Application of principal component analysis to distinguish patients with schizophrenia from healthy controls based on fractional anisotropy measurements

Role of Impulsivity in Explaining Social Gradient in Youth Tobacco Use Initiation: Does Race Matter?

Background

Socioeconomic status (SES) is traditionally viewed as a protective factor against impulsivity and subsequent tobacco use in youth. The prevailing model suggests that higher SES is associated with lower impulsivity, which in turn reduces the likelihood of future tobacco use. However, this pathway may not hold uniformly across racial groups due to differences in impulsivity and the phenomenon of Minorities' Diminished Returns (MDRs), where the protective effects of SES, such as educational attainment, tend to be weaker or even reversed for Black youth compared to their White counterparts.

Objectives

This study aims to examine the racial heterogeneity in the pathway from childhood SES to impulsivity and subsequent tobacco use initiation during adolescence, focusing on differences between Black and White youth.

Methods

Data were drawn from the Adolescent Brain Cognitive Development (ABCD) Study, which includes a diverse sample of youth aged 9 to 16 years. The analysis examined the relationship between baseline family SES (age 9), impulsivity (age 9), and subsequent tobacco use (ages 9 to 16). Impulsivity was measured using the Urgency, Premeditation (lack of), Perseverance (lack of), Sensation Seeking, and Positive Urgency Impulsive Behavior Scale (UPPS-P). Structural equation modeling (SEM) was employed, with analyses stratified by race to explore potential differences in these associations.

Results

Overall, 6,161 non-Latino White and 1,775 non-Latino Black adolescents entered our analysis. In the full sample, higher family SES was linked to lower childhood impulsivity and, consequently, less tobacco uses in adolescence. However, racial differences emerged upon stratification. Among White youth, higher SES was associated with lower impulsivity, leading to reduced tobacco use, consistent with the expected model. In contrast, among Black youth, higher SES was not associated with lower impulsivity, thereby disrupting the protective effect of SES on tobacco use through this pathway. These findings suggest that racial heterogeneity exists in the SES-impulsivity-tobacco use pathway, aligning with the MDRs framework, which highlights how structural factors may weaken the protective effects of high SES among Black youth.

Conclusions

These findings underscore the importance of considering racial heterogeneity in the relationships between SES, impulsivity, and tobacco use. The observed disparities suggest a need for targeted interventions that address the unique challenges faced by Black youth, who may not experience the same protective benefits of high SES as their White peers. These results carry significant implications for public health strategies aimed at reducing tobacco use in racially diverse populations.

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

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

Multivariate Associations Among White Matter, Neurocognition, and Social Cognition Across Individuals With Schizophrenia Spectrum Disorders and Healthy Controls

BACKGROUND AND HYPOTHESIS

Neurocognitive and social cognitive abilities are important contributors to functional outcomes in schizophrenia spectrum disorders (SSDs). An unanswered question of considerable interest is whether neurocognitive and social cognitive deficits arise from overlapping or distinct white matter impairment(s).

STUDY DESIGN

We sought to fill this gap, by harnessing a large sample of individuals from the multi-center Social Processes Initiative in the Neurobiology of the Schizophrenia(s) (SPINS) dataset, unique in its collection of advanced diffusion imaging and an extensive battery of cognitive assessments. We applied canonical correlation analysis to estimates of white matter microstructure, and cognitive performance, across people with and without an SSD.

STUDY RESULTS

Our results established that white matter circuitry is dimensionally and strongly related to both neurocognition and social cognition, and that microstructure of the uncinate fasciculus and the rostral body of the corpus callosum may assume a "privileged role" subserving both. Further, we found that participant-wise estimates of white matter microstructure, weighted by cognitive performance, were largely consistent with participants' categorical diagnosis, and predictive of (cross-sectional) functional outcomes.

CONCLUSIONS

The demonstrated strength of the relationship between white matter circuitry and neurocognition and social cognition underscores the potential for using relationships among these variables to identify biomarkers of functioning, with potential prognostic and therapeutic implications.

Data-driven multimodal fusion: approaches and applications in psychiatric research

In the era of big data, where vast amounts of information are being generated and collected at an unprecedented rate, there is a pressing demand for innovative data-driven multi-modal fusion methods. These methods aim to integrate diverse neuroimaging perspectives to extract meaningful insights and attain a more comprehensive understanding of complex psychiatric disorders. However, analyzing each modality separately may only reveal partial insights or miss out on important correlations between different types of data. This is where data-driven multi-modal fusion techniques come into play. By combining information from multiple modalities in a synergistic manner, these methods enable us to uncover hidden patterns and relationships that would otherwise remain unnoticed. In this paper, we present an extensive overview of data-driven multimodal fusion approaches with or without prior information, with specific emphasis on canonical correlation analysis and independent component analysis. The applications of such fusion methods are wide-ranging and allow us to incorporate multiple factors such as genetics, environment, cognition, and treatment outcomes across various brain disorders. After summarizing the diverse neuropsychiatric magnetic resonance imaging fusion applications, we further discuss the emerging neuroimaging analyzing trends in big data, such as N-way multimodal fusion, deep learning approaches, and clinical translation. Overall, multimodal fusion emerges as an imperative approach providing valuable insights into the underlying neural basis of mental disorders, which can uncover subtle abnormalities or potential biomarkers that may benefit targeted treatments and personalized medical interventions.

Cytoarchitectureal changes in hippocampal subregions of the NZB/W F1 mouse model of lupus

Over 50% of clinical patients affected by the systemic lupus erythematosus disease display impaired neurological cognitive functions and psychiatric disorders, a form called neuropsychiatric systemic lupus erythematosus. Hippocampus is one of the brain structures most sensitive to the cognitive deficits and psychiatric disorders related to neuropsychiatric lupus. The purpose of this study was to compare, layer by layer, neuron morphology in lupus mice model NZB/W F1 versus Wild Type mice. By a morphometric of cells identified on Nissl-stained sections, we evaluated structural alterations between NZB/W F1 and Wild Type mice in seven hippocampal subregions: Molecular dentate gyrus, Granular dentate gyrus, Polymorph dentate gyrus, Oriens layer, Pyramidal layer, Radiatum layer and Lacunosum molecular layer. By principal component analysis we distinguished healthy Wild Type from NZB/W F1 mice. In NZB/W F1 mice hippocampal cytoarchitecture, the neuronal cells resulted larger in size and more regular than those of Wild Type. In NZB/W F1, neurons were usually denser than in WT. The Pyramidal layer neurons were much denser in Wild Type than in NZB/W F1. Application of principal component analysis, allowed to distinguish NZB/W F1 lupus mice from healthy, showing as NZBW subjects presented a scattered distribution and intrasubject variability. Our results show a hypertrophy of the NZB/W F1 hippocampal neurons associated with an increase in perikaryal size within the CA1, CA2, CA3 region and the DG. These results help advance our understanding on hippocampal organization and structure in the NZB/W F1 lupus model, suggesting the hypothesis that the different subregions could be differentially affected in neuropsychiatric systemic lupus erythematosus disease. Leveraging an in-depth analysis of the morphology of neural cells in the hippocampal subregions and applying dimensionality reduction using PCA, we propose an efficient methodology to distinguish pathological NZBW mice from WT mice."

