Search

Background Disruptive behavior disorders (DBD) are heterogeneous at the clinical and the biological level. Therefore, the aims were to dissect the heterogeneous neurodevelopmental deviations of the affective brain circuitry and provide an integration of these differences across modalities. Methods We combined two novel approaches. First, normative modeling to map deviations from the typical age-related pattern at the level of the individual of (i) activity during emotion matching and (ii) of anatomical images derived from DBD cases (n = 77) and controls (n = 52) aged 8–18 years from the EU-funded Aggressotype and MATRICS consortia. Second, linked independent component analysis to integrate subject-specific deviations from both modalities. Results While cases exhibited on average a higher activity than would be expected for their age during face processing in regions such as the amygdala when compared to controls these positive deviations were widespread at the individual level. A multimodal integration of all functional and anatomical deviations explained 23% of the variance in the clinical DBD phenotype. Most notably, the top marker, encompassing the default mode network (DMN) and subcortical regions such as the amygdala and the striatum, was related to aggression across the whole sample. Conclusions Overall increased age-related deviations in the amygdala in DBD suggest a maturational delay, which has to be further validated in future studies. Further, the integration of individual deviation patterns from multiple imaging modalities allowed to dissect some of the heterogeneity of DBD and identified the DMN, the striatum and the amygdala as neural signatures that were associated with aggression., Psychological Medicine, 53 (9), ISSN:0033-2917, ISSN:1469-8978

Normative modeling is an emerging and innovative framework for mapping individual differences at the level of a single subject or observation in relation to a reference model. It involves charting centiles of variation across a population in terms of mappings between biology and behavior which can then be used to make statistical inferences at the level of the individual. The fields of computational psychiatry and clinical neuroscience have been slow to transition away from patient versus “healthy” control analytic approaches, likely due to a lack of tools designed to properly model biological heterogeneity of mental disorders. Normative modeling provides a solution to address this issue and moves analysis away from case-control comparisons that rely on potentially noisy clinical labels. In this article, we define a standardized protocol to guide users through, from start to finish, normative modeling analysis using the Predictive Clinical Neuroscience toolkit (PCNtoolkit). We describe the input data selection process, provide intuition behind the various modeling choices, and conclude by demonstrating several examples of down-stream analyses the normative model results may facilitate, such as stratification of high-risk individuals, subtyping, and behavioral predictive modeling. The protocol takes approximately 1-3 hours to complete.

Defining reference models for population variation, and the ability to study individual deviations is essential for understanding inter-individual variability and its relation to the onset and progression of medical conditions. In this work, we assembled a reference cohort of neuroimaging data from 82 sites (N=58,836; ages 2-100) and use normative modeling to characterize lifespan trajectories of cortical thickness and subcortical volume. Models are validated against a manually quality checked subset (N=24,354) and we provide an interface for transferring to new data sources. We showcase the clinical value by applying the models to a transdiagnostic psychiatric sample (N=1,985), showing they can be used to quantify variability underlying multiple disorders whilst also refining case-control inferences. These models will be augmented with additional samples and imaging modalities as they become available. This provides a common reference platform to bind results from different studies and ultimately paves the way for personalized clinical decision making.

Normative modeling aims to quantify the degree to which an individual’s brain deviates from a reference sample with respect to one or more variables, which can be used as a potential biomarker of a healthy brain and as a tool to study heterogeneity of psychiatric disorders. The application of normative models is hindered by methodological challenges and lacks standards for the usage and evaluation of normative models. In this paper, we present generalized additive models for location scale and shape (GAMLSS) for normative modeling of neuroimaging data, a flexible modeling framework that can model heteroskedasticity, non-linear effects of variables, and hierarchical structure of the data. It can model non-Gaussian distributions, and it allows for an automatic model order selection, thus improving the accuracy of normative models while mitigating problems of overfitting. Furthermore, we describe measures and diagnostic tools suitable for evaluating normative models and step-by-step examples of normative modeling, including fitting several candidate models, selecting the best models, and transferring them to new scan sites.

Contains fulltext : 208606.pdf (Publisher’s version ) (Open Access) Normative models are a class of emerging statistical techniques useful for understanding the heterogeneous biology underlying psychiatric disorders at the level of the individual participant. Analogous to normative growth charts used in paediatric medicine for plotting child development in terms of height or weight as a function of age, normative models chart variation in clinical cohorts in terms of mappings between quantitative biological measures and clinically relevant variables. An emerging body of literature has demonstrated that such techniques are excellent tools for parsing the heterogeneity in clinical cohorts by providing statistical inferences at the level of the individual participant with respect to the normative range. Here, we provide a unifying review of the theory and application of normative modelling for understanding the biological and clinical heterogeneity underlying mental disorders. We first provide a statistically grounded yet non-technical overview of the conceptual underpinnings of normative modelling and propose a conceptual framework to link the many different methodological approaches that have been proposed for this purpose. We survey the literature employing these techniques, focusing principally on applications of normative modelling to quantitative neuroimaging-based biomarkers in psychiatry and, finally, we provide methodological considerations and recommendations to guide future applications of these techniques. We show that normative modelling provides a means by which the importance of modelling individual differences can be brought from theory to concrete data analysis procedures for understanding heterogeneous mental disorders and ultimately a promising route towards precision medicine in psychiatry.

BackgroundThe present paper presents a fundamentally novel approach to model individual differences of persons with the same biologically heterogeneous mental disorder. Unlike prevalent case-control analyses, that assume a clear distinction between patient and control groups and thereby introducing the concept of an ‘average patient’, we describe each patient's biology individually, gaining insights into the different facets that characterize persistent attention-deficit/hyperactivity disorder (ADHD).MethodsUsing a normative modeling approach, we mapped inter-individual differences in reference to normative structural brain changes across the lifespan to examine the degree to which case-control analyses disguise differences between individuals.ResultsAt the level of the individual, deviations from the normative model were frequent in persistent ADHD. However, the overlap of more than 2% between participants with ADHD was only observed in few brain loci. On average, participants with ADHD showed significantly reduced gray matter in the cerebellum and hippocampus compared to healthy individuals. While the case-control differences were in line with the literature on ADHD, individuals with ADHD only marginally reflected these group differences.ConclusionsCase-control comparisons, disguise inter-individual differences in brain biology in individuals with persistent ADHD. The present results show that the ‘average ADHD patient’ has limited informative value, providing the first evidence for the necessity to explore different biological facets of ADHD at the level of the individual and practical means to achieve this end.

The striatum receives dense dopaminergic projections making it a key region of the dopaminergic system. Its dysfunction has been implicated in various conditions including Parkinson’s disease and substance use disorder. However, the investigation of dopamine-specific functioning in humans is problematic as the striatum is highly interconnected and current MRI approaches are unable to differentiate between dopaminergic and other projections. Here, we demonstrate that “connectopic mapping” –a novel approach for characterizing fine-grained and overlapping modes of functional connectivity– can be used to map dopaminergic projections and as such, enables the investigation of dopamine-related functioning both in health and disease.We applied connectopic mapping to resting-state functional MRI data of the Human Connectome Project (population cohort; N=839) and selected the second-order striatal connectivity mode for further analyses. We first validated its specificity to dopaminergic projections by demonstrating a very high spatial correlation (r=0.884) with dopamine transporter availability –a marker of dopaminergic projections– derived from DaT-SPECT scans of 209 healthy control subjects of the Parkinson’s Progression Markers Initiative. Next, we obtained the subject-specific second-order modes from 20 controls, and 39 Parkinson’s disease patients scanned under placebo and under dopamine replacement therapy (L-DOPA), and show that our proposed marker of dopamine function indeed tracks Parkinson’s disease diagnosis, symptom severity and sensitivity to L-DOPA. Finally, across 30 daily alcohol users and 38 daily smokers of the Human Connectome Project, we establish strong associations between the second-order striatal connectivity mode and self-reported weekly use of alcohol and nicotine.Our findings provide compelling evidence that the second-order mode of functional connectivity in striatum maps onto dopaminergic projections, tracks inter-individual differences in symptom severity and L-DOPA sensitivity in Parkinson’s disease patients, and exhibits strong associations with levels of nicotine and alcohol use in a population-based cohort. We hereby provide a new biomarker for dopamine-related dysfunction in the human brain with potential clinical utility that could foster insights into the neurobiological underpinnings of various dopamine-associated conditions.

