on the same 3.0 T magnetic resonance imaging (MRI) scanner at our hospital. Pre-processing includes calculating surface-based Regional Homogeneity (2DReHo) and cortical thickness. Then we defined the correlation coefficient between 2DReHo and cortical thickness as the functional-structural coupling index. Between-group comparisons were conducted on the Fisher's Z-transformed correlation coefficients. To identify specific regions of decoupling, the 2DReHo for each participant were divided by cortical thickness at each vertex, followed by threshold-free cluster enhancement (TFCE) multiple comparison correction. Binary logistic regression analysis was performed with DPD as the dependent variable, and significantly altered indicators as the independent variables. Receiver operating characteristic curves were constructed to compare the diagnostic performance of individual predictors and combinations using R and MedCalc software. DPD patients exhibited a significantly lower whole-brain functional-structural coupling index than NDPD patients and NC. Abnormal functional-structural coupling was primarily observed in the left inferior parietal lobule and right primary and early visual cortices in DPD patients. Receiver operating characteristic analysis revealed that the combination of cortical functional-structural coupling, surface-based ReHo, and thickness had the best diagnostic performance, achieving a sensitivity of 65% and specificity of 77.7%. This is the first study to explore the relationship between functional and structural changes in DPD patients and evaluate the diagnostic performance of these altered correlations to predict depression in Parkinson's disease patients. We posit that these changes in functional-structural relationships may serve as imaging biomarkers for depression in Parkinson's disease patients, potentially aiding in the classification and diagnosis of Parkinson's disease. Additionally, our findings provide functional and structural imaging evidence for exploring the neurobiological basis of depression in Parkinson's disease.

Employing graph attention networks to decode psycho-metabolic interactions in Schizophrenia

Schizophrenia is a severe mental disorder characterized by intricate and underexplored interactions between psychological symptoms and metabolic health, presenting challenges in understanding the disease mechanisms and designing effective treatment strategies. To delve deeply into the complex interactions between mental and metabolic health in patients with schizophrenia, this study constructed a psycho-metabolic interaction network and optimized the Graph Attention Network (GAT). This approach reveals complex data patterns that traditional statistical analyses fail to capture. The results show that weight management and medication management play a central role in the interplay between psychiatric disorders and metabolic health. Furthermore, additional analysis revealed significant correlations between the history of psychiatric symptoms and physical health indicators, as well as the key roles of biochemical markers(e.g., triglycerides and low-density lipoprotein cholesterol), which have not been sufficiently emphasized in previous studies. This highlights the importance of medication management approaches, weight management, psychological treatment, and biomarker monitoring in comprehensive treatment and underscores the significance of the biopsychosocial model. This study is the first to utilize a GNN to explore the interactions between schizophrenia symptoms and metabolic features, providing new insights into understanding psychiatric disorders and guiding the development of more comprehensive treatment strategies for schizophrenia.

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.

A novel spatiotemporal graph convolutional network framework for functional connectivity biomarkers identification of Alzheimer's disease

BACKGROUND

Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer's disease (AD). However, the identification of effective FC biomarkers remains challenging. In this study, we introduce a novel approach, the spatiotemporal graph convolutional network (ST-GCN) combined with the gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify FC biomarkers for AD.

METHODS

This multi-center cross-racial retrospective study involved 2,272 participants, including 1,105 cognitively normal (CN) subjects, 790 mild cognitive impairment (MCI) individuals, and 377 AD patients. All participants underwent functional magnetic resonance imaging (fMRI) and T1-weighted MRI scans. In this study, firstly, we optimized the STGC-GCAM model to enhance classification accuracy. Secondly, we identified novel AD-associated biomarkers using the optimized model. Thirdly, we validated the imaging biomarkers using Kaplan-Meier analysis. Lastly, we performed correlation analysis and causal mediation analysis to confirm the physiological significance of the identified biomarkers.

RESULTS

The STGC-GCAM model demonstrated great classification performance (The average area under the curve (AUC) values for different categories were: CN vs MCI = 0.98, CN vs AD = 0.95, MCI vs AD = 0.96, stable MCI vs progressive MCI = 0.79). Notably, the model identified specific brain regions, including the sensorimotor network (SMN), visual network (VN), and default mode network (DMN), as key differentiators between patients and CN individuals. These brain regions exhibited significant associations with the severity of cognitive impairment (p < 0.05). Moreover, the topological features of important brain regions demonstrated excellent predictive capability for the conversion from MCI to AD (Hazard ratio = 3.885, p < 0.001). Additionally, our findings revealed that the topological features of these brain regions mediated the impact of amyloid beta (Aβ) deposition (bootstrapped average causal mediation effect: β = -0.01 [-0.025, 0.00], p < 0.001) and brain glucose metabolism (bootstrapped average causal mediation effect: β = -0.02 [-0.04, -0.001], p < 0.001) on cognitive status.