Automated detection of schizophrenia using deep learning: a review for the last decade

Schizophrenia (SZ) is a devastating mental disorder that disrupts higher brain functions like thought, perception, etc., with a profound impact on the individual's life. Deep learning (DL) can detect SZ automatically by learning signal data characteristics hierarchically without the need for feature engineering associated with traditional machine learning. We performed a systematic review of DL models for SZ detection. Various deep models like long short-term memory, convolution neural networks, AlexNet, etc., and composite methods have been published based on electroencephalographic signals, and structural and/or functional magnetic resonance imaging acquired from SZ patients and healthy patients control subjects in diverse public and private datasets. The studies, the study datasets, and model methodologies are reported in detail. In addition, the challenges of DL models for SZ diagnosis and future works are discussed.

Feature and decision-level fusion for schizophrenia detection based on resting-state fMRI data

Mental disorders, especially schizophrenia, still pose a great challenge for diagnosis in early stages. Recently, computer-aided diagnosis techniques based on resting-state functional magnetic resonance imaging (Rs-fMRI) have been developed to tackle this challenge. In this work, we investigate different decision-level and feature-level fusion schemes for discriminating between schizophrenic and normal subjects. Four types of fMRI features are investigated, namely the regional homogeneity, voxel-mirrored homotopic connectivity, fractional amplitude of low-frequency fluctuations and amplitude of low-frequency fluctuations. Data denoising and preprocessing were first applied, followed by the feature extraction module. Four different feature selection algorithms were applied, and the best discriminative features were selected using the algorithm of feature selection via concave minimization (FSV). Support vector machine classifiers were trained and tested on the COBRE dataset formed of 70 schizophrenic subjects and 70 healthy subjects. The decision-level fusion method outperformed the single-feature-type approaches and achieved a 97.85% accuracy, a 98.33% sensitivity, a 96.83% specificity. Moreover, feature-fusion scheme resulted in a 98.57% accuracy, a 99.71% sensitivity, a 97.66% specificity, and an area under the ROC curve of 0.9984. In general, decision-level and feature-level fusion schemes boosted the performance of schizophrenia detectors based on fMRI features.

Schizophrenia: A Survey of Artificial Intelligence Techniques Applied to Detection and Classification

Artificial Intelligence in healthcare employs machine learning algorithms to emulate human cognition in the analysis of complicated or large sets of data. Specifically, artificial intelligence taps on the ability of computer algorithms and software with allowable thresholds to make deterministic approximate conclusions. In comparison to traditional technologies in healthcare, artificial intelligence enhances the process of data analysis without the need for human input, producing nearly equally reliable, well defined output. Schizophrenia is a chronic mental health condition that affects millions worldwide, with impairment in thinking and behaviour that may be significantly disabling to daily living. Multiple artificial intelligence and machine learning algorithms have been utilized to analyze the different components of schizophrenia, such as in prediction of disease, and assessment of current prevention methods. These are carried out in hope of assisting with diagnosis and provision of viable options for individuals affected. In this paper, we review the progress of the use of artificial intelligence in schizophrenia.

Multi-modal neuroimaging feature fusion via 3D Convolutional Neural Network architecture for schizophrenia diagnosis

Early and precise diagnosis of schizophrenia disorder (SZ) has an essential role in the quality of a patient’s life and future treatments. Structural and functional neuroimaging provides robust biomarkers for understanding the anatomical and functional changes associated with SZ. Each of the neuroimaging techniques shows only a different perspective on the functional or structural of the brain, while multi-modal fusion can reveal latent connections in the brain. In this paper, we propose an approach for the fusion of structural and functional brain data with a deep learning-based model to take advantage of data fusion and increase the accuracy of schizophrenia disorder diagnosis. The proposed method consists of an architecture of 3D convolutional neural networks (CNNs) that applied to magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and diffusion tensor imaging (DTI) extracted features. We use 3D MRI patches, fMRI spatial independent component analysis (ICA) map, and DTI fractional anisotropy (FA) as model inputs. Our method is validated on the COBRE dataset, and an average accuracy of 99.35% is obtained. The proposed method demonstrates promising classification performance and can be applied to real data.

Impact of Meteorological Conditions on the Dynamics of the COVID-19 Pandemic in Poland

Coronavirus disease 2019 (COVID-19) is an infectious disease caused by the novel coronavirus. The role of environmental factors in COVID-19 transmission is unclear. This study aimed to analyze the correlation between meteorological conditions (temperature, relative humidity, sunshine duration, wind speed) and dynamics of the COVID-19 pandemic in Poland. Data on a daily number of laboratory-confirmed COVID-19 cases and the number of COVID-19-related deaths were gatheredfrom the official governmental website. Meteorological observations from 55 synoptic stations in Poland were used. Moreover, reports on the movement of people across different categories of places were collected. A cross-correlation function, principal component analysis and random forest were applied. Maximum temperature, sunshine duration, relative humidity and variability of mean daily temperature affected the dynamics of the COVID-19 pandemic. An increase intemperature and sunshine hours decreased the number of confirmed COVID-19 cases. The occurrence of high humidity caused an increase in the number of COVID-19 cases 14 days later. Decreased sunshine duration and increased air humidity had a negative impact on the number of COVID-19-related deaths. Our study provides information that may be used by policymakers to support the decision-making process in nonpharmaceutical interventions against COVID-19.

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.

The Influencing Factors of Health-Seeking Preference and Community Health Service Utilization Among Patients in Primary Care Reform in Xiamen, China

INTRODUCTION

Patients often seek healthcare at general hospitals rather than at community healthcare centres (CHCs) which leads to inefficiency of health services. The primary healthcare reform developed by Xiamen has proven to break through the barriers of hierarchical diagnosis and treatment. The influencing factors of health-seeking behaviours of patients in the Xiamen reform, however, are unclear.

OBJECTIVE

This study aimed to assess patients' healthcare-seeking preferences and CHCs utilization, and identify influencing factors among patients affected by the Xiamen reform.

METHODS

A cross-sectional study composed of 2200 individuals with hypertension or diabetes was conducted in association with Xiamen's reform. The choice of health institutions was used to measure health-seeking preference. The probability and frequency of outpatient service use were used to measure CHC utilization. The social ecological model and two-part model were employed to examine influencing factors.

