A Review of Challenges in the Use of fMRI for Disease Classification / Characterization and A Projection Pursuit Application from Multi-site fMRI Schizophrenia Study

Neurodevelopmental subtypes of functional brain organization in the ABCD study using a rigorous analytic framework

The current study demonstrates that an individual's resting-state functional connectivity (RSFC) is a dependable biomarker for identifying differential patterns of cognitive and emotional functioning during late childhood. Using baseline RSFC data from the Adolescent Brain Cognitive Development (ABCD) study, which includes children aged 9-11, we identified four distinct RSFC subtypes. We introduce an integrated methodological pipeline for testing the reliability and importance of these subtypes. In the Identification phase, Leiden Community Detection defined RSFC subtypes, with their reproducibility confirmed through a split-sample technique in the Validation stage. The Evaluation phase showed that distinct cognitive and mental health profiles are associated with each subtype, with the Predictive phase indicating that subtypes better predict various cognitive and mental health characteristics than individual RSFC connections. The Replication stage employed bootstrapping and down-sampling methods to substantiate the reproducibility of these subtypes further. This work allows future explorations of developmental trajectories of these RSFC subtypes.

A new transfer entropy method for measuring directed connectivity from complex-valued fMRI data

Background

Inferring directional connectivity of brain regions from functional magnetic resonance imaging (fMRI) data has been shown to provide additional insights into predicting mental disorders such as schizophrenia. However, existing research has focused on the magnitude data from complex-valued fMRI data without considering the informative phase data, thus ignoring potentially important information.

Methods

We propose a new complex-valued transfer entropy (CTE) method to measure causal links among brain regions in complex-valued fMRI data. We use the transfer entropy to model a general non-linear magnitude-magnitude and phase-phase directed connectivity and utilize partial transfer entropy to measure the complementary phase and magnitude effects on magnitude-phase and phase-magnitude causality. We also define the significance of the causality based on a statistical test and the shuffling strategy of the two complex-valued signals.

Results

Simulated results verified higher accuracy of CTE than four causal analysis methods, including a simplified complex-valued approach and three real-valued approaches. Using experimental fMRI data from schizophrenia and controls, CTE yields results consistent with previous findings but with more significant group differences. The proposed method detects new directed connectivity related to the right frontal parietal regions and achieves 10.2-20.9% higher SVM classification accuracy when inferring directed connectivity using anatomical automatic labeling (AAL) regions as features.

Conclusion

The proposed CTE provides a new general method for fully detecting highly predictive directed connectivity from complex-valued fMRI data, with magnitude-only fMRI data as a specific case.

Unveiling the potential of machine learning in schizophrenia diagnosis: A meta-analytic study of task-based neuroimaging data

The emergence of machine learning (ML) techniques has opened up new avenues for identifying biomarkers associated with schizophrenia (SCZ) using task-related fMRI (t-fMRI) designs. To evaluate the effectiveness of this approach, we conducted a comprehensive meta-analysis of 31 t-fMRI studies using a bivariate model. Our findings revealed a high overall sensitivity of 0.83 and specificity of 0.82 for t-fMRI studies. Notably, neuropsychological domains modulated the classification performance, with selective attention demonstrating a significantly higher specificity than working memory (β = 0.98, z = 2.11, P = 0.04). Studies involving older, chronic patients with SCZ reported higher sensitivity (P <0.015) and specificity (P <0.001) than those involving younger, first-episode patients or high-risk individuals for psychosis. Additionally, we found that the severity of negative symptoms was positively associated with the specificity of the classification model (β = 7.19, z = 2.20, P = 0.03). Taken together, these results support the potential of using task-based fMRI data in combination with machine learning techniques to identify biomarkers related to symptom outcomes in SCZ, providing a promising avenue for improving diagnostic accuracy and treatment efficacy. Future attempts to deploy ML classification should consider the factors of algorithm choice, data quality and quantity, as well as issues related to generalization.

Groupwise structural sparsity for discriminative voxels identification

This paper investigates the selection of voxels for functional Magnetic Resonance Imaging (fMRI) brain data. We aim to identify a comprehensive set of discriminative voxels associated with human learning when exposed to a neutral visual stimulus that predicts an aversive outcome. However, due to the nature of the unconditioned stimuli (typically a noxious stimulus), it is challenging to obtain sufficient sample sizes for psychological experiments, given the tolerability of the subjects and ethical considerations. We propose a stable hierarchical voting (SHV) mechanism based on stability selection to address this challenge. This mechanism enables us to evaluate the quality of spatial random sampling and minimizes the risk of false and missed detections. We assess the performance of the proposed algorithm using simulated and publicly available datasets. The experiments demonstrate that the regularization strategy choice significantly affects the results' interpretability. When applying our algorithm to our collected fMRI dataset, it successfully identifies sparse and closely related patterns across subjects and displays stable weight maps for three experimental phases under the fear conditioning paradigm. These findings strongly support the causal role of aversive conditioning in altering visual-cortical activity.

Effects of randomness in the development of machine learning models in neuroimaging studies of schizophrenia

Numerous studies have used machine learning with neuroimaging data for identifying individuals with a schizophrenia diagnosis. However, inconsistent results have limited the ability of the psychiatric community to objectively judge and accept the value of this approach. One factor that has contributed to the inconsistency, but has long been ignored, is randomness in the practice of machine learning. This is manifest when executing the same machine learning pipeline multiple times on the same dataset but getting different results. In the current study, a dataset of anatomical MRI scans from 158 patients with first-episode medication-naïve schizophrenia and 166 matched controls was used to investigate the effect of randomness on classifier performance estimates under different algorithm complexity and data splitting ratios. The maximum discriminatory accuracy that could be reached was 62.6 % ± 4.7 % (43.5 %-79.3 %) obtained when using extra-trees classifiers without feature normalization. Regions contributing to discrimination were located at bilateral temporal lobes and right frontal lobe. The results show that randomness has a significant impact on the precision of model performance estimates, especially when the size of test set is small. Current neuroimaging feature engineering combined with machine learning still falls short of being able to make diagnoses in the clinical context, but has value in revealing patterns of regional brain alteration associated with the illness. The current results indicate that effects of randomness on model performance should be reported and considered in interpreting model utility and it is necessary to evaluate models on large test sets to obtain valid estimates of model performance.

