Diffusion tensor imaging reliably differentiates patients with schizophrenia from healthy volunteers

Unveiling Promising Neuroimaging Biomarkers for Schizophrenia Through Clinical and Genetic Perspectives

Schizophrenia is a complex and serious brain disorder. Neuroscientists have become increasingly interested in using magnetic resonance-based brain imaging-derived phenotypes (IDPs) to investigate the etiology of psychiatric disorders. IDPs capture valuable clinical advantages and hold biological significance in identifying brain abnormalities. In this review, we aim to discuss current and prospective approaches to identify potential biomarkers for schizophrenia using clinical multimodal neuroimaging and imaging genetics. We first described IDPs through their phenotypic classification and neuroimaging genomics. Secondly, we discussed the applications of multimodal neuroimaging by clinical evidence in observational studies and randomized controlled trials. Thirdly, considering the genetic evidence of IDPs, we discussed how can utilize neuroimaging data as an intermediate phenotype to make association inferences by polygenic risk scores and Mendelian randomization. Finally, we discussed machine learning as an optimum approach for validating biomarkers. Together, future research efforts focused on neuroimaging biomarkers aim to enhance our understanding of schizophrenia.

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.

Baseline symptom-related white matter tracts predict individualized treatment response to 12-week antipsychotic monotherapies in first-episode schizophrenia

There is significant heterogeneity in individual responses to antipsychotic drugs, but there is no reliable predictor of antipsychotics response in first-episode psychosis. This study aimed to investigate whether psychotic symptom-related alterations in fractional anisotropy (FA) and mean diffusivity (MD) of white matter (WM) at the early stage of the disorder may aid in the individualized prediction of drug response. Sixty-eight first-episode patients underwent baseline structural MRI scans and were subsequently randomized to receive a single atypical antipsychotic throughout the first 12 weeks. Clinical symptoms were evaluated using the eight "core symptoms" selected from the Positive and Negative Syndrome Scale (PANSS-8). Follow-up assessments were conducted at the 4th, 8th, and 12th weeks by trained psychiatrists. LASSO regression model and cross-validation were conducted to examine the performance of baseline symptom-related alterations FA and MD of WM in the prediction of individualized treatment outcome. Fifty patients completed both clinical follow-up assessments by the 8th and 12th weeks. 30 patients were classified as responders, and 20 patients were classified as nonresponders. At baseline, the altered diffusion properties of fiber tracts in the anterior thalamic radiation, corticospinal tract, callosum forceps minor, longitudinal fasciculi (ILF), inferior frontal-occipital fasciculi (IFOF) and superior longitudinal fasciculus (SLF) were related to the severity of symptoms. These abnormal fiber tracts, especially the ILF, IFOF, and SLF, significantly predicted the response to antipsychotic treatment at the individual level (AUC = 0.828, P < 0.001). These findings demonstrate that early microstructural WM changes contribute to the pathophysiology of psychosis and may serve as meaningful individualized predictors of response to antipsychotics.

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.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

In memory of Professor Iain Wilkinson: cognitive and neuroimaging endophenotypes in a consanguineous schizophrenia multiplex family

BACKGROUND

Schizophrenia endophenotypes may help elucidate functional effects of genetic risk variants in multiply affected consanguineous families that segregate recessive risk alleles of large effect size. We studied the association between a schizophrenia risk locus involving a 6.1Mb homozygous region on chromosome 13q22-31 in a consanguineous multiplex family and cognitive functioning, haemodynamic response and white matter integrity using neuroimaging.

METHODS

We performed CANTAB neuropsychological testing on four affected family members (all homozygous for the risk locus), ten unaffected family members (seven homozygous and three heterozygous) and ten healthy volunteers, and tested neuronal responses on fMRI during an n-back working memory task, and white matter integrity on diffusion tensor imaging (DTI) on four affected and six unaffected family members (four homozygous and two heterozygous) and three healthy volunteers. For cognitive comparisons we used a linear mixed model (Kruskal-Wallis) test, followed by posthoc Dunn's pairwise tests with a Bonferroni adjustment. For fMRI analysis, we counted voxels exceeding the p < 0.05 corrected threshold. DTI analysis was observational.

RESULTS

Family members with schizophrenia and unaffected family members homozygous for the risk haplotype showed attention (p < 0.01) and working memory deficits (p < 0.01) compared with healthy controls; a neural activation laterality bias towards the right prefrontal cortex (voxels reaching p < 0.05, corrected) and observed lower fractional anisotropy in the anterior cingulate cortex and left dorsolateral prefrontal cortex.

CONCLUSIONS

In this family, homozygosity at the 13q risk locus was associated with impaired cognition, white matter integrity, and altered laterality of neural activation.

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.

