Sparse network-based models for patient classification using fMRI

Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network

Background

Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity.

Purpose

To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN).

Methods

Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores.

Results

The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores.

Conclusion

The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI.

Supplementary Information

The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI

Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in the brain and is widely used for brain disorder analysis. Previous studies focus on extracting fMRI representations using machine/deep learning methods, but these features typically lack biological interpretability. The human brain exhibits a remarkable modular structure in spontaneous brain functional networks, with each module comprised of functionally interconnected brain regions-of-interest (ROIs). However, existing learning-based methods cannot adequately utilize such brain modularity prior. In this paper, we propose a brain modularity-constrained dynamic representation learning framework for interpretable fMRI analysis, consisting of dynamic graph construction, dynamic graph learning via a novel modularity-constrained graph neural network (MGNN), and prediction and biomarker detection. The designed MGNN is constrained by three core neurocognitive modules (i.e., salience network, central executive network, and default mode network), encouraging ROIs within the same module to share similar representations. To further enhance discriminative ability of learned features, we encourage the MGNN to preserve network topology of input graphs via a graph topology reconstruction constraint. Experimental results on 534 subjects with rs-fMRI scans from two datasets validate the effectiveness of the proposed method. The identified discriminative brain ROIs and functional connectivities can be regarded as potential fMRI biomarkers to aid in clinical diagnosis.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison

The brain's complex distributed dynamics are typically quantified using a limited set of manually selected statistical properties, leaving the possibility that alternative dynamical properties may outperform those reported for a given application. Here, we address this limitation by systematically comparing diverse, interpretable features of both intra-regional activity and inter-regional functional coupling from resting-state functional magnetic resonance imaging (rs-fMRI) data, demonstrating our method using case-control comparisons of four neuropsychiatric disorders. Our findings generally support the use of linear time-series analysis techniques for rs-fMRI case-control analyses, while also identifying new ways to quantify informative dynamical fMRI structures. While simple statistical representations of fMRI dynamics performed surprisingly well (e.g., properties within a single brain region), combining intra-regional properties with inter-regional coupling generally improved performance, underscoring the distributed, multifaceted changes to fMRI dynamics in neuropsychiatric disorders. The comprehensive, data-driven method introduced here enables systematic identification and interpretation of quantitative dynamical signatures of multivariate time-series data, with applicability beyond neuroimaging to diverse scientific problems involving complex time-varying systems.

Predicting the outcome of psilocybin treatment for depression from baseline fMRI functional connectivity

BACKGROUND

Psilocybin is a serotonergic psychedelic drug under assessment as a potential therapy for treatment-resistant and major depression. Heterogeneous treatment responses raise interest in predicting the outcome from baseline data.

METHODS

A machine learning pipeline was implemented to investigate baseline resting-state functional connectivity measured with functional magnetic resonance imaging (fMRI) as a predictor of symptom severity in psilocybin monotherapy for treatment-resistant depression (16 patients administered two 5 mg capsules followed by 25 mg, separated by one week). Generalizability was tested in a sample of 22 patients who participated in a psilocybin vs. escitalopram trial for moderate-to-severe major depression (two separate doses of 25 mg of psilocybin 3 weeks apart plus 6 weeks of daily placebo vs. two separate doses of 1 mg of psilocybin 3 weeks apart plus 6 weeks of daily oral escitalopram). The analysis was repeated using both samples combined.

RESULTS

Functional connectivity of visual, default mode and executive networks predicted early symptom improvement, while the salience network predicted responders up to 24 weeks after treatment (accuracy≈0.9). Generalization performance was borderline significant. Consistent results were obtained from the combined sample analysis. Fronto-occipital and fronto-temporal coupling predicted early and late symptom reduction, respectively.

LIMITATIONS

The number of participants and differences between the two datasets limit the generalizability of the findings, while the lack of a placebo arm limits their specificity.

CONCLUSIONS

Baseline neurophysiological measurements can predict the outcome of psilocybin treatment for depression. Future research based on larger datasets should strive to assess the generalizability of these predictions.

Decoding Autism: Uncovering patterns in brain connectivity through sparsity analysis with rs-fMRI data

BACKGROUND

In the realm of neuro-disorders, precise diagnosis and treatment rely heavily on objective imaging-based biomarker identification. This study employs a sparsity approach on resting-state fMRI to discern relevant brain region connectivity for predicting Autism.

NEW METHOD

The proposed methodology involves four key steps: (1) Utilizing three probabilistic brain atlases to extract functionally homogeneous brain regions from fMRI data. (2) Employing a hybrid approach of Graphical Lasso and Akaike Information Criteria to optimize sparse inverse covariance matrices for representing the brain functional connectivity. (3) Employing statistical techniques to scrutinize functional brain structures in Autism and Control subjects. (4) Implementing both autoencoder-based feature extraction and entire feature-based approach coupled with AI-based learning classifiers to predict Autism.

RESULTS

The ensemble classifier with the extracted feature set achieves a classification accuracy of 84.7% ± 0.3% using the MSDL atlas. Meanwhile, the 1D-CNN model, employing all features, exhibits superior classification accuracy of 88.6% ± 1.7% with the Smith 2009 (rsn70) atlas.

COMPARISON WITH EXISTING METHOD (S)

The proposed methodology outperforms the conventional correlation-based functional connectivity approach with a notably high prediction accuracy of more than 88%, whereas considering all direct and noisy indirect region-based functional connectivity, the traditional methods bound the prediction accuracy within 70% to 79%.

CONCLUSIONS

This study underscores the potential of sparsity-based FC analysis using rs-fMRI data as a prognostic biomarker for detecting Autism.

Distinct resting-state effective connectivity of large-scale networks in first-episode and recurrent major depression disorder: evidence from the REST-meta-MDD consortium

Introduction

Previous studies have shown disrupted effective connectivity in the large-scale brain networks of individuals with major depressive disorder (MDD). However, it is unclear whether these changes differ between first-episode drug-naive MDD (FEDN-MDD) and recurrent MDD (R-MDD).

Methods

This study utilized resting-state fMRI data from 17 sites in the Chinese REST-meta-MDD project, consisting of 839 patients with MDD and 788 normal controls (NCs). All data was preprocessed using a standardized protocol. Then, we performed a granger causality analysis to calculate the effectivity connectivity (EC) within and between brain networks for each participant, and compared the differences between the groups.