Decoding with confidence: Statistical control on decoder maps

In brain imaging, decoding is widely used to infer relationships between brain and cognition, or to craft brain-imaging biomarkers of pathologies. Yet, standard decoding procedures do not come with statistical guarantees, and thus do not give confidence bounds to interpret the pattern maps that they produce. Indeed, in whole-brain decoding settings, the number of explanatory variables is much greater than the number of samples, hence classical statistical inference methodology cannot be applied. Specifically, the standard practice that consists in thresholding decoding maps is not a correct inference procedure. We contribute a new statistical-testing framework for this type of inference. To overcome the statistical inefficiency of voxel-level control, we generalize the Family Wise Error Rate (FWER) to account for a spatial tolerance δ, introducing the δ-Family Wise Error Rate (δ-FWER). Then, we present a decoding procedure that can control the δ-FWER: the Ensemble of Clustered Desparsified Lasso (EnCluDL), a procedure for multivariate statistical inference on high-dimensional structured data. We evaluate the statistical properties of EnCluDL with a thorough empirical study, along with three alternative procedures including decoder map thresholding. We show that EnCluDL exhibits the best recovery properties while ensuring the expected statistical control.

Structural and Functional Features of Developing Brain Capillaries, and Their Alteration in Schizophrenia

Schizophrenia affects more than 1% of the world's population and shows very high heterogeneity in the positive, negative, and cognitive symptoms experienced by patients. The pathogenic mechanisms underlying this neurodevelopmental disorder are largely unknown, although it is proposed to emerge from multiple genetic and environmental risk factors. In this work, we explore the potential alterations in the developing blood vessel network which could contribute to the development of schizophrenia. Specifically, we discuss how the vascular network evolves during early postnatal life and how genetic and environmental risk factors can lead to detrimental changes. Blood vessels, capillaries in particular, constitute a dynamic and complex infrastructure distributing oxygen and nutrients to the brain. During postnatal development, capillaries undergo many structural and anatomical changes in order to form a fully functional, mature vascular network. Advanced technologies like magnetic resonance imaging and near infrared spectroscopy are now enabling to study how the brain vasculature and its supporting features are established in humans from birth until adulthood. Furthermore, the contribution of the different neurovascular unit elements, including pericytes, endothelial cells, astrocytes and microglia, to proper brain function and behavior, can be dissected. This investigation conducted among different brain regions altered in schizophrenia, such as the prefrontal cortex, may provide further evidence that schizophrenia can be considered a neurovascular disorder.

Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets

There are growing concerns about the generalizability of machine learning classifiers in neuroimaging. In order to evaluate this aspect across relatively large heterogeneous populations, we investigated four disorders: Autism spectrum disorder (N = 988), Attention deficit hyperactivity disorder (N = 930), Post-traumatic stress disorder (N = 87) and Alzheimer's disease (N = 132). We applied 18 different machine learning classifiers (based on diverse principles) wherein the training/validation and the hold-out test data belonged to samples with the same diagnosis but differing in either the age range or the acquisition site. Our results indicate that overfitting can be a huge problem in heterogeneous datasets, especially with fewer samples, leading to inflated measures of accuracy that fail to generalize well to the general clinical population. Further, different classifiers tended to perform well on different datasets. In order to address this, we propose a consensus-classifier by combining the predictive power of all 18 classifiers. The consensus-classifier was less sensitive to unmatched training/validation and holdout test data. Finally, we combined feature importance scores obtained from all classifiers to infer the discriminative ability of connectivity features. The functional connectivity patterns thus identified were robust to the classification algorithm used, age and acquisition site differences, and had diagnostic predictive ability in addition to univariate statistically significant group differences between the groups. A MATLAB toolbox called Machine Learning in NeuroImaging (MALINI), which implements all the 18 different classifiers along with the consensus classifier is available from Lanka et al. (2019) The toolbox can also be found at the following URL: https://github.com/pradlanka/malini .

Density-based clustering of static and dynamic functional MRI connectivity features obtained from subjects with cognitive impairment

Various machine-learning classification techniques have been employed previously to classify brain states in healthy and disease populations using functional magnetic resonance imaging (fMRI). These methods generally use supervised classifiers that are sensitive to outliers and require labeling of training data to generate a predictive model. Density-based clustering, which overcomes these issues, is a popular unsupervised learning approach whose utility for high-dimensional neuroimaging data has not been previously evaluated. Its advantages include insensitivity to outliers and ability to work with unlabeled data. Unlike the popular k-means clustering, the number of clusters need not be specified. In this study, we compare the performance of two popular density-based clustering methods, DBSCAN and OPTICS, in accurately identifying individuals with three stages of cognitive impairment, including Alzheimer’s disease. We used static and dynamic functional connectivity features for clustering, which captures the strength and temporal variation of brain connectivity respectively. To assess the robustness of clustering to noise/outliers, we propose a novel method called recursive-clustering using additive-noise (R-CLAN). Results demonstrated that both clustering algorithms were effective, although OPTICS with dynamic connectivity features outperformed in terms of cluster purity (95.46%) and robustness to noise/outliers. This study demonstrates that density-based clustering can accurately and robustly identify diagnostic classes in an unsupervised way using brain connectivity.

Hierarchical Structured Sparse Learning for Schizophrenia Identification

Fractional amplitude of low-frequency fluctuation (fALFF) has been widely used for resting-state functional magnetic resonance imaging (rs-fMRI) based schizophrenia (SZ) diagnosis. However, previous studies usually measure the fALFF within low-frequency fluctuation (from 0.01 to 0.08Hz), which cannot fully cover the complex neural activity pattern in the resting-state brain. In addition, existing studies usually ignore the fact that each specific frequency band can delineate the unique spontaneous fluctuations of neural activities in the brain. Accordingly, in this paper, we propose a novel hierarchical structured sparse learning method to sufficiently utilize the specificity and complementary structure information across four different frequency bands (from 0.01Hz to 0.25Hz) for SZ diagnosis. The proposed method can help preserve the partial group structures among multiple frequency bands and the specific characters in each frequency band. We further develop an efficient optimization algorithm to solve the proposed objective function. We validate the efficacy of our proposed method on a real SZ dataset. Also, to demonstrate the generality of the method, we apply our proposed method on a subset of Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results on both datasets demonstrate that our proposed method achieves promising performance in brain disease classification, compared with several state-of-the-art methods.

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.

