Classification of first-episode schizophrenia patients and healthy subjects by automated MRI measures of regional brain volume and cortical thickness

The potential role of the p75 receptor in schizophrenia: neuroimmunomodulation and making life or death decisions

The nerve growth factor receptor, also referred to as tumour necrosis factor II and the p75 neurotrophin receptor (p75), serves pleiotropic functions in both the peripheral and central nervous system, involving modulation of immune responses, cell survival and cell death signalling in response to multiple ligands including cytokines such as TNFα, as well as proneurotrophins and mature neurotrophins. Whilst in vitro and in vivo studies have characterised various responses of the p75 receptor in isolated conditions, it remains unclear whether the p75 receptor serves to provide neuroprotection or contributes to neurotoxicity in neuroinflammatory and neurotrophin-deficit conditions, such as those presenting in schizophrenia. The purpose of this mini-review is to characterise the potential signalling mechanisms of the p75 receptor respective to neuropathological changes prevailing in schizophrenia to ultimately propose how specific functions of the receptor may underlie altered levels of p75 in specific cell types. On the basis of this evaluation, this mini-review aims to promote avenues for future research in utilising the therapeutic potential of ligands for the p75 receptor in psychiatric disorders, whereby heightened inflammation and reductions in trophic signalling mechanisms coalesce in the brain, potentially resulting in tissue damage.

Cortical impoverishment in a stable subgroup of schizophrenia: Validation across various stages of psychosis

BACKGROUND

Cortical thinning is a well-known feature in schizophrenia. The considerable variation in the spatial distribution of thickness changes has been used to parse heterogeneity. A 'cortical impoverishment' subgroup with a generalized reduction in thickness has been reported. However, it is unclear if this subgroup is recoverable irrespective of illness stage, and if it relates to the glutamate hypothesis of schizophrenia.

METHODS

We applied hierarchical cluster analysis to cortical thickness data from magnetic resonance imaging scans of three datasets in different stages of psychosis (n = 288; 160 patients; 128 healthy controls) and studied the cognitive and symptom profiles of the observed subgroups. In one of the samples, we also studied the subgroup differences in 7-Tesla magnetic resonance spectroscopy glutamate concentration in the dorsal anterior cingulate cortex.

RESULTS

Our consensus-based clustering procedure consistently produced 2 subgroups of participants. Patients accounted for 75%-100% of participants in one subgroup that was characterized by significantly lower cortical thickness. Both subgroups were equally symptomatic in clinically unstable stages, but cortical impoverishment indicated a higher symptom burden in a clinically stable sample and higher glutamate levels in the first-episode sample. There were no subgroup differences in cognitive and functional outcome profiles or antipsychotic exposure across all stages.

CONCLUSIONS

Cortical thinning does not vary with functioning or cognitive impairment, but it is more prevalent among patients, especially those with glutamate excess in early stages and higher residual symptom burden at later stages, providing an important mechanistic clue to one of the several possible pathways to the illness.

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

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

Psychotic Symptom, Mood, and Cognition-associated Multimodal MRI Reveal Shared Links to the Salience Network Within the Psychosis Spectrum Disorders

Schizophrenia (SZ), schizoaffective disorder (SAD), and psychotic bipolar disorder share substantial overlap in clinical phenotypes, associated brain abnormalities and risk genes, making reliable diagnosis among the three illness challenging, especially in the absence of distinguishing biomarkers. This investigation aims to identify multimodal brain networks related to psychotic symptom, mood, and cognition through reference-guided fusion to discriminate among SZ, SAD, and BP. Psychotic symptom, mood, and cognition were used as references to supervise functional and structural magnetic resonance imaging (MRI) fusion to identify multimodal brain networks for SZ, SAD, and BP individually. These features were then used to assess the ability in discriminating among SZ, SAD, and BP. We observed shared links to functional and structural covariation in prefrontal, medial temporal, anterior cingulate, and insular cortices among SZ, SAD, and BP, although they were linked with different clinical domains. The salience (SAN), default mode (DMN), and fronto-limbic (FLN) networks were the three identified multimodal MRI features within the psychosis spectrum disorders from psychotic symptom, mood, and cognition associations. In addition, using these networks, we can classify patients and controls and distinguish among SZ, SAD, and BP, including their first-degree relatives. The identified multimodal SAN may be informative regarding neural mechanisms of comorbidity for psychosis spectrum disorders, along with DMN and FLN may serve as potential biomarkers in discriminating among SZ, SAD, and BP, which may help investigators better understand the underlying mechanisms of psychotic comorbidity from three different disorders via a multimodal neuroimaging perspective.

Associations between BMI and brain structures involved in food intake regulation in first-episode schizophrenia spectrum disorders and healthy controls

Structural brain differences have been described in first-episode schizophrenia spectrum disorders (FES), and often overlap with those evident in the metabolic syndrome (MetS). We examined the associations between body mass index (BMI) and brain structures involved in food intake regulation in minimally treated FES patients (n = 117) compared to healthy controls (n = 117). The effects of FES diagnosis, BMI and their interactions on our selected prefrontal cortical thickness and subcortical gray matter volume regions of interest (ROIs) were investigated with hierarchical multivariate regressions, followed by post-hoc regressions for the individual ROIs. In a secondary analysis, we examined the relationships of other MetS risk factors and psychopathology with the brain ROIs. Both illness and BMI significantly predicted the grouped prefrontal cortical thickness ROIs, whereas only BMI predicted the grouped subcortical volume ROIs. For the individual ROIs, schizophrenia diagnosis predicted thinner left and right frontal pole and right lateral OFC thickness, and increased BMI predicted thinner left and right caudal ACC thickness. There were no significant main or interaction effects for diagnosis and BMI on any of the individual subcortical volume ROIs. Secondary analyses suggest associations between several brain ROIs and individual MetS risk factors, but not with psychopathology. Our findings indicate differential, independent effects for FES diagnosis and BMI on brain structures. Limited evidence suggests that the BMI effects are more prominent in FES. Exploratory analyses suggest associations between other MetS risk factors and some brain ROIs.