Results

Our findings revealed that R-MDD exhibited increased EC in the fronto-parietal network (FPN) and decreased EC in the cerebellum network, while FEDN-MDD demonstrated increased EC from the sensorimotor network (SMN) to the FPN compared with the NCs. Importantly, the two MDD subgroups displayed significant differences in EC within the FPN and between the SMN and visual network. Moreover, the EC from the cingulo-opercular network to the SMN showed a significant negative correlation with the Hamilton Rating Scale for Depression (HAMD) score in the FEDN-MDD group.

Conclusion

These findings suggest that first-episode and recurrent MDD have distinct effects on the effective connectivity in large-scale brain networks, which could be potential neural mechanisms underlying their different clinical manifestations.

Network-based diagnostic probability estimation from resting-state functional magnetic resonance imaging

Brain functional connectivity is a useful biomarker for diagnosing brain disorders. Connectivity is measured using resting-state functional magnetic resonance imaging (rs-fMRI). Previous studies have used a sequential application of the graphical model for network estimation and machine learning to construct predictive formulas for determining outcomes (e.g., disease or health) from the estimated network. However, the resulting network had limited utility for diagnosis because it was estimated independent of the outcome. In this study, we proposed a regression method with scores from rs-fMRI based on supervised sparse hierarchical components analysis (SSHCA). SSHCA has a hierarchical structure that consists of a network model (block scores at the individual level) and a scoring model (super scores at the population level). A regression model, such as the multiple logistic regression model with super scores as the predictor, was used to estimate diagnostic probabilities. An advantage of the proposed method was that the outcome-related (supervised) network connections and multiple scores corresponding to the sub-network estimation were helpful for interpreting the results. Our results in the simulation study and application to real data show that it is possible to predict diseases with high accuracy using the constructed model.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Information flow and dynamic functional connectivity during electroconvulsive therapy in patients with depression

BACKGROUND

Electroconvulsive therapy is effectively used for treatment-resistant depression; however, its neural mechanism is largely unknown. Resting-state functional magnetic resonance imaging is promising for monitoring outcomes of electroconvulsive therapy for depression. This study aimed to explore the imaging correlates of the electroconvulsive therapy effects on depression using Granger causality analysis and dynamic functional connectivity analyses.

METHODS

We performed advanced analyses of resting-state functional magnetic resonance imaging data at the beginning and intermediate stages and end of the therapeutic course to identify neural markers that reflect or predict the therapeutic effects of electroconvulsive therapy on depression.

RESULTS

We demonstrated that information flow between the functional networks analyzed by Granger causality changes during electroconvulsive therapy, and this change was correlated with the therapeutic outcome. Information flow and the dwell time (an index reflecting the temporal stability of functional connectivity) before electroconvulsive therapy are correlated with depressive symptoms during and after treatment.

LIMITATIONS

First, the sample size was small. A larger group is needed to confirm our findings. Second, the influence of concomitant pharmacotherapy on our results was not fully addressed, although we expected it to be minimal because only minor changes in pharmacotherapy occurred during electroconvulsive therapy. Third, different scanners were used the groups, although the acquisition parameters were the same; a direct comparison between patient and healthy participant data was not possible. Thus, we presented the data of the healthy participants separately from that of the patients as a reference.

CONCLUSIONS

These results show the specific properties of functional brain connectivity.

Artificial intelligence ecosystem for computational psychiatry: Ideas to practice

Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms. One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable. This may help researchers develop more effective treatments and interventions for mental health problems. This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry. The artificial intelligence ecosystem for computational psychiatry includes data acquisition, preparation, modeling, application, and evaluation. This approach allows researchers to integrate data from a variety of sources, such as brain imaging, genetics, and behavioral experiments, to obtain a more complete understanding of mental health conditions. Through the process of data preprocessing, training, and testing, the data that are required for model building can be prepared. By using machine learning, neural networks, artificial intelligence, and other methods, researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors. Despite the continuous development and breakthrough of computational psychiatry, it has not yet influenced routine clinical practice and still faces many challenges, such as data availability and quality, biological risks, equity, and data protection. As we move progress in this field, it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) data have been widely used for automated diagnosis of brain disorders such as major depressive disorder (MDD) to assist in timely intervention. Multi-site fMRI data have been increasingly employed to augment sample size and improve statistical power for investigating MDD. However, previous studies usually suffer from significant inter-site heterogeneity caused for instance by differences in scanners and/or scanning protocols. To address this issue, we develop a novel discrepancy-based unsupervised cross-domain fMRI adaptation framework (called UFA-Net) for automated MDD identification. The proposed UFA-Net is designed to model spatio-temporal fMRI patterns of labeled source and unlabeled target samples via an attention-guided graph convolution module, and also leverage a maximum mean discrepancy constrained module for unsupervised cross-site feature alignment between two domains. To the best of our knowledge, this is one of the first attempts to explore unsupervised rs-fMRI adaptation for cross-site MDD identification. Extensive evaluation on 681 subjects from two imaging sites shows that the proposed method outperforms several state-of-the-art methods. Our method helps localize disease-associated functional connectivity abnormalities and is therefore well interpretable and can facilitate fMRI-based analysis of MDD in clinical practice.

Spatiotemporal EEG Dynamics of Prospective Memory in Ageing and Mild Cognitive Impairment

Prospective memory (PM, the memory of future intentions) is one of the first complaints of those that develop dementia-related disease. Little is known about the neurophysiology of PM in ageing and those with mild cognitive impairment (MCI). By using a novel artificial neural network to investigate the spatial and temporal features of PM related brain activity, new insights can be uncovered. Young adults (n = 30), healthy older adults (n = 39) and older adults with MCI (n = 27) completed a working memory and two PM (perceptual, conceptual) tasks. Time-locked electroencephalographic potentials (ERPs) from 128-electrodes were analysed using a brain-inspired spiking neural network (SNN) architecture. Local and global connectivity from the SNNs was then evaluated. SNNs outperformed other machine learning methods in classification of brain activity between younger, older and older adults with MCI. SNNs trained using PM related brain activity had better classification accuracy than working memory related brain activity. In general, younger adults exhibited greater local cluster connectivity compared to both older adult groups. Older adults with MCI demonstrated decreased global connectivity in response to working memory and perceptual PM tasks but increased connectivity in the conceptual PM models relative to younger and healthy older adults. SNNs can provide a useful method for differentiating between those with and without MCI. Using brain activity related to PM in combination with SNNs may provide a sensitive biomarker for detecting cognitive decline. Cognitively demanding tasks may increase the amount connectivity in older adults with MCI as a means of compensation.