A toolbox for brain network construction and classification (BrainNetClass)

Brain functional network has been increasingly used in understanding brain functions and diseases. While many network construction methods have been proposed, the progress in the field still largely relies on static pairwise Pearson's correlation-based functional network and group-level comparisons. We introduce a "Brain Network Construction and Classification (BrainNetClass)" toolbox to promote more advanced brain network construction methods to the filed, including some state-of-the-art methods that were recently developed to capture complex and high-order interactions among brain regions. The toolbox also integrates a well-accepted and rigorous classification framework based on brain connectome features toward individualized disease diagnosis in a hope that the advanced network modeling could boost the subsequent classification. BrainNetClass is a MATLAB-based, open-source, cross-platform toolbox with both graphical user-friendly interfaces and a command line mode targeting cognitive neuroscientists and clinicians for promoting reliability, reproducibility, and interpretability of connectome-based, computer-aided diagnosis. It generates abundant classification-related results from network presentations to contributing features that have been largely ignored by most studies to grant users the ability of evaluating the disease diagnostic model and its robustness and generalizability. We demonstrate the effectiveness of the toolbox on real resting-state functional MRI datasets. BrainNetClass (v1.0) is available at https://github.com/zzstefan/BrainNetClass.

Sparse representation and dictionary learning model incorporating group sparsity and incoherence to extract abnormal brain regions associated with schizophrenia

Schizophrenia is a complex mental illness, the mechanism of which is currently unclear. Using sparse representation and dictionary learning (SDL) model to analyze functional magnetic resonance imaging (fMRI) dataset of schizophrenia is currently a popular method for exploring the mechanism of the disease. The SDL method decomposed the fMRI data into a sparse coding matrix X and a dictionary matrix D. However, these traditional methods overlooked group structure information in X and the coherence between the atoms in D. To address this problem, we propose a new SDL model incorporating group sparsity and incoherence, namely GS2ISDL to detect abnormal brain regions. Specifically, GS2ISDL uses the group structure information that defined by AAL anatomical template from fMRI dataset as priori to achieve inter-group sparsity in X. At the same time, L ₁ - norm is enforced on X to achieve intra-group sparsity. In addition, our algorithm also imposes incoherent constraint on the dictionary matrix D to reduce the coherence between the atoms in D, which can ensure the uniqueness of X and the discriminability of the atoms. To validate our proposed model GS2ISDL, we compared it with both IK-SVD and SDL algorithm for analyzing fMRI dataset collected by Mind Clinical Imaging Consortium (MCIC). The results show that the accuracy, sensitivity, recall and MCC values of GS2ISDL are 93.75%, 95.23%, 80.50% and 88.19%, respectively, which outperforms both IK-SVD and SDL. The ROIs extracted by GS2ISDL model (such as Precentral gyrus, Hippocampus and Caudate nucleus, etc.) are further verified by the literature review on schizophrenia studies, which have significant biological significance.

Construction, comparison and evolution of networks in life sciences and other disciplines

Network approaches have become pervasive in many research fields. They allow for a more comprehensive understanding of complex relationships between entities as well as their group-level properties and dynamics. Many networks change over time, be it within seconds or millions of years, depending on the nature of the network. Our focus will be on comparative network analyses in life sciences, where deciphering temporal network changes is a core interest of molecular, ecological, neuropsychological and evolutionary biologists. Further, we will take a journey through different disciplines, such as social sciences, finance and computational gastronomy, to present commonalities and differences in how networks change and can be analysed. Finally, we envision how borrowing ideas from these disciplines could enrich the future of life science research.

Estimating Dynamic Functional Brain Connectivity With a Sparse Hidden Markov Model

Estimating dynamic functional network connectivity (dFNC) of the brain from functional magnetic resonance imaging (fMRI) data can reveal both spatial and temporal organization and can be applied to track the developmental trajectory of brain maturity as well as to study mental illness. Resting state fMRI (rs-fMRI) is regarded as a promising task since it reflects the spontaneous brain activity without an external stimulus. The sliding window method has been successfully used to extract dFNC but typically assumes a fixed window size. The hidden Markov model (HMM) based method is an alternative approach for estimating time-varying connectivity. In this paper, we propose a sparse HMM based on Gaussian HMM and Gaussian graphical model (GGM). In this model, the time-varying neural processes are represented as discrete brain states which are described with functional connectivity networks. By enforcing the sparsity on the precision matrix, we can get interpretable connectivity between different functional regions. The optimization of our model can be realized with the expectation maximization (EM) and graphical least absolute shrinkage and selection operator (glasso) algorithms. The proposed model is validated on both simulated blood oxygenation-level dependent (BOLD) time series and rs-fMRI data. Results indicate that the proposed model can capture both stationary and abrupt brain activity fluctuations. We also compare dFNC patterns between children and young adults from the Philadelphia Neurodevelopmental Cohort (PNC) study. Both spatial and temporal behavior of the dFNC are analyzed and compared. The results provide insight into the developmental trajectory across childhood and motivate further research on brain connectivity.

Locally Linear Embedding and fMRI Feature Selection in Psychiatric Classification

BACKGROUND

Functional magnetic resonance imaging (fMRI) provides non-invasive measures of neuronal activity using an endogenous Blood Oxygenation-Level Dependent (BOLD) contrast. This article introduces a nonlinear dimensionality reduction (Locally Linear Embedding) to extract informative measures of the underlying neuronal activity from BOLD time-series. The method is validated using the Leave-One-Out-Cross-Validation (LOOCV) accuracy of classifying psychiatric diagnoses using resting-state and task-related fMRI.

METHODS

Locally Linear Embedding of BOLD time-series (into each voxel's respective tensor) was used to optimise feature selection. This uses Gauß' Principle of Least Constraint to conserve quantities over both space and time. This conservation was assessed using LOOCV to greedily select time points in an incremental fashion on training data that was categorised in terms of psychiatric diagnoses.

FINDINGS

The embedded fMRI gave highly diagnostic performances (> 80%) on eleven publicly-available datasets containing healthy controls and patients with either Schizophrenia, Attention-Deficit Hyperactivity Disorder (ADHD), or Autism Spectrum Disorder (ASD). Furthermore, unlike the original fMRI data before or after using Principal Component Analysis (PCA) for artefact reduction, the embedded fMRI furnished significantly better than chance classification (defined as the majority class proportion) on ten of eleven datasets.

INTERPRETATION

Locally Linear Embedding appears to be a useful feature extraction procedure that retains important information about patterns of brain activity distinguishing among psychiatric cohorts.