Multikernel Capsule Network for Schizophrenia Identification

Schizophrenia seriously affects the quality of life. To date, both simple (e.g., linear discriminant analysis) and complex (e.g., deep neural network) machine-learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. To overcome the aforementioned drawbacks, we proposed a multikernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match partition sizes of the brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of the widely used dropout strategy in deep learning, we developed capsule dropout in the capsule layer to prevent overfitting of the model. The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. MKCapsnet is promising for schizophrenia identification. Our study first utilized the capsule neural network for analyzing functional connectivity of magnetic resonance imaging (MRI) and proposed a novel multikernel capsule structure with the consideration of brain anatomical parcellation, which could be a new way to reveal brain mechanisms. In addition, we provided useful information in the parameter setting, which is informative for further studies using a capsule network for other neurophysiological signal classification.

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.

Sex is a defining feature of neuroimaging phenotypes in major brain disorders

Sex is a biological variable that contributes to individual variability in brain structure and behavior. Neuroimaging studies of population-based samples have identified normative differences in brain structure between males and females, many of which are exacerbated in psychiatric and neurological conditions. Still, sex differences in MRI outcomes are understudied, particularly in clinical samples with known sex differences in disease risk, prevalence, and expression of clinical symptoms. Here we review the existing literature on sex differences in adult brain structure in normative samples and in 14 distinct psychiatric and neurological disorders. We discuss commonalities and sources of variance in study designs, analysis procedures, disease subtype effects, and the impact of these factors on MRI interpretation. Lastly, we identify key problems in the neuroimaging literature on sex differences and offer potential recommendations to address current barriers and optimize rigor and reproducibility. In particular, we emphasize the importance of large-scale neuroimaging initiatives such as the Enhancing NeuroImaging Genetics through Meta-Analyses consortium, the UK Biobank, Human Connectome Project, and others to provide unprecedented power to evaluate sex-specific phenotypes in major brain diseases.

Volume Reduction of the Dorsal Lateral Prefrontal Cortex Prior to the Onset of Frank Psychosis in Individuals with an At-Risk Mental State

Although some individuals with at-risk mental states (ARMS) develop overt psychosis, surrogate markers which can reliably predict a future onset of psychosis are not well established. The dorsal lateral prefrontal cortex (DLPFC) is thought to be involved in psychotic disorders such as schizophrenia. In this study, 73 ARMS patients and 74 healthy controls underwent 1.5-T 3D magnetic resonance imaging scans at three sites. Using labeled cortical distance mapping, cortical thickness, gray matter (GM) volume, and surface area of DLPFC were estimated. These measures were compared across the diagnostic groups. We also evaluated cognitive function among 36 ARMS subjects to clarify the relationships between the DLPFC morphology and cognitive performance. The GM volume of the right DLPFC was significantly reduced in ARMS subjects who later developed frank psychosis (ARMS-P) relative to those who did not (P = 0.042). There was a positive relationship between the right DLPFC volume and the duration prior to the onset of frank psychosis in ARMS-P subjects (r = 0.58, P = 0.018). Our data may suggest that GM reduction of the DLPFC might be a potential marker of future onset of psychosis in individuals with ARMS.

Prolonged P300 Latency in Antipsychotic-Free Subjects with At-Risk Mental States Who Later Developed Schizophrenia

We measured P300, an event-related potential, in subjects with at-risk mental states (ARMS) and aimed to determine whether P300 parameter can predict progression to overt schizophrenia. Thirty-three subjects with ARMS, 39 with schizophrenia, and 28 healthy controls participated in the study. All subjects were antipsychotic-free. Subjects with ARMS were followed-up for more than two years. Cognitive function was measured by the Brief assessment of Cognition in Schizophrenia (BACS) and Schizophrenia Cognition Rating Scale (SCoRS), while the modified Global Assessment of Functioning (mGAF) was used to assess global function. Patients with schizophrenia showed smaller P300 amplitudes and prolonged latency at Pz compared to those of healthy controls and subjects with ARMS. During the follow-up period, eight out of 33 subjects with ARMS developed overt psychosis (ARMS-P) while 25 did not (ARMS-NP). P300 latency of ARMS-P was significantly longer than that of ARMS-NP. At baseline, ARMS-P elicited worse cognitive functions, as measured by the BACS and SCoRS compared to ARMS-NP. We also detected a significant relationship between P300 amplitudes and mGAF scores in ARMS subjects. Our results suggest the usefulness of prolonged P300 latency and cognitive impairment as a predictive marker of later development of schizophrenia in vulnerable individuals.

Baseline Cortical Thickness Reductions in Clinical High Risk for Psychosis: Brain Regions Associated with Conversion to Psychosis Versus Non-Conversion as Assessed at One-Year Follow-Up in the Shanghai-At-Risk-for-Psychosis (SHARP) Study

OBJECTIVE

To assess cortical thickness (CT) and surface area (SA) of frontal, temporal, and parietal brain regions in a large clinical high risk for psychosis (CHR) sample, and to identify cortical brain abnormalities in CHR who convert to psychosis and in the whole CHR sample, compared with the healthy controls (HC).

METHODS

Magnetic resonance imaging, clinical, and cognitive data were acquired at baseline in 92 HC, 130 non-converters, and 22 converters (conversion assessed at 1-year follow-up). CT and SA at baseline were calculated for frontal, temporal, and parietal subregions. Correlations between regions showing group differences and clinical scores and age were also obtained.