Common and unique neural activities in subclinical depression and major depressive disorder indicate the development of brain impairments in different depressive stages

BACKGROUND

Subclinical depression (SD) and major depressive disorder (MDD) can be considered as the early and late stages of depression, but the characteristics of intrinsic neural activity in different depressive stages are largely unknown.

METHODS

Twenty-six SD, 36 MDD subjects and 33 well-matched healthy controls (HCs) were recruited and underwent resting-state functional magnetic resonance imaging (rs-fMRI). Voxel-wise regional homogeneity (ReHo) was analyzed to explore the alterations of intrinsic neural activity, and machine learning classification based on ReHo features was performed to assess potential performance for diagnostic classification.

RESULTS

Common alterations of ReHo in both SD and MDD groups were found in the bilateral middle temporal gyrus and the left middle occipital gyrus. Opposite alterations in SD and MDD groups were found in the right superior cerebellum. Moreover, increased ReHo in the bilateral precuneus was only found in MDD, while increased ReHo in the right middle frontal gyrus and precentral gyrus were unique to SD. The distinct ReHo values correctly identified SD, MDD, and HC by linear support vector machine (SVM) with an accuracy of 77.89 %, which further verified the discrimination ability of altered ReHo in these brain regions.

LIMITATION

The sample size is relatively small.

CONCLUSION

Common and unique ReHo alterations provided insights into the development of brain impairments in depression, and helped to understand the pathophysiology of SD and MDD.

Personalized Diagnosis and Treatment for Neuroimaging in Depressive Disorders

Depressive disorders are highly heterogeneous in nature. Previous studies have not been useful for the clinical diagnosis and prediction of outcomes of major depressive disorder (MDD) at the individual level, although they provide many meaningful insights. To make inferences beyond group-level analyses, machine learning (ML) techniques can be used for the diagnosis of subtypes of MDD and the prediction of treatment responses. We searched PubMed for relevant studies published until December 2021 that included depressive disorders and applied ML algorithms in neuroimaging fields for depressive disorders. We divided these studies into two sections, namely diagnosis and treatment outcomes, for the application of prediction using ML. Structural and functional magnetic resonance imaging studies using ML algorithms were included. Thirty studies were summarized for the prediction of an MDD diagnosis. In addition, 19 studies on the prediction of treatment outcomes for MDD were reviewed. We summarized and discussed the results of previous studies. For future research results to be useful in clinical practice, ML enabling individual inferences is important. At the same time, there are important challenges to be addressed in the future.

Abnormal spontaneous neural activity in hippocampal-cortical system of patients with obsessive-compulsive disorder and its potential for diagnosis and prediction of early treatment response

Early brain functional changes induced by pharmacotherapy in patients with obsessive-compulsive disorder (OCD) in relation to drugs per se or because of the impact of such drugs on the improvement of OCD remain unclear. Moreover, no neuroimaging biomarkers are available for diagnosis of OCD and prediction of early treatment response. We performed a longitudinal study involving 34 patients with OCD and 36 healthy controls (HCs). Patients with OCD received 5-week treatment with paroxetine (40 mg/d). Resting-state functional magnetic resonance imaging (fMRI), regional homogeneity (ReHo), support vector machine (SVM), and support vector regression (SVR) were applied to acquire and analyze the imaging data. Compared with HCs, patients with OCD had higher ReHo values in the right superior temporal gyrus and bilateral hippocampus/parahippocampus/fusiform gyrus/cerebellum at baseline. ReHo values in the left hippocampus and parahippocampus decreased significantly after treatment. The reduction rate (RR) of ReHo values was positively correlated with the RRs of the scores of Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) and obsession. Abnormal ReHo values at baseline could serve as potential neuroimaging biomarkers for OCD diagnosis and prediction of early therapeutic response. This study highlighted the important role of the hippocampal-cortical system in the neuropsychological mechanism underlying OCD, pharmacological mechanism underlying OCD treatment, and the possibility of building models for diagnosis and prediction of early treatment response based on spontaneous activity in the hippocampal-cortical system.

Identification of Young High-Functioning Autism Individuals Based on Functional Connectome Using Graph Isomorphism Network: A Pilot Study

Accumulated studies have determined the changes in functional connectivity in autism spectrum disorder (ASD) and spurred the application of machine learning for classifying ASD. Graph Neural Network provides a new method for network analysis in brain disorders to identify the underlying network features associated with functional deficits. Here, we proposed an improved model of Graph Isomorphism Network (GIN) that implements the Weisfeiler-Lehman (WL) graph isomorphism test to learn the graph features while taking into account the importance of each node in the classification to improve the interpretability of the algorithm. We applied the proposed method on multisite datasets of resting-state functional connectome from Autism Brain Imaging Data Exchange (ABIDE) after stringent quality control. The proposed method outperformed other commonly used classification methods on five different evaluation metrics. We also identified salient ROIs in visual and frontoparietal control networks, which could provide potential neuroimaging biomarkers for ASD identification.