Neuroimaging in Psychiatry and Neurodevelopment: why the emperor has no clothes

Neuroimaging has been a dominant force in guiding research into psychiatric and neurodevelopmental disorders for decades, yet researchers have been unable to formulate sensitive or specific imaging tests for these conditions. The search for neuroimaging biomarkers has been constrained by limited reproducibility of imaging techniques, limited tools for evaluating neurochemistry, heterogeneity of patient populations not defined by brain-based phenotypes, limited exploration of temporal components of brain function, and relatively few studies evaluating developmental and longitudinal trajectories of brain function. Opportunities for development of clinically impactful imaging metrics include longer duration functional imaging data sets, new engineering approaches to mitigate suboptimal spatiotemporal resolution, improvements in image post-processing and analysis strategies, big data approaches combined with data sharing of multisite imaging samples, and new techniques that allow dynamical exploration of brain function across multiple timescales. Despite narrow clinical impact of neuroimaging methods, there is reason for optimism that imaging will contribute to diagnosis, prognosis, and treatment monitoring for psychiatric and neurodevelopmental disorders in the near future.

Tractography-based classification in distinguishing patients with first-episode schizophrenia from healthy individuals

BACKGROUND

Schizophrenia has been characterized as a neurodevelopmental disorder of brain disconnectivity. However, whether disrupted integrity of white matter tracts in schizophrenia can potentially serve as individual discriminative biomarkers remains unclear.

METHODS

A random forest algorithm was applied to tractography-based diffusion properties obtained from a cohort of 65 patients with first-episode schizophrenia (FES) and 60 healthy individuals to investigate the machine-learning discriminative power of white matter disconnectivity. Recursive feature elimination was used to select the ultimate white matter features in the classification. Relationships between algorithm-predicted probabilities and clinical characteristics were also examined in the FES group.

RESULTS

The classifier was trained by 80% of the sample. Patients were distinguished from healthy individuals with an overall accuracy of 71.0% (95% confident interval: 61.1%, 79.6%), a sensitivity of 67.3%, a specificity of 75.0%, and the area under receiver operating characteristic curve (AUC) was 79.3% (χ2 p < 0.001). In validation using the held-up 20% of the sample, patients were distinguished from healthy individuals with an overall accuracy of 76.0% (95% confident interval: 54.9%, 90.6%), a sensitivity of 76.9%, a specificity of 75.0%, and an AUC of 73.1% (χ2 p = 0.012). Diffusion properties of inter-hemispheric fibres, the cerebello-thalamo-cortical circuits and the long association fibres were identified to be the most discriminative in the classification. Higher predicted probability scores were found in younger patients.

CONCLUSIONS

Our findings suggest that the widespread connectivity disruption observed in FES patients, especially in younger patients, might be considered potential individual discriminating biomarkers.

Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.

Machine learning in major depression: From classification to treatment outcome prediction

AIMS

Major depression disorder (MDD) is the single greatest cause of disability and morbidity, and affects about 10% of the population worldwide. Currently, there are no clinically useful diagnostic biomarkers that are able to confirm a diagnosis of MDD from bipolar disorder (BD) in the early depressive episode. Therefore, exploring translational biomarkers of mood disorders based on machine learning is in pressing need, though it is challenging, but with great potential to improve our understanding of these disorders.

DISCUSSIONS

In this study, we review popular machine-learning methods used for brain imaging classification and predictions, and provide an overview of studies, specifically for MDD, that have used magnetic resonance imaging data to either (a) classify MDDs from controls or other mood disorders or (b) investigate treatment outcome predictors for individual patients. Finally, challenges, future directions, and potential limitations related to MDD biomarker identification are also discussed, with a goal of offering a comprehensive overview that may help readers to better understand the applications of neuroimaging data mining in depression.

CONCLUSIONS

We hope such efforts may highlight the need for an urgently needed paradigm shift in treatment, to guide personalized optimal clinical care.

A review and outlook on visual analytics for uncertainties in functional magnetic resonance imaging

Analysis of functional magnetic resonance imaging (fMRI) plays a pivotal role in uncovering an understanding of the brain. fMRI data contain both spatial volume and temporal signal information, which provide a depiction of brain activity. The analysis pipeline, however, is hampered by numerous uncertainties in many of the steps; often seen as one of the last hurdles for the domain. In this review, we categorise fMRI research into three pipeline phases: (i) image acquisition and processing; (ii) image analysis; and (iii) visualisation and human interpretation, to explore the uncertainties that arise in each phase, including the compound effects due to the inter-dependence of steps. Attempts at mitigating uncertainties rely on providing interactive visual analytics that aid users in understanding the effects of the uncertainties and adjusting their analyses. This impetus for visual analytics comes in light of considerable research investigating uncertainty throughout the pipeline. However, to the best of our knowledge, there is yet to be a comprehensive review on the importance and utility of uncertainty visual analytics (UVA) in addressing fMRI concerns, which we term fMRI-UVA. Such techniques have been broadly implemented in related biomedical fields, and its potential for fMRI has recently been explored; however, these attempts are limited in their scope and utility, primarily focussing on addressing small parts of single pipeline phases. Our comprehensive review of the fMRI uncertainties from the perspective of visual analytics addresses the three identified phases in the pipeline. We also discuss the two interrelated approaches for future research opportunities for fMRI-UVA.

Decoding diagnosis and lifetime consumption in alcohol dependence from grey-matter pattern information

OBJECTIVE

We investigated the potential of computer-based models to decode diagnosis and lifetime consumption in alcohol dependence (AD) from grey-matter pattern information. As machine-learning approaches to psychiatric neuroimaging have recently come under scrutiny due to unclear generalization and the opacity of algorithms, our investigation aimed to address a number of methodological criticisms.

METHOD

Participants were adult individuals diagnosed with AD (N = 119) and substance-naïve controls (N = 97) ages 20-65 who underwent structural MRI. Machine-learning models were applied to predict diagnosis and lifetime alcohol consumption.

RESULTS

A classification scheme based on regional grey matter attained 74% diagnostic accuracy and predicted lifetime consumption with high accuracy (r = 0.56, P < 10^-10 ). A key advantage of the classification scheme was its algorithmic transparency, revealing cingulate, insular and inferior frontal cortices as important brain areas underlying classification. Validation of the classification scheme on data of an independent trial was successful with nearly identical accuracy, addressing the concern of generalization. Finally, compared to a blinded radiologist, computer-based classification showed higher accuracy and sensitivity, reduced age and gender biases, but lower specificity.

CONCLUSION

Computer-based models applied to whole-brain grey-matter predicted diagnosis and lifetime consumption in AD with good accuracy. Computer-based classification may be particularly suited as a screening tool with high sensitivity.

