Identifying patients with obsessive-compulsive disorder using whole-brain anatomy

Dissecting Psychiatric Heterogeneity and Comorbidity with Core Region-Based Machine Learning

Machine learning approaches are increasingly being applied to neuroimaging data from patients with psychiatric disorders to extract brain-based features for diagnosis and prognosis. The goal of this review is to discuss recent practices for evaluating machine learning applications to obsessive-compulsive and related disorders and to advance a novel strategy of building machine learning models based on a set of core brain regions for better performance, interpretability, and generalizability. Specifically, we argue that a core set of co-altered brain regions (namely 'core regions') comprising areas central to the underlying psychopathology enables the efficient construction of a predictive model to identify distinct symptom dimensions/clusters in individual patients. Hypothesis-driven and data-driven approaches are further introduced showing how core regions are identified from the entire brain. We demonstrate a broadly applicable roadmap for leveraging this core set-based strategy to accelerate the pursuit of neuroimaging-based markers for diagnosis and prognosis in a variety of psychiatric disorders.

Relationship between white matter alterations and contamination subgroup in obsessive compulsive disorder: A diffusion tensor imaging study

Approximately 2%-3% of the world population suffers from obsessive-compulsive disorder (OCD). Several brain regions have been involved in the pathophysiology of OCD, but brain volumes in OCD may vary depending on specific OCD symptom dimensions. The study aims to explore how white matter structure changes in particular OCD symptom dimensions. Prior studies attempt to find the correlation between Y-BOCS scores and OCD patients. However, in this study, we separated the contamination subgroup in OCD and compared directly to healthy control to find regions that exactly related to contamination symptoms. To evaluate structural alterations, diffusion tensor imaging was acquired from 30 OCD patients and 34 demographically matched healthy controls. Data were processed using tract-based spatial statistics (TBSS) analysis. First, by comparing all OCD to healthy controls, significant fractional anisotropy (FA) decreased in the right anterior thalamic radiation, right corticospinal tract, and forceps minor observed. Then by comparing the contamination subgroup to healthy control, FA decreases in the forceps minor region. Consequently, forceps minor plays a central role in the pathophysiology of contamination behaviors. Finally, other subgroups were compared to healthy control and discovered that FA in the right corticospinal tract and right anterior thalamic radiation is reduced.

Prediction of Obsessive-Compulsive Disorder: Importance of Neurobiology-Aided Feature Design and Cross-Diagnosis Transfer Learning

BACKGROUND

Machine learning applications using neuroimaging provide a multidimensional, data-driven approach that captures the level of complexity necessary for objectively aiding diagnosis and prognosis in psychiatry. However, models learned from small training samples often have limited generalizability, which continues to be a problem with automated diagnosis of mental illnesses such as obsessive-compulsive disorder (OCD). Earlier studies have shown that features incorporating prior neurobiological knowledge of brain function and combining brain parcellations from various sources can potentially improve the overall prediction. However, it is unknown whether such knowledge-driven methods can provide a performance that is comparable to state-of-the-art approaches based on neural networks.

METHODS

In this study, we apply a transparent and explainable multiparcellation ensemble learning framework EMPaSchiz (Ensemble algorithm with Multiple Parcellations for Schizophrenia prediction) to the task of predicting OCD, based on a resting-state functional magnetic resonance imaging dataset of 350 subjects. Furthermore, we apply transfer learning using the features found effective for schizophrenia to OCD to leverage the commonality in brain alterations across these psychiatric diagnoses.

RESULTS

We show that our knowledge-based approach leads to a prediction performance of 80.3% accuracy for OCD diagnosis that is better than domain-agnostic and automated feature design using neural networks. Furthermore, we show that a selection of reduced feature sets can be transferred from schizophrenia to the OCD prediction model without significant loss in prediction performance.

CONCLUSIONS

This study presents a machine learning framework for OCD prediction with neurobiology-aided feature design using resting-state functional magnetic resonance imaging that is generalizable and reasonably interpretable.

Common abnormality of gray matter integrity in substance use disorder and obsessive-compulsive disorder: A comparative voxel-based meta-analysis

The objective of the current study is to determine robust transdiagnostic brain structural markers for compulsivity by capitalizing on the increasing number of case‐control studies examining gray matter volume (GMV) alterations in substance use disorders (SUD) and obsessive‐compulsive disorder (OCD). Voxel‐based meta‐analysis within the individual disorders and conjunction analysis were employed to reveal common GMV alterations between SUDs and OCD. Meta‐analytic coordinates and signed brain volumetric maps determining directed (reduced/increased) GMV alterations between the disorder groups and controls served as the primary outcome. The separate meta‐analysis demonstrated that SUD and OCD patients exhibited widespread GMV reductions in frontocortical regions including prefrontal, cingulate, and insular. Conjunction analysis revealed that the left inferior frontal gyrus (IFG) consistently exhibited decreased GMV across all disorders. Functional characterization suggests that the IFG represents a core hub in the cognitive control network and exhibits bidirectional (Granger) causal interactions with the striatum. Only OCD showed increased GMV in the dorsal striatum with higher changes being associated with more severe OCD symptomatology. Together the findings demonstrate robustly decreased GMV across the disorders in the left IFG, suggesting a transdiagnostic brain structural marker. The functional characterization as a key hub in the cognitive control network and casual interactions with the striatum suggest that deficits in inhibitory control mechanisms may promote compulsivity and loss of control that characterize both disorders.

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.

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.

Altered network connectivity predicts response to cognitive-behavioral therapy in pediatric obsessive-compulsive disorder

Obsessive-compulsive disorder (OCD) is commonly associated with alterations in cortico-striato-thalamo-cortical brain networks. Yet, recent investigations of large-scale brain networks suggest that more diffuse alterations in brain connectivity may underlie its pathophysiology. Few studies have assessed functional connectivity within or between networks across the whole brain in pediatric OCD or how patterns of connectivity associate with treatment response. Resting-state functional magnetic resonance imaging scans were acquired from 25 unmedicated, treatment-naive children and adolescents with OCD (12.8 ± 2.9 years) and 23 matched healthy control (HC) participants (11.0 ± 3.3 years) before participants with OCD completed a course of cognitive-behavioral therapy (CBT). Participants were re-scanned after 12-16 weeks. Whole-brain connectomic analyses were conducted to assess baseline group differences and group-by-time interactions, corrected for multiple comparisons. Relationships between functional connectivity and OCD symptoms pre- and post-CBT were examined using longitudinal cross-lagged panel modeling. Reduced connectivity in OCD relative to HC participants was detected between default mode and task-positive network regions. Greater (less altered) connectivity between left angular gyrus and left frontal pole predicted better response to CBT in the OCD group. Altered connectivity between task-positive and task-negative networks in pediatric OCD may contribute to the impaired control over intrusive thoughts early in the illness. This is the first study to show that altered connectivity between large-scale network regions may predict response to CBT in pediatric OCD, highlighting the clinical relevance of these networks as potential circuit-based targets for the development of novel treatments.