Multiview Feature Learning With Multiatlas-Based Functional Connectivity Networks for MCI Diagnosis

Functional connectivity (FC) networks built from resting-state functional magnetic resonance imaging (rs-fMRI) has shown promising results for the diagnosis of Alzheimer's disease and its prodromal stage, that is, mild cognitive impairment (MCI). FC is usually estimated as a temporal correlation of regional mean rs-fMRI signals between any pair of brain regions, and these regions are traditionally parcellated with a particular brain atlas. Most existing studies have adopted a predefined brain atlas for all subjects. However, the constructed FC networks inevitably ignore the potentially important subject-specific information, particularly, the subject-specific brain parcellation. Similar to the drawback of the "single view" (versus the "multiview" learning) in medical image-based classification, FC networks constructed based on a single atlas may not be sufficient to reveal the underlying complicated differences between normal controls and disease-affected patients due to the potential bias from that particular atlas. In this study, we propose a multiview feature learning method with multiatlas-based FC networks to improve MCI diagnosis. Specifically, a three-step transformation is implemented to generate multiple individually specified atlases from the standard automated anatomical labeling template, from which a set of atlas exemplars is selected. Multiple FC networks are constructed based on these preselected atlas exemplars, providing multiple views of the FC network-based feature representations for each subject. We then devise a multitask learning algorithm for joint feature selection from the constructed multiple FC networks. The selected features are jointly fed into a support vector machine classifier for multiatlas-based MCI diagnosis. Extensive experimental comparisons are carried out between the proposed method and other competing approaches, including the traditional single-atlas-based method. The results indicate that our method significantly improves the MCI classification, demonstrating its promise in the brain connectome-based individualized diagnosis of brain diseases.

Prediction of depression symptoms in individual subjects with face and eye movement tracking

BACKGROUND

Depression is a challenge to diagnose reliably and the current gold standard for trials of DSM-5 has been in agreement between two or more medical specialists. Research studies aiming to objectively predict depression have typically used brain scanning. Less expensive methods from cognitive neuroscience may allow quicker and more reliable diagnoses, and contribute to reducing the costs of managing the condition. In the current study we aimed to develop a novel inexpensive system for detecting elevated symptoms of depression based on tracking face and eye movements during the performance of cognitive tasks.

METHODS

In total, 75 participants performed two novel cognitive tasks with verbal affective distraction elements while their face and eye movements were recorded using inexpensive cameras. Data from 48 participants (mean age 25.5 years, standard deviation of 6.1 years, 25 with elevated symptoms of depression) passed quality control and were included in a case-control classification analysis with machine learning.

RESULTS

Classification accuracy using cross-validation (within-study replication) reached 79% (sensitivity 76%, specificity 82%), when face and eye movement measures were combined. Symptomatic participants were characterised by less intense mouth and eyelid movements during different stages of the two tasks, and by differences in frequencies and durations of fixations on affectively salient distraction words.

CONCLUSIONS

Elevated symptoms of depression can be detected with face and eye movement tracking during the cognitive performance, with a close to clinically-relevant accuracy (~80%). Future studies should validate these results in larger samples and in clinical populations.

The Altered Pattern of the Functional Connectome Related to Pathological Biomarkers in Individuals for Autism Spectrum Disorder Identification

Objective

Autism spectrum disorder (ASD) is a common neurodevelopmental disorder characterized by the development of multiple symptoms, with incidences rapidly increasing worldwide. An important step in the early diagnosis of ASD is to identify informative biomarkers. Currently, the use of functional brain network (FBN) is deemed important for extracting data on brain imaging biomarkers. Unfortunately, most existing studies have reported the utilization of the information from the connection to train the classifier; such an approach ignores the topological information and, in turn, limits its performance. Thus, effective utilization of the FBN provides insights for improving the diagnostic performance.

Methods

We propose the combination of the information derived from both FBN and its corresponding graph theory measurements to identify and distinguish ASD from normal controls (NCs). Specifically, a multi-kernel support vector machine (MK-SVM) was used to combine multiple types of information.

Results

The experimental results illustrate that the combination of information from multiple connectome features (i.e., functional connections and graph measurements) can provide a superior identification performance with an area under the receiver operating characteristic curve (ROC) of 0.9191 and an accuracy of 82.60%. Furthermore, the graph theoretical analysis illustrates that the significant nodal graph measurements and consensus connections exists mostly in the salience network (SN), default mode network (DMN), attention network, frontoparietal network, and social network.

Conclusion

This work provides insights into potential neuroimaging biomarkers that may be used for the diagnosis of ASD and offers a new perspective for the exploration of the brain pathophysiology of ASD through machine learning.

A neural network approach to optimising treatments for depression using data from specialist and community psychiatric services in Australia, New Zealand and Japan

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

Convolutional Neural Network With Graphical Lasso to Extract Sparse Topological Features for Brain Disease Classification

The functional connectivity provides new insights into the mechanisms of the human brain at network-level, which has been proved to be an effective biomarker for brain disease classification. Recently, machine learning methods have played an important role in functional connectivity classification, among which convolutional neural network (CNN) based methods become a new hot topic since they can extract topological features in the brain network. However, the conventional CNN-based methods haven't taken sparse connectivity patterns (SCPs) of the human brain into consideration, which may lead to redundancy of the topological features, and limit their performance and generalization. To solve it, we propose a novel CNN-based model with graphical Lasso (CNNGLasso) to extract sparse topological features for brain disease classification. First, we develop a novel graphical Lasso model for revealing the SCPs at group-level. Then, the SCPs are used to guide the topological feature extraction. Finally, the obtained sparse topological features are used to classify the patients from normal controls. The experiment results on the ABIDE dataset demonstrate that the CNNGLasso outperforms the others on various performances. Besides, the abnormal brain regions derived from the trained model are consistent with the previous investigations, which further proves the application prospect of the CNNGLasso.

Diagnosis of obsessive-compulsive disorder via spatial similarity-aware learning and fused deep polynomial network

Obsessive-compulsive disorder (OCD) is a type of hereditary mental illness, which seriously affect the normal life of the patients. Sparse learning has been widely used in detecting brain diseases objectively by removing redundant information and retaining monitor valuable biological characteristics from the brain functional connectivity network (BFCN). However, most existing methods ignore the relationship between brain regions in each subject. To solve this problem, this paper proposes a spatial similarity-aware learning (SSL) model to build BFCNs. Specifically, we embrace the spatial relationship between adjacent or bilaterally symmetric brain regions via a smoothing regularization term in the model. We develop a novel fused deep polynomial network (FDPN) model to further learn the powerful information and attempt to solve the problem of curse of dimensionality using BFCN features. In the FDPN model, we stack a multi-layer deep polynomial network (DPN) and integrate the features from multiple output layers via the weighting mechanism. In this way, the FDPN method not only can identify the high-level informative features of BFCN but also can solve the problem of curse of dimensionality. A novel framework is proposed to detect OCD and unaffected first-degree relatives (UFDRs), which combines deep learning and traditional machine learning methods. We validate our algorithm in the resting-state functional magnetic resonance imaging (rs-fMRI) dataset collected by the local hospital and achieve promising performance.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Spontaneous and deliberate modes of creativity: Multitask eigen-connectivity analysis captures latent cognitive modes during creative thinking