RESULTS

CT but not SA was significantly reduced in CHR compared with HC. Two patterns of findings emerged: (1) In converters, CT was significantly reduced relative to non-converters and controls in the banks of superior temporal sulcus, Heschl's gyrus, and pars triangularis and (2) CT in the inferior parietal and supramarginal gyrus, and at trend level in the pars opercularis, fusiform, and middle temporal gyri was significantly reduced in all high-risk individuals compared with HC. Additionally, reduced CT correlated significantly with older age in HC and in non-converters but not in converters.

CONCLUSIONS

These results show for the first time that fronto-temporo-parietal abnormalities characterized all CHR, that is, both converters and non-converters, relative to HC, while CT abnormalities in converters relative to CHR-NC and HC were found in core auditory and language processing regions.

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

BACKGROUND

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Neuroanatomical abnormalities in first-episode psychosis across independent samples: a multi-centre mega-analysis

BACKGROUND

Neuroanatomical abnormalities in first-episode psychosis (FEP) tend to be subtle and widespread. The vast majority of previous studies have used small samples, and therefore may have been underpowered. In addition, most studies have examined participants at a single research site, and therefore the results may be specific to the local sample investigated. Consequently, the findings reported in the existing literature are highly heterogeneous. This study aimed to overcome these issues by testing for neuroanatomical abnormalities in individuals with FEP that are expressed consistently across several independent samples.

METHODS

Structural Magnetic Resonance Imaging data were acquired from a total of 572 FEP and 502 age and gender comparable healthy controls at five sites. Voxel-based morphometry was used to investigate differences in grey matter volume (GMV) between the two groups. Statistical inferences were made at p < 0.05 after family-wise error correction for multiple comparisons.

RESULTS

FEP showed a widespread pattern of decreased GMV in fronto-temporal, insular and occipital regions bilaterally; these decreases were not dependent on anti-psychotic medication. The region with the most pronounced decrease - gyrus rectus - was negatively correlated with the severity of positive and negative symptoms.

CONCLUSIONS

This study identified a consistent pattern of fronto-temporal, insular and occipital abnormalities in five independent FEP samples; furthermore, the extent of these alterations is dependent on the severity of symptoms and duration of illness. This provides evidence for reliable neuroanatomical alternations in FEP, expressed above and beyond site-related differences in anti-psychotic medication, scanning parameters and recruitment criteria.

Hierarchical Structured Sparse Learning for Schizophrenia Identification

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

Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis

Neuropsychiatric disorders are diagnosed based on behavioral criteria, which makes the diagnosis challenging. Objective biomarkers such as neuroimaging are needed, and when coupled with machine learning, can assist the diagnostic decision and increase its reliability. Sixty-four schizophrenia, 36 autism spectrum disorder (ASD), and 106 typically developing individuals were analyzed. FreeSurfer was used to obtain the data from the participant's brain scans. Six classifiers were utilized to classify the subjects. Subsequently, 26 ultra-high risk for psychosis (UHR) and 17 first-episode psychosis (FEP) subjects were run through the trained classifiers. Lastly, the classifiers' output of the patient groups was correlated with their clinical severity. All six classifiers performed relatively well to distinguish the subject groups, especially support vector machine (SVM) and Logistic regression (LR). Cortical thickness and subcortical volume feature groups were most useful for the classification. LR and SVM were highly consistent with clinical indices of ASD. When UHR and FEP groups were run with the trained classifiers, majority of the cases were classified as schizophrenia, none as ASD. Overall, SVM and LR were the best performing classifiers. Cortical thickness and subcortical volume were most useful for the classification, compared to surface area. LR, SVM, and DT's output were clinically informative. The trained classifiers were able to help predict the diagnostic category of both UHR and FEP Individuals.

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.

Bridging the associations between dopamine, brain volumetric variation and IQ in drug-naïve schizophrenia

BACKGROUND

Although patients with schizophrenia are well-known to exhibit significant brain volume reduction and cognitive function impairment, it remains unclear as to whether the reduction/impairment is correlated with dopaminergic activity under drug-naïve conditions.

METHODS

51 drug-naïve patients with and 128 healthy subjects were recruited in this study. DAT by [^99mTc]TRODAT-1 single-photon emission computed tomography (SPECT), regional gray matter volume (GMV) by voxel-based morphometry (VBM) analysis, and cognitive function in terms of IQ were measured in both groups.

RESULT

A significantly lower DAT availability existed in the drug-naïve group as compared with the healthy subjects (1.67 ± 0.45 vs. 1.98 ± 0.37, P < 0.005). DAT availability was significantly positively correlated with GMV in the left middle frontal lobe (r = 0.58, P < 0.005), the GMV being significantly reduced in the patients with schizophrenia (0.45 ± 0.10 vs. 0.49 ± 0.07, P < 0.005). Furthermore, the GMV in the left middle frontal lobe was significantly and positively correlated with full IQ (r = 0.34, P = 0.02) in the patients with schizophrenia, but not in the controls.

CONCLUSIONS

Dysregulated dopaminergic activity may modulate volume variation in specific brain areas, and brain volume might alter IQ in drug-naïve patients with schizophrenia.

