A neuroimaging measure to capture heterogeneous patterns of atrophy in Parkinson's disease and dementia with Lewy bodies.

INTRODUCTION: Parkinson's disease (PD) and Dementia with Lewy bodies (DLB) show heterogeneous brain atrophy patterns which group-average analyses fail to capture. Neuroanatomical normative modelling overcomes this by comparing individuals to a large reference cohort. Patient-specific atrophy patterns are measured objectively and summarised to index overall neurodegeneration (the 'total outlier count'). We aimed to quantify patterns of neurodegenerative dissimilarity in participants with PD and DLB and evaluate the potential clinical relevance of total outlier count by testing its association with key clinical measures in PD and DLB. MATERIALS AND METHODS: We included 108 participants with PD and 61 with DLB. PD participants were subclassified into high and low visual performers as this has previously been shown to stratify those at increased dementia risk. We generated z-scores from T1w-MRI scans for each participant relative to normative regional cortical thickness and subcortical volumes, modelled in a reference cohort (n = 58,836). Outliers (z < -1.96) were aggregated across 169 brain regions per participant. To measure dissimilarity, individuals' Hamming distance scores were calculated. We also examined total outlier counts between high versus low visual performance in PD; and PD versus DLB; and tested associations between these and cognition. RESULTS: There was significantly greater inter-individual dissimilarity in brain-outlier patterns in PD poor compared to high visual performers (W = 522.5; p < 0.01) and in DLB compared to PD (W = 5649; p < 0.01). PD poor visual performers had significantly greater total outlier counts compared to high (ß = -4.73 (SE = 1.30); t = -3.64; p < 0.01) whereas a conventional group-level GLM failed to identify differences. Higher total outlier counts were associated with poorer MoCA (ß = -0.55 (SE = 0.27), t = -2.04, p = 0.05) and composite cognitive scores (ß = -2.01 (SE = 0.79); t = -2.54; p = 0.02) in DLB, and visuoperception (ß = -0.67 (SE = 0.19); t = -3.59; p < 0.01), in PD. CONCLUSIONS: Neuroanatomical normative modelling shows promise as a clinically informative technique in PD and DLB, where patterns of atrophy are variable.

Predicting long-term outcome of Internet-delivered cognitive behavior therapy for social anxiety disorder using fMRI and support vector machine learning.

Cognitive behavior therapy (CBT) is an effective treatment for social anxiety disorder (SAD), but many patients do not respond sufficiently and a substantial proportion relapse after treatment has ended. Predicting an individual's long-term clinical response therefore remains an important challenge. This study aimed at assessing neural predictors of long-term treatment outcome in participants with SAD 1 year after completion of Internet-delivered CBT (iCBT). Twenty-six participants diagnosed with SAD underwent iCBT including attention bias modification for a total of 13 weeks. Support vector machines (SVMs), a supervised pattern recognition method allowing predictions at the individual level, were trained to separate long-term treatment responders from nonresponders based on blood oxygen level-dependent (BOLD) responses to self-referential criticism. The Clinical Global Impression-Improvement scale was the main instrument to determine treatment response at the 1-year follow-up. Results showed that the proportion of long-term responders was 52% (12/23). From multivariate BOLD responses in the dorsal anterior cingulate cortex (dACC) together with the amygdala, we were able to predict long-term response rate of iCBT with an accuracy of 92% (confidence interval 95% 73.2-97.6). This activation pattern was, however, not predictive of improvement in the continuous Liebowitz Social Anxiety Scale-Self-report version. Follow-up psychophysiological interaction analyses revealed that lower dACC-amygdala coupling was associated with better long-term treatment response. Thus, BOLD response patterns in the fear-expressing dACC-amygdala regions were highly predictive of long-term treatment outcome of iCBT, and the initial coupling between these regions differentiated long-term responders from nonresponders. The SVM-neuroimaging approach could be of particular clinical value as it allows for accurate prediction of treatment outcome at the level of the individual.

Using structural neuroanatomy to identify trauma survivors with and without post-traumatic stress disorder at the individual level.