Current neuroimaging acquisition and processing approaches tend to be optimised for quality rather than speed. However, rapid acquisition and processing of neuroimaging data can lead to novel neuroimaging paradigms, such as adaptive acquisition, where rapidly processed data is used to inform subsequent image acquisition steps. Here we first evaluate the impact of several processing steps on the processing time and quality of registration of manually labelled T1-weighted MRI scans. Subsequently, we apply the selected rapid processing pipeline both to rapidly acquired multicontrast EPImix scans of 95 participants (which include T1-FLAIR, T2, T2*, T2-FLAIR, DWI & ADC contrasts, acquired in ∼1 minute), as well as to slower, more standard single-contrast T1-weighted scans of a subset of 66 participants. We quantify the correspondence between EPImix and single-contrast T1-weighted scans, using correlations between voxels and regions of interest across participants, measures of within- and between-participant identifiability as well as regional structural covariance networks. Furthermore, we explore the use of EPImix for the rapid construction of morphometric similarity networks. Finally, we quantify the reliability of EPImix-derived data using test-retest scans of 10 participants. Our results demonstrate that quantitative information can be derived from a neuroimaging scan acquired and processed within minutes, which could further be used to implement adaptive multimodal imaging and tailor neuroimaging examinations to individual patients.Abstract FigureGraphical abstract.

The potential of normative modeling to make individualized predictions from neuroimaging data has enabled inferences that go beyond the case-control approach. However, site effects are often confounded with variables of interest in a complex manner and can bias estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compared the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange) data set in our experiments. In addition, we used data from individuals with autism to test whether our models are able to retain clinically useful information while removing site effects. We compared the proposed single stage hierarchical Bayesian method to several harmonization techniques commonly used to deal with additive and multiplicative site effects using a two stage regression, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance related to age and sex as biological variation of interest. In addition, we made predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method showed the best predictive performance according to multiple metrics. Beyond that, the resulting z-scores showed little to no residual site effects, yet still retained clinically useful information. In contrast, performance was particularly poor for the regression model and the ComBat model in which age and sex were not explicitly modeled. In all two stage harmonization models, predictions were poorly scaled, suffering from a loss of more than 90 % of the original variance. Our results show the value of hierarchical Bayesian regression methods for accommodating site variation in neuroimaging data, which provides an alternative to harmonization techniques. While the approach we propose may have broad utility, our approach is particularly well suited to normative modelling where the primary interest is in accurate modelling of inter-subject variation and statistical quantification of deviations from a reference model.1HighlightsDevelopment and presentation of normative modeling approach based on hierarchical Bayesian modeling that can be applied to large multi-site neuroimaging data sets.Comparison of performance of Hierarchical Bayesian model including site as predictor to several common ways to harmonize for multi-site effects.Presentation of normative modeling as site correction tool.

Machine learning predictive models are being used in neuroimaging to predict information about the task or stimuli or to identify potentially clinically useful biomarkers. However, the predictions can be driven by confounding variables unrelated to the signal of interest, such as scanner effect or head motion, limiting the clinical usefulness and interpretation of machine learning models. The most common method to control for confounding effects is regressing out the confounding variables separately from each input variable before machine learning modeling. However, we show that this method is insufficient because machine learning models can learn information from the data that cannot be regressed out. Instead of regressing out confounding effects from each input variable, we propose controlling for confounds post-hoc on the level of machine learning predictions. This allows partitioning of the predictive performance into the performance that can be explained by confounds and performance independent of confounds. This approach is flexible and allows for parametric and non-parametric confound adjustment. We show in real and simulated data that this method correctly controls for confounding effects even when traditional input variable adjustment produces false-positive findings.

The complexity of social interactions is a defining property of the human species. Many social neuroscience experiments have sought to map ‘perspective taking’, ‘empathy’, and other canonical psychological constructs to distinguishable brain circuits. This predominant research paradigm was seldom complemented by bottom-up studies of the unknown sources of variation that add up to measures of social brain structure; perhaps due to a lack of large population datasets. We aimed at a systematic de-construction of social brain morphology into its elementary building blocks in the UK Biobank cohort (n=~10,000). Coherent patterns of structural co-variation were explored within a recent atlas of social brain locations, enabled through translating autoencoder algorithms from deep learning. The artificial neural networks learned rich subnetwork representations that became apparent from social brain variation at population scale. The learned subnetworks carried essential information about the co-dependence configurations between social brain regions, with the nucleus accumbens, medial prefrontal cortex, and temporoparietal junction embedded at the core. Some of the uncovered subnetworks contributed to predicting examined social traits in general, while other subnetworks helped predict specific facets of social functioning, such as feelings of loneliness. Our population-level evidence indicates that hidden subsystems of the social brain underpin interindividual variation in dissociable aspects of social lifestyle.

BackgroundAutism Spectrum Disorder (henceforth ‘autism’) is a highly heterogeneous neurodevelopmental condition with few effective treatments for core and associated features. To make progress we need to both identify and validate neural markers that help to parse heterogeneity to tailor therapies to specific neurobiological profiles. Atypical hemispheric lateralization is a stable feature across studies in autism, however its potential of lateralization as a neural stratification marker has not been widely examined.MethodsIn order to dissect heterogeneity in lateralization in autism, we used the large EU-AIMS Longitudinal European Autism Project dataset comprising 352 individuals with autism and 233 neurotypical (NT) controls as well as a replication dataset from ABIDE (513 autism, 691 NT) using a promising approach that moves beyond mean-group comparisons. We derived grey matter voxelwise laterality values for each subject and modelled individual deviations from the normative pattern of brain laterality across age using normative modeling.ResultsResults showed that individuals with autism had highly individualized patterns of both extreme right- and leftward deviations, particularly in language-, motor- and visuospatial regions, associated with symptom severity. Language delay (LD) explained most variance in extreme rightward patterns, whereas core autism symptom severity explained most variance in extreme leftward patterns. Follow-up analyses showed that a stepwise pattern emerged with individuals with autism with LD showing more pronounced rightward deviations than autism individuals without LD.ConclusionOur analyses corroborate the need for novel (dimensional) approaches to delineate the heterogeneous neuroanatomy in autism, and indicate atypical lateralization may constitute a neurophenotype for clinically meaningful stratification in autism.

Population variability in social lifestyle is reflected in brain morphology in sex-dependent ways., In human and nonhuman primates, sex differences typically explain much interindividual variability. Male and female behaviors may have played unique roles in the likely coevolution of increasing brain volume and more complex social dynamics. To explore possible divergence in social brain morphology between men and women living in different social environments, we applied probabilistic generative modeling to ~10,000 UK Biobank participants. We observed strong volume effects especially in the limbic system but also in regions of the sensory, intermediate, and higher association networks. Sex-specific brain volume effects in the limbic system were linked to the frequency and intensity of social contact, such as indexed by loneliness, household size, and social support. Across the processing hierarchy of neural networks, different conditions for social interplay may resonate in and be influenced by brain anatomy in sex-dependent ways.