Reduced Cortical Thickness in Schizophrenia and Schizotypal Disorder

Schizotypal disorder is characterized by odd behavior and attenuated forms of schizophrenic features without the manifestation of overt and sustained psychoses. Past studies suggest that schizotypal disorder shares biological and psychological commonalties with schizophrenia. Structural magnetic resonance imaging (MRI) studies have demonstrated both common and distinct regional gray matter changes between schizophrenia and schizotypal disorder. However, no study has compared cortical thickness, which is thought to be a specific indicator of cortical atrophy, between schizophrenia and schizotypal disorder. The subjects consisted of 102 schizophrenia and 46 schizotypal disorder patients who met the International Classification of Diseases, 10th edition criteria and 79 gender- and age-matched healthy controls. Each participant underwent a T1-weighted 3-D MRI scan using a 1.5-Tesla scanner. Cortical thickness was estimated using FreeSurfer. Consistent with previous studies, schizophrenia patients exhibited wide-spread cortical thinning predominantly in the frontal and temporal regions as compared with healthy subjects. Patients with schizotypal disorder had a significantly reduced cortical thickness in the left fusiform and parahippocampal gyri, right medial superior frontal gyrus, right inferior frontal gyrus, and right medial orbitofrontal cortex as compared with healthy controls. Schizophrenia patients had thinner cortices in the left precentral and paracentral gyri than those with schizotypal disorder. Common cortical thinning patterns observed in schizophrenia and schizotypal disorder patients may be associated with vulnerability to psychosis. Our results also suggest that distinct cortical changes in schizophrenia and schizotypal disorder may be associated with the differences in the manifestation of clinical symptoms among these disorders.

Integrating machining learning and multimodal neuroimaging to detect schizophrenia at the level of the individual

Schizophrenia is a severe psychiatric disorder associated with both structural and functional brain abnormalities. In the past few years, there has been growing interest in the application of machine learning techniques to neuroimaging data for the diagnostic and prognostic assessment of this disorder. However, the vast majority of studies published so far have used either structural or functional neuroimaging data, without accounting for the multimodal nature of the disorder. Structural MRI and resting‐state functional MRI data were acquired from a total of 295 patients with schizophrenia and 452 healthy controls at five research centers. We extracted features from the data including gray matter volume, white matter volume, amplitude of low‐frequency fluctuation, regional homogeneity and two connectome‐wide based metrics: structural covariance matrices and functional connectivity matrices. A support vector machine classifier was trained on each dataset separately to distinguish the subjects at individual level using each of the single feature as well as their combination, and 10‐fold cross‐validation was used to assess the performance of the model. Functional data allow higher accuracy of classification than structural data (mean 82.75% vs. 75.84%). Within each modality, the combination of images and matrices improves performance, resulting in mean accuracies of 81.63% for structural data and 87.59% for functional data. The use of all combined structural and functional measures allows the highest accuracy of classification (90.83%). We conclude that combining multimodal measures within a single model is a promising direction for developing biologically informed diagnostic tools in schizophrenia.

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.

Variation in fourteen brain structure volumes in schizophrenia: A comprehensive meta-analysis of 246 studies

Despite hundreds of structural MRI studies documenting smaller brain volumes on average in schizophrenia compared to controls, little attention has been paid to group differences in the variability of brain volumes. Examination of variability may help interpret mean group differences in brain volumes and aid in better understanding the heterogeneity of schizophrenia. Variability in 246 MRI studies was meta-analyzed for 13 structures that have shown medium to large mean effect sizes (Cohen's d≥0.4): intracranial volume, total brain volume, lateral ventricles, third ventricle, total gray matter, frontal gray matter, prefrontal gray matter, temporal gray matter, superior temporal gyrus gray matter, planum temporale, hippocampus, fusiform gyrus, insula; and a control structure, caudate nucleus. No significant differences in variability in cortical/subcortical volumes were detected in schizophrenia relative to controls. In contrast, increased variability was found in schizophrenia compared to controls for intracranial and especially lateral and third ventricle volumes. These findings highlight the need for more attention to ventricles and detailed analyses of brain volume distributions to better elucidate the pathophysiology of schizophrenia.

Sex and gender differences in schizophrenic psychoses-a critical review

Many sex and gender differences in schizophrenic psychoses have been reported, but few have been soundly replicated. A stable finding is the later age of onset in women compared to men. Gender differences in symptomatology, comorbidity, and neurocognition seem to reflect findings in the general population. There is increasing evidence for estrogens being psychoprotective in women and for hypothalamic-pituitary-gonadal dysfunction in both sexes.More methodologically sound, longitudinal, multi-domain, interdisciplinary research investigating both sex (biological) and gender (psychosocial) factors is required to better understand the different pathogenesis and etiologies of schizophrenic psychoses in women and men, thereby leading to better tailored treatments and improved outcomes.

Sexually dimorphic subcortical brain volumes in emerging psychosis

BACKGROUND

In schizophrenic psychoses, the normal sexual dimorphism of the brain has been shown to be disrupted or even reversed. Little is known, however, at what time point in emerging psychosis this occurs. We have therefore examined, if these alterations are already present in the at-risk mental state (ARMS) for psychosis and in first episode psychosis (FEP) patients.

METHODS

Data from 65 ARMS (48 (73.8%) male; age=25.1±6.32) and 50 FEP (37 (74%) male; age=27±6.56) patients were compared to those of 70 healthy controls (HC; 27 (38.6%) male; age=26±4.97). Structural T1-weighted images were acquired using a 3 Tesla magnetic resonance imaging (MRI) scanner. Linear mixed effects models were used to investigate whether subcortical brain volumes are dependent on sex.

RESULTS

We found men to have larger total brain volumes (p<0.001), and smaller bilateral caudate (p=0.008) and hippocampus volume (p<0.001) than women across all three groups. Older subjects had more GM and WM volume than younger subjects. No significant sex×group interaction was found.

CONCLUSIONS

In emerging psychosis there still seem to exist patterns of normal sexual dimorphism in total brain and caudate volume. The only structure affected by reversed sexual dimorphism was the hippocampus, with women showing larger volumes than men even in HC. Thus, we conclude that subcortical volumes may not be primarily affected by disrupted sexual dimorphism in emerging psychosis.