Differences in atypical resting-state effective connectivity distinguish autism from schizophrenia

Autism and schizophrenia share overlapping genetic etiology, common changes in brain structure and common cognitive deficits. A number of studies using resting state fMRI have shown that machine learning algorithms can distinguish between healthy controls and individuals diagnosed with either autism spectrum disorder or schizophrenia. However, it has not yet been determined whether machine learning algorithms can be used to distinguish between the two disorders. Using a linear support vector machine, we identify features that are most diagnostic for each disorder and successfully use them to classify an independent cohort of subjects. We find both common and divergent connectivity differences largely in the default mode network as well as in salience, and motor networks. Using divergent connectivity differences, we are able to distinguish autistic subjects from those with schizophrenia. Understanding the common and divergent connectivity changes associated with these disorders may provide a framework for understanding their shared cognitive deficits.

Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework

Investigation of the brain's functional connectome can improve our understanding of how an individual brain's organizational changes influence cognitive function and could result in improved individual risk stratification. Brain connectome studies in adults and older children have shown that abnormal network properties may be useful as discriminative features and have exploited machine learning models for early diagnosis in a variety of neurological conditions. However, analogous studies in neonates are rare and with limited significant findings. In this paper, we propose an artificial neural network (ANN) framework for early prediction of cognitive deficits in very preterm infants based on functional connectome data from resting state fMRI. Specifically, we conducted feature selection via stacked sparse autoencoder and outcome prediction via support vector machine (SVM). The proposed ANN model was unsupervised learned using brain connectome data from 884 subjects in autism brain imaging data exchange database and SVM was cross-validated on 28 very preterm infants (born at 23-31 weeks of gestation and without brain injury; scanned at term-equivalent postmenstrual age). Using 90 regions of interests, we found that the ANN model applied to functional connectome data from very premature infants can predict cognitive outcome at 2 years of corrected age with an accuracy of 70.6% and area under receiver operating characteristic curve of 0.76. We also noted that several frontal lobe and somatosensory regions, significantly contributed to prediction of cognitive deficits 2 years later. Our work can be considered as a proof of concept for utilizing ANN models on functional connectome data to capture the individual variability inherent in the developing brains of preterm infants. The full potential of ANN will be realized and more robust conclusions drawn when applied to much larger neuroimaging datasets, as we plan to do.

FReM - Scalable and stable decoding with fast regularized ensemble of models

Brain decoding relates behavior to brain activity through predictive models. These are also used to identify brain regions involved in the cognitive operations related to the observed behavior. Training such multivariate models is a high-dimensional statistical problem that calls for suitable priors. State of the art priors -eg small total-variation- enforce spatial structure on the maps to stabilize them and improve prediction. However, they come with a hefty computational cost. We build upon very fast dimension reduction with spatial structure and model ensembling to achieve decoders that are fast on large datasets and increase the stability of the predictions and the maps. Our approach, fast regularized ensemble of models (FReM), includes an implicit spatial regularization by using a voxel grouping with a fast clustering algorithm. In addition, it aggregates different estimators obtained across splits of a cross-validation loop, each time keeping the best possible model. Experiments on a large number of brain imaging datasets show that our combination of voxel clustering and model ensembling improves decoding maps stability and reduces the variance of prediction accuracy. Importantly, our method requires less samples than state-of-the-art methods to achieve a given level of prediction accuracy. Finally, FreM is much faster than other spatially-regularized methods and, in addition, it can better exploit parallel computing resources.

Visibility graphs for fMRI data: Multiplex temporal graphs and their modulations across resting-state networks

Visibility algorithms are a family of methods that map time series into graphs, such that the tools of graph theory and network science can be used for the characterization of time series. This approach has proved a convenient tool, and visibility graphs have found applications across several disciplines. Recently, an approach has been proposed to extend this framework to multivariate time series, allowing a novel way to describe collective dynamics. Here we test their application to fMRI time series, following two main motivations, namely that (a) this approach allows vs to simultaneously capture and process relevant aspects of both local and global dynamics in an easy and intuitive way, and (b) this provides a suggestive bridge between time series and network theory that nicely fits the consolidating field of network neuroscience. Our application to a large open dataset reveals differences in the similarities of temporal networks (and thus in correlated dynamics) across resting-state networks, and gives indications that some differences in brain activity connected to psychiatric disorders could be picked up by this approach.

Integration of SNPs-FMRI-methylation data with sparse multi-CCA for schizophrenia study

Schizophrenia (SZ) is a complex mental disorder associated with genetic variations, brain development and activities, and environmental factors. There is an increasing interest in combining genetic, epigenetic and neuroimaging datasets to explore different level of biomarkers for the correlation and interaction between these diverse factors. Sparse Multi-Canonical Correlation Analysis (sMCCA) is a powerful tool that can analyze the correlation of three or more datasets. In this paper, we propose the sMCCA model for imaging genomics study. We show the advantage of sMCCA over sparse CCA (sCCA) through the simulation testing, and further apply it to the analysis of real data (SNPs, fMRI and methylation) from schizophrenia study. Some new genes and brain regions related to SZ disease are discovered by sMCCA and the relationships among these biomarkers are further discussed.

Multi-center machine learning in imaging psychiatry: A meta-model approach

One of the biggest problems in automated diagnosis of psychiatric disorders from medical images is the lack of sufficiently large samples for training. Sample size is especially important in the case of highly heterogeneous disorders such as schizophrenia, where machine learning models built on relatively low numbers of subjects may suffer from poor generalizability. Via multicenter studies and consortium initiatives researchers have tried to solve this problem by combining data sets from multiple sites. The necessary sharing of (raw) data is, however, often hindered by legal and ethical issues. Moreover, in the case of very large samples, the computational complexity might become too large. The solution to this problem could be distributed learning. In this paper we investigated the possibility to create a meta-model by combining support vector machines (SVM) classifiers trained on the local datasets, without the need for sharing medical images or any other personal data. Validation was done in a 4-center setup comprising of 480 first-episode schizophrenia patients and healthy controls in total. We built SVM models to separate patients from controls based on three different kinds of imaging features derived from structural MRI scans, and compared models built on the joint multicenter data to the meta-models. The results showed that the combined meta-model had high similarity to the model built on all data pooled together and comparable classification performance on all three imaging features. Both similarity and performance was superior to that of the local models. We conclude that combining models is thus a viable alternative that facilitates data sharing and creating bigger and more informative models.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Using Functional or Structural Magnetic Resonance Images and Personal Characteristic Data to Identify ADHD and Autism