CONCLUSIONS

This study presents the STGC-GCAM framework, which identifies FC biomarkers using a large multi-site fMRI dataset.

Defocused mode in depressed mood and its changes in time-frequency attention-related beta

Depressed mood has been proposed to possibly possess a unique mode of defocused attention. However, this argument needs to be supported by experimental evidence based on attentional performance. The present study used a perceptual load paradigm, combining factors of perceptual load, distractor-target compatibility, and eccentricity, to investigate the degree of attentional distraction in depressed mood. In addition, the mode of attentional distraction associated with depressed mood was explored with the time-frequency features of electroencephalography (EEG). The behavioral results showed that the high depressed mood (HD) group had significantly higher attentional distraction than the low depressed mood (LD) group. EEG results showed that 1) the beta power (especially beta-2, 18-30 Hz) of the two groups differed in the medio-late part of the attentional distraction, with significantly lower power in the HD group than in the LD group; 2) the results of the correlation between beta-2 power and depression scores revealed a significant negative correlation. These results imply that beta-2 is a potential marker that may be sensitive to depressed mood during attentional processing, which was further supported by the classification results of the support vector machine (SVM) with 80.65% accuracy between the HD and LD groups.

Aberrant brain network topology in youth with a familial risk for bipolar disorder: a task-based fMRI connectome study

BACKGROUND

Youth with a family history of bipolar disorder (BD) may be at increased risk for mood disorders and for developing side effects after antidepressant exposure. The neurobiological basis of these risks remains poorly understood. We aimed to identify biomarkers underlying risk by characterizing abnormalities in the brain connectome of symptomatic youth at familial risk for BD.

METHODS

Depressed and/or anxious youth (n = 119, age = 14.9 ± 1.6 years) with a family history of BD but no prior antidepressant exposure and typically developing controls (n = 57, age = 14.8 ± 1.7 years) received functional magnetic resonance imaging (fMRI) during an emotional continuous performance task. A generalized psychophysiological interaction (gPPI) analysis was performed to compare their brain connectome patterns, followed by machine learning of topological metrics.

RESULTS

High-risk youth showed weaker connectivity patterns that were mainly located in the default mode network (DMN) (network weight = 50.1%) relative to controls, and connectivity patterns derived from the visual network (VN) constituted the largest proportion of aberrant stronger pairs (network weight = 54.9%). Global local efficiency (Elocal , p = .022) and clustering coefficient (Cp , p = .029) and nodal metrics of the right superior frontal gyrus (SFG) (Elocal : p < .001; Cp : p = .001) in the high-risk group were significantly higher than those in healthy subjects, and similar patterns were also found in the left insula (degree: p = .004; betweenness: p = .005; age-by-group interaction, p = .038) and right hippocampus (degree: p = .003; betweenness: p = .003). The case-control classifier achieved a cross-validation accuracy of 78.4%.

CONCLUSIONS

Our findings of abnormal connectome organization in the DMN and VN may advance mechanistic understanding of risk for BD. Neuroimaging biomarkers of increased network segregation in the SFG and altered topological centrality in the insula and hippocampus in broader limbic systems may be used to target interventions tailored to mitigate the underlying risk of brain abnormalities in these at-risk youth.

Cross-Domain Identification of Multisite Major Depressive Disorder Using End-to-End Brain Dynamic Attention Network

Establishing objective and quantitative imaging markers at individual level can assist in accurate diagnosis of Major Depressive Disorder (MDD). However, the clinical heterogeneity of MDD and the shift to multisite data decreased identification accuracy. To address these issues, the Brain Dynamic Attention Network (BDANet) is innovatively proposed, and analyzed bimodal scans from 2055 participants of the Rest-meta-MDD consortium. The end-to-end BDANet contains two crucial components. The Dynamic BrainGraph Generator dynamically focuses and represents topological relationships between Regions of Interest, overcoming limitations of static methods. The Ensemble Classifier is constructed to obfuscate domain sources to achieve inter-domain alignment. Finally, BDANet dynamically generates sample-specific brain graphs by downstream recognition tasks. The proposed BDANet achieved an accuracy of 81.6%. The regions with high attribution for classification were mainly located in the insula, cingulate cortex and auditory cortex. The level of brain connectivity in p24 region was negatively correlated ( [Formula: see text]) with the severity of MDD. Additionally, sex differences in connectivity strength were observed in specific brain regions and functional subnetworks ( [Formula: see text] or [Formula: see text]). These findings based on a large multisite dataset support the conclusion that BDANet can better solve the problem of the clinical heterogeneity of MDD and the shift of multisite data. It also illustrates the potential utility of BDANet for personalized accurate identification, treatment and intervention of MDD.