Brain morphologic changes in early stages of psychosis: Implications for clinical application and early intervention

To date, a large number of magnetic resonance imaging (MRI) studies have been conducted in schizophrenia, which generally demonstrate gray matter reduction, predominantly in the frontal and temporo-limbic regions, as well as gross brain abnormalities (e.g., a deviated sulcogyral pattern). Although the causes as well as timing and course of these findings remain elusive, these morphologic changes (especially gross brain abnormalities and medial temporal lobe atrophy) are likely present at illness onset, possibly reflecting early neurodevelopmental abnormalities. In addition, longitudinal MRI studies suggest that patients with schizophrenia and related psychoses also have progressive gray matter reduction during the transition period from prodrome to overt psychosis, as well as initial periods after psychosis onset, while such changes may become almost stable in the chronic stage. These active brain changes during the early phases seem to be relevant to the development of clinical symptoms in a region-specific manner (e.g., superior temporal gyrus atrophy and positive psychotic symptoms), but may be at least partly ameliorated by antipsychotic medication. Recently, increasing evidence from MRI findings in individuals at risk for developing psychosis has suggested that those who subsequently develop psychosis have baseline brain changes, which could be at least partly predictive of later transition into psychosis. In this article, we selectively review previous MRI findings during the course of psychosis and also refer to the possible clinical applicability of these neuroimaging research findings, especially in the diagnosis of schizophrenia and early intervention for psychosis.

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.

Estimation of Symptom Severity Scores for Patients with Schizophrenia Using ERP Source Activations during a Facial Affect Discrimination Task

Precise diagnosis of psychiatric diseases and a comprehensive assessment of a patient's symptom severity are important in order to establish a successful treatment strategy for each patient. Although great efforts have been devoted to searching for diagnostic biomarkers of schizophrenia over the past several decades, no study has yet investigated how accurately these biomarkers are able to estimate an individual patient's symptom severity. In this study, we applied electrophysiological biomarkers obtained from electroencephalography (EEG) analyses to an estimation of symptom severity scores of patients with schizophrenia. EEG signals were recorded from 23 patients while they performed a facial affect discrimination task. Based on the source current density analysis results, we extracted voxels that showed a strong correlation between source activity and symptom scores. We then built a prediction model to estimate the symptom severity scores of each patient using the source activations of the selected voxels. The symptom scores of the Positive and Negative Syndrome Scale (PANSS) were estimated using the linear prediction model. The results of leave-one-out cross validation (LOOCV) showed that the mean errors of the estimated symptom scores were 3.34 ± 2.40 and 3.90 ± 3.01 for the Positive and Negative PANSS scores, respectively. The current pilot study is the first attempt to estimate symptom severity scores in schizophrenia using quantitative EEG features. It is expected that the present method can be extended to other cognitive paradigms or other psychological illnesses.

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

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

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

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

Age prediction on the basis of brain anatomical measures

In this study, we examined whether age can be predicted on the basis of different anatomical features obtained from a large sample of healthy subjects (n = 3,144). From this sample we obtained different anatomical feature sets: (1) 11 larger brain regions (including cortical volume, thickness, area, subcortical volume, cerebellar volume, etc.), (2) 148 cortical compartmental thickness measures, (3) 148 cortical compartmental area measures, (4) 148 cortical compartmental volume measures, and (5) a combination of the above-mentioned measures. With these anatomical feature sets, we predicted age using 6 statistical techniques (multiple linear regression, ridge regression, neural network, k-nearest neighbourhood, support vector machine, and random forest). We obtained very good age prediction accuracies, with the highest accuracy being R²  = 0.84 (prediction on the basis of a neural network and support vector machine approaches for the entire data set) and the lowest being R²  = 0.40 (prediction on the basis of a k-nearest neighborhood for cortical surface measures). Interestingly, the easy-to-calculate multiple linear regression approach with the 11 large brain compartments resulted in a very good prediction accuracy (R²  = 0.73), whereas the application of the neural network approach for this data set revealed very good age prediction accuracy (R²  = 0.83). Taken together, these results demonstrate that age can be predicted well on the basis of anatomical measures. The neural network approach turned out to be the approach with the best results. In addition, it was evident that good prediction accuracies can be achieved using a small but nevertheless age-representative dataset of brain features. Hum Brain Mapp 38:997-1008, 2017. © 2016 Wiley Periodicals, Inc.

Connectivity of the anterior insula differentiates participants with first-episode schizophrenia spectrum disorders from controls: a machine-learning study

BACKGROUND

Early diagnosis of schizophrenia could improve the outcomes and limit the negative effects of untreated illness. Although participants with schizophrenia show aberrant functional connectivity in brain networks, these between-group differences have a limited diagnostic utility. Novel methods of magnetic resonance imaging (MRI) analyses, such as machine learning (ML), may help bring neuroimaging from the bench to the bedside. Here, we used ML to differentiate participants with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls based on resting-state functional connectivity (rsFC).

METHOD

We acquired resting-state functional MRI data from 63 patients with FES who were individually matched by age and sex to 63 healthy controls. We applied linear kernel support vector machines (SVM) to rsFC within the default mode network, the salience network and the central executive network.

RESULTS

The SVM applied to the rsFC within the salience network distinguished the FES from the control participants with an accuracy of 73.0% (p = 0.001), specificity of 71.4% and sensitivity of 74.6%. The classification accuracy was not significantly affected by medication dose, or by the presence of psychotic symptoms. The functional connectivity within the default mode or the central executive networks did not yield classification accuracies above chance level.

CONCLUSIONS

Seed-based functional connectivity maps can be utilized for diagnostic classification, even early in the course of schizophrenia. The classification was probably based on trait rather than state markers, as symptoms or medications were not significantly associated with classification accuracy. Our results support the role of the anterior insula/salience network in the pathophysiology of FES.