See Duerden and Thompson (doi:10.1093/brain/awz421) for a scientific commentary on this article. Interpreting neonatal clinical neuroimaging is challenging due to rapid brain maturation over short periods. O'Muircheartaigh et al. use statistical modelling to build growth curves of tissue intensity and shape, and show that focal white matter injuries present as deviations from these curves in individual neonates., Premature birth occurs during a period of rapid brain growth. In this context, interpreting clinical neuroimaging can be complicated by the typical changes in brain contrast, size and gyrification occurring in the background to any pathology. To model and describe this evolving background in brain shape and contrast, we used a Bayesian regression technique, Gaussian process regression, adapted to multiple correlated outputs. Using MRI, we simultaneously estimated brain tissue intensity on T1- and T2-weighted scans as well as local tissue shape in a large cohort of 408 neonates scanned cross-sectionally across the perinatal period. The resulting model provided a continuous estimate of brain shape and intensity, appropriate to age at scan, degree of prematurity and sex. Next, we investigated the clinical utility of this model to detect focal white matter injury. In individual neonates, we calculated deviations of a neonate’s observed MRI from that predicted by the model to detect punctate white matter lesions with very good accuracy (area under the curve > 0.95). To investigate longitudinal consistency of the model, we calculated model deviations in 46 neonates who were scanned on a second occasion. These infants’ voxelwise deviations from the model could be used to identify them from the other 408 images in 83% (T2-weighted) and 76% (T1-weighted) of cases, indicating an anatomical fingerprint. Our approach provides accurate estimates of non-linear changes in brain tissue intensity and shape with clear potential for radiological use.

Network connectivity fingerprints are among today's best choices to obtain a faithful sampling of an individual's brain and cognition. Widely available MRI scanners can provide rich information tapping into network recruitment and reconfiguration that now scales to hundreds and thousands of humans. Here, we contemplate the advantages of analysing such connectome profiles using Bayesian strategies. These analysis techniques afford full probability estimates of the studied network coupling phenomena, provide analytical machinery to separate epistemological uncertainty and biological variability in a coherent manner, usher us towards avenues to go beyond binary statements on existence versus non-existence of an effect, and afford credibility estimates around all model parameters at play which thus enable single-subject predictions with rigorous uncertainty intervals. We illustrate the brittle boundary between healthy and diseased brain circuits by autism spectrum disorder as a recurring theme where, we argue, network-based approaches in neuroscience will require careful probabilistic answers. This article is part of the theme issue ‘Unifying the essential concepts of biological networks: biological insights and philosophical foundations’.

Patients with major depressive disorder (MDD) show heterogeneous treatment response and highly variable clinical trajectories: while some patients experience swift recovery, others show relapsing-remitting or chronic courses. Predicting individual clinical trajectories at an early stage is a key challenge for psychiatry and might facilitate individually tailored interventions. So far, however, reliable predictors at the single-patient level are absent. Here, we evaluated the utility of a machine learning strategy – generative embedding (GE) – which combines interpretable generative models with discriminative classifiers. Specifically, we used functional magnetic resonance imaging (fMRI) data of emotional face perception in 85 MDD patients from the NEtherlands Study of Depression and Anxiety (NESDA) who had been followed up over two years and classified into three subgroups with distinct clinical trajectories. Combining a generative model of effective (directed) connectivity with support vector machines (SVMs), we could predict whether a given patient would experience chronic depression vs. fast remission with a balanced accuracy of 79%. Gradual improvement vs. fast remission could still be predicted above-chance, but less convincingly, with a balanced accuracy of 61%. Generative embedding outperformed classification based on conventional (descriptive) features, such as functional connectivity or local activation estimates, which were obtained from the same data and did not allow for above-chance classification accuracy. Furthermore, predictive performance of GE could be assigned to a specific network property: the trial-by-trial modulation of connections by emotional content. Given the limited sample size of our study, the present results are preliminary but may serve as proof-of-concept, illustrating the potential of GE for obtaining clinical predictions that are interpretable in terms of network mechanisms. Our findings suggest that abnormal dynamic changes of connections involved in emotional face processing might be associated with higher risk of developing a less favorable clinical course., NeuroImage: Clinical, 26, ISSN:2213-1582

The meaning of a sentence can be understood, whether presented in written or spoken form. Therefore, it is highly probable that brain processes supporting language comprehension are at least partly independent of sensory modality. To identify where and when in the brain language processing is independent of sensory modality, we directly compared neuromagnetic brain signals of 200 human subjects (102 males) either reading or listening to sentences. We used multiset canonical correlation analysis to align individual subject data in a way that boosts those aspects of the signal that are common to all, allowing us to capture word-by-word signal variations, consistent across subjects and at a fine temporal scale. Quantifying this consistency in activation across both reading and listening tasks revealed a mostly left-hemispheric cortical network. Areas showing consistent activity patterns included not only areas previously implicated in higher-level language processing, such as left prefrontal, superior and middle temporal areas, and anterior temporal lobe, but also parts of the control network as well as subcentral and more posterior temporal-parietal areas. Activity in this supramodal sentence-processing network starts in temporal areas and rapidly spreads to the other regions involved. The findings indicate not only the involvement of a large network of brain areas in supramodal language processing but also that the linguistic information contained in the unfolding sentences modulates brain activity in a word-specific manner across subjects.SIGNIFICANCE STATEMENTThe brain can extract meaning from written and spoken messages alike. This requires activity of both brain circuits capable of processing sensory modality-specific aspects of the input signals as well as coordinated brain activity to extract modality-independent meaning from the input. Using traditional methods, it is difficult to disentangle modality-specific activation from modality-independent activation. In this work, we developed and applied a multivariate methodology that allows for a direct quantification of sensory modality-independent brain activity, revealing fast activation of a wide network of brain areas, both including and extending beyond the core network for language.

The expanding behavioral repertoire of the developing brain during childhood and adolescence is shaped by complex brain–environment interactions and flavored by unique life experiences. The transition into young adulthood offers opportunities for adaptation and growth but also increased susceptibility to environmental perturbations, such as the characteristics of social relationships, family environment, quality of schools and activities, financial security, urbanization and pollution, drugs, cultural practices, and values, that all act in concert with our genetic architecture and biology. Our multivariate brain–behavior mapping in 7,577 children aged 9 to 11 y across 585 brain imaging phenotypes and 617 cognitive, behavioral, psychosocial, and socioeconomic measures revealed three population modes of brain covariation, which were robust as assessed by cross-validation and permutation testing, taking into account siblings and twins, identified using genetic data. The first mode revealed traces of perinatal complications, including preterm and twin birth, eclampsia and toxemia, shorter period of breastfeeding, and lower cognitive scores, with higher cortical thickness and lower cortical areas and volumes. The second mode reflected a pattern of sociocognitive stratification, linking lower cognitive ability and socioeconomic status to lower cortical thickness, area, and volumes. The third mode captured a pattern related to urbanicity, with particulate matter pollution (PM 25 ) inversely related to home value, walkability, and population density, associated with diffusion properties of white matter tracts. These results underscore the importance of a multidimensional and interdisciplinary understanding, integrating social, psychological, and biological sciences, to map the constituents of healthy development and to identify factors that may precede maladjustment and mental illness.