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.

Multi-feature concatenation and multi-classifier stacking: An interpretable and generalizable machine learning method for MDD discrimination with rsfMRI

Major depressive disorder (MDD) is a serious and heterogeneous psychiatric disorder that needs accurate diagnosis. Resting-state functional MRI (rsfMRI), which captures multiple perspectives on brain structure, function, and connectivity, is increasingly applied in the diagnosis and pathological research of MDD. Different machine learning algorithms are then developed to exploit the rich information in rsfMRI and discriminate MDD patients from normal controls. Despite recent advances reported, the MDD discrimination accuracy has room for further improvement. The generalizability and interpretability of the discrimination method are not sufficiently addressed either. Here, we propose a machine learning method (MFMC) for MDD discrimination by concatenating multiple features and stacking multiple classifiers. MFMC is tested on the REST-meta-MDD data set that contains 2428 subjects collected from 25 different sites. MFMC yields 96.9% MDD discrimination accuracy, demonstrating a significant improvement over existing methods. In addition, the generalizability of MFMC is validated by the good performance when the training and testing subjects are from independent sites. The use of XGBoost as the meta classifier allows us to probe the decision process of MFMC. We identify 13 feature values related to 9 brain regions including the posterior cingulate gyrus, superior frontal gyrus orbital part, and angular gyrus, which contribute most to the classification and also demonstrate significant differences at the group level. The use of these 13 feature values alone can reach 87% of MFMC's full performance when taking all feature values. These features may serve as clinically useful diagnostic and prognostic biomarkers for MDD in the future.

Applications of machine learning and deep learning in SPECT and PET imaging: General overview, challenges and future prospects

The integration of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging techniques with machine learning (ML) algorithms, including deep learning (DL) models, is a promising approach. This integration enhances the precision and efficiency of current diagnostic and treatment strategies while offering invaluable insights into disease mechanisms. In this comprehensive review, we delve into the transformative impact of ML and DL in this domain. Firstly, a brief analysis is provided of how these algorithms have evolved and which are the most widely applied in this domain. Their different potential applications in nuclear imaging are then discussed, such as optimization of image adquisition or reconstruction, biomarkers identification, multimodal fusion and the development of diagnostic, prognostic, and disease progression evaluation systems. This is because they are able to analyse complex patterns and relationships within imaging data, as well as extracting quantitative and objective measures. Furthermore, we discuss the challenges in implementation, such as data standardization and limited sample sizes, and explore the clinical opportunities and future horizons, including data augmentation and explainable AI. Together, these factors are propelling the continuous advancement of more robust, transparent, and reliable systems.

Classification of suicidality by training supervised machine learning models with brain MRI findings: A systematic review

BACKGROUND

Suicide is a global public health issue causing around 700,000 deaths worldwide each year. Therefore, identifying suicidal thoughts and behaviors in patients can help lower the suicide-related mortality rate. This review aimed to investigate the feasibility of suicidality identification by applying supervised Machine Learning (ML) methods to Magnetic Resonance Imaging (MRI) data.

METHODS

We conducted a systematic search on PubMed, Scopus, and Web of Science to identify studies examining suicidality by applying ML methods to MRI features. Also, the Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed for the quality assessment.

RESULTS

23 studies met the inclusion criteria. Of these, 20 developed prediction models without external validation and 3 developed prediction models with external validation. The performance of ML models varied among the reviewed studies, with the highest reported values of accuracies and Area Under the Curve (AUC) ranging from 51.7 % to 100 % and 0.52 to 1, respectively. Over half of the studies that reported accuracy (12/21) or AUC (13/16) achieved values of ≥0.8. Our comparative analysis indicated that deep learning exhibited the highest predictive performance compared to other ML models. The most commonly identified discriminative imaging features were resting-state functional connectivity and grey matter volume within prefrontal-limbic structures.

LIMITATIONS

Small sample sizes, lack of external validation, heterogeneous study designs, and ML model development.