Multi-center MRI prediction models: Predicting sex and illness course in first episode psychosis patients

Structural Magnetic Resonance Imaging (MRI) studies have attempted to use brain measures obtained at the first-episode of psychosis to predict subsequent outcome, with inconsistent results. Thus, there is a real need to validate the utility of brain measures in the prediction of outcome using large datasets, from independent samples, obtained with different protocols and from different MRI scanners. This study had three main aims: 1) to investigate whether structural MRI data from multiple centers can be combined to create a machine-learning model able to predict a strong biological variable like sex; 2) to replicate our previous finding that an MRI scan obtained at first episode significantly predicts subsequent illness course in other independent datasets; and finally, 3) to test whether these datasets can be combined to generate multicenter models with better accuracy in the prediction of illness course. The multi-center sample included brain structural MRI scans from 256 males and 133 females patients with first episode psychosis, acquired in five centers: University Medical Center Utrecht (The Netherlands) (n=67); Institute of Psychiatry, Psychology and Neuroscience, London (United Kingdom) (n=97); University of São Paulo (Brazil) (n=64); University of Cantabria, Santander (Spain) (n=107); and University of Melbourne (Australia) (n=54). All images were acquired on 1.5-Tesla scanners and all centers provided information on illness course during a follow-up period ranging 3 to 7years. We only included in the analyses of outcome prediction patients for whom illness course was categorized as either "continuous" (n=94) or "remitting" (n=118). Using structural brain scans from all centers, sex was predicted with significant accuracy (89%; p<0.001). In the single- or multi-center models, illness course could not be predicted with significant accuracy. However, when reducing heterogeneity by restricting the analyses to male patients only, classification accuracy improved in some samples. This study provides proof of concept that combining multi-center MRI data to create a well performing classification model is possible. However, to create complex multi-center models that perform accurately, each center should contribute a sample either large or homogeneous enough to first allow accurate classification within the single-center.

Cortical thickness and surface area correlates with cognitive dysfunction among first-episode psychosis patients

BACKGROUND

In studies using magnetic resonance imaging (MRI), some have reported specific brain structure-function relationships among first-episode psychosis (FEP) patients, but findings are inconsistent. We aimed to localize the brain regions where cortical thickness (CTh) and surface area (cortical area; CA) relate to neurocognition, by performing an MRI on participants and measuring their neurocognitive performance using the Cambridge Neuropsychological Test Automated Battery (CANTAB), in order to investigate any significant differences between FEP patients and control subjects (CS).

METHOD

Exploration of potential correlations between specific cognitive functions and brain structure was performed using CANTAB computer-based neurocognitive testing and a vertex-by-vertex whole-brain MRI analysis of 63 FEP patients and 30 CS.

RESULTS

Significant correlations were found between cortical parameters in the frontal, temporal, cingular and occipital brain regions and performance in set-shifting, working memory manipulation, strategy usage and sustained attention tests. These correlations were significantly dissimilar between FEP patients and CS.

CONCLUSIONS

Significant correlations between CTh and CA with neurocognitive performance were localized in brain areas known to be involved in cognition. The results also suggested a disrupted structure-function relationship in FEP patients compared with CS.

Sex/gender differences in the brain and cognition in schizophrenia

The early conceptualizations of schizophrenia have noted some sex/gender differences in epidemiology and clinical expression of the disorder. Over the past few decades, the interest in differences between male and female patients has expanded to encompass brain morphology and neurocognitive function. Despite some variability and methodological shortcomings, a few patterns emerge from the available literature. Most studies of gross neuroanatomy show more enlarged ventricles and smaller frontal lobes in men than in women with schizophrenia; finding reflecting normal sexual dimorphism. In comparison, studies of brain asymmetry and specific corticolimbic structures, suggest a disturbance in normal sexual dimorphism. The neurocognitive findings are somewhat consistent with this picture. Studies of cognitive functions mediated by the lateral frontal network tend to show sex differences in patients which are in the same direction as those observed in the general population, whereas studies of processes mediated by the corticolimbic system more frequently reveal reversal of normal sexual dimorphisms. These trends are faint and future research would need to delineate neurocognitive differences between men and women with various subtypes of schizophrenia (e.g., early versus late onset), while taking into consideration hormonal status and gender of tested participants.

Classification of first-episode psychosis in a large cohort of patients using support vector machine and multiple kernel learning techniques

First episode psychosis (FEP) patients are of particular interest for neuroimaging investigations because of the absence of confounding effects due to medications and chronicity. Nonetheless, imaging data are prone to heterogeneity because for example of age, gender or parameter setting differences. With this work, we wanted to take into account possible nuisance effects of age and gender differences across dataset, not correcting the data as a pre-processing step, but including the effect of nuisance covariates in the classification phase. To this aim, we developed a method which, based on multiple kernel learning (MKL), exploits the effect of these confounding variables with a subject-depending kernel weighting procedure. We applied this method to a dataset of cortical thickness obtained from structural magnetic resonance images (MRI) of 127 FEP patients and 127 healthy controls, who underwent either a 3Tesla (T) or a 1.5T MRI acquisition. We obtained good accuracies, notably better than those obtained with standard SVM or MKL methods, up to more than 80% for frontal and temporal areas. To our best knowledge, this is the largest classification study in FEP population, showing that fronto-temporal cortical thickness can be used as a potential marker to classify patients with psychosis.

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.

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.

Cortical morphology and early adverse birth events in men with first-episode psychosis

BACKGROUND

Reduced cortical gray-matter volume is commonly observed in patients with psychosis. Cortical volume is a composite measure that includes surface area, thickness and gyrification. These three indices show distinct maturational patterns and may be differentially affected by early adverse events. The study goal was to determine the impact of two distinct obstetrical complications (OCs) on cortical morphology.