Despite substantial progress in the quest of demystifying the brain basis of creativity, several questions remain open. One such issue concerns the relationship between two latent cognitive modes during creative thinking, i.e., deliberate goal-directed cognition and spontaneous thought generation. Although an interplay between deliberate and spontaneous thinking is often implicated in the creativity literature (e.g., dual-process models), a bottom-up data-driven validation of the cognitive processes associated with creative thinking is still lacking. Here, we attempted to capture the latent modes of creative thinking by utilizing a data-driven approach on a novel continuous multitask paradigm (CMP) that widely sampled a hypothetical two-dimensional cognitive plane of deliberate and spontaneous thinking in a single fMRI session. The CMP consisted of eight task blocks ranging from undirected mind wandering to goal-directed working memory task, while also included two widely-used creativity tasks, i.e., alternate uses task (AUT) and remote association task (RAT). Using eigen-connectivity (EC) analysis on the multitask whole-brain functional connectivity (FC) patterns, we embedded the multitask FCs into a low-dimensional latent space. The first two latent components, as revealed by the EC analysis, broadly mapped onto the two cognitive modes of deliberate and spontaneous thinking, respectively. Further, in this low-dimensional space, both creativity tasks were located in the upper right corner of high deliberate and spontaneous thinking (creative cognitive space). Neuroanatomically, the creative cognitive space was represented by not only increased intra-network connectivity within executive control and default mode network, but also by higher coupling between the two canonical brain networks. Further, individual differences reflected in the low-dimensional connectivity embeddings were related to differences in deliberate and spontaneous thinking abilities. Altogether, using a continuous multitask paradigm and a data-driven approach, we provide initial empirical evidence for the contribution of both deliberate and spontaneous modes of cognition during creative thinking.

Convolutional Neural Network with Sparse Strategies to Classify Dynamic Functional Connectivity

Classification of dynamic functional connectivity (DFC) is becoming a promising approach for diagnosing various neurodegenerative diseases. However, the existing methods generally face the problem of overfitting. To solve it, this paper proposes a convolutional neural network with three sparse strategies named SCNN to classify DFC. Firstly, an element-wise filter is designed to impose sparse constraints on the DFC matrix by replacing the redundant elements with zeroes, where the DFC matrix is specially constructed to quantify the spatial and temporal variation of DFC. Secondly, a 11 convolutional filter is adopted to reduce the dimensionality of the sparse DFC matrix, and remove meaningless features resulted from zero elements in the subsequent convolution process. Finally, an extra sparse optimization classifier is employed to optimize the parameters of the above two filters, which can effectively improve the ability of SCNN to extract discriminative features. Experimental results on multiple resting-state fMRI datasets demonstrate that the proposed model provides a better classification performance of DFC compared with several state-of-the-art methods, and can identify the abnormal brain functional connectivity.

Exploring brain connectivity changes in major depressive disorder using functional-structural data fusion: A CAN-BIND-1 study

There is a growing interest in examining the wealth of data generated by fusing functional and structural imaging information sources. These approaches may have clinical utility in identifying disruptions in the brain networks that underlie major depressive disorder (MDD). We combined an existing software toolbox with a mathematically dense statistical method to produce a novel processing pipeline for the fast and easy implementation of data fusion analysis (FATCAT‐awFC). The novel FATCAT‐awFC pipeline was then utilized to identify connectivity (conventional functional, conventional structural and anatomically weighted functional connectivy) changes in MDD patients compared to healthy comparison participants (HC). Data were acquired from the Canadian Biomarker Integration Network for Depression (CAN‐BIND‐1) study. Large‐scale resting‐state networks were assessed. We found statistically significant anatomically‐weighted functional connectivity (awFC) group differences in the default mode network and the ventral attention network, with a modest effect size (d < 0.4). Functional and structural connectivity seemed to overlap in significance between one region‐pair within the default mode network. By combining structural and functional data, awFC served to heighten or reduce the magnitude of connectivity differences in various regions distinguishing MDD from HC. This method can help us more fully understand the interconnected nature of structural and functional connectivity as it relates to depression.

Spatio-temporal graph convolutional network for diagnosis and treatment response prediction of major depressive disorder from functional connectivity

The pathophysiology of major depressive disorder (MDD) has been explored to be highly associated with the dysfunctional integration of brain networks. It is therefore imperative to explore neuroimaging biomarkers to aid diagnosis and treatment. In this study, we developed a spatiotemporal graph convolutional network (STGCN) framework to learn discriminative features from functional connectivity for automatic diagnosis and treatment response prediction of MDD. Briefly, dynamic functional networks were first obtained from the resting-state fMRI with the sliding temporal window method. Secondly, a novel STGCN approach was proposed by introducing the modules of spatial graph attention convolution (SGAC) and temporal fusion. A novel SGAC was proposed to improve the feature learning ability and special anatomy prior guided pooling was developed to enable the feature dimension reduction. A temporal fusion module was proposed to capture the dynamic features of functional connectivity between adjacent sliding windows. Finally, the STGCN proposed approach was utilized to the tasks of diagnosis and antidepressant treatment response prediction for MDD. Performances of the framework were comprehensively examined with large cohorts of clinical data, which demonstrated its effectiveness in classifying MDD patients and predicting the treatment response. The sound performance suggests the potential of the STGCN for the clinical use in diagnosis and treatment prediction.