Diagnostic neuroimaging markers of obsessive-compulsive disorder: Initial evidence from structural and functional MRI studies

As of yet, no diagnostic biomarkers are available for obsessive-compulsive disorder (OCD), and its diagnosis relies entirely upon the recognition of behavioural features assessed through clinical interview. Neuroimaging studies have shown that various brain structures are abnormal in OCD patients compared to healthy controls. However, the majority of these results are based on average differences between groups, which limits diagnostic usage in clinical practice. In recent years, a growing number of studies have applied multivariate pattern analysis (MVPA) techniques on neuroimaging data to extract patterns of altered brain structure, function and connectivity typical for OCD. MVPA techniques can be used to develop predictive models that extract regularities in data to classify individual subjects based on their diagnosis. In the present paper, we reviewed the literature of MVPA studies using data from different imaging modalities to distinguish OCD patients from controls. A systematic search retrieved twelve articles that fulfilled the inclusion and exclusion criteria. Reviewed studies have been able to classify OCD diagnosis with accuracies ranging from 66% up to 100%. Features important for classification were different across imaging modalities and widespread throughout the brain. Although studies have shown promising results, sample sizes used are typically small which can lead to high variance of the estimated model accuracy, cohort-specific solutions and lack of generalizability of findings. Some of the challenges are discussed that need to be overcome in order to move forward toward clinical applications.

Brain alterations in low-frequency fluctuations across multiple bands in obsessive compulsive disorder

The extent of functional abnormalities in frontal-subcortical circuits in obsessive-compulsive disorder (OCD) is still unclear. Although neuroimaging studies, in general, and resting-state functional Magnetic Resonance Imaging (rs-fMRI), in particular, have provided relevant information regarding such alterations, rs-fMRI studies have been typically limited to the analysis of between-region functional connectivity alterations at low-frequency signal fluctuations (i.e., <0.08 Hz). Conversely, the local attributes of Blood Oxygen Level Dependent (BOLD) signal across different frequency bands have been seldom studied, although they may provide valuable information. Here, we evaluated local alterations in low-frequency fluctuations across different oscillation bands in OCD. Sixty-five OCD patients and 50 healthy controls underwent an rs-fMRI assessment. Alterations in the fractional amplitude of low-frequency fluctuations (fALFF) were evaluated, voxel-wise, across four different bands (from 0.01 Hz to 0.25 Hz). OCD patients showed decreased fALFF values in medial orbitofrontal regions and increased fALFF values in the dorsal-medial prefrontal cortex (DMPFC) at frequency bands <0.08 Hz. This pattern was reversed at higher frequencies, where increased fALFF values also appeared in medial temporal lobe structures and medial thalamus. Clinical variables (i.e., symptom-specific severities) were associated with fALFF values across the different frequency bands. Our findings provide novel evidence about the nature and regional distribution of functional alterations in OCD, which should contribute to refine neurobiological models of the disorder. We suggest that the evaluation of the local attributes of BOLD signal across different frequency bands may be a sensitive approach to further characterize brain functional alterations in psychiatric disorders.

The relevance of feature selection methods to the classification of obsessive-compulsive disorder based on volumetric measures

BACKGROUND

Magnetic resonance images (MRI) show detectable anatomical and functional differences between individuals with obsessive-compulsive disorder (OCD) and healthy subjects. Moreover, machine learning techniques have been proposed as tools to identify potential biomarkers and, ultimately, to support clinical diagnosis. However, few studies to date have investigated feature selection (FS) influences in OCD MRI-based classification.

METHODS

Volumes of cortical and subcortical structures, from MRI data of 38 OCD patients (split into two groups according symptoms severity) and 36 controls, were submitted to seven feature selection algorithms. FS aims to select the most relevant and less redundant features which discriminate between two classes. Then, a classification step was applied, from which the classification performances before and after different FS were compared. For the performance evaluation, leave-one-subject-out accuracies of Support Vector Machine classifiers were considered.

RESULTS

Using different FS algorithms, performance improvement was achieved for Controls vs. All OCD discrimination (19.08% of improvement reducing by 80% the amount of features), Controls vs. Low OCD (20.10%, 75%), Controls vs. High OCD (17.32%, 85%) and Low OCD vs. High OCD (10.53%, 75%). Furthermore, all algorithms pointed out classical cortico-striato-thalamo-cortical circuitry structures as relevant features for OCD classification.

LIMITATIONS

Limitations include the sample size and using only filter approaches for FS.

CONCLUSIONS

Our results suggest that FS positively impacts OCD classification using machine-learning techniques. Complementarily, FS algorithms were able to select biologically plausible features automatically.

A Neural Marker of Obsessive-Compulsive Disorder from Whole-Brain Functional Connectivity

Obsessive-compulsive disorder (OCD) is a common psychiatric disorder with a lifetime prevalence of 2–3%. Recently, brain activity in the resting state is gathering attention for exploring altered functional connectivity in psychiatric disorders. Although previous resting-state functional magnetic resonance imaging studies investigated the neurobiological abnormalities of patients with OCD, there are concerns that should be addressed. One concern is the validity of the hypothesis employed. Most studies used seed-based analysis of the fronto-striatal circuit, despite the potential for abnormalities in other regions. A hypothesis-free study is a promising approach in such a case, while it requires researchers to handle a dataset with large dimensions. Another concern is the reliability of biomarkers derived from a single dataset, which may be influenced by cohort-specific features. Here, our machine learning algorithm identified an OCD biomarker that achieves high accuracy for an internal dataset (AUC = 0.81; N = 108) and demonstrates generalizability to an external dataset (AUC = 0.70; N = 28). Our biomarker was unaffected by medication status, and the functional networks contributing to the biomarker were distributed widely, including the frontoparietal and default mode networks. Our biomarker has the potential to deepen our understanding of OCD and to be applied clinically.