METHOD

A detailed birth history and MRI scans were obtained for 36 patients with first-episode psychosis and 16 healthy volunteers.

RESULTS

Perinatal hypoxia and slow fetal growth were associated with cortical volume (Cohen's d = 0.76 and d = 0.89, respectively) in patients. However, the pattern of associations differed across the three components of cortical volume. Both hypoxia and fetal growth were associated with cortical surface area (d = 0.88 and d = 0.72, respectively), neither of these two OCs was related to cortical thickness, and hypoxia but not fetal growth was associated with gyrification (d = 0.85). No significant associations were found within the control sample.

CONCLUSIONS

Cortical dysmorphology was associated with OCs. The use of a global measure of cortical morphology or a global measure of OCs obscured important relationships between these measures. Gyrification is complete before 2 years and its strong relationship with hypoxia suggests an early disruption to brain development. Cortical thickness matures later and, consistent with previous research, we found no association between thickness and OCs. Finally, cortical surface area is largely complete by puberty and the present results suggest that events during childhood do not fully compensate for the effects of early disruptive events.

The use of dynamic susceptibility contrast (DSC) MRI to automatically classify patients with first episode psychosis

Hemodynamic changes in the brain have been reported in major psychosis in respect to healthy controls, and could unveil the basis of structural brain modifications happening in patients. The study of first episode psychosis is of particular interest because the confounding role of chronicity and medication can be excluded. The aim of this work is to automatically discriminate first episode psychosis patients and normal controls on the basis of brain perfusion employing a support vector machine (SVM) classifier. 35 normal controls and 35 first episode psychosis underwent dynamic susceptibility contrast magnetic resonance imaging, and cerebral blood flow and volume, along with mean transit time were obtained. We investigated their behavior in the whole brain and in selected regions of interest, in particular the left and right frontal, parietal, temporal and occipital lobes, insula, caudate and cerebellum. The distribution of values of perfusion indexes were used as features in a support vector machine classifier. Mean values of blood flow and volume were slightly lower in patients, and the difference reached statistical significance in the right caudate, left and right frontal lobes, and in left cerebellum. Linear SVM reached an accuracy of 83% in the classification of patients and normal controls, with the highest accuracy associated with the right frontal lobe and left parietal lobe. In conclusion, we found evidence that brain perfusion could be used as a potential marker to classify patients with psychosis, who show reduced blood flow and volume in respect to normal controls.

[Neuroimaging in psychiatry: multivariate analysis techniques for diagnosis and prognosis]

BACKGROUND

Multiple studies successfully applied multivariate analysis to neuroimaging data demonstrating the potential utility of neuroimaging for clinical diagnostic and prognostic purposes.

OBJECTIVES

Summary of the current state of research regarding the application of neuroimaging in the field of psychiatry.

MATERIAL AND METHODS

Literature review of current studies.

RESULTS

Results of current studies indicate the potential application of neuroimaging data across various diagnoses, such as depression, schizophrenia, bipolar disorder and dementia. Potential applications include disease classification, differential diagnosis and prediction of disease course.

CONCLUSION

The results of the studies are heterogeneous although some studies report promising findings. Further multicentre studies are needed with clearly specified patient populations to systematically investigate the potential utility of neuroimaging for the clinical routine.

Mismatch negativity and p3a/reorienting complex in subjects with schizophrenia or at-risk mental state

Introduction: We measured duration mismatch negativity (dMMN), P3a, and reorienting negativity (RON) in subjects with at-risk mental state (ARMS), patients with first-episode or chronic schizophrenia, and healthy volunteers. The main interest was to determine if these event-related potentials provide a biomarker associated with progression to overt schizophrenia in ARMS subjects.

Methods: Nineteen ARMS subjects meeting the criteria of the Comprehensive Assessment of ARMS, 38 patients with schizophrenia (19 first-episode and 19 chronic), and 19 healthy controls participated in the study. dMMN, P3a, and RON were measured with an auditory odd-ball paradigm at baseline.

Results: During the follow-up period (2.2 years), 4 out of the 19 ARMS subjects transitioned to schizophrenia (Converters) while 15 did not (non-Converters). dMMN amplitudes of Converters were significantly smaller than those of non-Converters at frontal and central electrodes before onset of illness. dMMN amplitudes of non-Converters did not differ from those of healthy controls, while Converters showed significantly smaller dMMN amplitudes compared to control subjects. RON amplitudes were also reduced at frontal and central electrodes in subjects with schizophrenia, but not ARMS. Converter subjects tended to show smaller RON amplitudes compared to non-Converters.

Conclusions: Our data confirm that diminished dMMN amplitudes provide a biomarker, which is present before and after the development of psychosis. In this respect, RON amplitudes may also be useful, as suggested for the first time based on longitudinal observations.

Smoking status as a potential confounder in the study of brain structure in schizophrenia

Several but not all MRI studies have reported volume reductions in the hippocampus and dorsolateral prefrontal cortex (DLPFC) in patients with schizophrenia. Given the high prevalence of smoking among schizophrenia patients and the fact that smoking has also been associated with alterations in brain morphology, this study evaluated whether a proportion of the known gray matter reductions in key brain regions may be attributed to smoking rather than to schizophrenia alone. We examined structural MRI data of 112 schizophrenia patients (53 smokers and 59 non-smokers) and 77 healthy non-smoker controls collected by the MCIC study of schizophrenia. An automated atlas based probabilistic method was used to generate volumetric measures of the hippocampus and DLPFC. The two patient groups were matched with respect to demographic and clinical variables. Smoker schizophrenia patients showed significantly lower hippocampal and DLPFC volumes than non-smoker schizophrenia patients. Gray matter volume reductions associated with smoking status ranged between 2.2% and 2.8%. Furthermore, we found significant volume differences between smoker patients and healthy controls in the hippocampus and DLPFC, but not between non-smoker patients and healthy controls. Our data suggest that a proportion of the volume reduction seen in the hippocampus and DLPFC in schizophrenia is associated with smoking rather than with the diagnosis of schizophrenia. These results may have important implications for brain imaging studies comparing schizophrenia patients and other groups with a lower smoking prevalence.