Alzheimer's disease detection using depthwise separable convolutional neural networks

To diagnose Alzheimer's disease (AD), neuroimaging methods such as magnetic resonance imaging have been employed. Recent progress in computer vision with deep learning (DL) has further inspired research focused on machine learning algorithms. However, a few limitations of these algorithms, such as the requirement for large number of training images and the necessity for powerful computers, still hinder the extensive usage of AD diagnosis based on machine learning. In addition, large number of training parameters and heavy computation make the DL systems difficult in integrating with mobile embedded devices, for example the mobile phones. For AD detection using DL, most of the current research solely focused on improving the classification performance, while few studies have been done to obtain a more compact model with less complexity and relatively high recognition accuracy. In order to solve this problem and improve the efficiency of the DL algorithm, a deep separable convolutional neural network model is proposed for AD classification in this paper. The depthwise separable convolution (DSC) is used in this work to replace the conventional convolution. Compared to the traditional neural networks, the parameters and computing cost of the proposed neural network are found greatly reduced. The parameters and computational costs of the proposed neural network are found to be significantly reduced compared with conventional neural networks. With its low power consumption, the proposed model is particularly suitable for embedding mobile devices. Experimental findings show that the DSC algorithm, based on the OASIS magnetic resonance imaging dataset, is very successful for AD detection. Moreover, transfer learning is employed in this work to improve model performance. Two trained models with complex networks, namely AlexNet and GoogLeNet, are used for transfer learning, with average classification rates of 91.40%, 93.02% and a less power consumption.

Resting-State Functional Connectivity in Mathematical Expertise

To what extent are different levels of expertise reflected in the functional connectivity of the brain? We addressed this question by using resting-state functional magnetic resonance imaging (fMRI) in mathematicians versus non-mathematicians. To this end, we investigated how the two groups of participants differ in the correlation of their spontaneous blood oxygen level-dependent fluctuations across the whole brain regions during resting state. Moreover, by using the classification algorithm in machine learning, we investigated whether the resting-state fMRI networks between mathematicians and non-mathematicians were distinguished depending on features of functional connectivity. We showed diverging involvement of the frontal-thalamic-temporal connections for mathematicians and the medial-frontal areas to precuneus and the lateral orbital gyrus to thalamus connections for non-mathematicians. Moreover, mathematicians who had higher scores in mathematical knowledge showed a weaker connection strength between the left and right caudate nucleus, demonstrating the connections' characteristics related to mathematical expertise. Separate functional networks between the two groups were validated with a maximum classification accuracy of 91.19% using the distinct resting-state fMRI-based functional connectivity features. We suggest the advantageous role of preconfigured resting-state functional connectivity, as well as the neural efficiency for experts' successful performance.

Time-evolving controllability of effective connectivity networks during seizure progression

Over one third of the estimated 3 million people with epilepsy in the United States are medication resistant. Responsive neurostimulation from chronically implanted electrodes provides a promising treatment alternative to resective surgery. However, determining optimal personalized stimulation parameters, including when and where to intervene to guarantee a positive patient outcome, is a major open challenge. Network neuroscience and control theory offer useful tools that may guide improvements in parameter selection for control of anomalous neural activity. Here we use a method to characterize dynamic controllability across consecutive effective connectivity (EC) networks based on regularized partial correlations between implanted electrodes during the onset, propagation, and termination regimes of 34 seizures. We estimate regularized partial correlation adjacency matrices from 1-s time windows of intracranial electrocorticography recordings using the Graphical Least Absolute Shrinkage and Selection Operator (GLASSO). Average and modal controllability metrics calculated from each resulting EC network track the time-varying controllability of the brain on an evolving landscape of conditionally dependent network interactions. We show that average controllability increases throughout a seizure and is negatively correlated with modal controllability throughout. Our results support the hypothesis that the energy required to drive the brain to a seizure-free state from an ictal state is smallest during seizure onset, yet we find that applying control energy at electrodes in the seizure onset zone may not always be energetically favorable. Our work suggests that a low-complexity model of time-evolving controllability may offer insights for developing and improving control strategies targeting seizure suppression.

Borderline personality disorder classification based on brain network measures during emotion regulation

Borderline Personality Disorder (BPD) is characterized by an increased emotional sensitivity and dysfunctional capacity to regulate emotions. While amygdala and prefrontal cortex interactions are regarded as the critical neural mechanisms underlying these problems, the empirical evidence hereof is inconsistent. In the current study, we aimed to systematically test different properties of brain connectivity and evaluate the predictive power to detect borderline personality disorder. Patients with borderline personality disorder (n = 51), cluster C personality disorder (n = 26) and non-patient controls (n = 44), performed an fMRI emotion regulation task. Brain network analyses focused on two properties of task-related connectivity: phasic refers to task-event dependent changes in connectivity, while tonic was defined as task-stable background connectivity. Three different network measures were estimated (strength, local efficiency, and participation coefficient) and entered as separate models in a nested cross-validated linear support vector machine classification analysis. Borderline personality disorder vs. non-patient controls classification showed a balanced accuracy of 55%, which was not significant under a permutation null-model, p = 0.23. Exploratory analyses did indicate that the tonic strength model was the highest performing model (balanced accuracy 62%), and the amygdala was one of the most important features. Despite being one of the largest data-sets in the field of BPD fMRI research, the sample size may have been limited for this type of classification analysis. The results and analytic procedures do provide starting points for future research, focusing on network measures of tonic connectivity, and potentially focusing on subgroups of BPD.

Fused Sparse Network Learning for Longitudinal Analysis of Mild Cognitive Impairment

Alzheimer's disease (AD) is a neurodegenerative disease with an irreversible and progressive process. To understand the brain functions and identify the biomarkers of AD and early stages of the disease [also known as, mild cognitive impairment (MCI)], it is crucial to build the brain functional connectivity network (BFCN) using resting-state functional magnetic resonance imaging (rs-fMRI). Existing methods have been mainly developed using only a single time-point rs-fMRI data for classification. In fact, multiple time-point data is more effective than a single time-point data in diagnosing brain diseases by monitoring the disease progression patterns using longitudinal analysis. In this article, we utilize multiple rs-fMRI time-point to identify early MCI (EMCI) and late MCI (LMCI), by integrating the fused sparse network (FSN) model with parameter-free centralized (PFC) learning. Specifically, we first construct the FSN framework by building multiple time-point BFCNs. The multitask learning via PFC is then leveraged for longitudinal analysis of EMCI and LMCI. Accordingly, we can jointly learn the multiple time-point features constructed from the BFCN model. The proposed PFC method can automatically balance the contributions of different time-point information via learned specific and common features. Finally, the selected multiple time-point features are fused by a similarity network fusion (SNF) method. Our proposed method is evaluated on the public AD neuroimaging initiative phase-2 (ADNI-2) database. The experimental results demonstrate that our method can achieve quite promising performance and outperform the state-of-the-art methods.