CONCLUSIONS

Most of the studies developed ML models capable of ML-based suicide identification, although ML models' predictive performance varied across the reviewed studies. Thus, further well-designed is necessary to uncover the true potential of different ML models in this field.

AMGCN-L: an adaptive multi-time-window graph convolutional network with long-short-term memory for depression detection

Objective.Depression is a common chronic mental disorder characterized by high rates of prevalence, recurrence, suicide, and disability as well as heavy disease burden. An accurate diagnosis of depression is a prerequisite for treatment. However, existing questionnaire-based diagnostic methods are limited by the innate subjectivity of medical practitioners and subjects. In the search for a more objective diagnostic methods for depression, researchers have recently started to use deep learning approaches.Approach.In this work, a deep-learning network, named adaptively multi-time-window graph convolutional network (GCN) with long-short-term memory (LSTM) (i.e. AMGCN-L), is proposed. This network can automatically categorize depressed and non-depressed people by testing for the existence of inherent brain functional connectivity and spatiotemporal features contained in electroencephalogram (EEG) signals. AMGCN-L is mainly composed of two sub-networks: the first sub-network is an adaptive multi-time-window graph generation block with which adjacency matrices that contain brain functional connectivity on different time periods are adaptively designed. The second sub-network consists of GCN and LSTM, which are used to fully extract the innate spatial and temporal features of EEG signals, respectively.Main results.Two public datasets, namely the patient repository for EEG data and computational tools, and the multi-modal open dataset for mental-disorder analysis, were used to test the performance of the proposed network; the depression recognition accuracies achieved in both datasets (using tenfold cross-validation) were 90.38% and 90.57%, respectively.Significance.This work demonstrates that GCN and LSTM have eminent effects on spatial and temporal feature extraction, respectively, suggesting that the exploration of brain connectivity and the exploitation of spatiotemporal features benefit the detection of depression. Moreover, the proposed method provides effective support and supplement for the detection of clinical depression and later treatment procedures.

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Neurological disorders (NDs), such as Alzheimer's disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.

Classification of recurrent major depressive disorder using a new time series feature extraction method through multisite rs-fMRI data

BACKGROUND

Major depressive disorder (MDD) has a high rate of recurrence. Identifying patients with recurrent MDD is advantageous in adopting prevention strategies to reduce the disabling effects of depression.

METHOD

We propose a novel feature extraction method that includes dynamic temporal information, and inputs the extracted features into a graph convolutional network (GCN) to achieve classification of recurrent MDD. We extract the average time series using an atlas from resting-state functional magnetic resonance imaging (fMRI) data. Pearson correlation was calculated between brain region sequences at each time point, representing the functional connectivity at each time point. The connectivity is used as the adjacency matrix and the brain region sequences as node features for a GCN model to classify recurrent MDD. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to analyze the contribution of different brain regions to the model. Brain regions making greater contribution to classification were considered to be the regions with altered brain function in recurrent MDD.

RESULT

We achieved a classification accuracy of 75.8 % for recurrent MDD on the multi-site dataset, the Rest-meta-MDD. The brain regions closely related to recurrent MDD have been identified.

LIMITATION

The pre-processing stage may affect the final classification performance and harmonizing site differences may improve the classification performance.

CONCLUSION

The experimental results demonstrate that the proposed method can effectively classify recurrent MDD and extract dynamic changes of brain activity patterns in recurrent depression.

Automatic recognition of schizophrenia from brain-network features using graph convolutional neural network

Schizophrenia is a severe mental illness that imposes considerable economic burden on families and society. However, its clinical diagnosis primarily relies on scales and doctors' clinical experience and lacks an objective and accurate diagnostic approach. In recent years, graph convolutional neural networks (GCN) have been used to assist in psychiatric diagnosis owing to their ability to learn spatial-association information. Therefore, this study proposes a schizophrenia automatic recognition model based on graph convolutional neural network. Herein, the resting-state electroencephalography (EEG) data of 103 first-episode schizophrenia patients and 92 normal controls (NCs) were obtained. The automatic recognition model was trained with a nodal feature matrix that comprised the time and frequency-domain features of the EEG signals and local features of the brain network. The most significant regions that contributed to the model classification were identified, and the correlation between the node topological features of each significant region and clinical evaluation metrics was explored. Experiments were conducted to evaluate the performance of the model using 10-fold cross-validation. The best performance in the theta frequency band with a 6 s epoch length and phase-locked value. The recognition accuracy was 90.01%. The most significant region for identifying with first-episode schizophrenia patients and NCs was located in the parietal lobe. The results of this study verify the applicability of the proposed novel method for the identification and diagnosis of schizophrenia.