RESULTS

As high as 72.5% of the subjects, including those who were under 60 years old, had low education level, with long disease duration, good self-report health and low household income expressed a preference for CHC (P<0.05). Also, participants who had good-condition CHCs (χ²=6.736, P=0.010), joined in three-in-one chronic disease management (χ²=81.615, P<0.01) and were insured by medical insurance (χ²=21.142, P<0.01) significantly preferred to visit CHCs for treatment. In addition, patients who had a preference for CHC utilized many more CHCs (P<0.01). Analysis of influencing factors found that education, self-reported health, smoking, household income, condition of the CHC, whether the patient had joined the healthcare reform and whether the patient had medical insurance were important factors affecting health-seeking preference and CHC utilization (P<0.05).

CONCLUSION

The Xiamen healthcare reform made some achievements in improving CHC utilization. However, certain challenges remain. The government should further strengthen CHCs, deepen and expand healthcare reform, and make efforts to guide reasonable healthcare-seeking behaviour and improve the efficiency of primary health systems.

Personalized microstructural evaluation using a Mahalanobis-distance based outlier detection strategy on epilepsy patients' DTI data - Theory, simulations and example cases

Quantitative MRI methods have recently gained extensive interest and are seeing substantial developments; however, their application in single patient vs control group comparisons is often limited by inherent statistical difficulties. One such application is detecting malformations of cortical development (MCDs) behind drug resistant epilepsies, a task that, especially when based solely on conventional MR images, may represent a serious challenge. We aimed to develop a novel straightforward voxel-wise evaluation method based on the Mahalanobis-distance, combining quantitative MRI data into a multidimensional parameter space and detecting lesion voxels as outliers. Simulations with standard multivariate Gaussian distribution and resampled DTI-eigenvalue data of 45 healthy control subjects determined the optimal critical value, cluster size threshold, and the expectable lesion detection performance through ROC-analyses. To reduce the effect of false positives emanating from registration artefacts and gyrification differences, an automatic classification method was applied, fine-tuned using a leave-one-out strategy based on diffusion and T1-weighted data of the controls. DWI processing, including thorough corrections and robust tensor fitting was performed with ExploreDTI, spatial coregistration was achieved with the DARTEL tools of SPM12. Additional to simulations, clusters of outlying diffusion profile, concordant with neuroradiological evaluation and independent calculations with the MAP07 toolbox were identified in 12 cases of a 13 patient example population with various types of MCDs. The multidimensional approach proved sufficiently sensitive in pinpointing regions of abnormal tissue microstructure using DTI data both in simulations and in the heterogeneous example population. Inherent limitations posed by registration artefacts, age-related differences, and the different or mixed pathologies limit the generalization of specificity estimation. Nevertheless, the proposed statistical method may aid the everyday examination of individual subjects, ever so more upon extending the framework with quantitative information from other modalities, e.g. susceptibility mapping, relaxometry, or perfusion.

Autoconnectivity: A new perspective on human brain function

BACKGROUND

Autocorrelation (AC) in fMRI time-series is a well-known phenomenon, typically attributed to colored noise and therefore removed from the data. We hypothesize that AC reflects systematic and meaningful signal fluctuations that may be tied to neural activity and provide evidence to support this hypothesis.

NEW METHOD

Each fMRI time-series is modeled as an autoregressive process from which the autocorrelation is quantified. Then, autocorrelation during resting-state fMRI and auditory oddball (AOD) task in schizophrenia and healthy volunteers is examined.

RESULTS

During resting-state, AC was higher in the visual cortex while during AOD task, frontal part of the brain exhibited higher AC in both groups. AC values were significantly lower in specific brain regions in schizophrenia patients (such as thalamus during resting-state) compared to healthy controls in two independent datasets. Moreover, AC values had significant negative correlation with patients' symptoms. AC differences discriminated patients from healthy controls with high accuracy (resting-state).

COMPARISON WITH EXISTING METHODS

Contrary to most prior works, the results suggest AC shows meaningful patterns that are discriminative between patients and controls. Our results are in line with recent works attributing autocorrelation to feedback loop of brain's regulatory circuit.

CONCLUSIONS

Autoconnectivity is cognitive state dependent (resting-state vs. task) and mental state dependent (healthy vs. schizophrenia). The concept of autoconnectivity resembles a recurrent neural network and provides a new perspective of functional integration in the brain. These findings may have important implications for understanding of brain function in health and disease as well as for analysis of fMRI time-series.

Identification of brain regions associated with working memory deficit in schizophrenia

Background: Schizophrenia, a severe psychological disorder, shows symptoms such as hallucinations and delusions. In addition, patients with schizophrenia often exhibit a deficit in working memory which adversely impacts the attentiveness and the behavioral characteristics of a person. Although several clinical efforts have already been made to study working memory deficit in schizophrenia, in this paper, we investigate the applicability of a machine learning approach for identification of the brain regions that get affected by schizophrenia leading to the dysfunction of the working memory. Methods: We propose a novel scheme for identification of the affected brain regions from functional magnetic resonance imaging data by deploying group independent component analysis in conjunction with feature extraction based on statistical measures, followed by sequential forward feature selection. The features that show highest accuracy during the classification between healthy and schizophrenia subjects are selected. Results: This study reveals several brain regions like cerebellum, inferior temporal gyrus, superior temporal gyrus, superior frontal gyrus, insula, and amygdala that have been reported in the existing literature, thus validating the proposed approach. We are also able to identify some functional changes in the brain regions, such as Heschl gyrus and the vermian area, which have not been reported in the literature involving working memory studies amongst schizophrenia patients. Conclusions: As our study confirms the results obtained in earlier studies, in addition to pointing out some brain regions not reported in earlier studies, the findings are likely to serve as a cue for clinical investigation, leading to better medical intervention.

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.

Diagnostic value of structural and diffusion imaging measures in schizophrenia

Objectives

Many studies have attempted to discriminate patients with schizophrenia from healthy controls by machine learning using structural or functional MRI. We included both structural and diffusion MRI (dMRI) and performed random forest (RF) and support vector machine (SVM) in this study.

Methods

We evaluated the performance of classifying schizophrenia using RF method and SVM with 504 features (volume and/or fractional anisotropy and trace) from 184 brain regions. We enrolled 47 patients and 23 age- and sex-matched healthy controls and resampled our data into a balanced dataset using a Synthetic Minority Oversampling Technique method. We randomly permuted the classification of all participants as a patient or healthy control 100 times and ran the RF and SVM with leave one out cross validation for each permutation. We then compared the sensitivity and specificity of the original dataset and the permuted dataset.

Results

Classification using RF with 504 features showed a significantly higher rate of performance compared to classification by chance: sensitivity (87.6% vs. 47.0%) and specificity (95.9 vs. 48.4%) performed by RF, sensitivity (89.5% vs. 48.0%) and specificity (94.5% vs. 47.1%) performed by SVM.