Background Sociocommunicative difficulties, including abnormalities in eye contact, are core diagnostic features of autism spectrum disorder (ASD). Many studies have used eye tracking to measure reduced attention to faces in autistic people; however, most of this work has not taken advantage of eye-tracking temporal resolution to examine temporal profiles of attention. Methods We used growth curve analysis to model attention to static social scenes as a function of time in a large (N = 650) sample of autistic participants and neurotypical participants across a wide age range (6–30 years). Results The model yielded distinct temporal profiles of attention to faces in the groups. Initially, both groups showed a relatively high probability of attending to faces, followed by decline after several seconds. The neurotypical participants, however, were significantly more likely to return their attention to faces in the latter part of each 20-second trial, with increasing probability with age. In contrast, the probability of returning to the face in the autistic participants remained low across development. In participants with ASD, more atypical profiles of attention were associated with lower Vineland Adaptive Behavior Scales communication scores and a higher curvature in one data-driven cluster correlated with symptom severity. Conclusions These findings show that social attention not only is reduced in ASD, but also differs in its temporal dynamics. The neurotypical participants became more sophisticated in how they deployed their social attention across age, a pattern that was significantly reduced in the participants with ASD, possibly reflecting delayed acquisition of social expertise.

Importance Schizophrenia and bipolar disorder are severe and complex brain disorders characterized by substantial clinical and biological heterogeneity. However, case-control studies often ignore such heterogeneity through their focus on the average patient, which may be the core reason for a lack of robust biomarkers indicative of an individual’s treatment response and outcome. Objectives To investigate the degree to which case-control analyses disguise interindividual differences in brain structure among patients with schizophrenia and bipolar disorder and to map the brain alterations linked to these disorders at the level of individual patients. Design, Setting, and Participants This study used cross-sectional, T1-weighted magnetic resonance imaging data from participants recruited for the Thematically Organized Psychosis study from October 27, 2004, to October 17, 2012. Data were reanalyzed in 2017 and 2018. Patients were recruited from inpatient and outpatient clinics in the Oslo area of Norway, and healthy individuals from the same catchment area were drawn from the national population registry. Main Outcomes and Measures Interindividual differences in brain structure among patients with schizophrenia and bipolar disorder. Voxel-based morphometry maps were computed, which were used for normative modeling to map the range of interindividual differences in brain structure. Results This study included 218 patients with schizophrenia spectrum disorders (mean [SD] age, 30 [9.3] years; 126 [57.8%] male), of whom 163 had schizophrenia (mean [SD] age, 31 [8.7] years; 105 [64.4%] male) and 190 had bipolar disorder (mean [SD] age, 34 [11.3] years; 79 [41.6%] male), and 256 healthy individuals (mean [SD] age, 34 [9.5] years; 140 [54.7%] male). At the level of the individual, deviations from the normative model were frequent in both disorders but highly heterogeneous. Overlap of more than 2% among patients was observed in only a few loci, primarily in frontal, temporal, and cerebellar regions. The proportion of alterations was associated with diagnosis and cognitive and clinical characteristics within clinical groups. Patients with schizophrenia, on average, had significantly reduced gray matter in frontal regions, cerebellum, and temporal cortex. In patients with bipolar disorder, mean deviations were primarily present in cerebellar regions. Conclusions and Relevance This study found that group-level differences disguised biological heterogeneity and interindividual differences among patients with the same diagnosis. This finding suggests that the idea of the average patient is a noninformative construct in psychiatry that falls apart when mapping abnormalities at the level of the individual patient. This study presents a workable route toward precision medicine in psychiatry.

Contains fulltext : 175106.pdf (Publisher’s version ) (Open Access) There is evidence that the human cerebellum is involved not only in motor control but also in other cognitive functions. Several studies have shown that language-related activation is lateralized toward the right cerebellar hemisphere in most people, in accordance with leftward cerebral cortical lateralization for language and a general contralaterality of cerebral-cerebellar activations. In terms of behavior, hand use elicits asymmetrical activation in the cerebellum, while hand preference is weakly associated with language lateralization. However, it is not known how, or whether, these functional relations are reflected in anatomy. We investigated volumetric gray matter asymmetries of cerebellar lobules in an MRI data set comprising 2226 subjects. We tested these cerebellar asymmetries for associations with handedness, and for correlations with cerebral cortical anatomical asymmetries of regions important for language or hand motor control, as defined by two different automated image analysis methods and brain atlases, and supplemented with extensive visual quality control. No significant associations of cerebellar asymmetries to handedness were found. Some significant associations of cerebellar lobular asymmetries to cerebral cortical asymmetries were found, but none of these correlations were greater than 0.14, and they were mostly method-/atlas-dependent. On the basis of this large and highly powered study, we conclude that there is no overt structural manifestation of cerebellar functional lateralization and connectivity, in respect of hand motor control or language laterality.

Preterm-born children are at increased risk of lifelong neurodevelopmental difficulties. Group-wise analyses of magnetic resonance imaging show many differences between preterm- and term-born infants but do not reliably predict neurocognitive prognosis for individual infants. This might be due to the unrecognized heterogeneity of cerebral injury within the preterm group. This study aimed to determine whether atypical brain microstructural development following preterm birth is significantly variable between infants. Using Gaussian process regression, a technique that allows a single-individual inference, we characterized typical variation of brain microstructure using maps of fractional anisotropy and mean diffusivity in a sample of 270 term-born neonates. Then, we compared 82 preterm infants to these normative values to identify brain regions with atypical microstructure and relate observed deviations to degree of prematurity and neurocognition at 18 months. Preterm infants showed strikingly heterogeneous deviations from typical development, with little spatial overlap between infants. Greater and more extensive deviations, captured by a whole brain atypicality index, were associated with more extreme prematurity and predicted poorer cognitive and language abilities at 18 months. Brain microstructural development after preterm birth is highly variable between individual infants. This poorly understood heterogeneity likely relates to both the etiology and prognosis of brain injury. ispartof: Cerebral Cortex vol:30 issue:9 pages:4800-4810 ispartof: location:United States status: Published online

The expanding behavioral repertoire of the developing brain during childhood and adolescence is shaped by complex brain-environment interactions and flavored by unique life experiences. The transition into young adulthood offer opportunities for adaptation and growth, but also increased susceptibility to environmental perturbations, such as the characteristics of social relationships, family environment, quality of schools and activities, financial security, urbanization and pollution, drugs, cultural practices, and values, that all act in concert with our genetic architecture and biology. Our multivariate brain-behavior mapping in 7,577 children aged 9-11 years across 585 brain imaging phenotypes, and 617 cognitive, behavioral, psychosocial and socioeconomic measures revealed three population modes of brain co-variation, which were robust as assessed by cross-validation and permutation testing, taking into account siblings and twins, identified using genetic data. The first mode revealed traces of perinatal complications, including pre-term and twin-birth, eclampsia and toxemia, shorter period of breast feeding and lower cognitive scores, with higher cortical thickness and lower cortical areas and volumes. The second mode reflected a pattern of socio-cognitive stratification, linking lower cognitive ability and socioeconomic status to lower cortical thickness, area and volumes. The third mote captured a pattern related to urbanicity, with particulate matter pollution (PM25) inversely related to home value, walkability and population density, associated with diffusion properties of white matter tracts. These results underscore the importance of a multidimensional and interdisciplinary understanding, integrating social, psychological and biological sciences, to map the constituents of healthy development and to identify factors that may precede maladjustment and mental illness.

Contains fulltext : 208638.pdf (Publisher’s version ) (Closed access) Pattern classification and stratification approaches have increasingly been used in research on Autism Spectrum Disorder (ASD) over the last ten years with the goal of translation towards clinical applicability. Here, we present an extensive scoping literature review on those two approaches. We screened a total of 635 studies, of which 57 pattern classification and 19 stratification studies were included. We observed large variance across pattern classification studies in terms of predictive performance from about 60% to 98% accuracy, which is among other factors likely linked to sampling bias, different validation procedures across studies, the heterogeneity of ASD and differences in data quality. Stratification studies were less prevalent with only two studies reporting replications and just a few showing external validation. While some identified strata based on cognition and intelligence reappear across studies, biology as a stratification marker is clearly underexplored. In summary, mapping biological differences at the level of the individual with ASD is a major challenge for the field now. Conceptualizing those mappings and individual trajectories that lead to the diagnosis of ASD, will become a major challenge in the near future.