A clinical tool that can diagnose psychiatric illness using functional or structural magnetic resonance (MR) brain images has the potential to greatly assist physicians and improve treatment efficacy. Working toward the goal of automated diagnosis, we propose an approach for automated classification of ADHD and autism based on histogram of oriented gradients (HOG) features extracted from MR brain images, as well as personal characteristic data features. We describe a learning algorithm that can produce effective classifiers for ADHD and autism when run on two large public datasets. The algorithm is able to distinguish ADHD from control with hold-out accuracy of 69.6% (over baseline 55.0%) using personal characteristics and structural brain scan features when trained on the ADHD-200 dataset (769 participants in training set, 171 in test set). It is able to distinguish autism from control with hold-out accuracy of 65.0% (over baseline 51.6%) using functional images with personal characteristic data when trained on the Autism Brain Imaging Data Exchange (ABIDE) dataset (889 participants in training set, 222 in test set). These results outperform all previously presented methods on both datasets. To our knowledge, this is the first demonstration of a single automated learning process that can produce classifiers for distinguishing patients vs. controls from brain imaging data with above-chance accuracy on large datasets for two different psychiatric illnesses (ADHD and autism). Working toward clinical applications requires robustness against real-world conditions, including the substantial variability that often exists among data collected at different institutions. It is therefore important that our algorithm was successful with the large ADHD-200 and ABIDE datasets, which include data from hundreds of participants collected at multiple institutions. While the resulting classifiers are not yet clinically relevant, this work shows that there is a signal in the (f)MRI data that a learning algorithm is able to find. We anticipate this will lead to yet more accurate classifiers, over these and other psychiatric disorders, working toward the goal of a clinical tool for high accuracy differential diagnosis.

Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines

Decoding, i.e. prediction from brain images or signals, calls for empirical evaluation of its predictive power. Such evaluation is achieved via cross-validation, a method also used to tune decoders' hyper-parameters. This paper is a review on cross-validation procedures for decoding in neuroimaging. It includes a didactic overview of the relevant theoretical considerations. Practical aspects are highlighted with an extensive empirical study of the common decoders in within- and across-subject predictions, on multiple datasets -anatomical and functional MRI and MEG- and simulations. Theory and experiments outline that the popular "leave-one-out" strategy leads to unstable and biased estimates, and a repeated random splits method should be preferred. Experiments outline the large error bars of cross-validation in neuroimaging settings: typical confidence intervals of 10%. Nested cross-validation can tune decoders' parameters while avoiding circularity bias. However we find that it can be favorable to use sane defaults, in particular for non-sparse decoders.

Noise concerns and post-processing procedures in cerebral blood flow (CBF) and cerebral blood volume (CBV) functional magnetic resonance imaging

Functional neuroimaging with blood oxygenation level-dependent (BOLD) contrast has emerged as the most popular method for evaluating qualitative changes in brain function in humans. At typical human field strengths (1.5-3.0T), BOLD contrast provides a measure of changes in transverse water relaxation rates in and around capillary and venous blood, and as such provides only a surrogate marker of brain function that depends on dynamic changes in hemodynamics (e.g., cerebral blood flow and volume) and metabolism (e.g., oxygen extraction fraction and the cerebral metabolic rate of oxygen consumption). Alternative functional neuroimaging methods that are specifically sensitive to these constituents of the BOLD signal are being developed and applied in a growing number of clinical and neuroscience applications of quantitative cerebral physiology. These methods require additional considerations for interpreting and quantifying their contrast responsibly. Here, an overview of two popular methods, arterial spin labeling and vascular space occupancy, is presented specifically in the context of functional neuroimaging. Appropriate post-processing and experimental acquisition strategies are summarized with the motivation of reducing sensitivity to noise and unintended signal sources and improving quantitative accuracy of cerebral hemodynamics.

Supervised, Multivariate, Whole-Brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research

We examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healthy controls, this method allowed us to select brain areas relevant to schizophrenia, such as the left prefrontal cortex, the anterior cingulum, the right anterior insula, the thalamus, and the hippocampus. Nevertheless, the classification performance based on such reduced data was not significantly better than the classification of data reduced by mass univariate selection using a t-test or unsupervised multivariate reduction using principal component analysis. Moreover, we found no important influence of the type of imaging features, namely local deformations or gray matter volumes, and the classification method, specifically linear discriminant analysis or linear support vector machines, on the classification results. However, we ascertained significant effect of a cross-validation setting on classification performance as classification results were overestimated even though the resampling was performed during the selection of brain imaging features. Therefore, it is critically important to perform cross-validation in all steps of the analysis (not only during classification) in case there is no external validation set to avoid optimistically biasing the results of classification studies.

Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition

We investigated a combination of three classification algorithms, namely the modified maximum uncertainty linear discriminant analysis (mMLDA), the centroid method, and the average linkage, with three types of features extracted from three-dimensional T1-weighted magnetic resonance (MR) brain images, specifically MR intensities, grey matter densities, and local deformations for distinguishing 49 first episode schizophrenia male patients from 49 healthy male subjects. The feature sets were reduced using intersubject principal component analysis before classification. By combining the classifiers, we were able to obtain slightly improved results when compared with single classifiers. The best classification performance (81.6% accuracy, 75.5% sensitivity, and 87.8% specificity) was significantly better than classification by chance. We also showed that classifiers based on features calculated using more computation-intensive image preprocessing perform better; mMLDA with classification boundary calculated as weighted mean discriminative scores of the groups had improved sensitivity but similar accuracy compared to the original MLDA; reducing a number of eigenvectors during data reduction did not always lead to higher classification accuracy, since noise as well as the signal important for classification were removed. Our findings provide important information for schizophrenia research and may improve accuracy of computer-aided diagnostics of neuropsychiatric diseases.

On the generalizability of resting-state fMRI machine learning classifiers

Machine learning classifiers have become increasingly popular tools to generate single-subject inferences from fMRI data. With this transition from the traditional group level difference investigations to single-subject inference, the application of machine learning methods can be seen as a considerable step forward. Existing studies, however, have given scarce or no information on the generalizability to other subject samples, limiting the use of such published classifiers in other research projects. We conducted a simulation study using publicly available resting-state fMRI data from the 1000 Functional Connectomes and COBRE projects to examine the generalizability of classifiers based on regional homogeneity of resting-state time series. While classification accuracies of up to 0.8 (using sex as the target variable) could be achieved on test datasets drawn from the same study as the training dataset, the generalizability of classifiers to different study samples proved to be limited albeit above chance. This shows that on the one hand a certain amount of generalizability can robustly be expected, but on the other hand this generalizability should not be overestimated. Indeed, this study substantiates the need to include data from several sites in a study investigating machine learning classifiers with the aim of generalizability.