Structural and diffusion MRI based schizophrenia classification using 2D pretrained and 3D naive Convolutional Neural Networks

The ability of automatic feature learning makes Convolutional Neural Network (CNN) potentially suitable to uncover the complex and widespread brain changes in schizophrenia. Despite that, limited studies have been done on schizophrenia identification using interpretable deep learning approaches on multimodal neuroimaging data. Here, we developed a deep feature approach based on pre-trained 2D CNN and naive 3D CNN models trained from scratch for schizophrenia classification by integrating 3D structural and diffusion magnetic resonance imaging (MRI) data. We found that the naive 3D CNN models outperformed the pretrained 2D CNN models and the handcrafted feature-based machine learning approach using support vector machine during both cross-validation and testing on an independent dataset. Multimodal neuroimaging-based models accomplished performance superior to models based on a single modality. Furthermore, we identified brain grey matter and white matter regions critical for illness classification at the individual- and group-level which supported the salience network and striatal dysfunction hypotheses in schizophrenia. Our findings underscore the potential of CNN not only to automatically uncover and integrate multimodal 3D brain imaging features for schizophrenia identification, but also to provide relevant neurobiological interpretations which are crucial for developing objective and interpretable imaging-based probes for prognosis and diagnosis in psychiatric disorders.

Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p &lt; 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p &lt; 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

Searching for Imaging Biomarkers of Psychotic Dysconnectivity

BACKGROUND

Progress in precision psychiatry is predicated on identifying reliable individual-level diagnostic biomarkers. For psychosis, measures of structural and functional connectivity could be promising biomarkers given consistent reports of dysconnectivity across psychotic disorders using magnetic resonance imaging.

METHODS

We leveraged data from four independent cohorts of patients with psychosis and control subjects with observations from approximately 800 individuals. We used group-level analyses and two supervised machine learning algorithms (support vector machines and ridge regression) to test within-, between-, and across-sample classification performance of white matter and resting-state connectivity metrics.

RESULTS

Although we replicated group-level differences in brain connectivity, individual-level classification was suboptimal. Classification performance within samples was variable across folds (highest area under the curve [AUC] range = 0.30) and across datasets (average support vector machine AUC range = 0.50; average ridge regression AUC range = 0.18). Classification performance between samples was similarly variable or resulted in AUC values of approximately 0.65, indicating a lack of model generalizability. Furthermore, collapsing across samples (resting-state functional magnetic resonance imaging, N = 888; diffusion tensor imaging, N = 860) did not improve model performance (maximal AUC = 0.67). Ridge regression models generally outperformed support vector machine models, although classification performance was still suboptimal in terms of clinical relevance. Adjusting for demographic covariates did not greatly affect results.

CONCLUSIONS

Connectivity measures were not suitable as diagnostic biomarkers for psychosis as assessed in this study. Our results do not negate that other approaches may be more successful, although it is clear that a systematic approach to individual-level classification with large independent validation samples is necessary to properly vet neuroimaging features as diagnostic biomarkers.

Improving the predictive potential of diffusion MRI in schizophrenia using normative models-Towards subject-level classification

Diffusion MRI studies consistently report group differences in white matter between individuals diagnosed with schizophrenia and healthy controls. Nevertheless, the abnormalities found at the group-level are often not observed at the individual level. Among the different approaches aiming to study white matter abnormalities at the subject level, normative modeling analysis takes a step towards subject-level predictions by identifying affected brain locations in individual subjects based on extreme deviations from a normative range. Here, we leveraged a large harmonized diffusion MRI dataset from 512 healthy controls and 601 individuals diagnosed with schizophrenia, to study whether normative modeling can improve subject-level predictions from a binary classifier. To this aim, individual deviations from a normative model of standard (fractional anisotropy) and advanced (free-water) dMRI measures, were calculated by means of age and sex-adjusted z-scores relative to control data, in 18 white matter regions. Even though larger effect sizes are found when testing for group differences in z-scores than are found with raw values (p < .001), predictions based on summary z-score measures achieved low predictive power (AUC < 0.63). Instead, we find that combining information from the different white matter tracts, while using multiple imaging measures simultaneously, improves prediction performance (the best predictor achieved AUC = 0.726). Our findings suggest that extreme deviations from a normative model are not optimal features for prediction. However, including the complete distribution of deviations across multiple imaging measures improves prediction, and could aid in subject-level classification.

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.

Anatomy and White Matter Connections of the Lingual Gyrus and Cuneus

BACKGROUND

The medial occipital lobe, composed of the lingual gyrus and cuneus, is necessary for both basic and higher level visual processing. It is also known to facilitate cross-modal, nonvisual functions, such as linguistic processing and verbal memory, after the loss of the visual senses. A detailed cortical model elucidating the white matter connectivity associated with this area could improve our understanding of the interacting brain networks that underlie complex human processes and postoperative outcomes related to vision and language.

METHODS

Generalized q-sampling imaging tractography, validated by gross anatomic dissection for qualitative visual agreement, was performed on 10 healthy adult controls obtained from the Human Connectome Project.

RESULTS

Major white matter connections were identified by tractography and validated by gross dissection, which connected the medial occipital lobe with itself and the adjacent cortices, especially the temporal lobe. The short- and long-range connections identified consisted mainly of U-shaped association fibers, intracuneal fibers, and inferior fronto-occipital fasciculus, inferior longitudinal fasciculus, middle longitudinal fasciculus, and lingual-fusiform connections.

CONCLUSIONS

The medial occipital lobe is an extremely interconnected system, supporting its ability to perform coordinated basic visual processing, but also serves as a center for many long-range association fibers, supporting its importance in nonvisual functions, such as language and memory. The presented data represent clinically actionable anatomic information that can be used in multimodal navigation of white matter lesions in the medial occipital lobe to prevent neurologic deficits and improve patients' quality of life after cerebral surgery.