Comparative Multimodal Meta-analysis of Structural and Functional Brain Abnormalities in Autism Spectrum Disorder and Obsessive-Compulsive Disorder

BACKGROUND

Autism spectrum disorder (ASD) and obsessive-compulsive disorder (OCD) share inhibitory control deficits possibly underlying poor control over stereotyped and repetitive and compulsive behaviors, respectively. However, it is unclear whether these symptom profiles are mediated by common or distinct neural profiles. This comparative multimodal meta-analysis assessed shared and disorder-specific neuroanatomy and neurofunction of inhibitory functions.

METHODS

A comparative meta-analysis of 62 voxel-based morphometry and 26 functional magnetic resonance imaging (fMRI) studies of inhibitory control was conducted comparing gray matter volume and activation abnormalities between patients with ASD (structural MRI: 911; fMRI: 188) and OCD (structural MRI: 928; fMRI: 247) and control subjects. Multimodal meta-analysis compared groups across voxel-based morphometry and fMRI.

RESULTS

Both disorders shared reduced function and structure in the rostral and dorsomedial prefrontal cortex including the anterior cingulate. OCD patients had a disorder-specific increase in structure and function of left basal ganglia (BG) and insula relative to control subjects and ASD patients, who had reduced right BG and insula volumes versus OCD patients. In fMRI, ASD patients showed disorder-specific reduced left dorsolateral-prefrontal activation and reduced posterior cingulate deactivation, whereas OCD patients showed temporoparietal underactivation.

CONCLUSIONS

The multimodal comparative meta-analysis shows shared and disorder-specific abnormalities. Whereas the rostrodorsomedial prefrontal cortex was smaller in structure and function in both disorders, this was concomitant with increased structure and function in BG and insula in OCD patients, but a reduction in ASD patients, presumably reflecting a disorder-specific frontostriatoinsular dysregulation in OCD in the form of poor frontal control over overactive BG, and a frontostriatoinsular maldevelopment in ASD with reduced structure and function in this network. Disorder-differential mechanisms appear to drive overlapping phenotypes of inhibitory control abnormalities in patients with ASD and OCD.

Meta-analytic investigations of common and distinct grey matter alterations in youths and adults with obsessive-compulsive disorder

Obsessive-compulsive disorder (OCD) is a disabling illness with onset generally in childhood. OCD-youths differ from OCD-adults with regard to gender distribution, comorbidity patterns and treatment options. However, little is known about the neural correlate differences underpin those two populations. The current meta-analysis summarizes voxel based morphometry findings to elucidate whether differences of neural correlates exist between these two populations. Both OCD-youths and OCD-adults demonstrated greater striatal volume and smaller prefrontal grey matter volume (GMV). However, smaller GMV in left visual cortex was observed in OCD-youths only, while smaller GMV in anterior cingulate gyrus and greater GMV in cerebellum were demonstrated only in OCD-adults. Meta-regression showed greater GMV in left putamen was most prominent in samples with higher percentages of medicated OCD-adults. Our findings confirmed the most consistent GMV alterations in OCD were in prefrontal-striatal circuitry. Besides, other regions may involve at different developmental stages including deficits of visual cortex in OCD-youths and abnormalities of limbic-cerebellar circuit in OCD-adults. Medication effect may be more pronounced in the striatum, especially the putamen.

Alterations of white matter fractional anisotropy in unmedicated obsessive-compulsive disorder

BACKGROUND

Abnormalities in white matter (WM) have previously been reported in patients with obsessive-compulsive disorder (OCD). However, there was some inconsistency in the results obtained for altered regions of WM. The aim of this study was to investigate fractional anisotropy (FA) in the WM of the whole brain in patients with OCD by using diffusion tensor imaging (DTI).

METHODS

In total, 28 unmedicated patients with OCD and 28 healthy volunteers underwent DTI scan. A voxel-based analysis was used to compare FA values in WM of the two groups at a voxel threshold of P<0.005 with an extent threshold of k>72 voxels (P<0.05; Alphasim correction). Subsequently, correlation analysis was conducted in order to find the correlation between the mean FA values in significantly altered brain regions and Yale-Brown Obsessive Compulsive Scale (Y-BOCS) scores of the OCD patients.

RESULTS

Compared with healthy volunteers, the OCD patients had lower FA value in the left lingual gyrus, right midbrain, and right precuneus. There were no regions with significantly higher FA values in OCD patients compared with healthy volunteers. The mean FA values in the above regions (left lingual, r=0.019, P=0.923; right midbrain, r=-0.208, P=0.289; and right precuneus, r=-0.273, P=0.161) had no significant correlation with the Y-BOCS scores of the OCD patients.

CONCLUSION

The findings of this study suggest that alterations in WM of the left lingual gyrus, right midbrain, and right precuneus are associated with the pathophysiology mechanism of OCD, and these microstructural alterations do not correlate with symptom severity of OCD.

Assessing paedophilia based on the haemodynamic brain response to face images

OBJECTIVES

Objective assessment of sexual preferences may be of relevance in the treatment and prognosis of child sexual offenders. Previous research has indicated that this can be achieved by pattern classification of brain responses to sexual child and adult images. Our recent research showed that human face processing is tuned to sexual age preferences. This observation prompted us to test whether paedophilia can be inferred based on the haemodynamic brain responses to adult and child faces.

METHODS

Twenty-four men sexually attracted to prepubescent boys or girls (paedophiles) and 32 men sexually attracted to men or women (teleiophiles) were exposed to images of child and adult, male and female faces during a functional magnetic resonance imaging (fMRI) session.

RESULTS

A cross-validated, automatic pattern classification algorithm of brain responses to facial stimuli yielded four misclassified participants (three false positives), corresponding to a specificity of 91% and a sensitivity of 95%.

CONCLUSIONS

These results indicate that the functional response to facial stimuli can be reliably used for fMRI-based classification of paedophilia, bypassing the problem of showing child sexual stimuli to paedophiles.