Conclusions

Machine learning using RF and SVM with both volume and diffusion measures can discriminate patients with schizophrenia with a high degree of performance. Further replications are required.

Individualized prediction of schizophrenia based on the whole-brain pattern of altered white matter tract integrity

BACKGROUND

A schizophrenia diagnosis relies on characteristic symptoms identified by trained physicians, and is thus prone to subjectivity. This study developed a procedure for the individualized prediction of schizophrenia based on whole-brain patterns of altered white matter tract integrity.

METHODS

The study comprised training (108 patients and 144 controls) and testing (60 patients and 60 controls) groups. Male and female participants were comparable in each group and were analyzed separately. All participants underwent diffusion spectrum imaging of the head, and the data were analyzed using the tract-based automatic analysis method to generate a standardized two-dimensional array of white matter tract integrity, called the connectogram. Unique patterns in the connectogram that most accurately identified schizophrenia were systematically reviewed in the training group. Then, the diagnostic performance of the patterns was individually verified in the testing group by using receiver-operating characteristic curve analysis.

RESULTS

The performance was high in men (accuracy = 0.85) and satisfactory in women (accuracy = 0.75). In men, the pattern was located in discrete fiber tracts, as has been consistently reported in the literature; by contrast, the pattern was widespread over all tracts in women. These distinct patterns suggest that there is a higher variability in the microstructural alterations in female patients than in male patients.

CONCLUSIONS

The individualized prediction of schizophrenia is feasible based on the different whole-brain patterns of tract integrity. The optimal masks and their corresponding regions in the fiber tracts could serve as potential imaging biomarkers for schizophrenia. Hum Brain Mapp 39:575-587, 2018. © 2017 Wiley Periodicals, Inc.

Altered structural network architecture is predictive of the presence of psychotic symptoms in patients with 22q11.2 deletion syndrome

22q11.2 deletion syndrome (22q11DS) represents a homogeneous model of schizophrenia particularly suitable for the search of neural biomarkers of psychosis. Impairments in structural connectivity related to the presence of psychotic symptoms have been reported in patients with 22q11DS. However, the relationships between connectivity changes in patients with different symptomatic profiles are still largely unknown and warrant further investigations.

In this study, we used structural connectivity to discriminate patients with 22q11DS with (N = 31) and without (N = 31) attenuated positive psychotic symptoms. Different structural connectivity measures were used, including the number of streamlines connecting pairs of brain regions, graph theoretical measures, and diffusion measures. We used univariate group comparisons as well as predictive multivariate approaches.

The univariate comparison of connectivity measures between patients with or without attenuated positive psychotic symptoms did not give significant results. However, the multivariate prediction revealed that altered structural network architecture discriminates patient subtypes (accuracy = 67.7%). Among the regions contributing to the classification we found the anterior cingulate cortex, which is known to be associated to the presence of psychotic symptoms in patients with 22q11DS. Furthermore, a significant discrimination (accuracy = 64%) was obtained with fractional anisotropy and radial diffusivity in the left inferior longitudinal fasciculus and the right cingulate gyrus.

Our results point to alterations in structural network architecture and white matter microstructure in patients with 22q11DS with attenuated positive symptoms, mainly involving connections of the limbic system. These alterations may therefore represent a potential biomarker for an increased risk of psychosis that should be further tested in longitudinal studies.

•

Altered network architecture discriminates psychotic patients with 22q11DS;

•

Altered diffusivity measures are evident in psychotic patients with 22q11DS;

•

White matter alterations associated to psychosis are located in limbic regions.

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.

Multivariate characterization of white matter heterogeneity in autism spectrum disorder

The complexity and heterogeneity of neuroimaging findings in individuals with autism spectrum disorder has suggested that many of the underlying alterations are subtle and involve many brain regions and networks. The ability to account for multivariate brain features and identify neuroimaging measures that can be used to characterize individual variation have thus become increasingly important for interpreting and understanding the neurobiological mechanisms of autism. In the present study, we utilize the Mahalanobis distance, a multidimensional counterpart of the Euclidean distance, as an informative index to characterize individual brain variation and deviation in autism. Longitudinal diffusion tensor imaging data from 149 participants (92 diagnosed with autism spectrum disorder and 57 typically developing controls) between 3.1 and 36.83 years of age were acquired over a roughly 10-year period and used to construct the Mahalanobis distance from regional measures of white matter microstructure. Mahalanobis distances were significantly greater and more variable in the autistic individuals as compared to control participants, demonstrating increased atypicalities and variation in the group of individuals diagnosed with autism spectrum disorder. Distributions of multivariate measures were also found to provide greater discrimination and more sensitive delineation between autistic and typically developing individuals than conventional univariate measures, while also being significantly associated with observed traits of the autism group. These results help substantiate autism as a truly heterogeneous neurodevelopmental disorder, while also suggesting that collectively considering neuroimaging measures from multiple brain regions provides improved insight into the diversity of brain measures in autism that is not observed when considering the same regions separately. Distinguishing multidimensional brain relationships may thus be informative for identifying neuroimaging-based phenotypes, as well as help elucidate underlying neural mechanisms of brain variation in autism spectrum disorders.

Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images

Structural abnormalities in schizophrenia (SZ) patients have been well documented with structural magnetic resonance imaging (MRI) data using voxel-based morphometry (VBM) and region of interest (ROI) analyses. However, these analyses can only detect group-wise differences and thus, have a poor predictive value for individuals. In the present study, we applied a machine learning method that combined support vector machine (SVM) with recursive feature elimination (RFE) to discriminate SZ patients from normal controls (NCs) using their structural MRI data. We first employed both VBM and ROI analyses to compare gray matter volume (GMV) and white matter volume (WMV) between 41 SZ patients and 42 age- and sex-matched NCs. The method of SVM combined with RFE was used to discriminate SZ patients from NCs using significant between-group differences in both GMV and WMV as input features. We found that SZ patients showed GM and WM abnormalities in several brain structures primarily involved in the emotion, memory, and visual systems. An SVM with a RFE classifier using the significant structural abnormalities identified by the VBM analysis as input features achieved the best performance (an accuracy of 88.4%, a sensitivity of 91.9%, and a specificity of 84.4%) in the discriminative analyses of SZ patients. These results suggested that distinct neuroanatomical profiles associated with SZ patients might provide a potential biomarker for disease diagnosis, and machine-learning methods can reveal neurobiological mechanisms in psychiatric diseases.