An fMRI Feature Selection Method Based on a Minimum Spanning Tree for Identifying Patients with Autism

Autism spectrum disorder (ASD) is a neurodevelopmental disorder originating in infancy and childhood that may cause language barriers and social difficulties. However, in the diagnosis of ASD, the current machine learning methods still face many challenges in determining the location of biomarkers. Here, we proposed a novel feature selection method based on the minimum spanning tree (MST) to seek neuromarkers for ASD. First, we constructed an undirected graph with nodes of candidate features. At the same time, a weight calculation method considering both feature redundancy and discriminant ability was introduced. Second, we utilized the Prim algorithm to construct the MST from the initial graph structure. Third, the sum of the edge weights of all connected nodes was sorted for each node in the MST. Then, N features corresponding to the nodes with the first N smallest sum were selected as classification features. Finally, the support vector machine (SVM) algorithm was used to evaluate the discriminant performance of the aforementioned feature selection method. Comparative experiments results show that our proposed method has improved the ASD classification performance, i.e., the accuracy, sensitivity, and specificity were 86.7%, 87.5%, and 85.7%, respectively.

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.

Anatomy and white matter connections of the fusiform gyrus

The fusiform gyrus is understood to be involved in the processing of high-order visual information, particularly related to faces, bodies, and stimuli characterized by high spatial frequencies. A detailed understanding of the exact location and nature of associated white-tracts could significantly improve post-operative morbidity related to declining capacity. Through generalized q-sampling imaging (GQI) validated by gross dissection as a direct anatomical method of identifying white matter tracts, we have characterized these connections based on relationships to other well-known structures. We created the white matter tracts using GQI and confirmed the tracts using gross dissection. These dissections demonstrated connections to the occipital lobe from the fusiform gyrus along with longer association fibers that course through this gyrus. The fusiform gyrus is an important region implicated in such tasks as the visual processing of human faces and bodies, as well as the perception of stimuli with high spatial frequencies. Post-surgical outcomes related to this region may be better understood in the context of the fiber-bundle anatomy highlighted by this study.

Detecting cognitive impairment in HIV-infected individuals using mutual connectivity analysis of resting state functional MRI

It is estimated that more than 50% of the individuals affected with Human Immunodeficiency Virus (HIV) present deficits in multiple cognitive domains, collectively known as HIV-associated neurocognitive disorder (HAND). Early stages of brain injury may be clinically silent but potentially measurable via neuroimaging. A total of 40 subjects (20 HIV positive and 20 age-matched controls) volunteered for the study. All subjects underwent a standard battery of neuropsychological tests used for the clinical diagnosis of HAND. Fourteen HIV+ and five healthy subjects showed signs of neurological impairment. Connectivity was computed using mutual connectivity analysis (MCA) with generalized radial basis function neural network, a framework for quantifying non-linear connectivity as well as conventional correlation from 160 regional time-series that were extracted based on the Dosenbach (DOS) atlas. We subsequently applied graph theoretic as well as network analysis approaches for characterizing the connectivity matrices obtained and localizing between-group differences. We focused on trying to detect cognitive impairment using the subset of 29 (14 subjects with HAND and 15 cognitively normal controls) subjects. For the global analysis, significant differences (p < 0.05) were seen in the variance in degree, modularity and Smallworldness. Regional analysis revealed changes occurring mainly in portions of the lateral occipital cortex and the cingulate cortex. Furthermore, using Network Based Statistics (NBS), we uncovered an affected sub-network of 19 nodes comprising predominantly of regions of the default mode network. Similar analysis using the conventional correlation method revealed no significant results at a global scale, while regional analysis shows some differences spread across resting state networks. These results suggest that there is a subtle reorganization occurring in the topology of brain networks in HAND, which can be captured using improved connectivity analysis.

Schizophrenia Exhibits Bi-directional Brain-Wide Alterations in Cortico-Striato-Cerebellar Circuits

Distributed neural dysconnectivity is considered a hallmark feature of schizophrenia (SCZ), yet a tension exists between studies pinpointing focal disruptions versus those implicating brain-wide disturbances. The cerebellum and the striatum communicate reciprocally with the thalamus and cortex through monosynaptic and polysynaptic connections, forming cortico-striatal-thalamic-cerebellar (CSTC) functional pathways that may be sensitive to brain-wide dysconnectivity in SCZ. It remains unknown if the same pattern of alterations persists across CSTC systems, or if specific alterations exist along key functional elements of these networks. We characterized connectivity along major functional CSTC subdivisions using resting-state functional magnetic resonance imaging in 159 chronic patients and 162 matched controls. Associative CSTC subdivisions revealed consistent brain-wide bi-directional alterations in patients, marked by hyper-connectivity with sensory-motor cortices and hypo-connectivity with association cortex. Focusing on the cerebellar and striatal components, we validate the effects using data-driven k-means clustering of voxel-wise dysconnectivity and support vector machine classifiers. We replicate these results in an independent sample of 202 controls and 145 patients, additionally demonstrating that these neural effects relate to cognitive performance across subjects. Taken together, these results from complementary approaches implicate a consistent motif of brain-wide alterations in CSTC systems in SCZ, calling into question accounts of exclusively focal functional disturbances.