Brain structural correlates of obsessive-compulsive disorder with and without preceding stressful life events

Objectives There is growing evidence supporting a role for stressful life events (SLEs) at obsessive-compulsive disorder (OCD) onset, but neurobiological correlates of such effect are not known. We evaluated regional grey matter (GM) changes associated with the presence/absence of SLEs at OCD onset. Methods One hundred and twenty-four OCD patients and 112 healthy controls were recruited. Patients were split into two groups according to the presence (n = 56) or absence (n = 68) of SLEs at disorder's onset. A structural magnetic resonance image was acquired for each participant and pre-processed with Statistical Parametric Mapping software (SPM8) to obtain a volume-modulated GM map. Between-group differences in sociodemographic, clinical and whole-brain regional GM volumes were assessed. Results SLEs were associated with female sex, later age at disorder's onset, more contamination/cleaning and less hoarding symptoms. In comparison with controls, patients without SLEs showed GM volume increases in bilateral dorsal putamen and the central tegmental tract of the brainstem. By contrast, patients with SLEs showed specific GM volume increases in the right anterior cerebellum. Conclusions Our findings support the idea that neuroanatomical alterations of OCD patients partially depend on the presence of SLEs at disorder's onset.

Integrating Genetic, Neuropsychological and Neuroimaging Data to Model Early-Onset Obsessive Compulsive Disorder Severity

We propose an integrative approach that combines structural magnetic resonance imaging data (MRI), diffusion tensor imaging data (DTI), neuropsychological data, and genetic data to predict early-onset obsessive compulsive disorder (OCD) severity. From a cohort of 87 patients, 56 with complete information were used in the present analysis. First, we performed a multivariate genetic association analysis of OCD severity with 266 genetic polymorphisms. This association analysis was used to select and prioritize the SNPs that would be included in the model. Second, we split the sample into a training set (N = 38) and a validation set (N = 18). Third, entropy-based measures of information gain were used for feature selection with the training subset. Fourth, the selected features were fed into two supervised methods of class prediction based on machine learning, using the leave-one-out procedure with the training set. Finally, the resulting model was validated with the validation set. Nine variables were used for the creation of the OCD severity predictor, including six genetic polymorphisms and three variables from the neuropsychological data. The developed model classified child and adolescent patients with OCD by disease severity with an accuracy of 0.90 in the testing set and 0.70 in the validation sample. Above its clinical applicability, the combination of particular neuropsychological, neuroimaging, and genetic characteristics could enhance our understanding of the neurobiological basis of the disorder.

Neural Correlates of Response to Pharmacotherapy in Obsessive-Compulsive Disorder: Individualized Cortical Morphology-Based Structural Covariance

BACKGROUND

Primary pharmacotherapy regimen for obsessive-compulsive disorder (OCD) named Serotonin reuptake inhibitors (SRIs) does not attain sufficient symptom improvement in 40-60% of OCD. We aimed to decode the differential profile of OCD-related brain pathology per subject in the context of cortical surface area (CSA) or thickness (CT)-based individualized structural covariance (ISC) and to demonstrate the potential of which as a biomarker of treatment response to SRI-based pharmacotherapy in OCD using the support vector machine (SVM).

METHODS

T1-weighted magnetic resonance imaging was obtained at 3T from 56 unmedicated OCD subjects and 75 healthy controls (HCs) at baseline. After 4months of SRI-based pharmacotherapy, the OCD subjects were classified as responders (OCD-R,N=25; ≥35% improvement) or nonresponders (OCD-NR,N=31; <35% improvement) according to the percentage change in the Yale-Brown Obsessive Compulsive Scale total score. Cortical ISCs sustaining between-group difference (p<.001) for every run of leave-one-out group-comparison were packaged as feature set for group classification using the SVM.

RESULTS

An optimal feature set of the top 12 ISCs including a CT-ISC between the dorsolateral prefrontal cortex versus precuneus, a CSA-ISC between the anterior insula versus intraparietal sulcus, as well as perisylvian area-related ISCs predicted the initial prognosis of OCD as OCD-R or OCD-NR with an accuracy of 89.0% (sensitivity 88.4%, specificity 90.1%). Extended sets of ISCs distinguished the OCD subjects from the HCs with 90.7-95.6% accuracy (sensitivity 90.8-96.2%, specificity 91.1-95.0%).

CONCLUSION

We showed the potential of cortical morphology-based ISCs, which reflect dysfunctional cortical maturation process, as a possible biomarker that predicts the clinical treatment response to SRI-based pharmacotherapy in OCD.

Metabolic Topology of Neurodegenerative Disorders: Influence of Cognitive and Motor Deficits

Parkinson disease with and without dementia (PDD and PD, respectively), dementia with Lewy bodies (DLB), and Alzheimer dementia (AD) traditionally have been viewed as distinct clinical and pathologic entities. However, intriguing overlaps in biochemical, clinical, and imaging findings question the concept of distinct entities and suggest a continuous spectrum in which individual patients express PD-typical patterns and AD-typical patterns to a variable degree.

METHODS

Following this concept, we built a topological map based on regional patterns of the cerebral metabolic rate of glucose as measured with (18)F-FDG PET to rank and localize single subjects' disease status according to PD-typical (PD vs. controls) and AD-typical (AD vs. controls) pattern expression in patients clinically characterized as PD, PDD, DLB, amnestic mild cognitive impairment, and AD.

RESULTS

The topology generally confirmed an indivisible spectrum of disease manifestation according to 2 separable expression patterns. The expression values derived from the first pattern were highly correlated with individual cognitive, but not motor, disability. The opposite was found for the corresponding expression values of the second pattern.

CONCLUSION

The metabolic imaging analysis supports the notion that there is a continuous spectrum of neurodegeneration between AD and PD. Furthermore, PDD and DLB may in fact represent 1 overlapping disease entity, characterized by the presence of mixed neuropathology and only different by the time course.

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.

Meta-analytic investigations of structural grey matter, executive domain-related functional activations, and white matter diffusivity in obsessive compulsive disorder: an integrative review

Obsessive-compulsive disorder (OCD) is a debilitating disorder. However, existing neuroimaging findings involving executive function and structural abnormalities in OCD have been mixed. Here we conducted meta-analyses to investigate differences in OCD samples and controls in: Study 1 - grey matter structure; Study 2 - executive function task-related activations during (i) response inhibition, (ii) interference, and (iii) switching tasks; and Study 3 - white matter diffusivity. Results showed grey matter differences in the frontal, striatal, thalamus, parietal and cerebellar regions; task domain-specific neural differences in similar regions; and abnormal diffusivity in major white matter regions in OCD samples compared to controls. Our results reported concurrence of abnormal white matter diffusivity with corresponding abnormalities in grey matter and task-related functional activations. Our findings suggested the involvement of other brain regions not included in the cortico-striato-thalamo-cortical network, such as the cerebellum and parietal cortex, and questioned the involvement of the orbitofrontal region in OCD pathophysiology. Future research is needed to clarify the roles of these brain regions in the disorder.