BACKGROUND: At present there are no objective, biological markers that can be used to reliably identify individuals with post-traumatic stress disorder (PTSD). This study assessed the diagnostic potential of structural magnetic resonance imaging (sMRI) for identifying trauma-exposed individuals with and without PTSD. METHOD: sMRI scans were acquired from 50 survivors of the Sichuan earthquake of 2008 who had developed PTSD, 50 survivors who had not developed PTSD and 40 healthy controls who had not been exposed to the earthquake. Support vector machine (SVM), a multivariate pattern recognition technique, was used to develop an algorithm that distinguished between the three groups at an individual level. The accuracy of the algorithm and its statistical significance were estimated using leave-one-out cross-validation and permutation testing. RESULTS: When survivors with PTSD were compared against healthy controls, both grey and white matter allowed discrimination with an accuracy of 91% (p < 0.001). When survivors without PTSD were compared against healthy controls, the two groups could be discriminated with accuracies of 76% (p < 0.001) and 85% (p < 0.001) based on grey and white matter, respectively. Finally, when survivors with and without PTSD were compared directly, grey matter allowed discrimination with an accuracy of 67% (p < 0.001); in contrast the two groups could not be distinguished based on white matter. CONCLUSIONS: These results reveal patterns of neuroanatomical alterations that could be used to inform the identification of trauma survivors with and without PTSD at the individual level, and provide preliminary support to the development of SVM as a clinically useful diagnostic aid.

Examination of the predictive value of structural magnetic resonance scans in bipolar disorder: a pattern classification approach.

BACKGROUND: Bipolar disorder (BD) is one of the leading causes of disability worldwide. Patients are further disadvantaged by delays in accurate diagnosis ranging between 5 and 10 years. We applied Gaussian process classifiers (GPCs) to structural magnetic resonance imaging (sMRI) data to evaluate the feasibility of using pattern recognition techniques for the diagnostic classification of patients with BD. METHOD: GPCs were applied to gray (GM) and white matter (WM) sMRI data derived from two independent samples of patients with BD (cohort 1: n = 26; cohort 2: n = 14). Within each cohort patients were matched on age, sex and IQ to an equal number of healthy controls. RESULTS: The diagnostic accuracy of the GPC for GM was 73% in cohort 1 and 72% in cohort 2; the sensitivity and specificity of the GM classification were respectively 69% and 77% in cohort 1 and 64% and 99% in cohort 2. The diagnostic accuracy of the GPC for WM was 69% in cohort 1 and 78% in cohort 2; the sensitivity and specificity of the WM classification were both 69% in cohort 1 and 71% and 86% respectively in cohort 2. In both samples, GM and WM clusters discriminating between patients and controls were localized within cortical and subcortical structures implicated in BD. CONCLUSIONS: Our results demonstrate the predictive value of neuroanatomical data in discriminating patients with BD from healthy individuals. The overlap between discriminative networks and regions implicated in the pathophysiology of BD supports the biological plausibility of the classifiers.

Multivariate decoding of brain images using ordinal regression.

Neuroimaging data are increasingly being used to predict potential outcomes or groupings, such as clinical severity, drug dose response, and transitional illness states. In these examples, the variable (target) we want to predict is ordinal in nature. Conventional classification schemes assume that the targets are nominal and hence ignore their ranked nature, whereas parametric and/or non-parametric regression models enforce a metric notion of distance between classes. Here, we propose a novel, alternative multivariate approach that overcomes these limitations - whole brain probabilistic ordinal regression using a Gaussian process framework. We applied this technique to two data sets of pharmacological neuroimaging data from healthy volunteers. The first study was designed to investigate the effect of ketamine on brain activity and its subsequent modulation with two compounds - lamotrigine and risperidone. The second study investigates the effect of scopolamine on cerebral blood flow and its modulation using donepezil. We compared ordinal regression to multi-class classification schemes and metric regression. Considering the modulation of ketamine with lamotrigine, we found that ordinal regression significantly outperformed multi-class classification and metric regression in terms of accuracy and mean absolute error. However, for risperidone ordinal regression significantly outperformed metric regression but performed similarly to multi-class classification both in terms of accuracy and mean absolute error. For the scopolamine data set, ordinal regression was found to outperform both multi-class and metric regression techniques considering the regional cerebral blood flow in the anterior cingulate cortex. Ordinal regression was thus the only method that performed well in all cases. Our results indicate the potential of an ordinal regression approach for neuroimaging data while providing a fully probabilistic framework with elegant approaches for model selection.

Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level.

BACKGROUND: Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM. METHOD: Three age- and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested. RESULTS: Successful classification accuracies (p < 0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%). CONCLUSIONS: The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.

PRoNTo: pattern recognition for neuroimaging toolbox.