White matter structure in schizophrenia and autism: Abnormal diffusion across the brain in schizophrenia

BACKGROUND

Schizophrenia and autism share many behavioral and neurological similarities, including altered white matter tract structure. However, because schizophrenia and autism are rarely compared directly, it is difficult to establish whether white matter abnormalities are disorder-specific or are common across these disorders that share some symptomatology.

METHODS

In the current study, we compared white matter water diffusion using tensor imaging in 25 adults with autism, 15 adults with schizophrenia, all with IQ scores above 88, and 19 neurotypical adults.

RESULTS

Although the three groups evinced no statistically significant differences in measures of fractional anisotropy (FA), the schizophrenia group showed significantly greater mean diffusivity (MD; Cohen's d > 0.77), due to greater radial diffusivity (RD; Cohen's d > 0.92), compared to both the autism and control groups. This effect was evident across the brain rather than specific to a particular tract.

CONCLUSIONS

The greater MD and RD in schizophrenia appears to be diagnosis-specific. The altered diffusion may reflect subtle abnormalities in myelination, which could be a potential mechanism underlying the widespread behavioral deficits associated with schizophrenia.

Whole-brain structural magnetic resonance imaging-based classification of primary dysmenorrhea in pain-free phase: a machine learning study

To develop a machine learning model to investigate the discriminative power of whole-brain gray-matter (GM) images derived from primary dysmenorrhea (PDM) women and healthy controls (HCs) during the pain-free phase and further evaluate the predictive ability of contributing features in predicting the variance in menstrual pain intensity. Sixty patients with PDM and 54 matched female HCs were recruited from the local university. All participants underwent the head and pelvic magnetic resonance imaging scans to calculate GM volume and myometrium-apparent diffusion coefficient (ADC) during their periovulatory phase. Questionnaire assessment was also conducted. A support vector machine algorithm was used to develop the classification model. The significance of model performance was determined by the permutation test. Multiple regression analysis was implemented to explore the relationship between discriminative features and intensity of menstrual pain. Demographics and myometrium ADC-based classifications failed to pass the permutation tests. Brain-based classification results demonstrated that 75.44% of subjects were correctly classified, with 83.33% identification of the patients with PDM (P < 0.001). In the regression analysis, demographical indicators and myometrium ADC accounted for a total of 29.37% of the variance in pain intensity. After regressing out these factors, GM features explained 60.33% of the remaining variance. Our results suggested that GM volume can be used to discriminate patients with PDM and HCs during the pain-free phase, and neuroimaging features can further predict the variance in the intensity of menstrual pain, which may provide a potential imaging marker for the assessment of menstrual pain intervention.

White matter microstructure and network-connectivity in emerging adults with subclinical psychotic experiences

Group comparisons of individuals with psychotic disorder and controls have shown alterations in white matter microstructure. Whether white matter microstructure and network connectivity is altered in adolescents with subclinical psychotic experiences (PE) at the lowest end of the psychosis severity spectrum is less clear. DWI scan were acquired in 48 individuals with PE and 43 healthy controls (HC). Traditional tensor-derived indices: Fractional Anisotropy, Axial Diffusivity, Mean Diffusivity and Radial Diffusivity, as well as network connectivity measures (global/local efficiency and clustering coefficient) were compared between the groups. Subclinical psychopathology was assessed with the Community Assessment of Psychic Experiences (CAPE) and Montgomery-Åsberg Depression Rating Scale (MADRS) questionnaires and, in order to capture momentary subclinical expression of psychosis, the Experience Sampling Method (ESM) questionnaires. Within the PE-group, interactions between subclinical (momentary) symptoms and brain regions in the model of tensor-derived indices and network connectivity measures were investigated in a hypothesis-generating fashion. Whole brain analyses showed no group differences in tensor-derived indices and network connectivity measures. In the PE-group, a higher positive symptom distress score was associated with both higher local efficiency and clustering coefficient in the right middle temporal pole. The findings indicate absence of microstructural white matter differences between emerging adults with subclinical PE and controls. In the PE-group, attenuated symptoms were positively associated with network efficiency/cohesion, which requires replication and may indicate network alterations in emerging mild psychopathology.

A multivoxel pattern analysis framework with mutual connectivity analysis investigating changes in resting state connectivity in patients with HIV associated neurocognitve disorder