Multimodal fusion of brain imaging data: A key to finding the missing link(s) in complex mental illness

It is becoming increasingly clear that combining multi-modal brain imaging data is able to provide more information for individual subjects by exploiting the rich multimodal information that exists. However, the number of studies that do true multimodal fusion (i.e. capitalizing on joint information among modalities) is still remarkably small given the known benefits. In part, this is because multi-modal studies require broader expertise in collecting, analyzing, and interpreting the results than do unimodal studies. In this paper, we start by introducing the basic reasons why multimodal data fusion is important and what it can do, and importantly how it can help us avoid wrong conclusions and help compensate for imperfect brain imaging studies. We also discuss the challenges that need to be confronted for such approaches to be more widely applied by the community. We then provide a review of the diverse studies that have used multimodal data fusion (primarily focused on psychosis) as well as provide an introduction to some of the existing analytic approaches. Finally, we discuss some up-and-coming approaches to multi-modal fusion including deep learning and multimodal classification which show considerable promise. Our conclusion is that multimodal data fusion is rapidly growing, but it is still underutilized. The complexity of the human brain coupled with the incomplete measurement provided by existing imaging technology makes multimodal fusion essential in order to mitigate against misdirection and hopefully provide a key to finding the missing link(s) in complex mental illness.

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.

A full-brain, bootstrapped analysis of diffusion tensor imaging robustly differentiates Parkinson disease from healthy controls

There is a compelling need for early, accurate diagnosis of Parkinson's disease (PD). Various magnetic resonance imaging modalities are being explored as an adjunct to diagnosis. A significant challenge in using MR imaging for diagnosis is developing appropriate algorithms for extracting diagnostically relevant information from brain images. In previous work, we have demonstrated that individual subject variability can have a substantial effect on identifying and determining the borders of regions of analysis, and that this variability may impact on prediction accuracy. In this paper we evaluate a new statistical algorithm to determine if we can improve accuracy of prediction using a subjects left-out validation of a DTI analysis. Twenty subjects with PD and 22 healthy controls were imaged to evaluate if a full brain diffusion tensor imaging-fractional anisotropy (DTI-FA) map might be capable of segregating PD from controls. In this paper, we present a new statistical algorithm based on bootstrapping. We compare the capacity of this algorithm to classify the identity of subjects left out of the analysis with the accuracy of other statistical techniques, including standard cluster-thresholding. The bootstrapped analysis approach was able to correctly discriminate the 20 subjects with PD from the 22 healthy controls (area under the receiver operator curve or AUROC 0.90); however the sensitivity and specificity of standard cluster-thresholding techniques at various voxel-specific thresholds were less effective (AUROC 0.72-0.75). Based on these results sufficient information to generate diagnostically relevant statistical maps may already be collected by current MRI scanners. We present one statistical technique that might be used to extract diagnostically relevant information from a full brain analysis.

Finding imaging patterns of structural covariance via Non-Negative Matrix Factorization

In this paper, we investigate the use of Non-Negative Matrix Factorization (NNMF) for the analysis of structural neuroimaging data. The goal is to identify the brain regions that co-vary across individuals in a consistent way, hence potentially being part of underlying brain networks or otherwise influenced by underlying common mechanisms such as genetics and pathologies. NNMF offers a directly data-driven way of extracting relatively localized co-varying structural regions, thereby transcending limitations of Principal Component Analysis (PCA), Independent Component Analysis (ICA) and other related methods that tend to produce dispersed components of positive and negative loadings. In particular, leveraging upon the well known ability of NNMF to produce parts-based representations of image data, we derive decompositions that partition the brain into regions that vary in consistent ways across individuals. Importantly, these decompositions achieve dimensionality reduction via highly interpretable ways and generalize well to new data as shown via split-sample experiments. We empirically validate NNMF in two data sets: i) a Diffusion Tensor (DT) mouse brain development study, and ii) a structural Magnetic Resonance (sMR) study of human brain aging. We demonstrate the ability of NNMF to produce sparse parts-based representations of the data at various resolutions. These representations seem to follow what we know about the underlying functional organization of the brain and also capture some pathological processes. Moreover, we show that these low dimensional representations favorably compare to descriptions obtained with more commonly used matrix factorization methods like PCA and ICA.

A review of feature reduction techniques in neuroimaging

Machine learning techniques are increasingly being used in making relevant predictions and inferences on individual subjects neuroimaging scan data. Previous studies have mostly focused on categorical discrimination of patients and matched healthy controls and more recently, on prediction of individual continuous variables such as clinical scores or age. However, these studies are greatly hampered by the large number of predictor variables (voxels) and low observations (subjects) also known as the curse-of-dimensionality or small-n-large-p problem. As a result, feature reduction techniques such as feature subset selection and dimensionality reduction are used to remove redundant predictor variables and experimental noise, a process which mitigates the curse-of-dimensionality and small-n-large-p effects. Feature reduction is an essential step before training a machine learning model to avoid overfitting and therefore improving model prediction accuracy and generalization ability. In this review, we discuss feature reduction techniques used with machine learning in neuroimaging studies.

Neuroanatomical classification in a population-based sample of psychotic major depression and bipolar I disorder with 1 year of diagnostic stability

The presence of psychotic features in the course of a depressive disorder is known to increase the risk for bipolarity, but the early identification of such cases remains challenging in clinical practice. In the present study, we evaluated the diagnostic performance of a neuroanatomical pattern classification method in the discrimination between psychotic major depressive disorder (MDD), bipolar I disorder (BD-I), and healthy controls (HC) using a homogenous sample of patients at an early course of their illness. Twenty-three cases of first-episode psychotic mania (BD-I) and 19 individuals with a first episode of psychotic MDD whose diagnosis remained stable during 1 year of followup underwent 1.5 T MRI at baseline. A previously validated multivariate classifier based on support vector machine (SVM) was employed and measures of diagnostic performance were obtained for the discrimination between each diagnostic group and subsamples of age- and gender-matched controls recruited in the same neighborhood of the patients. Based on T1-weighted images only, the SVM-classifier afforded poor discrimination in all 3 pairwise comparisons: BD-I versus HC; MDD versus HC; and BD-I versus MDD. Thus, at the population level and using structural MRI only, we failed to achieve good discrimination between BD-I, psychotic MDD, and HC in this proof of concept study.

Discrimination between schizophrenia and major depressive disorder by magnetic resonance imaging of the female brain

BACKGROUND

Although schizophrenia and major depressive disorder (MDD) differ on a variety of neuroanatomical measures, a diagnostic tool to discriminate these disorders has not yet been established. We tried to identify structural changes of the brain that best discriminate between schizophrenia and MDD on the basis of gray matter volume, ventricle volume, and diffusion tensor imaging (DTI).

METHOD

The first exploration sample consisted of 25 female patients with schizophrenia and 25 females with MDD. Regional brain volumes and fractional anisotropy (FA) values were entered into a discriminant analysis. The second validation sample consisted of 18 female schizophrenia and 16 female MDD patients.

RESULTS

The stepwise discriminant analysis resulted in correct classification rates of 0.80 in the schizophrenic group and 0.76 in MDD. In the second validation sample, the obtained model yielded correct classification rates of 0.72 in the schizophrenia group and 0.88 in the MDD group.