Review of fMRI Data Analysis

Classification of brain states obtained through functional magnetic resonance imaging (fMRI) poses a serious challenges for neuroimaging community to uncover discriminating patterns of brain state activity that define independent thought processes. This challenge came into existence because of the large number of voxels in a typical fMRI scan, the classifier is presented with a massive feature set coupled with a relatively small training samples. One of the most popular research topics in last few years is the application of machine learning algorithms for mental states classification, decoding brain activation, and finding the variable of interest from fMRI data. In classification scenario, different algorithms have different biases, in the sequel performances differs across datasets, and for a particular dataset the accuracy varies from classifier to classifier. To overcome the limitations of individual techniques, hybridization or fusion of these machine learning techniques emerged in recent years which have shown promising result and open up new direction of research. This paper reviews the machine learning techniques ranging from individual classifiers, ensemble, and hybrid techniques used in cognitive classification with a well balance treatment of their applications, performance, and limitations. It also discusses many open research challenges for further research.

The MCIC collection: a shared repository of multi-modal, multi-site brain image data from a clinical investigation of schizophrenia

Expertly collected, well-curated data sets consisting of comprehensive clinical characterization and raw structural, functional and diffusion-weighted DICOM images in schizophrenia patients and sex and age-matched controls are now accessible to the scientific community through an on-line data repository (coins.mrn.org). The Mental Illness and Neuroscience Discovery Institute, now the Mind Research Network (MRN, http://www.mrn.org/ ), comprised of investigators at the University of New Mexico, the University of Minnesota, Massachusetts General Hospital, and the University of Iowa, conducted a cross-sectional study to identify quantitative neuroimaging biomarkers of schizophrenia. Data acquisition across multiple sites permitted the integration and cross-validation of clinical, cognitive, morphometric, and functional neuroimaging results gathered from unique samples of schizophrenia patients and controls using a common protocol across sites. Particular effort was made to recruit patients early in the course of their illness, at the onset of their symptoms. There is a relatively even sampling of illness duration in chronic patients. This data repository will be useful to 1) scientists who can study schizophrenia by further analysis of this cohort and/or by pooling with other data; 2) computer scientists and software algorithm developers for testing and validating novel registration, segmentation, and other analysis software; and 3) educators in the fields of neuroimaging, medical image analysis and medical imaging informatics who need exemplar data sets for courses and workshops. Sharing provides the opportunity for independent replication of already published results from this data set and novel exploration. This manuscript describes the inclusion/exclusion criteria, imaging parameters and other information that will assist those wishing to use this data repository.

Neuroimaging predictors of cognitive performance across a standardized neurocognitive battery

OBJECTIVE

The advent of functional MRI (fMRI) enables the identification of brain regions recruited for specific behavioral tasks. Most fMRI studies focus on group effects in single tasks, which limits applicability where assessment of individual differences and multiple brain systems is needed.

METHOD

We demonstrate the feasibility of concurrently measuring fMRI activation patterns and performance on a computerized neurocognitive battery (CNB) in 212 healthy individuals at 2 sites. Cross-validated sparse regression of regional brain amplitude and extent of activation were used to predict concurrent performance on 6 neurocognitive tasks: abstraction/mental flexibility, attention, emotion processing, and verbal, face, and spatial memory.

RESULTS

Brain activation was task responsive and domain specific, as reported in previous single-task studies. Prediction of performance was robust for most tasks, particularly for abstraction/mental flexibility and visuospatial memory.

CONCLUSIONS

The feasibility of administering a comprehensive neuropsychological battery in the scanner was established, and task-specific brain activation patterns improved prediction beyond demographic information. This benchmark index of performance-associated brain activation can be applied to link brain activation with neurocognitive performance during standardized testing. This first step in standardizing a neurocognitive battery for use in fMRI may enable quantitative assessment of patients with brain disorders across multiple cognitive domains. Such data may facilitate identification of neural dysfunction associated with poor performance, allow for identification of individuals at risk for brain disorders, and help guide early intervention and rehabilitation of neurocognitive deficits.

Multivariate classification of blood oxygen level-dependent FMRI data with diagnostic intention: a clinical perspective

SUMMARY

There has been a recent upsurge of reports about applications of pattern-recognition techniques from the field of machine learning to functional MR imaging data as a diagnostic tool for systemic brain disease or psychiatric disorders. Entities studied include depression, schizophrenia, attention deficit hyperactivity disorder, and neurodegenerative disorders like Alzheimer dementia. We review these recent studies which-despite the optimism from some articles-predominantly constitute explorative efforts at the proof-of-concept level. There is some evidence that, in particular, support vector machines seem to be promising. However, the field is still far from real clinical application, and much work has to be done regarding data preprocessing, model optimization, and validation. Reporting standards are proposed to facilitate future meta-analyses or systematic reviews.

Three-way FMRI-DTI-methylation data fusion based on mCCA+jICA and its application to schizophrenia

Multi-modal fusion is an effective approach in biomedical imaging which combines multiple data types in a joint analysis and overcomes the problem that each modality provides a limited view of the brain. In this paper, we propose an exploratory fusion model, we term "mCCA+jICA", by combining two multivariate approaches: multi-set canonical correlation analysis (mCCA) and joint independent component analysis (jICA). This model can freely combine multiple, disparate data sets and explore their joint information in an accurate and effective manner, so that high decomposition accuracy and valid modal links can be achieved simultaneously. We compared mCCA+jICA with its alternatives in simulation and applied it to real fMRI-DTI-methylation data fusion, to identify brain abnormalities in schizophrenia. The results replicate previous reports and add to our understanding of the neural correlates of schizophrenia, and suggest more generally a promising approach to identify potential brain illness biomarkers.

Classification of schizophrenia patients based on resting-state functional network connectivity

There is a growing interest in automatic classification of mental disorders based on neuroimaging data. Small training data sets (subjects) and very large amount of high dimensional data make it a challenging task to design robust and accurate classifiers for heterogeneous disorders such as schizophrenia. Most previous studies considered structural MRI, diffusion tensor imaging and task-based fMRI for this purpose. However, resting-state data has been rarely used in discrimination of schizophrenia patients from healthy controls. Resting data are of great interest, since they are relatively easy to collect, and not confounded by behavioral performance on a task. Several linear and non-linear classification methods were trained using a training dataset and evaluate with a separate testing dataset. Results show that classification with high accuracy is achievable using simple non-linear discriminative methods such as k-nearest neighbors (KNNs) which is very promising. We compare and report detailed results of each classifier as well as statistical analysis and evaluation of each single feature. To our knowledge our effects represent the first use of resting-state functional network connectivity (FNC) features to classify schizophrenia.