Functional MRI (fMRI) quantifies brain activity non-invasively by measuring the blood oxygen level dependent (BOLD) response to neuronal activity. It was recently demonstrated, on realistic fMRI simulations, that nonlinear connectivity approaches, such as Mutual Connectivity Analysis with Local Models (MCA-LM), are better suited for extracting connectivity measures than conventional techniques of cross-correlating time-series pairs. In this work, we investigate the application of MCA-LM in extracting meaningful connectivity measures aiding in distinguishing healthy controls from individuals presenting with symptoms of HIV Associated Neurocognitive Disorder (HAND), which occurs as a result of HIV infection of the central nervous system. The pairwise connectivity measures provide a high-dimensional representation of connectivity profiles for subjects and are used as features for classification. We adopt feature selection (FS) techniques reducing the number of redundant and noisy features, while also controlling the complexity of the classifiers. We investigate three FS techniques: 1) Kendall's τ, 2) Information Gain Attribute selection 3) ReliefF and two classifiers:1) AdaBoost and 2) Random Forests. Our results demonstrate that MCA-LM consistently outperforms correlation in terms of Area under the Receiver Operating Characteristic Curve and accuracy. Improved performance with MCA-LM suggests that such a nonlinear approach is better at capturing meaningful connectivity relationships between brain regions. This demonstrates potential for developing novel neuroimaging-derived biomarkers for HAND. Furthermore, FS helps identify connections between anatomical regions that are affected by HAND. In this work, we show that the regions of the basal ganglia and frontal cortex, which are known to be affected by HAND according to current literature, are identified as most discriminative.

Classification of First-Episode Schizophrenia Using Multimodal Brain Features: A Combined Structural and Diffusion Imaging Study

Recent neuroanatomical pattern recognition studies have shown some promises for developing an objective neuroimaging-based classification related to schizophrenia. This study explored the feasibility of reliably identifying schizophrenia using single and multimodal multivariate neuroimaging features. Multiple brain measures including regional gray matter (GM) volume, cortical thickness, gyrification, fractional anisotropy (FA), and mean diffusivity (MD) were extracted using fully automated procedures. We used Gradient Boosting Decision Tree to identify the most frequently selected features of each set of neuroanatomical metric and fused multimodal measures. The current classification model was trained and validated based on 98 patients with first-episode schizophrenia (FES) and 106 matched healthy controls (HCs). The classification model was trained and tested in an independent dataset of 54 patients with FES and 48 HCs using imaging data acquired on a different magnetic resonance imaging scanner. Using the most frequently selected features from fused structural and diffusion tensor imaging metrics, a classification accuracy of 75.05% was achieved, which was higher than accuracy derived from a single imaging metric. Most prominent discriminative features included cortical thickness of left transverse temporal gyrus and right parahippocampal gyrus, the FA of left corticospinal tract and right external capsule. In the independent cohort, average accuracy was 76.54%, derived from combined features selected from cortical thickness, gyrification, FA, and MD. These features characterized by GM abnormalities and white matter disruptions have discriminative power with respect to the underlying pathological changes in the brain of individuals having schizophrenia. Our results further highlight the potential advantage of multimodal data fusion for identifying schizophrenia.

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.

Development of Neuroimaging-Based Biomarkers in Psychiatry

This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.

Perspectives on Machine Learning for Classification of Schizotypy Using fMRI Data

Functional magnetic resonance imaging is capable of estimating functional activation and connectivity in the human brain, and lately there has been increased interest in the use of these functional modalities combined with machine learning for identification of psychiatric traits. While these methods bear great potential for early diagnosis and better understanding of disease processes, there are wide ranges of processing choices and pitfalls that may severely hamper interpretation and generalization performance unless carefully considered. In this perspective article, we aim to motivate the use of machine learning schizotypy research. To this end, we describe common data processing steps while commenting on best practices and procedures. First, we introduce the important role of schizotypy to motivate the importance of reliable classification, and summarize existing machine learning literature on schizotypy. Then, we describe procedures for extraction of features based on fMRI data, including statistical parametric mapping, parcellation, complex network analysis, and decomposition methods, as well as classification with a special focus on support vector classification and deep learning. We provide more detailed descriptions and software as supplementary material. Finally, we present current challenges in machine learning for classification of schizotypy and comment on future trends and perspectives.

Identifying mild-moderate Parkinson's disease using whole-brain functional connectivity

OBJECTIVE

Our study aims to extract significant disorder-associated patterns from whole brain functional connectivity to distinguish mild-moderate Parkinson's disease (PD) patients from controls.

METHODS

Resting-state fMRI data were measured from thirty-six PD individuals and thirty-five healthy controls. Multivariate pattern analysis was applied to investigate whole-brain functional connectivity patterns in individuals with 'mild-moderate' PD. Additionally, the relationship between the asymmetry of functional connectivity and the side of the initial symptoms was also analyzed.

RESULTS

In a leave-one-out cross-validation, we got the generalization rate of 80.28% for distinguishing PD patients from controls. The most discriminative functional connectivity was found in cortical networks that included the default mode, sensorimotor and attention networks. Compared to patients with the left side initially affected, an increased abnormal functional connectivity was found in patients in whom the right side was initially affected.

CONCLUSIONS

Our results indicated that discriminative functional connectivity is likely associated with disturbances of cortical networks involved in sensorimotor control and attention. The spatiotemporal patterns of motor asymmetry may be related to the lateralized dysfunction on the early stages of PD.

SIGNIFICANCE

This study identifies discriminative functional connectivity that is associated with disturbances of cortical networks. Our results demonstrated new evidence regarding the functional brain changes related to the unilateral motor symptoms of early PD.