CONCLUSION

Our results suggest that schizophrenia and MDD have differential structural changes in the examined brain regions and that the obtained discriminant score may be useful to discriminate the two disorders.

Clinical utility of machine-learning approaches in schizophrenia: improving diagnostic confidence for translational neuroimaging

Machine-learning approaches are becoming commonplace in the neuroimaging literature as potential diagnostic and prognostic tools for the study of clinical populations. However, very few studies provide clinically informative measures to aid in decision-making and resource allocation. Head-to-head comparison of neuroimaging-based multivariate classifiers is an essential first step to promote translation of these tools to clinical practice. We systematically evaluated the classifier performance using back-to-back structural MRI in two field strengths (3- and 7-T) to discriminate patients with schizophrenia (n = 19) from healthy controls (n = 20). Gray matter (GM) and white matter images were used as inputs into a support vector machine to classify patients and control subjects. Seven Tesla classifiers outperformed the 3-T classifiers with accuracy reaching as high as 77% for the 7-T GM classifier compared to 66.6% for the 3-T GM classifier. Furthermore, diagnostic odds ratio (a measure that is not affected by variations in sample characteristics) and number needed to predict (a measure based on Bayesian certainty of a test result) indicated superior performance of the 7-T classifiers, whereby for each correct diagnosis made, the number of patients that need to be examined using the 7-T GM classifier was one less than the number that need to be examined if a different classifier was used. Using a hypothetical example, we highlight how these findings could have significant implications for clinical decision-making. We encourage the reporting of measures proposed here in future studies utilizing machine-learning approaches. This will not only promote the search for an optimum diagnostic tool but also aid in the translation of neuroimaging to clinical use.

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.

Neuroanatomical pattern classification in a population-based sample of first-episode schizophrenia

Recent neuroanatomical pattern classification studies have attempted to individually classify cases with psychotic disorders using morphometric MRI data in an automated fashion. However, this approach has not been tested in population-based samples, in which variable patterns of comorbidity and disease course are typically found. We aimed to evaluate the diagnostic accuracy (DA) of the above technique to discriminate between incident cases of first-episode schizophrenia identified in a circumscribed geographical region over a limited period of time, in comparison with next-door healthy controls. Sixty-two cases of first-episode schizophrenia or schizophreniform disorder and 62 age, gender and educationally-matched controls underwent 1.5 T MRI scanning at baseline, and were naturalistically followed-up over 1 year. T1-weighted images were used to train a high-dimensional multivariate classifier, and to generate both spatial maps of the discriminative morphological patterns between groups and ROC curves. The spatial map discriminating first-episode schizophrenia patients from healthy controls revealed a complex pattern of regional volumetric abnormalities in the former group, affecting fronto-temporal-occipital gray and white matter regions bilaterally, including the inferior fronto-occipital fasciculus, as well as the third and lateral ventricles. However, an overall modest DA (73.4%) was observed for the individual discrimination between first-episode schizophrenia patients and controls, and the classifier failed to predict 1-year prognosis (remitting versus non-remitting course) of first-episode schizophrenia (DA=58.3%). In conclusion, using a "real world" sample recruited with epidemiological methods, the application of a neuroanatomical pattern classifier afforded only modest DA to classify first-episode schizophrenia subjects and next-door healthy controls, and poor discriminative power to predict the 1-year prognosis of first-episode schizophrenia.

Combination of Resting State fMRI, DTI, and sMRI Data to Discriminate Schizophrenia by N-way MCCA + jICA

Multimodal brain imaging data have shown increasing utility in answering both scientifically interesting and clinically relevant questions. Each brain imaging technique provides a different view of brain function or structure, while multimodal fusion capitalizes on the strength of each and may uncover hidden relationships that can merge findings from separate neuroimaging studies. However, most current approaches have focused on pair-wise fusion and there is still relatively little work on N-way data fusion and examination of the relationships among multiple data types. We recently developed an approach called “mCCA + jICA” as a novel multi-way fusion method which is able to investigate the disease risk factors that are either shared or distinct across multiple modalities as well as the full correspondence across modalities. In this paper, we applied this model to combine resting state fMRI (amplitude of low-frequency fluctuation, ALFF), gray matter (GM) density, and DTI (fractional anisotropy, FA) data, in order to elucidate the abnormalities underlying schizophrenia patients (SZs, n = 35) relative to healthy controls (HCs, n = 28). Both modality-common and modality-unique abnormal regions were identified in SZs, which were then used for successful classification for seven modality-combinations, showing the potential for a broad applicability of the mCCA + jICA model and its results. In addition, a pair of GM-DTI components showed significant correlation with the positive symptom subscale of Positive and Negative Syndrome Scale (PANSS), suggesting that GM density changes in default model network along with white-matter disruption in anterior thalamic radiation are associated with increased positive PANSS. Findings suggest the DTI anisotropy changes in frontal lobe may relate to the corresponding functional/structural changes in prefrontal cortex and superior temporal gyrus that are thought to play a role in the clinical expression of SZ.

A review of multivariate methods for multimodal fusion of brain imaging data

The development of various neuroimaging techniques is rapidly improving the measurements of brain function/structure. However, despite improvements in individual modalities, it is becoming increasingly clear that the most effective research approaches will utilize multi-modal fusion, which takes advantage of the fact that each modality provides a limited view of the brain. The goal of multi-modal fusion is to capitalize on the strength of each modality in a joint analysis, rather than a separate analysis of each. This is a more complicated endeavor that must be approached more carefully and efficient methods should be developed to draw generalized and valid conclusions from high dimensional data with a limited number of subjects. Numerous research efforts have been reported in the field based on various statistical approaches, e.g. independent component analysis (ICA), canonical correlation analysis (CCA) and partial least squares (PLS). In this review paper, we survey a number of multivariate methods appearing in previous multimodal fusion reports, mostly fMRI with other modality, which were performed with or without prior information. A table for comparing optimization assumptions, purpose of the analysis, the need of priors, dimension reduction strategies and input data types is provided, which may serve as a valuable reference that helps readers understand the trade-offs of the 7 methods comprehensively. Finally, we evaluate 3 representative methods via simulation and give some suggestions on how to select an appropriate method based on a given research.

Normative development of white matter tracts: similarities and differences in relation to age, gender, and intelligence

The white matter of the brain undergoes a range of structural changes throughout development; from conception to birth, in infancy, and onwards through childhood and adolescence. Several studies have used diffusion magnetic resonance imaging (dMRI) to investigate these changes, but a consensus has not yet emerged on which white matter tracts undergo changes in the later stages of development or what the most important driving factors are behind these changes. In this study of typically developing 8- to 16-year-old children, we use a comprehensive data-driven approach based on principal components analysis to identify effects of age, gender, and brain volume on dMRI parameters, as well as their relative importance. We also show that secondary components of these parameters predict full-scale IQ, independently of the age- and gender-related effects. This overarching assessment of the common factors and gender differences in normal white matter tract development will help to advance understanding of this process in late childhood and adolescence.