Clinical prediction from structural brain MRI scans: a large-scale empirical study

Multivariate pattern analysis (MVPA) methods have become an important tool in neuroimaging, revealing complex associations and yielding powerful prediction models. Despite methodological developments and novel application domains, there has been little effort to compile benchmark results that researchers can reference and compare against. This study takes a significant step in this direction. We employed three classes of state-of-the-art MVPA algorithms and common types of structural measurements from brain Magnetic Resonance Imaging (MRI) scans to predict an array of clinically relevant variables (diagnosis of Alzheimer's, schizophrenia, autism, and attention deficit and hyperactivity disorder; age, cerebrospinal fluid derived amyloid-β levels and mini-mental state exam score). We analyzed data from over 2,800 subjects, compiled from six publicly available datasets. The employed data and computational tools are freely distributed ( https://www.nmr.mgh.harvard.edu/lab/mripredict), making this the largest, most comprehensive, reproducible benchmark image-based prediction experiment to date in structural neuroimaging. Finally, we make several observations regarding the factors that influence prediction performance and point to future research directions. Unsurprisingly, our results suggest that the biological footprint (effect size) has a dramatic influence on prediction performance. Though the choice of image measurement and MVPA algorithm can impact the result, there was no universally optimal selection. Intriguingly, the choice of algorithm seemed to be less critical than the choice of measurement type. Finally, our results showed that cross-validation estimates of performance, while generally optimistic, correlate well with generalization accuracy on a new dataset.

Gender differences in obsessive-compulsive disorder: findings from a large Indian sample

AIM

Gender has been considered as one of the possible factors mediating phenotypic expression of obsessive-compulsive disorder (OCD). We examined gender differences in a large sample of subjects with OCD from India with respect to socio-demographic parameters, symptom characteristics, and comorbidity patterns.

METHODS

Consecutive patients (n=545) who consulted a specialty OCD clinic over 5 years at a large psychiatric hospital in India were evaluated.

RESULTS

Men (n=332) compared to women (n=213) with OCD had an earlier onset (p<0.001), higher frequency of sexual (p<0.001) and religious obsessions (p=0.001) pathological doubts (p<0.001) and checking (p<0.001) and repeating compulsions (p<0.001), and a greater tendency to have comorbid social phobia (p=0.006). Women compared to men were more likely to be married, had a higher frequency of fear of contamination (p=0.017), comorbid depression (p=0.014) and greater suicidal risk (p=0.003).

CONCLUSIONS

Our study provides further evidence for gender related differences in clinical features of obsessive-compulsive disorder. Our findings are only partly comparable with results from studies across the world possibly due to various biological and cultural factors mediating the phenotypic expression of OCD across the genders. There is a need to examine the biological basis for these gender differences.

Discovering brain regions relevant to obsessive-compulsive disorder identification through bagging and transduction

In the present study we applied a multivariate feature selection method based on the analysis of the sign consistency of voxel weights across bagged linear Support Vector Machines (SVMs) with the aim of detecting brain regions relevant for the discrimination of subjects with obsessive-compulsive disorder (OCD, n=86) from healthy controls (n=86). Each participant underwent a structural magnetic resonance imaging (sMRI) examination that was pre-processed in Statistical Parametric Mapping (SPM8) using the standard pipeline of voxel-based morphometry (VBM) studies. Subsequently, we applied our multivariate feature selection algorithm, which also included an L2 norm regularization to account for the clustering nature of MRI data, and a transduction-based refinement to further control overfitting. Our approach proved to be superior to two state-of-the-art feature selection methods (i.e., mass-univariate t-Test selection and recursive feature elimination), since, following the application of transductive refinement, we obtained a lower test error rate of the final classifier. Importantly, the regions identified by our method have been previously reported to be altered in OCD patients in studies using traditional brain morphometry methods. By contrast, the discrimination patterns obtained with the t-Test and the recursive feature elimination approaches extended across fewer brain regions and included fewer voxels per cluster. These findings suggest that the feature selection method presented here provides a more comprehensive characterization of the disorder, thus yielding not only a superior identification of OCD patients on the basis of their brain anatomy, but also a discrimination map that incorporates most of the alterations previously described to be associated with the disorder.

A role for the precuneus in thought-action fusion: evidence from participants with significant obsessive-compulsive symptoms

Likelihood thought-action fusion (TAF-L) refers to a cognitive bias in which individuals believe that the mere thought of a negative event increases its likelihood of occurring in reality. TAF-L is most commonly associated with obsessive-compulsive disorder (OCD) but is also present in depression, generalized anxiety disorder and psychosis. We induced TAF-L in individuals with high (High-OC, N = 23) and low (Low-OC, N = 24) levels of OC traits, and used low resolution electromagnetic tomography (LORETA) to localise the accompanying electrical brain activity patterns. The results showed greater TAF-L in the High-OC than in the Low-OC group (p < .005), which was accompanied by significantly greater upper beta frequency (19-30 Hz) activity in the precuneus (p < .05). Further, the precuneus activity was positively correlated with self-reported magnitude of TAF-L (p < .01), suggesting a specific role of this region in this cognitive bias. Results are discussed with reference to self-referential processing and the default-mode network.

Brain structural alterations in obsessive-compulsive disorder patients with autogenous and reactive obsessions

Obsessive-compulsive disorder (OCD) is a clinically heterogeneous condition. Although structural brain alterations have been consistently reported in OCD, their interaction with particular clinical subtypes deserves further examination. Among other approaches, a two-group classification in patients with autogenous and reactive obsessions has been proposed. The purpose of the present study was to assess, by means of a voxel-based morphometry analysis, the putative brain structural correlates of this classification scheme in OCD patients. Ninety-five OCD patients and 95 healthy controls were recruited. Patients were divided into autogenous (n = 30) and reactive (n = 65) sub-groups. A structural magnetic resonance image was acquired for each participant and pre-processed with SPM8 software to obtain a volume-modulated gray matter map. Whole-brain and voxel-wise comparisons between the study groups were then performed. In comparison to the autogenous group, reactive patients showed larger gray matter volumes in the right Rolandic operculum. When compared to healthy controls, reactive patients showed larger volumes in the putamen (bilaterally), while autogenous patients showed a smaller left anterior temporal lobe. Also in comparison to healthy controls, the right middle temporal gyrus was smaller in both patient subgroups. Our results suggest that autogenous and reactive obsessions depend on partially dissimilar neural substrates. Our findings provide some neurobiological support for this classification scheme and contribute to unraveling the neurobiological basis of clinical heterogeneity in OCD.