Lower Prefrontal and Hippocampal Volume and Diffusion Tensor Imaging Differences Reflect Structural and Functional Abnormalities in Abstinent Individuals with Alcohol Use Disorder

BACKGROUND

Alcohol use disorder (AUD) is known to have adverse effects on brain structure and function. Multimodal assessments investigating volumetric, diffusion, and cognitive characteristics may facilitate understanding of the consequences of long-term alcohol use on brain circuitry, their structural impairment patterns, and their impact on cognitive function in AUD.

METHODS

Voxel- and surface-based volumetric estimations, diffusion tensor imaging (DTI), and neuropsychological tests were performed on 60 individuals: 30 abstinent individuals with AUD (DSM-IV) and 30 healthy controls. Group differences in the volumes of cortical and subcortical regions, fractional anisotropy (FA), axial and radial diffusivities (AD and RD, respectively), and performance on neuropsychological tests were analyzed, and the relationship among significantly different measures was assessed using canonical correlation.

RESULTS

AUD participants had significantly smaller volumes in left pars orbitalis, right medial orbitofrontal, right caudal middle frontal, and bilateral hippocampal regions, lower FA in 9 white matter (WM) regions, and higher FA in left thalamus, compared to controls. In AUD, lower FA in 6 of 9 WM regions was due to higher RD and due to lower AD in the left external capsule. AUD participants scored lower on problem-solving ability, visuospatial memory span, and working memory. Positive correlations of prefrontal cortical, left hippocampal volumes, and FA in 4 WM regions with visuospatial memory performance and negative correlation with lower problem-solving ability were observed. Significant positive correlation between age and FA was observed in bilateral putamen.

CONCLUSIONS

Findings showed specific structural brain abnormalities to be associated with visuospatial memory and problem-solving ability-related impairments observed in AUD. Higher RD in 6 WM regions suggests demyelination, and lower AD in left external capsule suggests axonal loss in AUD. The positive correlation between FA and age in bilateral putamen may reflect accumulation of iron depositions with increasing age.

Anatomy and white matter connections of the orbitofrontal gyrus

OBJECTIVE

The orbitofrontal cortex (OFC) is understood to have a role in outcome evaluation and risk assessment and is commonly involved with infiltrative tumors. A detailed understanding of the exact location and nature of associated white matter tracts could significantly improve postoperative morbidity related to declining capacity. Through diffusion tensor imaging–based fiber tracking validated by gross anatomical dissection as ground truth, the authors have characterized these connections based on relationships to other well-known structures.

METHODS

Diffusion imaging from the Human Connectome Project for 10 healthy adult controls was used for tractography analysis. The OFC was evaluated as a whole based on connectivity with other regions. All OFC tracts were mapped in both hemispheres, and a lateralization index was calculated with resultant tract volumes. Ten postmortem dissections were then performed using a modified Klingler technique to demonstrate the location of major tracts.

RESULTS

The authors identified 3 major connections of the OFC: a bundle to the thalamus and anterior cingulate gyrus, passing inferior to the caudate and medial to the vertical fibers of the thalamic projections; a bundle to the brainstem, traveling lateral to the caudate and medial to the internal capsule; and radiations to the parietal and occipital lobes traveling with the inferior fronto-occipital fasciculus.

CONCLUSIONS

The OFC is an important center for processing visual, spatial, and emotional information. Subtle differences in executive functioning following surgery for frontal lobe tumors may be better understood in the context of the fiber-bundle anatomy highlighted by this study.

An Update on Promising Biomarkers in Schizophrenia

Given the heterogeneity of symptoms in patients with schizophrenia and current treatment limitations, biomarkers may play an important role in diagnosis, subtype stratification, and the assessment of treatment response. Though many potential biomarkers have been studied, we have chosen to focus on some of the most promising and potentially clinically relevant biomarkers to review herein. These include markers of inflammation, neuroimaging biomarkers, brain-derived neurotrophic factor, genetic/epigenetic markers, and speech analysis. This will provide a broad overview of putative biomarkers that could become clinically relevant in the future, though none currently appear ready to assist the clinician in identifying cases of schizophrenia, subtypes of the disorder, treatment choice, or response. Nonetheless, some biomarkers, such as C-reactive protein (CRP), may be useful at identifying individuals who may be more highly inflamed, which could drive treatment choice. Though checking CRP is not a standard of practice, this is one example of how biomarkers may drive treatment decisions in the future, supporting precision medicine. Similarly, technological advances may one day allow clinicians to detect changes in speech patterns, which could represent a noninvasive, clinically useful tool in the future. We conclude the review by highlighting two important potential clinical uses for biomarkers in schizophrenia: the identification of individuals who may convert from clinical high risk and the stratification of patients via different biomarkers that may supersede clinical diagnosis. Given the enormous burden of illness of schizophrenia, the search for clinically relevant biomarkers is of great importance to improve the lives of patients with the disorder.

The crossed frontal aslant tract: A possible pathway involved in the recovery of supplementary motor area syndrome

INTRODUCTION

Supplementary motor area (SMA) syndrome is a constellation of temporary symptoms that may occur following tumors of the frontal lobe. Affected patients develop akinesia and mutism but often recover within weeks to months. With our own case examples and with correlations to fiber tracking validated by gross anatomical dissection as ground truth, we describe a white matter pathway through which recovery may occur.