Independent component analysis of DTI reveals multivariate microstructural correlations of white matter in the human brain

It has recently been demonstrated that specific patterns of correlation exist in diffusion tensor imaging (DTI) parameters across white matter tracts in the normal human brain. These microstructural correlations are thought to reflect phylogenetic and functional similarities between different axonal fiber pathways. However, this earlier work was limited in three major respects: (1) the analysis was restricted to only a dozen selected tracts; (2) the DTI measurements were averaged across whole tracts, whereas metrics such as fractional anisotropy (FA) are known to vary considerably within single tracts; and (3) a univariate measure of correlation was used. In this investigation, we perform an automated multivariate whole-brain voxel-based study of white matter FA correlations using independent component analysis (ICA) of tract-based spatial statistics computed from 3T DTI in 53 healthy adult volunteers. The resulting spatial maps of the independent components show voxels for which the FA values within each map co-vary across individuals. The strongest FA correlations were found in anatomically recognizable tracts and tract segments, either singly or in homologous pairs. Hence, ICA of DTI provides an automated unsupervised decomposition of the normal human brain into multiple separable microstructurally correlated white matter regions, many of which correspond to anatomically familiar classes of white matter pathways. Further research is needed to determine whether whole-brain ICA of DTI represents a novel alternative to tractography for feature extraction in studying the normal microstructure of human white matter as well as the abnormal white matter microstructure found in neurological and psychiatric disorders.

Putative diffusion tensor neuroimaging endophenotypes in schizophrenia: a review of the early evidence

Although schizophrenia has a high heritability, the genetic effects conferring diathesis to schizophrenia are thought to be complex and underlain by multifactorial polygenic inheritance. ‘Endophenotypes’, or ‘intermediate phenotypes’, are narrowed constructs of genetic risk that are assumed to be more proximal to the gene effects in the disease pathway than clinical phenotypes. A current aim in schizophrenia research is to identify promising putative endophenotypes for use in molecular genetics studies. Recently, much of the focus has been on neurocognitive, conventional T1-weighted structural MRI, functional MRI and electrophysiological endophenotypes. Diffusion tensor imaging has emerged as another important structural neuroimaging modality in the aim to identify abnormalities in brain connectivity and diffusivity in schizophrenia, and abnormalities detected via this method may be promising candidate endophenotypes. In this article, we present the first comprehensive review of the early evidence that qualifies diffusion tensor abnormalities as potentially appropriate endophenotypes of schizophrenia.

A baseline for the multivariate comparison of resting-state networks

As the size of functional and structural MRI datasets expands, it becomes increasingly important to establish a baseline from which diagnostic relevance may be determined, a processing strategy that efficiently prepares data for analysis, and a statistical approach that identifies important effects in a manner that is both robust and reproducible. In this paper, we introduce a multivariate analytic approach that optimizes sensitivity and reduces unnecessary testing. We demonstrate the utility of this mega-analytic approach by identifying the effects of age and gender on the resting-state networks (RSNs) of 603 healthy adolescents and adults (mean age: 23.4 years, range: 12–71 years). Data were collected on the same scanner, preprocessed using an automated analysis pipeline based in SPM, and studied using group independent component analysis. RSNs were identified and evaluated in terms of three primary outcome measures: time course spectral power, spatial map intensity, and functional network connectivity. Results revealed robust effects of age on all three outcome measures, largely indicating decreases in network coherence and connectivity with increasing age. Gender effects were of smaller magnitude but suggested stronger intra-network connectivity in females and more inter-network connectivity in males, particularly with regard to sensorimotor networks. These findings, along with the analysis approach and statistical framework described here, provide a useful baseline for future investigations of brain networks in health and disease.

Diffusion tensor imaging reliably differentiates patients with schizophrenia from healthy volunteers

The objective of this research was to determine whether fractional anisotropy (FA) and mean diffusivity (MD) maps derived from diffusion tensor imaging (DTI) of the brain are able to reliably differentiate patients with schizophrenia from healthy volunteers. DTI and high resolution structural magnetic resonance scans were acquired in 50 patients with schizophrenia and 50 age- and sex-matched healthy volunteers. FA and MD maps were estimated from the DTI data and spatially normalized to the Montreal Neurologic Institute standard stereotactic space. Individuals were divided randomly into two groups of 50, a training set, and a test set, each comprising 25 patients and 25 healthy volunteers. A pattern classifier was designed using Fisher's linear discriminant analysis (LDA) based on the training set of images to categorize individuals in the test set as either patients or healthy volunteers. Using the FA maps, the classifier correctly identified 94% of the cases in the test set (96% sensitivity and 92% specificity). The classifier achieved 98% accuracy (96% sensitivity and 100% specificity) when using the MD maps as inputs to distinguish schizophrenia patients from healthy volunteers in the test dataset. Utilizing FA and MD data in combination did not significantly alter the accuracy (96% sensitivity and specificity). Patterns of water self-diffusion in the brain as estimated by DTI can be used in conjunction with automated pattern recognition algorithms to reliably distinguish between patients with schizophrenia and normal control subjects.

Identification of imaging biomarkers in schizophrenia: a coefficient-constrained independent component analysis of the mind multi-site schizophrenia study

A number of recent studies have combined multiple experimental paradigms and modalities to find relevant biological markers for schizophrenia. In this study, we extracted fMRI features maps from the analysis of three experimental paradigms (auditory oddball, Sternberg item recognition, sensorimotor) for a large number (n=154) of patients with schizophrenia and matched healthy controls. We used the general linear model (GLM) and independent component analysis (ICA) to extract feature maps (i.e. ICA component maps and GLM contrast maps), which were then subjected to a coefficient-constrained independent component analysis (CCICA) to identify potential neurobiological markers. A total of 29 different feature maps were extracted for each subject. Our results show a number of optimal feature combinations that reflect a set of brain regions that significantly discriminate between patients and controls in the spatial heterogeneity and amplitude of their feature signals. Spatial heterogeneity was seen in regions such as the superior/middle temporal and frontal gyri, bilateral parietal lobules, and regions of the thalamus. Most strikingly, an ICA feature representing a bilateral frontal pole network was consistently seen in the ten highest feature results when ranked on differences found in the amplitude of their feature signals. The implication of this frontal pole network and the spatial variability which spans regions comprising of bilateral frontal/temporal lobes and parietal lobules suggests that they might play a significant role in the pathophysiology of schizophrenia.