Task MRI-Based Functional Brain Network of Major Depression

This chapter will focus on task magnetic resonance imaging (MRI) to understand the biological mechanisms and pathophysiology of brain in major depressive disorder (MDD), which would have minor alterations in the brain function. Therefore, the functional study, such as task MRI functional connectivity, would play a crucial role to explore the brain function in MDD. Different kinds of tasks would determine the alterations in functional connectivity in task MRI studies of MDD. The emotion-related tasks are linked with alterations in anterior cingulate cortex, insula, and default mode network. The emotional memory task is linked with amygdala-hippocampus alterations. The reward-related task would be related to the reward circuit alterations, such as fronto-straital. The cognitive-related tasks would be associated with frontal-related functional connectivity alterations, such as the dorsolateral prefrontal cortex, anterior cingulate cortex, and other frontal regions. The visuo-sensory characteristics of tasks might be associated with the parieto-occipital alterations. The frontolimbic regions might be major components of task MRI-based functional connectivity in MDD. However, different scenarios and tasks would influence the representations of results.

Cost-effectiveness of neuroimaging technologies in management of psychiatric and insomnia disorders: A meta-analysis and prospective cost analysis

BACKGROUND

The optimal diagnostic strategy for patients with psychiatric and insomnia disorders has not been established yet.

PURPOSE

The purpose of this study was to perform cost-effectiveness analysis of six neuroimaging technologies in diagnosis of patients with psychiatric and insomnia disorders.

METHODS

An economic evaluation study was conducted in three parts, including a systematic review for determining diagnostic accuracy, a descriptive cross-sectional study with Activity-Based Costing (ABC) technique for tracing resource consumption, and a cost-effectiveness analysis using a short-term decision-analytic model.

RESULTS

In the first phase, 93 diagnostic accuracy studies were included in the systematic review. The accumulated results (meta-analysis) showed that the highest diagnostic accuracy for psychiatric and insomnia disorders was attributed to PET (sensitivity of 90% and specificity of 80%) and MRI (sensitivity of 76% and specificity of 78%) respectively. In the second phase of the study, we calculated the cost of each technology. The results showed that MRI has the lowest cost. Based on the results in the model of cost-effectiveness sMRI ($ 50.08 per accurate diagnosis) and MRI ($ 58.54 per accurate diagnosis) were more cost-effective neuroimaging technologies.

CONCLUSION

In psychiatric disorders, no single strategy was characterized by both low cost and high accuracy. However, MRI and PET scan had lower cost and higher accuracy for psychiatric disorders, respectively. MRI was the least costly with the highest diagnostic accuracy in insomnia disorders. Based on our model, sMRI in psychiatric disorders and MRI in insomnia disorders were the most cost-effective technologies.

A Bayesian method for inference of effective connectivity in brain networks for detecting the Mozart effect

Several studies claim that listening to Mozart music affects cognition and can be used to treat neurological conditions like epilepsy. Research into this Mozart effect has not addressed how dynamic interactions between brain networks, i.e. effective connectivity, are affected. The Granger-causality analysis is often used to infer effective connectivity. First, we investigate if a new method, Bayesian topology identification, can be used as an alternative. Both methods are evaluated on simulation data, where the Bayesian method outperforms the Granger-causality analysis in the inference of connectivity graphs of dynamic networks, especially for short data lengths. In the second part, the Bayesian method is extended to enable the inference of changes in effective connectivity between groups of subjects. Next, we apply both methods to fMRI scans of 16 healthy subjects, who were scanned before and after the exposure to Mozart's sonata K448 at least 2 hours a day for 7 days. Here, we investigate if the effective connectivity of the subjects significantly changed after listening to Mozart music. The Bayesian method detected changes in effective connectivity between networks related to cognitive processing and control in the connection from the central executive to the superior sensori-motor network, in the connection from the posterior default mode to the fronto-parietal right network, and in the connection from the anterior default mode to the dorsal attention network. This last connection was only detected in a subgroup of subjects with a longer listening duration. Only in this last connection, an effect was found by the Granger-causality analysis.

Diagnostic classification of autism using resting-state fMRI data improves with full correlation functional brain connectivity compared to partial correlation

BACKGROUND

Autism Spectrum Disorder (ASD) is a neurodevelopmental disability with altered connectivity in brain networks.

NEW METHOD

In this study, brain connections in Resting-state functional Magnetic Resonance Imaging (Rs-fMRI) of ASD and Typical Developing (TD) are analyzed by partial and full correlation methods such as Gaussian Graphical Least Absolute Shrinkage and Selection Operator (GLASSO), Max-Det Matrix Completion (MDMC), and Pearson Correlation Co-Efficient (PCCE). We investigated Functional Connectivity (FC) of ASD and TD brain from 238 functionally defined regions of interest. Furthermore, we constructed a series of feature sets by applying conditional random forests and conditional permutation importance. We built classifier models by Random Forest (RF), Oblique RF (ORF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) for each feature set. FC features are ranked based on p-value and we analyzed the top 20 FC features.

RESULTS

We achieved a single-trial test accuracy of 72.5 %, though MDMC-SVM and PCCE-CNN pipelines. Further, PCCE-CNN pipeline gives better average test accuracy (70.31 %) and area under the curve (0.73) compared to other pipelines. We found that top-20 PCCE based FC features are from networks such as Dorsal Attention (DA), Cingulo-Opercular Task Control (COTC), somatosensory motor hand and subcortical. In addition, among top 20 PCCE features, many FC links are found between COTC and DA (4 connections) which helped to discriminate the ASD and TD.

COMPARISON WITH EXISTING METHODS AND CONCLUSIONS

The generalized classifier models built in our study for highly heterogeneous participants perform better than previous studies with similar data sets and diagnostic groups.