METHODS

Diffusion spectrum imaging from the Human Connectome Project was used for tractography analysis. SMA outflow tracts were mapped in both hemispheres using a predefined seeding region. Postmortem dissections of 10 cadaveric brains were performed using a modified Klingler technique to verify the tractography results.

RESULTS

Two cases were identified in our clinical records in which patients sustained permanent SMA syndrome after complete disconnection of the SMA and corpus callosum (CC). After investigating the postoperative anatomy of these resections, we identified a pattern of nonhomologous connections through the CC connecting the premotor area to the contralateral premotor and SMAs. The transcallosal fibers have projections from the previously described frontal aslant tract (FAT) and thus, we have termed this path the "crossed FAT."

CONCLUSIONS

We hypothesize that this newly described tract may facilitate recovery from SMA syndrome by maintaining interhemispheric connectivity through the supplementary motor and premotor areas.

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.

Functional Segmentation of the Anterior Limb of the Internal Capsule: Linking White Matter Abnormalities to Specific Connections

The anterior limb of the internal capsule (ALIC) carries thalamic and brainstem fibers from prefrontal cortical regions that are associated with different aspects of emotion, motivation, cognition processing, and decision-making. This large fiber bundle is abnormal in several psychiatric illnesses and a major target for deep brain stimulation. Yet, we have very little information about where specific prefrontal fibers travel within the bundle. Using a combination of tracing studies and diffusion MRI in male nonhuman primates, as well as diffusion MRI in male and female human subjects, we segmented the human ALIC into five regions based on the positions of axons from different cortical regions within the capsule. Fractional anisotropy (FA) abnormalities in patients with bipolar disorder were detected when FA was averaged in the ALIC segment that carries ventrolateral prefrontal cortical connections. Together, the results set the stage for linking abnormalities within the ALIC to specific connections and demonstrate the utility of applying connectivity profiles of large white matter bundles based on animal anatomic studies to human connections and associating disease abnormalities in those pathways with specific connections. The ability to functionally segment large white matter bundles into their components begins a new era of refining how we think about white matter organization and use that information in understanding abnormalities.SIGNIFICANCE STATEMENT The anterior limb of the internal capsule (ALIC) connects prefrontal cortex with the thalamus and brainstem and is abnormal in psychiatric illnesses. However, we know little about the location of specific prefrontal fibers within the bundle. Using a combination of animal tracing studies and diffusion MRI in animals and human subjects, we segmented the human ALIC into five regions based on the positions of axons from different cortical regions. We then demonstrated that differences in FA values between bipolar disorder patients and healthy control subjects were specific to a given segment. Together, the results set the stage for linking abnormalities within the ALIC to specific connections and for refining how we think about white matter organization in general.

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.

The details of structural disconnectivity in psychotic disorder: A family-based study of non-FA diffusion weighted imaging measures

BACKGROUND

Diffusion tensor imaging (DTI) studies in psychotic disorder have shown reduced FA, often interpreted as disturbed white matter integrity. The observed 'dysintegrity' may be of multifactorial origin, as changes in FA are thought to reflect a combination of changes in myelination, fiber organization and number of axons. Examining the structural substrate of the diffusion tensor in individuals with (risk for) psychotic disorder may provide better understanding of the underlying structural changes.

METHODS

DTI scans were acquired from 85 patients with psychotic disorder, 93 siblings of patients with psychotic disorder and 80 controls. Cross-sectional group comparisons were performed using Tract-Based Spatial Statistics (TBSS) on six DTI measures: axial diffusivity (AXD), radial diffusivity (RD), mean diffusivity (MD), and the case linear (CL), case planar (CP) and case spherical (CS) tensor shape measures.

RESULTS

AXD did not differ between the groups. RD and CS values were significantly increased in patients compared to controls and siblings, with no significant differences between the latter two groups. MD was higher in patients compared to controls (but not siblings), with no difference between siblings and controls. CL was smaller in patients than in siblings and controls, and CP was smaller in both patients and siblings as compared to controls.

CONCLUSION

The differences between individuals with psychotic disorder and healthy controls, derived from detailed diffusion data analyses, suggest less fiber orientation and increased free water movement in the patients. There was some evidence for association with familial risk expressed by decreased fiber orientation.

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.

Evaluating the diagnostic utility of applying a machine learning algorithm to diffusion tensor MRI measures in individuals with major depressive disorder

Using MRI to diagnose mental disorders has been a long-term goal. Despite this, the vast majority of prior neuroimaging work has been descriptive rather than predictive. The current study applies support vector machine (SVM) learning to MRI measures of brain white matter to classify adults with Major Depressive Disorder (MDD) and healthy controls. In a precisely matched group of individuals with MDD (n =25) and healthy controls (n =25), SVM learning accurately (74%) classified patients and controls across a brain map of white matter fractional anisotropy values (FA). The study revealed three main findings: 1) SVM applied to DTI derived FA maps can accurately classify MDD vs. healthy controls; 2) prediction is strongest when only right hemisphere white matter is examined; and 3) removing FA values from a region identified by univariate contrast as significantly different between MDD and healthy controls does not change the SVM accuracy. These results indicate that SVM learning applied to neuroimaging data can classify the presence versus absence of MDD and that predictive information is distributed across brain networks rather than being highly localized. Finally, MDD group differences revealed through typical univariate contrasts do not necessarily reveal patterns that provide accurate predictive information.