Pre-COVID brain functional connectome features prospectively predict emergence of distress symptoms after onset of the COVID-19 pandemic

BACKGROUND

Persistent psychological distress associated with the coronavirus disease 2019 (COVID-19) pandemic has been well documented. This study aimed to identify pre-COVID brain functional connectome that predicts pandemic-related distress symptoms among young adults.

METHODS

Baseline neuroimaging studies and assessment of general distress using the Depression, Anxiety and Stress Scale were performed with 100 healthy individuals prior to wide recognition of the health risks associated with the emergence of COVID-19. They were recontacted for the Impact of Event Scale-Revised and the Posttraumatic Stress Disorder Checklist in the period of community-level outbreaks, and for follow-up distress evaluation again 1 year later. We employed the network-based statistic approach to identify connectome that predicted the increase of distress based on 136-region-parcellation with assigned network membership. Predictive performance of connectome features and causal relations were examined by cross-validation and mediation analyses.

RESULTS

The connectome features that predicted emergence of distress after COVID contained 70 neural connections. Most within-network connections were located in the default mode network (DMN), and affective network-DMN and dorsal attention network-DMN links largely constituted between-network pairs. The hippocampus emerged as the most critical hub region. Predictive models of the connectome remained robust in cross-validation. Mediation analyses demonstrated that COVID-related posttraumatic stress partially explained the correlation of connectome to the development of general distress.

CONCLUSIONS

Brain functional connectome may fingerprint individuals with vulnerability to psychological distress associated with the COVID pandemic. Individuals with brain neuromarkers may benefit from the corresponding interventions to reduce the risk or severity of distress related to fear of COVID-related challenges.

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

Introduction

The early diagnosis of major depressive disorder (MDD) is very important for patients that suffer from severe and irreversible consequences of depression. It has been indicated that functional connectivity (FC) analysis based on functional magnetic resonance imaging (fMRI) data can provide valuable biomarkers for clinical diagnosis. However, previous studies mainly focus on brain disease classification in small sample sizes, which may lead to dramatic divergences in classification accuracy.

Methods

This paper attempts to address this limitation by applying the deep graph convolutional neural network (DGCNN) method on a large multi-site MDD dataset. The resting-state fMRI data are acquired from 830 MDD patients and 771 normal controls (NC) shared by the REST-meta-MDD consortium.

Results

The DGCNN model trained with the binary network after thresholding, identified MDD patients from normal controls and achieved an accuracy of 72.1% with 10-fold cross-validation, which is 12.4%, 9.8%, and 7.6% higher than SVM, RF, and GCN, respectively. Moreover, the process of dataset reading and model training is faster. Therefore, it demonstrates the advantages of the DGCNN model with low time complexity and sound classification performance.

Discussion

Based on a large, multi-site dataset from MDD patients, the results expressed that DGCNN is not an extremely accurate method for MDD diagnosis. However, there is an improvement over previous methods with our goal of better understanding brain function and ultimately providing a biomarker or diagnostic capability for MDD diagnosis.

Ensemble graph neural network model for classification of major depressive disorder using whole-brain functional connectivity

Major depressive disorder (MDD) is characterized by impairments in mood and cognitive functioning, and it is a prominent source of global disability and stress. A functional magnetic resonance imaging (fMRI) can aid clinicians in their assessments of individuals for the identification of MDD. Herein, we employ a deep learning approach to the issue of MDD classification. Resting-state fMRI data from 821 individuals with MDD and 765 healthy controls (HCs) is employed for investigation. An ensemble model based on graph neural network (GNN) has been created with the goal of identifying patients with MDD among HCs as well as differentiation between first-episode and recurrent MDDs. The graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE models serve as a base models for the ensemble model that was developed with individual whole-brain functional networks. The ensemble's performance is evaluated using upsampling and downsampling, along with 10-fold cross-validation. The ensemble model achieved an upsampling accuracy of 71.18% and a downsampling accuracy of 70.24% for MDD and HC classification. While comparing first-episode patients with recurrent patients, the upsampling accuracy is 77.78% and the downsampling accuracy is 71.96%. According to the findings of this study, the proposed GNN-based ensemble model achieves a higher level of accuracy and suggests that our model produces can assist healthcare professionals in identifying MDD.