Pattern recognition predictive models have become an important tool for analysis of neuroimaging data and answering important questions from clinical and cognitive neuroscience. Regardless of the application, the most commonly used method to quantify model performance is to calculate prediction accuracy, i.e. the proportion of correctly classified samples. While simple and intuitive, other performance measures are often more appropriate with respect to many common goals of neuroimaging pattern recognition studies. In this paper, we will review alternative performance measures and focus on their interpretation and practical aspects of model evaluation. Specifically, we will focus on 4 families of performance measures: 1) categorical performance measures such as accuracy, 2) rank based performance measures such as the area under the curve, 3) probabilistic performance measures based on quadratic error such as Brier score, and 4) probabilistic performance measures based on information criteria such as logarithmic score. We will examine their statistical properties in various settings using simulated data and real neuroimaging data derived from public datasets. Results showed that accuracy had the worst performance with respect to statistical power, detecting model improvement, selecting informative features and reliability of results. Therefore in most cases, it should not be used to make statistical inference about model performance. Accuracy should also be avoided for evaluating utility of clinical models, because it does not take into account clinically relevant information, such as relative cost of false-positive and false-negative misclassification or calibration of probabilistic predictions. We recommend alternative evaluation criteria with respect to the goals of a specific machine learning model.

Cognitive abilities and mental disorders are complex traits sharing a largely unknown neuronal basis and aetiology. Their genetic architectures are highly polygenic and overlapping, which is supported by heterogeneous phenotypic expression and substantial clinical overlap. Brain network analysis provides a non-invasive means of dissecting biological heterogeneity yet its sensitivity, specificity and validity in clinical applications remains a major challenge. We used machine learning on static and dynamic temporal synchronization between all brain network nodes in 10,343 healthy individuals from the UK Biobank to predict (i) cognitive and mental health traits and (ii) their genetic underpinnings. We predicted age and sex to serve as our reference point. The traits of interest included individual level educational attainment and fluid intelligence (cognitive) and dimensional measures of depression, anxiety, and neuroticism (mental health). We predicted polygenic scores for educational attainment, fluid intelligence, depression, anxiety, and different neuroticism traits, in addition to schizophrenia. Beyond high accuracy for age and sex, permutation tests revealed above chance-level prediction accuracy for educational attainment and fluid intelligence. Educational attainment and fluid intelligence were mainly negatively associated with static brain connectivity in frontal and default mode networks, whereas age showed positive correlations with a more widespread pattern. In comparison, prediction accuracy for polygenic scores was at chance level across traits, which may serve as a benchmark for future studies aiming to link genetic factors and fMRI-based brain connectomics.SignificanceAlthough cognitive abilities and susceptibility to mental disorders reflect individual differences in brain function, neuroimaging is yet to provide a coherent account of the neuronal underpinnings. Here, we aimed to map the brain functional connectome of (i) cognitive and mental health traits and (ii) their polygenic architecture in a large population-based sample. We discovered high prediction accuracy for age and sex, and above-chance accuracy for educational attainment and intelligence (cognitive). In contrast, accuracies for dimensional measures of depression, anxiety and neuroticism (mental health), and polygenic scores across traits, were at chance level. These findings support the link between cognitive abilities and brain connectomics and provide a reference for studies mapping the brain connectomics of mental disorders and their genetic architectures.

In most areas of medicine, biological tests are routinely used to assist diagnosis and treatment allocation. However, this is not the case in psychiatry, which is now one of the last areas of medicine where diseases are still diagnosed based on symptoms and biological tests to assist treatment allocation remain to be developed. Heterogeneity is widely recognized as a major challenge toward achieving these objectives and many approaches to tackle such heterogeneity have been proposed over the years, largely aiming to partition psychiatric disorders into more consistent subtypes. However, none of these stratifications have translated toward clinical practice. Here, we review the different approaches employed, focusing on methods that use biological measures to stratify psychiatric disorders. We highlight several recent prominent studies and identify key challenges for the field. Specifically, we argue that a lack of validation or replication of prospective stratifications coupled with a widespread fixation on finding sharply defined subtypes has impeded progress. We outline recently proposed methodological innovations that may be useful to move forward. Many of these innovations provide inferences at the level of individual participants and do not rest on the assumption that the biological fingerprints underlying psychiatric disorders can be cleanly separated into subtypes.

BackgroundThe neuroanatomical basis of autism spectrum disorder (ASD) has remained elusive, mostly due to high biological and clinical heterogeneity among diagnosed individuals. Despite considerable effort towards understanding ASD using neuroimaging biomarkers, heterogeneity remains a barrier, partly because studies mostly employ case-control approaches, which assume that the clinical group is homogeneous.MethodsHere, we used an innovative normative modelling approach to parse biological heterogeneity in ASD. We aimed to dissect the neuroanatomy of ASD by mapping the deviations from a typical pattern of neuroanatomical development at the level of the individual and to show the necessity to look beyond the case-control paradigm to understand the neurobiology of ASD. We first estimated a vertex-wise normative model of cortical thickness development using Gaussian process regression, then mapped the deviation of each participant from the typical pattern. For this we employed a heterogeneous cross-sectional sample of 206 typically developing (TD) individuals (127 male), and 321 individuals (232 male) with ASD (aged 6-31).ResultsWe found few case-control differences but the ASD cohort showed highly individualized patterns of deviations in cortical thickness that were widespread across the brain. These deviations correlated with severity of repetitive behaviors and social communicative symptoms, although only repetitive behaviors survived corrections for multiple testing.ConclusionsOur results: (i) reinforce the notion that individuals with ASD show distinct, highly individualized trajectories of brain development and (ii) show that by focusing on common effects (i.e. the ‘average ASD participant’), the case-control approach disguises considerable inter-individual variation crucial for precision medicine.

Background: Mental disorders and individual characteristics such as intelligence and personality are complex traits sharing a largely unknown neuronal basis. Their genetic architectures are highly polygenic and overlapping, which is supported by heterogeneous phenotypic expression and substantial clinical overlap. Brain network analysis provides a non-invasive means of dissecting biological heterogeneity yet its sensitivity, specificity and validity in assessing individual characteristics relevant for brain function and mental health and their genetic underpinnings in clinical applications remains a challenge. Methods: In a machine learning approach, we predicted individual scores for educational attainment, fluid intelligence and dimensional measures of depression, anxiety and neuroticism using fMRI-based static and dynamic temporal synchronization between large-scale brain network nodes in 10,343 healthy individuals from the UK Biobank. In addition to age and sex to serve as our reference point, we also predicted individual polygenic scores for related phenotypes, and 13 different neuroticism traits and schizophrenia. Results: Beyond high accuracy for age and sex, supporting the biological sensitivity of the connectome-based features, permutation tests revealed above chance-level prediction accuracy for trait-level educational attainment and fluid intelligence. Educational attainment and fluid intelligence were mainly negatively associated with static brain connectivity in frontal and default mode networks, whereas age showed positive correlations with a more widespread pattern. In contrast, prediction accuracy was at chance level for depression, anxiety, neuroticism and polygenic scores across traits. Conclusion: These novel findings provide a benchmark for future studies linking the genetic architecture of individual and mental health traits with fMRI-based brain connectomics. The authors were funded by the Research Council of Norway (213837, 223723, 229129, 204966, 249795), the South-Eastern Norway Regional Health Authority (2014097, 2015073, 2016083, 2017112), the European Research Council under the European Union’s Horizon 2020 research and innovation program (ERC StG, Grant 802998), the Department of Psychology, University of Oslo and the KG Jebsen Stiftelsen.