In the past years, mass univariate statistical analyses of neuroimaging data have been complemented by the use of multivariate pattern analyses, especially based on machine learning models. While these allow an increased sensitivity for the detection of spatially distributed effects compared to univariate techniques, they lack an established and accessible software framework. The goal of this work was to build a toolbox comprising all the necessary functionalities for multivariate analyses of neuroimaging data, based on machine learning models. The "Pattern Recognition for Neuroimaging Toolbox" (PRoNTo) is open-source, cross-platform, MATLAB-based and SPM compatible, therefore being suitable for both cognitive and clinical neuroscience research. In addition, it is designed to facilitate novel contributions from developers, aiming to improve the interaction between the neuroimaging and machine learning communities. Here, we introduce PRoNTo by presenting examples of possible research questions that can be addressed with the machine learning framework implemented in PRoNTo, and cannot be easily investigated with mass univariate statistical analysis.

Test-retest reliability of the BOLD pharmacological MRI response to ketamine in healthy volunteers.

The pharmacological MRI (phMRI) technique is being increasingly used in both pre-clinical and clinical models to investigate pharmacological effects on task-free brain function. Ketamine, an N-methyl-d-aspartate receptor (NMDAR) antagonist, induces a strong phMRI response and represents a promising pharmacological model to investigate the role of glutamatergic abnormalities in psychiatric symptomatology. The aim of this study was to assess whether the brain response to ketamine is reliable in order to validate ketamine phMRI as a mechanistic marker of glutamatergic dysfunction and to determine its utility in repeated measures designs to detect the modulatory effect of other drugs. Thus we assessed the test-retest reliability of the brain response to ketamine in healthy volunteers and identified an optimal modelling approach with reliability as our selection criterion. PhMRI data were collected from 10 healthy male participants, at rest, on two separate occasions. Subanaesthetic doses of I.V. ketamine infusion (target plasma levels 50 ng/mL and 75 ng/mL) were administered in both sessions. Test-retest reliability of the ketamine phMRI response was assessed voxel-wise and on pre-defined ROIs for a range of temporal design matrices including different combinations of nuisance regressors designed to model shape variance, linear drift and head motion. Effect sizes are also reported. All models showed a significant and widespread response to low-dose ketamine in predicted cerebral networks and as expected, increasing the number of model parameters improved model fit. Reliability of the predefined ROIs differed between the different models assessed. Using reliability as the selection criterion, a model capturing subject motion and linear drift performed the best across two sessions. The anatomical distribution of effects for all models was consistent with results of previous imaging studies in humans with BOLD signal increases in regions including midline cingulate and supracingulate cortex, thalamus, insula, anterior temporal lobe and ventrolateral prefrontal structures, and BOLD signal decreases in the subgenual cingulate cortex. This study represents the first investigation of the test-retest reliability of the BOLD phMRI response to acute ketamine challenge. All models tested were effective at describing the ketamine response although the design matrix associated with the highest reliability may represent a robust and well-characterised ketamine phMRI assay more suitable for repeated-measures designs. This ketamine assay is applicable as a model of neurotransmitter dysfunction suitable as a pharmacodynamic imaging tool to test and validate modulatory interventions, as a model of NMDA hypofunction in psychiatric disorders, and may be adapted to understand potential antidepressant and analgesic effects of NMDAR antagonists.

PROBABILISTIC PREDICTION OF NEUROLOGICAL DISORDERS WITH A STATISTICAL ASSESSMENT OF NEUROIMAGING DATA MODALITIES.

For many neurological disorders, prediction of disease state is an important clinical aim. Neuroimaging provides detailed information about brain structure and function from which such predictions may be statistically derived. A multinomial logit model with Gaussian process priors is proposed to: (i) predict disease state based on whole-brain neuroimaging data and (ii) analyze the relative informativeness of different image modalities and brain regions. Advanced Markov chain Monte Carlo methods are employed to perform posterior inference over the model. This paper reports a statistical assessment of multiple neuroimaging modalities applied to the discrimination of three Parkinsonian neurological disorders from one another and healthy controls, showing promising predictive performance of disease states when compared to nonprobabilistic classifiers based on multiple modalities. The statistical analysis also quantifies the relative importance of different neuroimaging measures and brain regions in discriminating between these diseases and suggests that for prediction there is little benefit in acquiring multiple neuroimaging sequences. Finally, the predictive capability of different brain regions is found to be in accordance with the regional pathology of the diseases as reported in the clinical literature.