Confound-leakage: confound removal in machine learning leads to leakage

BACKGROUND

Machine learning (ML) approaches are a crucial component of modern data analysis in many fields, including epidemiology and medicine. Nonlinear ML methods often achieve accurate predictions, for instance, in personalized medicine, as they are capable of modeling complex relationships between features and the target. Problematically, ML models and their predictions can be biased by confounding information present in the features. To remove this spurious signal, researchers often employ featurewise linear confound regression (CR). While this is considered a standard approach for dealing with confounding, possible pitfalls of using CR in ML pipelines are not fully understood.

RESULTS

We provide new evidence that, contrary to general expectations, linear confound regression can increase the risk of confounding when combined with nonlinear ML approaches. Using a simple framework that uses the target as a confound, we show that information leaked via CR can increase null or moderate effects to near-perfect prediction. By shuffling the features, we provide evidence that this increase is indeed due to confound-leakage and not due to revealing of information. We then demonstrate the danger of confound-leakage in a real-world clinical application where the accuracy of predicting attention-deficit/hyperactivity disorder is overestimated using speech-derived features when using depression as a confound.

CONCLUSIONS

Mishandling or even amplifying confounding effects when building ML models due to confound-leakage, as shown, can lead to untrustworthy, biased, and unfair predictions. Our expose of the confound-leakage pitfall and provided guidelines for dealing with it can help create more robust and trustworthy ML models.

The inferior frontal gyrus and familial risk for bipolar disorder

Bipolar disorder (BD) is a familial disorder with high heritability. Genetic factors have been linked to the pathogenesis of BD. Relatives of probands with BD who are at familial risk can exhibit brain abnormalities prior to illness onset. Given its involvement in prefrontal cognitive control and in frontolimbic circuitry that regulates emotional reactivity, the inferior frontal gyrus (IFG) has been a focus of research in studies of BD-related pathology and BD-risk mechanism. In this review, we discuss multimodal neuroimaging findings of the IFG based on studies comparing at-risk relatives and low-risk controls. Review of these studies in at-risk cases suggests the presence of both risk and resilience markers related to the IFG. At-risk individuals exhibited larger gray matter volume and increased functional activities in IFG compared with low-risk controls, which might result from an adaptive brain compensation to support emotion regulation as an aspect of psychological resilience. Functional connectivity between IFG and downstream limbic or striatal areas was typically decreased in at-risk individuals relative to controls, which could contribute to risk-related problems of cognitive and emotional control. Large-scale and longitudinal investigations on at-risk individuals will further elucidate the role of IFG and other brain regions in relation to familial risk for BD, and together guide identification of at-risk individuals for primary prevention.

Multi-site harmonization of MRI data uncovers machine-learning discrimination capability in barely separable populations: An example from the ABIDE dataset

•

Multi-site MRI data encode confounding information which may mask case-control differences.

•

The impact of the NeuroHarmonize method is evaluated in the ASD-control classification.

•

We verified the successful removal of the site effect by the harmonization protocol.

•

The increment in the classification performance is quantified after data harmonization.

•

We identified the anatomical features that contributed to the two-class separation.

Machine Learning (ML) techniques have been widely used in Neuroimaging studies of Autism Spectrum Disorders (ASD) both to identify possible brain alterations related to this condition and to evaluate the predictive power of brain imaging modalities. The collection and public sharing of large imaging samples has favored an even greater diffusion of the use of ML-based analyses. However, multi-center data collections may suffer the batch effect, which, especially in case of Magnetic Resonance Imaging (MRI) studies, should be curated to avoid confounding effects for ML classifiers and masking biases. This is particularly important in the study of barely separable populations according to MRI data, such as subjects with ASD compared to controls with typical development (TD). Here, we show how the implementation of a harmo- nization protocol on brain structural features unlocks the case-control ML separation capability in the analysis of a multi-center MRI dataset. This effect is demonstrated on the ABIDE data collection, involving subjects encompassing a wide age range. After data harmonization, the overall ASD vs. TD discrimination capability by a Random Forest (RF) classifier improves from a very low performance (AUC = 0.58 ± 0.04) to a still low, but reasonably significant AUC = 0.67 ± 0.03. The performances of the RF classifier have been evaluated also in the age-specific subgroups of children, adolescents and adults, obtaining AUC = 0.62 ± 0.02, AUC = 0.65 ± 0.03 and AUC = 0.69 ± 0.06, respectively. Specific and consistent patterns of anatomical differences related to the ASD condition have been identified for the three different age subgroups.