Predicting obsessive-compulsive disorder severity combining neuroimaging and machine learning methods

BACKGROUND

Recently, machine learning methods have been used to discriminate, on an individual basis, patients from healthy controls through brain structural magnetic resonance imaging (MRI). However, the application of these methods to predict the severity of psychiatric symptoms is less common.

METHODS

Herein, support vector regression (SVR) was employed to evaluate whether gray matter volumes encompassing cortical-subcortical loops contain discriminative information to predict obsessive-compulsive disorder (OCD) symptom severity in 37 treatment-naïve adult OCD patients.

RESULTS

The Pearson correlation coefficient between predicted and observed symptom severity scores was 0.49 (p=0.002) for total Dimensional Yale-Brown Obsessive-Compulsive Scale (DY-BOCS) and 0.44 (p=0.006) for total Yale-Brown Obsessive-Compulsive Scale (Y-BOCS). The regions that contained the most discriminative information were the left medial orbitofrontal cortex and the left putamen for both scales.

LIMITATIONS

Our sample is relatively small and our results must be replicated with independent and larger samples.

CONCLUSIONS

These results indicate that machine learning methods such as SVR analysis may identify neurobiological markers to predict OCD symptom severity based on individual structural MRI datasets.

Multivariate pattern analysis of DTI reveals differential white matter in individuals with obsessive-compulsive disorder

Diffusion tensor imaging (DTI) studies have revealed group differences in white matter between patients with obsessive‐compulsive disorder (OCD) and healthy controls. However, the results of these studies were based on average differences between the two groups, and therefore had limited clinical applicability. The objective of this study was to investigate whether fractional anisotropy (FA) of white matter can be used to discriminate between patients with OCD and healthy controls at the level of the individual. DTI data were acquired from 28 OCD patients and 28 demographically matched healthy controls, scanned using a 3T MRI system. Differences in FA values of white matter between OCD and healthy controls were examined using a multivariate pattern classification technique known as support vector machine (SVM). SVM applied to FA images correctly identified OCD patients with a sensitivity of 86% and a specificity of 82% resulting in a statistically significant accuracy of 84% (P ≤ 0.001). This discrimination was based on a distributed network including bilateral prefrontal and temporal regions, inferior fronto‐occipital fasciculus, superior fronto‐parietal fasciculus, splenium of corpus callosum and left middle cingulum bundle. The present study demonstrates subtle and spatially distributed white matter abnormalities in individuals with OCD, and provides preliminary support for the suggestion that that these could be used to aid the identification of individuals with OCD in clinical practice. Hum Brain Mapp 35:2643–2651, 2014. © 2013 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc..

Neuroimaging-based biomarkers in psychiatry: clinical opportunities of a paradigm shift

Neuroimaging research has substantiated the functional and structural abnormalities underlying psychiatric disorders but has, thus far, failed to have a significant impact on clinical practice. Recently, neuroimaging-based diagnoses and clinical predictions derived from machine learning analysis have shown significant potential for clinical translation. This review introduces the key concepts of this approach, including how the multivariate integration of patterns of brain abnormalities is a crucial component. We survey recent findings that have potential application for diagnosis, in particular early and differential diagnoses in Alzheimer disease and schizophrenia, and the prediction of clinical response to treatment in depression. We discuss the specific clinical opportunities and the challenges for developing biomarkers for psychiatry in the absence of a diagnostic gold standard. We propose that longitudinal outcomes, such as early diagnosis and prediction of treatment response, offer definite opportunities for progress. We propose that efforts should be directed toward clinically challenging predictions in which neuroimaging may have added value, compared with the existing standard assessment. We conclude that diagnostic and prognostic biomarkers will be developed through the joint application of expert psychiatric knowledge in addition to advanced methods of analysis.

Obsessive-compulsive symptoms and related sex differences in brain structure: an MRI study in Dutch twins

Neuroimaging studies have indicated abnormalities in cortico-striato-thalamo-cortical circuits in obsessive-compulsive disorder patients, but results have not been consistent. Since there are significant sex differences in human brain anatomy and obsessive-compulsive symptomatology and its developmental trajectories tend to be distinct in males and females, we investigated whether sex is a potential source of heterogeneity in neuroimaging studies on obsessive-compulsive symptoms. We selected male and female twin pairs who were concordant for scoring either high or low for obsessive-compulsive symptoms and a group of discordant pairs where one twin scored high and the co-twin scored low. The design included 24 opposite-sex twin pairs. Magnetic resonance imaging scans of 31 males scoring high for obsessive-compulsive symptoms, 41 low-scoring males, 58 high-scoring females, and 73 low-scoring females were analyzed and the interaction of obsessive-compulsive symptoms by sex on gray matter volume was assessed using voxel-based morphometry. An obsessive-compulsive symptom by sex interaction was observed for the left middle temporal gyrus, the right middle temporal gyrus, and the right precuneus. These interactions acted to reduce or hide a main effect in our study and illustrate the importance of taking sex into account when investigating the neurobiology of obsessive-compulsive symptoms.

Anxiety and affective disorder comorbidity related to serotonin and other neurotransmitter systems: obsessive-compulsive disorder as an example of overlapping clinical and genetic heterogeneity

Individuals with obsessive-compulsive disorder (OCD) have also been shown to have comorbid lifetime diagnoses of major depressive disorder (MDD; rates greater than 70%), bipolar disorder (rates greater than 10%) and other anxiety disorders (e.g. panic disorder, post-traumatic stress disorder (PTSD)). In addition, overlap exists in some common genetic variants (e.g. the serotonin transporter gene (SLC6A4), the brain-derived neurotrophic factor (BDNF) gene), and rare variants in genes/chromosomal abnormalities (e.g. the 22q11 microdeletion syndrome) found across the affective/anxiety disorder spectrums. OCD has been proposed as a possible independent entity for DSM-5, but by others thought best retained as an anxiety disorder subtype (its current designation in DSM-IV), and yet by others considered best in the affective disorder spectrum. This review focuses on OCD, a well-studied but still puzzling heterogeneous disorder, regarding alterations in serotonergic, dopaminergic and glutamatergic neurotransmission in addition to other systems involved, and how related genes may be involved in the comorbidity of anxiety and affective disorders. OCD resembles disorders such as depression, in which gene × gene interactions, gene × environment interactions and stress elements coalesce to yield OC symptoms and, in some individuals, full-blown OCD with multiple comorbid disorders.