BackgroundA diagnosis of dissociative identity disorder (DID) is controversial and prone to under- and misdiagnosis. From the moment of seeking treatment for symptoms to the time of an accurate diagnosis of DID individuals received an average of four prior other diagnoses and spent 7 years, with reports of up to 12 years, in mental health services.AimTo investigate whether data-driven pattern recognition methodologies applied to structural brain images can provide biomarkers to aid DID diagnosis.MethodStructural brain images of 75 participants were included: 32 female individuals with DID and 43 matched healthy controls. Individuals with DID were recruited from psychiatry and psychotherapy out-patient clinics. Probabilistic pattern classifiers were trained to discriminate cohorts based on measures of brain morphology.ResultsThe pattern classifiers were able to accurately discriminate between individuals with DID and healthy controls with high sensitivity (72%) and specificity (74%) on the basis of brain structure. These findings provide evidence for a biological basis for distinguishing between DID-affected and healthy individuals.ConclusionsWe propose a pattern of neuroimaging biomarkers that could be used to inform the identification of individuals with DID from healthy controls at the individual level. This is important and clinically relevant because the DID diagnosis is controversial and individuals with DID are often misdiagnosed. Ultimately, the application of pattern recognition methodologies could prevent unnecessary suffering of individuals with DID because of an earlier accurate diagnosis, which will facilitate faster and targeted interventions.Declaration of interestThe authors declare no competing financial interests.

Longitudinal imaging biomarkers are invaluable for understanding the course of neurodegeneration, promising the ability to track disease progression and to detect disease earlier than cross-sectional biomarkers. To properly realize their potential, biomarker trajectory models must be robust to both under-sampling and measurement errors and should be able to integrate multi-modal information to improve trajectory inference and prediction. Here we present a parametric Bayesian multi-task learning based approach to modeling univariate trajectories across subjects that addresses these criteria.Our approach learns multiple subjects’ trajectories within a single model that allows for different types of information sharing, i.e.coupling, across subjects. It optimizes a combination of uncoupled, fully coupled and kernel coupled models. Kernel-based coupling allows linking subjects’ trajectories based on one or more biomarker measures. We demonstrate this using Alzheimer’s Disease Neuroimaging Initiative (ADNI) data, where we model longitudinal trajectories of MRI-derived cortical volumes in neurodegeneration, with coupling based on APOE genotype, cerebrospinal fluid (CSF) and amyloid PET-based biomarkers. In addition to detecting established disease effects, we detect disease related changes within the insula that have not received much attention within the literature.Due to its sensitivity in detecting disease effects, its competitive predictive performance and its ability to learn the optimal parameter covariance from data rather than choosing a specific set of random and fixed effects a priori, we propose that our model can be used in place of or in addition to linear mixed effects models when modeling biomarker trajectories. A software implementation of the method is publicly available.

Attention-deficit/hyperactivity disorder (ADHD) is one of the most prevalent and heritable psychiatric disorders. While previous studies have focussed on mapping focal or connectivity differences at the group level, the present study employed pattern recognition to quantify group separation between unaffected siblings, participants with ADHD, and healthy controls on the basis of spatially distributed brain activations. This was achieved using an fMRI-adapted version of the Stop-Signal Task in a sample of 103 unaffected siblings, 184 participants with ADHD, and 128 healthy controls. We used activation maps derived from three task regressors as features in our analyses employing a Gaussian process classifier. We showed that unaffected siblings could be distinguished from participants with ADHD (area under the receiver operating characteristic curve (AUC) = 0.65, p = 0.002, 95% Modified Wald CI: 0.59–0.71 AUC) and healthy controls (AUC = 0.59, p = 0.030, 95% Modified Wald CI: 0.52–0.66 AUC), although the latter did not survive correction for multiple comparisons. Further, participants with ADHD could be distinguished from healthy controls (AUC = 0.64, p = 0.001, 95% Modified Wald CI: 0.58–0.70 AUC). Altogether the present results characterise a pattern of frontolateral, superior temporal and inferior parietal expansion that is associated with risk for ADHD. Unaffected siblings show differences primarily in frontolateral regions. This provides evidence for a neural profile shared between participants with ADHD and their healthy siblings., Highlights • Multivariate profile of risk shared between ADHD patients and unaffected siblings • Pattern of risk in frontolateral, superior temporal and inferior parietal regions • Benchmark estimate of classification performance in heterogeneous samples

BackgroundPsychiatric disorders are highly heterogeneous, defined based on symptoms with little connection to potential underlying biological mechanisms. A possible approach to dissect biological heterogeneity is to look for biologically meaningful subtypes. A recent study Drysdale et al. (2017) showed promising results along this line by simultaneously using resting state fMRI and clinical data and identified four distinct subtypes of depression with different clinical profiles and abnormal resting state fMRI connectivity. These subtypes were predictive of treatment response to transcranial magnetic stimulation therapy.ObjectiveHere, we attempted to replicate the procedure followed in the Drysdale et al. study and their findings in an independent dataset of a clinically more heterogeneous sample of 187 participants with depression and anxiety. We aimed to answer the following questions: 1) Using the same procedure, can we find a statistically significant and reliable relationship between brain connectivity and clinical symptoms? 2) Is the observed relationship similar to the one found in the original study? 3) Can we identify distinct and reliable subtypes? 4) Do they have similar clinical profiles as the subtypes identified in the original study?MethodsWe followed the original procedure as closely as possible, including a canonical correlation analysis to find a low dimensional representation of clinically relevant resting state fMRI features, followed by hierarchical clustering to identify subtypes. We extended the original procedure using additional statistical tests, to test the statistical significance of the relationship between resting state fMRI and clinical data, and the existence of distinct subtypes. Furthermore, we examined the stability of the whole procedure using resampling.Results and ConclusionWe were not able to replicate the findings of the original study. Relationships between brain connectivity and clinical symptoms were not statistically significant and we also did not find clearly distinct subtypes of depression. We argue, that based on our rigorous approach and in-depth review of the original results, that the evidence for the existence of the distinct resting state connectivity based subtypes of depression is weak and should be interpreted with caution.

Background Psychiatric disorders are highly heterogeneous, defined based on symptoms with little connection to potential underlying biological mechanisms. A possible approach to dissect biological heterogeneity is to look for biologically meaningful subtypes. A recent study Drysdale et al. (2017) showed promising results along this line by simultaneously using resting state fMRI and clinical data and identified four distinct subtypes of depression with different clinical profiles and abnormal resting state fMRI connectivity. These subtypes were predictive of treatment response to transcranial magnetic stimulation therapy. Objective Here, we attempted to replicate the procedure followed in the Drysdale et al. study and their findings in a different clinical population and a more heterogeneous sample of 187 participants with depression and anxiety. We aimed to answer the following questions: 1) Using the same procedure, can we find a statistically significant and reliable relationship between brain connectivity and clinical symptoms? 2) Is the observed relationship similar to the one found in the original study? 3) Can we identify distinct and reliable subtypes? 4) Do they have similar clinical profiles as the subtypes identified in the original study? Methods We followed the original procedure as closely as possible, including a canonical correlation analysis to find a low dimensional representation of clinically relevant resting state fMRI features, followed by hierarchical clustering to identify subtypes. We extended the original procedure using additional statistical tests, to test the statistical significance of the relationship between resting state fMRI and clinical data, and the existence of distinct subtypes. Furthermore, we examined the stability of the whole procedure using resampling. Results and conclusion As in the original study, we found extremely high canonical correlations between functional connectivity and clinical symptoms, and an optimal three-cluster solution. However, neither canonical correlations nor clusters were statistically significant. On the basis of our extensive evaluations of the analysis methodology used and within the limits of comparison of our sample relative to the sample used in Drysdale et al., we argue that the evidence for the existence of the distinct resting state connectivity-based subtypes of depression should be interpreted with caution.

Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by deficits in social interaction and communication, as well as repetitive and restrictive behaviors. The etiological and phenotypic complexity of ASD have so far hindered the development of clinically useful biomarkers for the condition. Neuroimaging studies have been valuable in establishing a biological basis for ASD. Increasingly, neuroimaging has been combined with ‘machine learning’ based pattern classification methods to make individual diagnostic predictions. Moving forward, the hope is that these techniques may not only facilitate the diagnostic process, but may also aid in fractionating the ASD phenotype into more biologically homogeneous sub-groups; with defined pathophysiology, predictable outcomes and/or responses to targeted treatments and/or interventions. This review chapter will first introduce ‘machine learning’ and pattern recognition methods in general, with a focus on their application to diagnostic classification. It will highlight why such approaches to biomarker discovery may have advantages over more conventional analytical methods. Magnetic resonance imaging (MRI) findings of atypical brain structure, function, and connectivity in ASD will be briefly reviewed before we describe how pattern recognition has been applied to generate predictive models for ASD. Last, we will discuss some limitations and pitfalls of pattern recognition analyses in ASD, and consider how the field can advance beyond the prediction of binary outcomes.

Depression is among the leading causes of disability in industrialized countries [1]. To effectively target interventions for patients at risk for a worse long-term clinical outcome, there is a need to identify predictors of chronicity and remission at an early stage. Many clinical, psychological and biological variables have been linked to different course trajectories of depression. These findings, however, are based on group comparisons with unknown translational value. A variable that is statistically significantly different between groups does not necessarily carry sufficient predictive power at the individual level, e.g. because the average difference between groups may be small or because of a high degree of variation within each group. This study evaluated the prognostic value of a wide range of clinical, psychological and biological (markers related to somatic health, metabolic syndrome, inflammation and autonomic nervous system) characteristics for predicting the course of depression and aimed to identify the best set of predictors. We used data from the Netherlands Study of Depression and Anxiety (NESDA), including unipolar depression patients recruited from the community, primary care and specialized mental health care, thereby capturing a broad range of illness severity [2]. Unipolar depressed patients (major depressive disorder or dysthymia, N=804) were assessed on a panel of 81 clinical, psychological and biological measures and were clinically followed-up for 2 years. Subjects were grouped according to (i) the presence of a depression diagnosis at 2-year follow-up (yes N=397, no N=407), and (ii) three disease course trajectory groups (rapid remission, N=356, gradual improvement N=273, chronic N=175) identified by a latent class growth analysis [3]. We used a penalized logistic regression to predict depression course and a stability selection method to select the optimal set of significant predictor variables from the multivariate model. Using all clinical, psychological and biological predictors, we could discriminate between the three course trajectory groups; rapid remission (REM) with 0.69 AUROC and 66% balanced accuracy, the gradual improving (IMP) group with 0.62 AUROC and 60% balanced accuracy, and the chronic (CHR) group with 0.66 AUROC and 61% balanced accuracy. Furthermore, we could discriminate between patients with and without a unipolar depression diagnosis at two-year follow-up with 0.66 AUROC and 62% balanced accuracy. We identified the total score on the Inventory of Depressive Symptomatology (IDS)[4] as the most important predictor for the naturalistic course of depression, especially for predicting rapid remission with an AUROC of 0.66 (62% accuracy) and for predicting the presence of an MDD diagnosis at follow-up with an AUROC of 0.69 (66 % accuracy). Furthermore, The IDS total score is the only variable that survived family wise error correction (with pfwer Amongst a wide set of psychological, biological and clinical (anxiety and depression) variables no other measure improved the prediction accuracy that was obtained based on self-reported depressive symptoms (IDS scores) alone. However, our best model only showed moderate predictive performance at best, hence, the prediction model requires further improvements to be clinically useful.

Contains fulltext : 151732.pdf (Publisher’s version ) (Open Access) AbstractBackground A chronic course of major depressive disorder (MDD) is associated with profound alterations in brain volumes and emotional and cognitive processing. However, no neurobiological markers have been identified that prospectively predict MDD course trajectories. This study evaluated the prognostic value of different neuroimaging modalities, clinical characteristics, and their combination to classify MDD course trajectories. Methods One hundred eighteen MDD patients underwent structural and functional magnetic resonance imaging (MRI) (emotional facial expressions and executive functioning) and were clinically followed-up at 2 years. Three MDD trajectories (chronic n = 23, gradual improving n = 36, and fast remission n = 59) were identified based on Life Chart Interview measuring the presence of symptoms each month. Gaussian process classifiers were employed to evaluate prognostic value of neuroimaging data and clinical characteristics (including baseline severity, duration, and comorbidity). Results Chronic patients could be discriminated from patients with more favorable trajectories from neural responses to various emotional faces (up to 73% accuracy) but not from structural MRI and functional MRI related to executive functioning. Chronic patients could also be discriminated from remitted patients based on clinical characteristics (accuracy 69%) but not when age differences between the groups were taken into account. Combining different task contrasts or data sources increased prediction accuracies in some but not all cases. Conclusions Our findings provide evidence that the prediction of naturalistic course of depression over 2 years is improved by considering neuroimaging data especially derived from neural responses to emotional facial expressions. Neural responses to emotional salient faces more accurately predicted outcome than clinical data.

Subcortical brain structures are integral to motion, consciousness, emotions, and learning. We identified common genetic variation related to the volumes of nucleus accumbens, amygdala, brainstem, caudate nucleus, globus pallidus, putamen, and thalamus, using genome-wide association analyses in over 40,000 individuals from CHARGE, ENIGMA and the UK-Biobank. We show that variability in subcortical volumes is heritable, and identify 25 significantly associated loci (20 novel). Annotation of these loci utilizing gene expression, methylation, and neuropathological data identified 62 candidate genes implicated in neurodevelopment, synaptic signaling, axonal transport, apoptosis, and susceptibility to neurological disorders. This set of genes is significantly enriched for Drosophila orthologs associated with neurodevelopmental phenotypes, suggesting evolutionarily conserved mechanisms. Our findings uncover novel biology and potential drug targets underlying brain development and disease.

The dominant approach to neuroimaging data analysis employs the voxel as the unit of computation. While convenient, voxels lack biological meaning and their size is arbitrarily determined by the resolution of the image. Here, we propose a multivariate spatial model in which neuroimaging data are characterised as a linearly weighted combination of multiscale basis functions which map onto underlying brain nuclei or networks or nuclei. In this model, the elementary building blocks are derived to reflect the functional anatomy of the brain during the resting state. This model is estimated using a Bayesian framework which accurately quantifies uncertainty and automatically finds the most accurate and parsimonious combination of basis functions describing the data. We demonstrate the utility of this framework by predicting quantitative SPECT images of striatal dopamine function and we compare a variety of basis sets including generic isotropic functions, anatomical representations of the striatum derived from structural MRI, and two different soft functional parcellations of the striatum derived from resting-state fMRI (rfMRI). We found that a combination of ∼50 multiscale functional basis functions accurately represented the striatal dopamine activity, and that functional basis functions derived from an advanced parcellation technique known as Instantaneous Connectivity Parcellation (ICP) provided the most parsimonious models of dopamine function. Importantly, functional basis functions derived from resting fMRI were more accurate than both structural and generic basis sets in representing dopamine function in the striatum for a fixed model order. We demonstrate the translational validity of our framework by constructing classification models for discriminating parkinsonian disorders and their subtypes. Here, we show that ICP approach is the only basis set that performs well across all comparisons and performs better overall than the classical voxel-based approach. This spatial model constitutes an elegant alternative to voxel-based approaches in neuroimaging studies; not only are their atoms biologically informed, they are also adaptive to high resolutions, represent high dimensions efficiently, and capture long-range spatial dependencies, which are important and challenging objectives for neuroimaging data., Highlights • A multivariate spatial model using brain parcellations as basis functions is proposed. • Brain regions can be modeled as a superposition of multiscale basis functions. • These basis functions are biologically meaningful and capture spatial dependencies. • Our framework allows to develop accurate and parsimonious clinical models. • The model is computationally efficient, enhances power and adapts to high resolutions.