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.

A CCA and ICA-Based Mixture Model for Identifying Major Depression Disorder

The fMRI signals are usually filtered before processing and analyzing. This process can result in the loss of information carried by the higher frequency in the low frequency fluctuation. ICA and CCA are two classical methods in fMRI. ICA finds the statistically independent components of the observed data, however these components are usually physiologically uninterpretable without auxiliary procedures. CCA decomposes two sets of data into component pairs in some order, however these components may be mixtures of real signals and noise. In order to obtain statistically independent components and avoid the loss of information in the process of filtering, we propose a mixed model based on ICA and CCA, which does not need to filter the data. It is shown by the experiments that the new model has some advantages compared with the classical ICA and CCA. The components obtained by the new model is statistically independent. The useful information included in the low frequency fluctuation can be preserved. Experiments on synthetic data show satisfying results. As an application, this new model is used to design an algorithm to discriminate the major depressions from normal controls, with encouraging experimental results.

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.

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.

Cocaine dependence and thalamic functional connectivity: a multivariate pattern analysis

Cocaine dependence is associated with deficits in cognitive control. Previous studies demonstrated that chronic cocaine use affects the activity and functional connectivity of the thalamus, a subcortical structure critical for cognitive functioning. However, the thalamus contains nuclei heterogeneous in functions, and it is not known how thalamic subregions contribute to cognitive dysfunctions in cocaine dependence. To address this issue, we used multivariate pattern analysis (MVPA) to examine how functional connectivity of the thalamus distinguishes 100 cocaine-dependent participants (CD) from 100 demographically matched healthy control individuals (HC). We characterized six task-related networks with independent component analysis of fMRI data of a stop signal task and employed MVPA to distinguish CD from HC on the basis of voxel-wise thalamic connectivity to the six independent components. In an unbiased model of distinct training and testing data, the analysis correctly classified 72% of subjects with leave-one-out cross-validation (p < 0.001), superior to comparison brain regions with similar voxel counts (p < 0.004, two-sample t test). Thalamic voxels that form the basis of classification aggregate in distinct subclusters, suggesting that connectivities of thalamic subnuclei distinguish CD from HC. Further, linear regressions provided suggestive evidence for a correlation of the thalamic connectivities with clinical variables and performance measures on the stop signal task. Together, these findings support thalamic circuit dysfunction in cognitive control as an important neural marker of cocaine dependence.

Accurate classification of schizophrenia patients based on novel resting-state fMRI features

There is a growing interest in automatic classification of mental disorders such as schizophrenia based on neuroimaging data. Most previous studies considered structural MRI, diffusion tensor imaging and task-based fMRI for this purpose. However, resting-state fMRI data has not been used much to evaluate 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. In this study, we extract two types of features from resting-state fMRI data: functional network connectivity features that capture internetwork connectivity patterns and autoconnectivity features capturing temporal connectivity of each brain network. Autoconnectivity is a novel concept we have recently proposed. We used minimum redundancy maximum relevancy to select features. Classification results using support vector machine shows that combining these two types of features can improve the classification on a large resting fMRI dataset consisting of 195 patients with schizophrenia and 175 healthy controls. We achieved the accuracy of 85% which is very promising.

Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks

Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis.

From estimating activation locality to predicting disorder: A review of pattern recognition for neuroimaging-based psychiatric diagnostics

Psychiatric disorders are increasingly being recognised as having a biological basis, but their diagnosis is made exclusively behaviourally. A promising approach for 'biomarker' discovery has been based on pattern recognition methods applied to neuroimaging data, which could yield clinical utility in future. In this review we survey the literature on pattern recognition for making diagnostic predictions in psychiatric disorders, and evaluate progress made in translating such findings towards clinical application. We evaluate studies on many criteria, including data modalities used, the types of features extracted and algorithm applied. We identify problems common to many studies, such as a relatively small sample size and a primary focus on estimating generalisability within a single study. Furthermore, we highlight challenges that are not widely acknowledged in the field including the importance of accommodating disease prevalence, the necessity of more extensive validation using large carefully acquired samples, the need for methodological innovations to improve accuracy and to discriminate between multiple disorders simultaneously. Finally, we identify specific clinical contexts in which pattern recognition can add value in the short to medium term.

Overdiagnosis in the era of neuropsychiatric imaging

New guidelines proposed by the National Institute of Mental Health are intended to transform the management of patients with psychiatric disorders. It is anticipated that neuroimaging and other biomarkers will play a more prominent role in diagnosis and prognosis, especially in the prodromal phase of illness. Earlier treatment of psychiatric disorders has the potential to improve outcomes significantly. However, diagnosis in the absence of symptoms can lead to overdiagnosis. Overdiagnosis is a problem in many fields of medicine but could pose additional problems in psychiatry because of the stigmatization that often accompanies a diagnosis of mental illness. This review discusses the magnetic resonance imaging methods that hold the most promise for evaluating neuropsychiatric disorders, the likelihood that they could lead to overdiagnosis, and opportunities to minimize the impact of overdiagnosis in psychiatric disorders.

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.