Brain structural abnormalities in obsessive-compulsive disorder: converging evidence from white matter and grey matter

INTRODUCTION

Specific cortico-striato-thalamic circuits are hypothesised to underlie the aetiology of obsessive-compulsive disorder (OCD). However, findings from neuroimaging studies have been inconsistent. In the current study, we attempted to provide a complete overview of structural alterations in OCD by conducting signed differential mapping (SDM) meta-analysis on grey matter and white matter studies of patients with OCD based on voxel-based morphometry (VBM) studies and diffusion tensor imaging (DTI) studies.

METHODS

Fifteen VBM and seven DTI case-control studies were included in this meta-analysis. SDM meta-analyses were performed to assess grey matter volume and white matter integrity changes in OCD patients and healthy controls.

RESULTS

We found that OCD patients had smaller grey matter volume than health controls in the frontal eye fields, medial frontal gyrus and anterior cingulate cortex. However, we showed that there was an increase in the grey matter volume in the lenticular nucleus, caudate nucleus and a small region in the right superior parietal lobule. OCD patients also had a lower fractional anisotropy (FA) in the cingulum bundles, inferior fronto-occipital fasciculus, and superior longitudinal fasciculus, while increased FA in the left uncinate fasciculus.

CONCLUSIONS

The current findings confirm the structural abnormalities of cortico-striato-thalamic circuits in OCD.

Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression

OBJECTIVES

Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data.

METHODS

We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers.

RESULTS

The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03).

CONCLUSIONS

These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.

Topology-based kernels with application to inference problems in Alzheimer's disease

Alzheimer's disease (AD) research has recently witnessed a great deal of activity focused on developing new statistical learning tools for automated inference using imaging data. The workhorse for many of these techniques is the support vector machine (SVM) framework (or more generally kernel-based methods). Most of these require, as a first step, specification of a kernel matrix K between input examples (i.e., images). The inner product between images I(i) and I(j) in a feature space can generally be written in closed form and so it is convenient to treat K as "given." However, in certain neuroimaging applications such an assumption becomes problematic. As an example, it is rather challenging to provide a scalar measure of similarity between two instances of highly attributed data such as cortical thickness measures on cortical surfaces. Note that cortical thickness is known to be discriminative for neurological disorders, so leveraging such information in an inference framework, especially within a multi-modal method, is potentially advantageous. But despite being clinically meaningful, relatively few works have successfully exploited this measure for classification or regression. Motivated by these applications, our paper presents novel techniques to compute similarity matrices for such topologically-based attributed data. Our ideas leverage recent developments to characterize signals (e.g., cortical thickness) motivated by the persistence of their topological features, leading to a scheme for simple constructions of kernel matrices. As a proof of principle, on a dataset of 356 subjects from the Alzheimer's Disease Neuroimaging Initiative study, we report good performance on several statistical inference tasks without any feature selection, dimensionality reduction, or parameter tuning.

Enhanced brain responsiveness during active emotional face processing in obsessive compulsive disorder

OBJECTIVES. The abnormal processing of emotional stimuli is common to a variety of psychiatric disorders. Specifically, patients with prominent anxiety symptoms generally overreact to emotional cues, which has been linked to increased amygdala activation. However, in OCD, enhanced responses are predominantly obtained using disease-specific stimuli and preferentially involve frontostriatal systems. METHODS. We assessed 21 OCD patients and 21 healthy controls with fMRI during an emotional face-processing paradigm involving active response generation to test for alterations in both brain activation and task-induced functional connectivity of the frontal cortex, the amygdala and the fusiform face area. RESULTS. OCD patients showed significantly greater activation of "face-processing" regions including the amygdala, fusiform gyrus and dorsolateral prefrontal cortex. The reciprocal connectivity between face-processing regions was enhanced in OCD. Importantly, we detected significant correlations between patients' clinical symptom severity and both task-related region activation and network functional connectivity. CONCLUSIONS. The results suggest that OCD patients may show enhanced brain responsiveness during emotional face-processing when tasks involve active response generation. Our findings diverge from previously described alterations in anxiety disorders, as patients showed enhanced amygdala-prefrontal connectivity as opposed to negative reciprocal interaction. This pattern would appear to be disorder-specific and was significantly related to obsessive-compulsive symptom severity.

Patient classification as an outlier detection problem: an application of the One-Class Support Vector Machine

Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers.

Functional alterations of large-scale brain networks related to cognitive control in obsessive-compulsive disorder

OBJECTIVES

Neuroimaging studies have consistently implicated alterations of the basal ganglia and orbitofrontal cortex in the pathophysiology of OCD, however, recent work also emphasizes more diffuse patterns of brain alteration as occurring in this disorder. The goal of this study was to extend such observations by investigating large-scale brain functional network correlates of cognitive-control performance in OCD patients.

EXPERIMENTAL DESIGN

We combined fMRI with a validated task of cognitive control and a multivariate statistical method to assess multiple functional networks encompassing broad task-relevant cortical regions in OCD patients and matched controls. Functional networks of interest were targeted a priori and the groups were compared in terms of the spatiotemporal profile of network responses (functional connectivity) during the task performance in a data-driven manner.

PRINCIPAL OBSERVATIONS

Task performance was equivalent in both groups and each distinct network demonstrated strong overlap in its general response during task. However, significant differences in functional connectivity were also observed between groups that appeared driven by specific phases of task performance. Such differences were most pronounced during rest-task transitions and mainly involved dorsal anterior cingulate and insular cortices within the paralimbic network. Relative heightened functional connectivity of insula in patients during task correlated with a measure of patients' state anxiety.

CONCLUSIONS

Our findings provide a novel functional imaging characterization of brain network alterations associated with cognitive-control in OCD. Additionally, these findings raise questions about the role of patients' arousal states on the performance of cognitive imaging tasks that are otherwise assumed to be emotionally neutral.

Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population

Alzheimer's Disease (AD) and other neurodegenerative diseases affect over 20 million people worldwide, and this number is projected to significantly increase in the coming decades. Proposed imaging-based markers have shown steadily improving levels of sensitivity/specificity in classifying individual subjects as AD or normal. Several of these efforts have utilized statistical machine learning techniques, using brain images as input, as means of deriving such AD-related markers. A common characteristic of this line of research is a focus on either (1) using a single imaging modality for classification, or (2) incorporating several modalities, but reporting separate results for each. One strategy to improve on the success of these methods is to leverage all available imaging modalities together in a single automated learning framework. The rationale is that some subjects may show signs of pathology in one modality but not in another-by combining all available images a clearer view of the progression of disease pathology will emerge. Our method is based on the Multi-Kernel Learning (MKL) framework, which allows the inclusion of an arbitrary number of views of the data in a maximum margin, kernel learning framework. The principal innovation behind MKL is that it learns an optimal combination of kernel (similarity) matrices while simultaneously training a classifier. In classification experiments MKL outperformed an SVM trained on all available features by 3%-4%. We are especially interested in whether such markers are capable of identifying early signs of the disease. To address this question, we have examined whether our multi-modal disease marker (MMDM) can predict conversion from Mild Cognitive Impairment (MCI) to AD. Our experiments reveal that this measure shows significant group differences between MCI subjects who progressed to AD, and those who remained stable for 3 years. These differences were most significant in MMDMs based on imaging data. We also discuss the relationship between our MMDM and an individual's conversion from MCI to AD.

Estimating local surface complexity maps using spherical harmonic reconstructions

Cortical surface complexity is a potential structural marker for certain diseases such as schizophrenia. In this study, we developed a measure of fractal dimension (FD) calculated from lowpass-filtered spherical harmonic brain surface reconstructions. A local FD measure was also computed at each vertex in a cortical surface mesh, visualizing local variations in surface complexity over the brain surface. We analyzed the surface complexity for 87 patients with DSM-IV schizophrenia (with stable psychopathology and treated with antipsychotic medication) and 108 matched healthy controls. The global FD for the right hemisphere in the schizophrenic group was significantly lower than that in controls. Local FD maps showed that the lower complexity was mainly due to differences in the prefrontal cortex.

Variations in the shape of the frontobasal brain region in obsessive-compulsive disorder

Obsessive-compulsive disorder (OCD) emerges during childhood through young adulthood coinciding with the late phases of postnatal brain development when fine remodeling of brain anatomy takes place. Previous research has suggested the existence of subtle anatomical alterations in OCD involving focal volume variations in different brain regions including the frontal lobes and basal ganglia. We investigated whether anatomical changes might also involve variations in the shape of the frontobasal region. A total of 101 OCD patients and 101 control subjects were examined using magnetic resonance imaging. A cross-sectional image highly representative of frontal-basal ganglia anatomy was selected in each individual and 25 reliable anatomical landmarks were identified to assess shape changes. A pixel-wise morphing approach was also used to dynamically illustrate the findings. We found significant group differences for overall landmark position and for most individual landmarks delimiting the defined frontobasal region. OCD patients showed a deformation pattern involving shortening of the anterior-posterior dimension of the frontal lobes and basal ganglia, and enlargement of cerebrospinal fluid spaces around the frontal opercula. In addition, we observed significant correlation of brain tissue shape variation with frontal sinus size. Identification of a global change in the shape of the frontobasal region may further contribute to characterizing the nature of brain alterations in OCD. The coincidence of brain shape variations with morphological changes in the frontal sinus indicates a potential association of OCD to late development disturbances, as the frontal sinus macroscopically emerges during the transition between childhood and adulthood.

Voxel-wise meta-analysis of grey matter changes in obsessive-compulsive disorder

BACKGROUND

Specific cortico-striato-thalamic circuits are hypothesised to mediate the symptoms of obsessive-compulsive disorder (OCD), but structural neuroimaging studies have been inconsistent.

AIMS

To conduct a meta-analysis of published and unpublished voxel-based morphometry studies in OCD.

METHOD

Twelve data-sets comprising 401 people with OCD and 376 healthy controls met inclusion criteria. A new improved voxel-based meta-analytic method, signed differential mapping (SDM), was developed to examine regions of increased and decreased grey matter volume in the OCD group v. control group. Results No between-group differences were found in global grey matter volumes. People with OCD had increased regional grey matter volumes in bilateral lenticular nuclei, extending to the caudate nuclei, as well as decreased volumes in bilateral dorsal medial frontal/anterior cingulate gyri. A descriptive analysis of quartiles, a sensitivity analysis as well as analyses of subgroups further confirmed these findings. Meta-regression analyses showed that studies that included individuals with more severe OCD were significantly more likely to report increased grey matter volumes in the basal ganglia. No effect of current antidepressant treatment was observed. Conclusions The results support a dorsal prefrontal-striatal model of the disorder and raise the question of whether functional alterations in other brain regions commonly associated with OCD, such as the orbitofrontal cortex, may reflect secondary compensatory strategies. Whether the reported differences between participants with OCD and controls precede the onset of the symptoms and whether they are specific to OCD remains to be established.

Endophenotypes of obsessive-compulsive disorder: rationale, evidence and future potential

Obsessive-compulsive disorder (OCD) is a heritable and debilitating neuropsychiatric condition. Attempts to delineate genetic contributions have met with limited success, and there is an ongoing search for intermediate trait or vulnerability markers rooted in the neurosciences. Such markers would be valuable for detecting people at risk of developing the condition, clarifying etiological factors and targeting novel treatments. This review begins with brief coverage of the epidemiology of OCD, and presents a hierarchical model of the condition. The advantages of neuropsychological assessment and neuroimaging as objective measures of brain integrity and function are discussed. We describe the concept of endophenotypes and examples of their successful use in medicine and psychiatry. Key areas of focus in the search for OCD endophenotypes are identified, such as measures of inhibitory control and probes of the integrity of orbitofrontal and posterior parietal cortices. Finally, we discuss exciting findings in unaffected first-degree relatives of patients with OCD that have led to the identification of several candidate endophenotypes of the disorder, with important implications for neurobiological understanding and treatment of this and related conditions.