Gaussian mixture model-based noise reduction in resting state fMRI data

Neuroimaging the default mode network (DMN) in resting state has been of significant interest for investigating pathological conditions as resting state data are less affected by the variability in the subject's performance and movement-related artefacts in the electromagnetic field which are often issues in event-related activation experiments. An issue to be considered with resting state data is the very low amplitude of the activation patterns which are not induced by any stimulation or stimulus paradigm. Though, many studies have suggested that amplitude of low frequency fluctuation (ALFF) analysis is suitable for resting state functional magnetic resonance imaging (fMRI) data analysis, the low signal-to-noise-ratio (SNR) of acquired neuroimaging data poses a significant problem in the accurate analysis of the same. In this work, a Gaussian Mixture Model (GMM) method to suppress the noise during data pre-processing before ALFF is applied (GMM-ALFF) is proposed, where the optimum numbers of Gaussian distributions are fitted to the data using the Bayesian information criterion (BIC). The method has been tested with artificial data as well as real resting state fMRI data collected from Alzheimer's disease patients with different levels of added noise. Improvement of as much as 40% for artificial datasets and at least 3% for real datasets (p<0.05) have been observed when applying the proposed GMM approach prior to the analysis with the existing ALFF approach.

Neurobiological narratives: experiences of mood disorder through the lens of neuroimaging

Many scientists, healthcare providers, policymakers and patients are awaiting in anticipation the application of biomedical technologies such as functional neuroimaging for the prediction, diagnosis and treatment of mental disorders. The potential efficacy of such applications is controversial, and functional neuroimaging is not yet routinely used in psychiatric clinics. However, commercial ventures and enthusiastic reporting indicate a pressing need to engage with the social and ethical issues raised by clinical translation. There has been little investigation of how individuals living with mental illness view functional neuroimaging, or of the potential psychological impacts of its clinical use. We conducted 12 semi-structured interviews with adults diagnosed with major depression or bipolar disorder, probing their experiences with mental health care and their perspectives on the prospect of receiving neuroimaging for prediction, diagnosis and planning treatment. The participants discussed the potential role of neuroimages in (i) mitigating stigma; (ii) supporting morally loaded explanations of mental illness due to an imbalance of brain chemistry; (iii) legitimising psychiatric symptoms, which may have previously been de-legitimised since they lacked objective representation, through objective representations of disorder; and (iv) reifying DSM-IV-TR disorder categories and links to identity. We discuss these anticipated outcomes in the context of participant lived experience and attitudes to biologisation of mental illness, and argue for bringing these voices into upstream ethics discussion.

Three-way (N-way) fusion of brain imaging data based on mCCA+jICA and its application to discriminating schizophrenia

Multimodal fusion is an effective approach to better understand brain diseases. However, most such instances have been limited to pair-wise fusion; because there are often more than two imaging modalities available per subject, there is a need for approaches that can combine multiple datasets optimally. In this paper, we extended our previous two-way fusion model called "multimodal CCA+joint ICA", to three or N-way fusion, that enables robust identification of correspondence among N data types and allows one to investigate the important question of whether certain disease risk factors are shared or distinct across multiple modalities. We compared "mCCA+jICA" with its alternatives in a 3-way fusion simulation and verified its advantages in both decomposition accuracy and modal linkage detection. We also applied it to real functional Magnetic Resonance Imaging (fMRI)-Diffusion Tensor Imaging (DTI) and structural MRI fusion to elucidate the abnormal architecture underlying schizophrenia (n=97) relative to healthy controls (n=116). Both modality-common and modality-unique abnormal regions were identified in schizophrenia. Specifically, the visual cortex in fMRI, the anterior thalamic radiation (ATR) and forceps minor in DTI, and the parietal lobule, cuneus and thalamus in sMRI were linked and discriminated between patients and controls. One fMRI component with regions of activity in motor cortex and superior temporal gyrus individually discriminated schizophrenia from controls. Finally, three components showed significant correlation with duration of illness (DOI), suggesting that lower gray matter volumes in parietal, frontal, and temporal lobes and cerebellum are associated with increased DOI, along with white matter disruption in ATR and cortico-spinal tracts. Findings suggest that the identified fractional anisotropy changes may relate to the corresponding functional/structural changes in the brain that are thought to play a role in the clinical expression of schizophrenia. The proposed "mCCA+jICA" method showed promise for elucidating the joint or coupled neuronal abnormalities underlying mental illnesses and improves our understanding of the disease process.

Identify schizophrenia using resting-state functional connectivity: an exploratory research and analysis

Background

Schizophrenia is a severe mental illness associated with the symptoms such as hallucination and delusion. The objective of this study was to investigate the abnormal resting-state functional connectivity patterns of schizophrenic patients which could identify furthest patients from healthy controls.

Methods

The whole-brain resting-state fMRI was performed on patients diagnosed with schizophrenia (n = 22) and on age- and gender-matched, healthy control subjects (n = 22). To differentiate schizophrenic individuals from healthy controls, the multivariate classification analysis was employed. The weighted brain regions were got by reconstruction arithmetic to extract highly discriminative functional connectivity information.

Results

The results showed that 93.2% (p < 0.001) of the subjects were correctly classified via the leave-one-out cross-validation method. And most of the altered functional connections identified located within the visual cortical-, default-mode-, and sensorimotor network. Furthermore, in reconstruction arithmetic, the fusiform gyrus exhibited the greatest amount of weight.

Conclusions

This study demonstrates that schizophrenic patients may be successfully differentiated from healthy subjects by using whole-brain resting-state fMRI, and the fusiform gyrus may play an important functional role in the physiological symptoms manifested by schizophrenic patients. The brain region of great weight may be the problematic region of information exchange in schizophrenia. Thus, our result may provide insights into the identification of potentially effective biomarkers for the clinical diagnosis of schizophrenia.

High classification accuracy for schizophrenia with rest and task FMRI data

We present a novel method to extract classification features from functional magnetic resonance imaging (fMRI) data collected at rest or during the performance of a task. By combining a two-level feature identification scheme with kernel principal component analysis (KPCA) and Fisher’s linear discriminant analysis (FLD), we achieve high classification rates in discriminating healthy controls from patients with schizophrenia. Experimental results using leave-one-out cross-validation show that features extracted from the default mode network (DMN) lead to a classification accuracy of over 90% in both data sets. Moreover, using a majority vote method that uses multiple features, we achieve a classification accuracy of 98% in auditory oddball (AOD) task and 93% in rest data. Several components, including DMN, temporal, and medial visual regions, are consistently present in the set of features that yield high classification accuracy. The features we have extracted thus show promise to be used as biomarkers for schizophrenia. Results also suggest that there may be different advantages to using resting fMRI data or task fMRI data.