The hippocampal formation is a brain structure integrally involved in episodic memory, spatial navigation, cognition and stress responsiveness. Structural abnormalities in hippocampal volume and shape are found in several common neuropsychiatric disorders. To identify the genetic underpinnings of hippocampal structure here we perform a genome-wide association study (GWAS) of 33,536 individuals and discover six independent loci significantly associated with hippocampal volume, four of them novel. Of the novel loci, three lie within genes (ASTN2, DPP4 and MAST4) and one is found 200 kb upstream of SHH. A hippocampal subfield analysis shows that a locus within the MSRB3 gene shows evidence of a localized effect along the dentate gyrus, subiculum, CA1 and fissure. Further, we show that genetic variants associated with decreased hippocampal volume are also associated with increased risk for Alzheimer's disease (rg=-0.155). Our findings suggest novel biological pathways through which human genetic variation influences hippocampal volume and risk for neuropsychiatric illness., published version, peerReviewed

SummaryAnatomical tracing studies in non-human primates have suggested that corticostriatal connectivity is topographically organized: nearby locations in striatum are connected with nearby locations in cortex. The topographic organization of corticostriatal connectivity is thought to underpin many goal-directed behaviours, but these topographies have not been completely characterised in humans and their relationship to uniquely human behaviours remains to be fully determined. Instead, the dominant approach employs parcellations that cannot model the continuous nature of the topography, nor accommodate overlapping cortical projections in the striatum. Here, we employ a different approach to studying human corticostriatal circuitry: we estimate smoothly-varying and spatially overlapping ‘connection topographies’ from resting state fMRI. These correspond exceptionally well with and extend the topographies predicted from primate tracing studies. We show that striatal topography is preserved in regions not previously known to have topographic connections with the striatum and that many goal-directed behaviours can be mapped precisely onto individual variations in the spatial layout of striatal connectivity.

Contains fulltext : 193103.pdf (Publisher’s version ) (Open Access) Brain regions are often topographically connected: nearby locations within one brain area connect with nearby locations in another area. Mapping these connection topographies, or ‘connectopies’ in short, is crucial for understanding how information is processed in the brain. Here, we propose principled, fully data-driven methods for mapping connectopies using functional magnetic resonance imaging (fMRI) data acquired at rest by combining spectral embedding of voxel-wise connectivity ‘fingerprints’ with a novel approach to spatial statistical inference. We apply the approach in human primary motor and visual cortex, and show that it can trace biologically plausible, overlapping connectopies in individual subjects that follow these regions' somatotopic and retinotopic maps. As a generic mechanism to perform inference over connectopies, the new spatial statistics approach enables rigorous statistical testing of hypotheses regarding the fine-grained spatial profile of functional connectivity and whether that profile is different between subjects or between experimental conditions. The combined framework offers a fundamental alternative to existing approaches to investigating functional connectivity in the brain, from voxel- or seed-pair wise characterizations of functional association, towards a full, multivariate characterization of spatial topography.

Background: Attention-deficit/hyperactivity disorder (ADHD) is biologically heterogeneous, with different biological predispositions — mediated through developmental processes — converging upon a common clinical phenotype. Brain imaging studies have variably shown altered brain structure, activity and connectivity in children and adults with ADHD. Recent methodological developments allow for the integration of information across imaging modalities, potentially yielding a more coherent view regarding the biology underlying the disorder. Methods: We analyzed a sample of adults with persistent ADHD and healthy controls using an advanced multimodal linked independent component analysis approach. Diffusion and structural MRI data were fused to form imaging markers reflecting independent components that explain variation across modalities. We included these markers as predictors into logistic regression models on adult ADHD and put those into context with predictions of estimated intelligence, age and sex. Results: We included 87 adults with ADHD and 93 controls in our analysis. Participants’ courses associated with all imaging markers explained 27.86% of the variance in adult ADHD. No single imaging modality dominated this result. Instead, it was explained by aggregation of relatively small effects across several modalities and markers. One of the top markers for adult ADHD was multimodal and linked to morphological and microstructural effects within anterior temporal brain regions; another was linked to cortical thickness. Several markers were also influenced by estimated intelligence, age and/or sex. Limitations: Although complex analytical approaches, such as the one applied here, provide insight into otherwise hidden mechanisms, they also increase the complexity of interpretations. Conclusion: No dominant imaging modality or marker characterizes structural brain phenotypes in adults with ADHD, but we can refine our characterization of the disorder by the integration of small effects across modalities.

Decoding models based on pattern recognition (PR) are becoming increasingly important tools for neuroimaging data analysis. In contrast to alternative (mass-univariate) encoding approaches that use hierarchical models to capture inter-subject variability, inter-subject differences are not typically handled efficiently in PR. In this work, we propose to overcome this problem by recasting the decoding problem in a multi-task learning (MTL) framework. In MTL, a single PR model is used to learn different but related “tasks” simultaneously. The primary advantage of MTL is that it makes more efficient use of the data available and leads to more accurate models by making use of the relationships between tasks. In this work, we construct MTL models where each subject is modelled by a separate task. We use a flexible covariance structure to model the relationships between tasks and induce coupling between them using Gaussian process priors. We present an MTL method for classification problems and demonstrate a novel mapping method suitable for PR models. We apply these MTL approaches to classifying many different contrasts in a publicly available fMRI dataset and show that the proposed MTL methods produce higher decoding accuracy and more consistent discriminative activity patterns than currently used techniques. Our results demonstrate that MTL provides a promising method for multi-subject decoding studies by focusing on the commonalities between a group of subjects rather than the idiosyncratic properties of different subjects., Highlights • In mass-univariate analysis, mixed effects models can capture subject variability. • In pattern recognition (PR), subject variability is usually not modelled explicitly. • Multi-task learning (MTL) is proposed to accommodate subject variability in PR. • The proposed approach improves predictive accuracy and pattern reproducibility. • A novel brain mapping approach is also proposed for MTL and existing PR models.

Feature selection (FS) methods play two important roles in the context of neuroimaging based classification: potentially increase classification accuracy by eliminating irrelevant features from the model and facilitate interpretation by identifying sets of meaningful features that best discriminate the classes. Although the development of FS techniques specifically tuned for neuroimaging data is an active area of research, up to date most of the studies have focused on finding a subset of features that maximizes accuracy. However, maximizing accuracy does not guarantee reliable interpretation as similar accuracies can be obtained from distinct sets of features. In the current paper we propose a new approach for selecting features: SCoRS (survival count on random subsamples) based on a recently proposed Stability Selection theory. SCoRS relies on the idea of choosing relevant features that are stable under data perturbation. Data are perturbed by iteratively sub-sampling both features (subspaces) and examples. We demonstrate the potential of the proposed method in a clinical application to classify depressed patients versus healthy individuals based on functional magnetic resonance imaging data acquired during visualization of happy faces.