Fusion of ULS Group Constrained High- and Low-Order Sparse Functional Connectivity Networks for MCI Classification

Functional connectivity networks, derived from resting-state fMRI data, have been found as effective biomarkers for identifying mild cognitive impairment (MCI) from healthy elderly. However, the traditional functional connectivity network is essentially a low-order network with the assumption that the brain activity is static over the entire scanning period, ignoring temporal variations among the correlations derived from brain region pairs. To overcome this limitation, we proposed a new type of sparse functional connectivity network to precisely describe the relationship of temporal correlations among brain regions. Specifically, instead of using the simple pairwise Pearson's correlation coefficient as connectivity, we first estimate the temporal low-order functional connectivity for each region pair based on an ULS Group constrained-UOLS regression algorithm, where a combination of ultra-least squares (ULS) criterion with a Group constrained topology structure detection algorithm is applied to detect the topology of functional connectivity networks, aided by an Ultra-Orthogonal Least Squares (UOLS) algorithm to estimate connectivity strength. Compared to the classical least squares criterion which only measures the discrepancy between the observed signals and the model prediction function, the ULS criterion takes into consideration the discrepancy between the weak derivatives of the observed signals and the model prediction function and thus avoids the overfitting problem. By using a similar approach, we then estimate the high-order functional connectivity from the low-order connectivity to characterize signal flows among the brain regions. We finally fuse the low-order and the high-order networks using two decision trees for MCI classification. Experimental results demonstrate the effectiveness of the proposed method on MCI classification.

Functional connectivity network estimation with an inter-similarity prior for mild cognitive impairment classification

Functional connectivity network (FCN) analysis is an effective technique for modeling human brain patterns and diagnosing neurological disorders such as Alzheimer's disease (AD) and its early stage, Mild Cognitive Impairment. However, accurately estimating biologically meaningful and discriminative FCNs remains challenging due to the poor quality of functional magnetic resonance imaging (fMRI) data and our limited understanding of the human brain. Inspired by the inter-similarity nature of FCNs, similar regions of interest tend to share similar connection patterns. Here, we propose a functional brain network modeling scheme by encoding Inter-similarity prior into a graph-regularization term, which can be easily solved with an efficient optimization algorithm. To illustrate its effectiveness, we conducted experiments to distinguish Mild Cognitive Impairment from normal controls based on their respective FCNs. Our method outperformed the baseline and state-of-the-art methods by achieving an 88.19% classification accuracy. Furthermore, post hoc inspection of the informative features showed that our method yielded more biologically meaningful functional brain connectivity.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection

Many vision-based applications rely on logistic regression for embedding classification within a probabilistic context, such as recognition in images and videos or identifying disease-specific image phenotypes from neuroimages. Logistic regression, however, often performs poorly when trained on data that is noisy, has irrelevant features, or when the samples are distributed across the classes in an imbalanced setting; a common occurrence in visual recognition tasks. To deal with those issues, researchers generally rely on ad-hoc regularization techniques or model a subset of these issues. We instead propose a mathematically sound logistic regression model that selects a subset of (relevant) features and (informative and balanced) set of samples during the training process. The model does so by applying cardinality constraints (via l₀-'norm' sparsity) on the features and samples. l₀ defines sparsity in mathematical settings but in practice has mostly been approximated (e.g., via l₁ or its variations) for computational simplicity. We prove that a local minimum to the non-convex optimization problems induced by cardinality constraints can be computed by combining block coordinate descent with penalty decomposition. On synthetic, image recognition, and neuroimaging datasets, we show that the accuracy of the method is higher than alternative methods and classifiers commonly used in the literature.

Dynamics of Cortical Local Connectivity during Sleep-Wake States and the Homeostatic Process

Sleep exerts modulatory effects on the cerebral cortex. Whether sleep modulates local connectivity in the cortex or only individual neural activity, however, is poorly understood. Here we investigated functional connectivity, that is, covarying activity between neurons, during spontaneous sleep-wake states and during and after sleep deprivation using calcium imaging of identified excitatory/inhibitory neurons in the motor cortex. Functional connectivity was estimated with a statistical learning approach glasso and quantified by "the probability of establishing connectivity (sparse/dense)" and "the strength of the established connectivity (weak/strong)." Local cortical connectivity was sparse in non-rapid eye movement (NREM) sleep and dense in REM sleep, which was similar in both excitatory and inhibitory neurons. The overall mean strength of the connectivity did not differ largely across spontaneous sleep-wake states. Sleep deprivation induced strong excitatory/inhibitory and dense inhibitory, but not excitatory, connectivity. Subsequent NREM sleep after sleep deprivation exhibited weak excitatory/inhibitory, sparse excitatory, and dense inhibitory connectivity. These findings indicate that sleep-wake states modulate local cortical connectivity, and the modulation is large and compensatory for stability of local circuits during the homeostatic control of sleep, which contributes to plastic changes in neural information flow.

Heterogeneity of Preictal Dynamics in Human Epileptic Seizures

It is generally understood that there is a preictal phase in the development of a seizure and this precictal period is the basis for seizure prediction attempts. The focus of this study is the preictal global spatiotemporal dynamics and its intra-patient variability. We analyzed preictal broadband brain connectivity from human electrocorticography (ECoG) recordings of 185 seizures (which included 116 clinical seizures) collected from 12 patients. ECoG electrodes record from only a part of the cortex, leaving large regions of the brain unobserved. Brain connectivity was therefore estimated using the sparse-plus-latent-regularized precision matrix (SLRPM) method, which calculates connectivity from partial correlations of the conditional statistics of the observed regions given the unobserved latent regions. Brain connectivity was quantified using eigenvector centrality (EC), from which a degree of heterogeneity was calculated for the preictal periods of all seizures in each patient. Results from the SLRPM method are compared to those from the sparse-regularized precision matrix (SRPM) and correlation methods, which do not account for the unobserved inputs when estimating brain connectivity. The degree of heterogeneity estimated by the SLRPM method is higher than those estimated by the SRPM and correlation methods for the preictal periods in most patients. These results reveal substantial heterogeneity or desynchronization among brain areas in the preictal period of human epileptic seizures. Furthermore, the SLRPM method identifies more onset channels from the preictal active electrodes compared to the SRPM and correlation methods. Finally, the correlation between the degree of heterogeneity and seizure severity of patients for SLRPM and SRPM methods were lower than that obtained from the correlation method. These results support recent findings suggesting that inhibitory neurons can have anti-seizure effects by inducing variability or heterogeneity across seizures. Understanding how this variability is linked to seizure initiation may lead to better predictions and controlling therapies.