Biomarkers for identifying first-episode schizophrenia patients using diffusion weighted imaging

Recent advances in diffusion weighted MR imaging (dMRI) has made it a tool of choice for investigating white matter abnormalities of the brain and central nervous system. In this work, we design a system that detects abnormal features (biomarkers) of first-episode schizophrenia patients and then classifies them using these features. We use two different models of the dMRI data, namely, spherical harmonics and the two-tensor model. The algorithm works by first computing several diffusion measures from each model. An affine-invariant representation of each subject is then computed, thus avoiding the need for registration. This representation is used within a kernel based feature selection algorithm to determine the biomarkers that are statistically different between the two populations. Confirmation of how well these biomarkers identify each population is obtained by using several classifiers such as, k-nearest neighbors, Parzen window classifier, and support vector machines to separate 21 first-episode patients from 20 age-matched normal controls. Classification results using leave-many-out cross-validation scheme are given for each representation. This algorithm is a first step towards early detection of schizophrenia.

Elucidating a magnetic resonance imaging-based neuroanatomic biomarker for psychosis: classification analysis using probabilistic brain atlas and machine learning algorithms

BACKGROUND

No objective diagnostic biomarkers or laboratory tests have yet been developed for psychotic illness. Magnetic resonance imaging (MRI) studies consistently find significant abnormalities in multiple brain structures in psychotic patients relative to healthy control subjects, but these abnormalities show substantial overlap with anatomic variation that is in the normal range and therefore nondiagnostic. Recently, efforts have been made to discriminate psychotic patients from healthy individuals using machine-learning-based pattern classification methods on MRI data.

METHODS

Three-dimensional cortical gray matter density (GMD) maps were generated for 36 patients with recent-onset psychosis and 36 sex- and age-matched control subjects using a cortical pattern matching method. Between-group differences in GMD were evaluated. Second, the sparse multinomial logistic regression classifier included in the Multivariate Pattern Analysis in Python machine-learning package was applied to the cortical GMD maps to discriminate psychotic patients from control subjects.

RESULTS

Patients showed significantly lower GMD, particularly in prefrontal, cingulate, and lateral temporal brain regions. Pattern classification analysis achieved 86.1% accuracy in discriminating patients from controls using leave-one-out cross-validation.

CONCLUSIONS

These results suggest that even at the early stage of illness, psychotic patients present distinct patterns of regional cortical gray matter changes that can be discriminated from the normal pattern. These findings indicate that we can detect complex patterns of brain abnormality in early stages of psychotic illness, which has critical implications for early identification and intervention in individuals at ultra-high risk for developing psychosis/schizophrenia.

Functional brain networks in schizophrenia: a review

Functional magnetic resonance imaging (fMRI) has become a major technique for studying cognitive function and its disruption in mental illness, including schizophrenia. The major proportion of imaging studies focused primarily upon identifying regions which hemodynamic response amplitudes covary with particular stimuli and differentiate between patient and control groups. In addition to such amplitude based comparisons, one can estimate temporal correlations and compute maps of functional connectivity between regions which include the variance associated with event-related responses as well as intrinsic fluctuations of hemodynamic activity. Functional connectivity maps can be computed by correlating all voxels with a seed region when a spatial prior is available. An alternative are multivariate decompositions such as independent component analysis (ICA) which extract multiple components, each of which is a spatially distinct map of voxels with a common time course. Recent work has shown that these networks are pervasive in relaxed resting and during task performance and hence provide robust measures of intact and disturbed brain activity. This in turn bears the prospect of yielding biomarkers for schizophrenia, which can be described both in terms of disrupted local processing as well as altered global connectivity between large-scale networks. In this review we will summarize functional connectivity measures with a focus upon work with ICA and discuss the meaning of intrinsic fluctuations. In addition, examples of how brain networks have been used for classification of disease will be shown. We present work with functional network connectivity, an approach that enables the evaluation of the interplay between multiple networks and how they are affected in disease. We conclude by discussing new variants of ICA for extracting maximally group discriminative networks from data. In summary, it is clear that identification of brain networks and their inter-relationships with fMRI has great potential to improve our understanding of schizophrenia.

An ICA-based method for the identification of optimal FMRI features and components using combined group-discriminative techniques

Extraction of relevant features from multitask functional MRI (fMRI) data in order to identify potential biomarkers for disease, is an attractive goal. In this paper, we introduce a novel feature-based framework, which is sensitive and accurate in detecting group differences (e.g. controls vs. patients) by proposing three key ideas. First, we integrate two goal-directed techniques: coefficient-constrained independent component analysis (CC-ICA) and principal component analysis with reference (PCA-R), both of which improve sensitivity to group differences. Secondly, an automated artifact-removal method is developed for selecting components of interest derived from CC-ICA, with an average accuracy of 91%. Finally, we propose a strategy for optimal feature/component selection, aiming to identify optimal group-discriminative brain networks as well as the tasks within which these circuits are engaged. The group-discriminating performance is evaluated on 15 fMRI feature combinations (5 single features and 10 joint features) collected from 28 healthy control subjects and 25 schizophrenia patients. Results show that a feature from a sensorimotor task and a joint feature from a Sternberg working memory (probe) task and an auditory oddball (target) task are the top two feature combinations distinguishing groups. We identified three optimal features that best separate patients from controls, including brain networks consisting of temporal lobe, default mode and occipital lobe circuits, which when grouped together provide improved capability in classifying group membership. The proposed framework provides a general approach for selecting optimal brain networks which may serve as potential biomarkers of several brain diseases and thus has wide applicability in the neuroimaging research community.

Joint source based morphometry identifies linked gray and white matter group differences

We present a multivariate approach called joint source based morphometry (jSBM), to identify linked gray and white matter regions which differ between groups. In jSBM, joint independent component analysis (jICA) is used to decompose preprocessed gray and white matter images into joint sources and statistical analysis is used to determine the significant joint sources showing group differences and their relationship to other variables of interest (e.g. age or sex). The identified joint sources are groupings of linked gray and white matter regions with common covariation among subjects. In this study, we first provide a simulation to validate the jSBM approach. To illustrate our method on real data, jSBM is then applied to structural magnetic resonance imaging (sMRI) data obtained from 120 chronic schizophrenia patients and 120 healthy controls to identify group differences. JSBM identified four joint sources as significantly associated with schizophrenia. Linked gray-white matter regions identified in each of the joint sources included: 1) temporal--corpus callosum, 2) occipital/frontal--inferior fronto-occipital fasciculus, 3) frontal/parietal/occipital/temporal--superior longitudinal fasciculus and 4) parietal/frontal--thalamus. Age effects on all four joint sources were significant, but sex effects were significant only for the third joint source. Our findings demonstrate that jSBM can exploit the natural linkage between gray and white matter by incorporating them into a unified framework. This approach is applicable to a wide variety of problems to study linked gray and white matter group differences.