Detecting volumetric changes in fMRI connectivity networks in schizophrenia patients

There is a growing interest in identifying neuroimaging-based biomarkers for schizophrenia. Previous studies have shown both functional and structural brain abnormalities in schizophrenia patients. One main category of these findings consists of volumetric abnormalities in brain structure in different cortical and subcortical structures in patients' brain. However there has been little work investigating changes in the brain's functional volumes. Nor has there been work studying differences in brain networks as opposed to single regions. In this study, we investigated the volumes of functional networks as potential biomarkers. Independent component analysis was used to decompose fMRI images into maximally independent spatial maps and corresponding time-courses. Volume of functional networks was computed from subject-specific back reconstructed spatial maps. The results show that different nodes of the default-mode network exhibit volumetric abnormalities in schizophrenia patients. Interestingly these networks are larger in patients compared to controls.

Effects of the neurogranin variant rs12807809 on thalamocortical morphology in schizophrenia

Although the genome wide supported psychosis susceptibility neurogranin (NRGN) gene is expressed in human brains, it is unclear how it impacts brain morphology in schizophrenia. We investigated the influence of NRGN rs12807809 on cortical thickness, subcortical volumes and shapes in patients with schizophrenia. One hundred and fifty six subjects (91 patients with schizophrenia and 65 healthy controls) underwent structural MRI scans and their blood samples were genotyped. A brain mapping algorithm, large deformation diffeomorphic metric mapping, was used to perform group analysis of subcortical shapes and cortical thickness. Patients with risk TT genotype were associated with widespread cortical thinning involving frontal, parietal and temporal cortices compared with controls with TT genotype. No volumetric difference in subcortical structures (hippocampus, thalamus, amygdala, basal ganglia) was observed between risk TT genotype in patients and controls. However, patients with risk TT genotype were associated with thalamic shape abnormalities involving regions related to pulvinar and medial dorsal nuclei. Our results revealed the influence of the NRGN gene on thalamocortical morphology in schizophrenia involving widespread cortical thinning and thalamic shape abnormalities. These findings help to clarify underlying NRGN mediated pathophysiological mechanisms involving cortical-subcortical brain networks in schizophrenia.

Elucidating neuroanatomical alterations in the at risk mental state and first episode psychosis: a combined voxel-based morphometry and voxel-based cortical thickness study

Previous studies have reported alterations in grey matter volume and cortical thickness in individuals at high risk of developing psychosis and patients in the early stages of the disorder. Because these studies have typically focused on either grey matter volume or cortical thickness separately, the relationship between these two types of alterations is currently unclear. In the present investigation we used both voxel-based cortical thickness (VBCT) and voxel-based morphometry (VBM) to examine neuroanatomical differences in 21 individuals with an At Risk Mental State (ARMS) for psychosis, 26 patients with a First Episode of Psychosis (FEP) and 24 healthy controls. Statistical inferences were made at P<0.05 after correction for multiple comparisons. Cortical thinning in the right superior temporal gyrus was observed in both individuals at high risk of developing psychosis and patients with a first episode of the disorder, and therefore is likely to represent a marker of vulnerability. In contrast, the right posterior cingulate cortex showed cortical thinning in FEP patients relative to individuals at high risk, and therefore appears to be implicated in the onset of the disease. These neuroanatomical differences were expressed in terms of cortical thickness but not in terms of grey matter volume, and therefore may reflect specific cortical atrophy as opposed to variations in sulcal and gyral morphology.

Can structural MRI aid in clinical classification? A machine learning study in two independent samples of patients with schizophrenia, bipolar disorder and healthy subjects

Although structural magnetic resonance imaging (MRI) has revealed partly non-overlapping brain abnormalities in schizophrenia and bipolar disorder, it is unknown whether structural MRI scans can be used to separate individuals with schizophrenia from those with bipolar disorder. An algorithm capable of discriminating between these two disorders could become a diagnostic aid for psychiatrists. Here, we scanned 66 schizophrenia patients, 66 patients with bipolar disorder and 66 healthy subjects on a 1.5T MRI scanner. Three support vector machines were trained to separate patients with schizophrenia from healthy subjects, patients with schizophrenia from those with bipolar disorder, and patients with bipolar disorder from healthy subjects, respectively, based on their gray matter density images. The predictive power of the models was tested using cross-validation and in an independent validation set of 46 schizophrenia patients, 47 patients with bipolar disorder and 43 healthy subjects scanned on a 3T MRI scanner. Schizophrenia patients could be separated from healthy subjects with an average accuracy of 90%. Additionally, schizophrenia patients and patients with bipolar disorder could be distinguished with an average accuracy of 88%.The model delineating bipolar patients from healthy subjects was less accurate, correctly classifying 67% of the healthy subjects and only 53% of the patients with bipolar disorder. In the latter group, lithium and antipsychotics use had no influence on the classification results. Application of the 1.5T models on the 3T validation set yielded average classification accuracies of 76% (healthy vs schizophrenia), 66% (bipolar vs schizophrenia) and 61% (healthy vs bipolar). In conclusion, the accurate separation of schizophrenia from bipolar patients on the basis of structural MRI scans, as demonstrated here, could be of added value in the differential diagnosis of these two disorders. The results also suggest that gray matter pathology in schizophrenia and bipolar disorder differs to such an extent that they can be reliably differentiated using machine learning paradigms.

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.