Search

Objective: The larger sample sizes available from multi-site publicly available neuroimaging data repositories makes machine-learning based diagnostic classification of mental disorders more feasible by alleviating the curse of dimensionality. However, since multi-site data are aggregated post-hoc, i.e. they were acquired from different scanners with different acquisition parameters, non-neural inter-site variability may mask inter-group differences that are at least in part neural in origin. Hence, the advantages gained by the larger sample size in the context of machine-learning based diagnostic classification may not be realized. Methods: We address this issue using harmonization of multi-site neuroimaging data using the ComBat technique, which is based on an empirical Bayes formulation to remove inter-site differences in data distributions, to improve diagnostic classification accuracy. Specifically, we demonstrate this using ABIDE (Autism Brain Imaging Data Exchange) multi-site data for classifying individuals with Autism from healthy controls using resting state fMRI-based functional connectivity data. Results: Our results show that higher classification accuracies across multiple classification models can be obtained (especially for models based on artificial neural networks) from multi-site data post harmonization with the ComBat technique as compared to without harmonization, outperforming earlier results from existing studies using ABIDE. Furthermore, our network ablation analysis facilitated important insights into autism spectrum disorder pathology and the connectivity in networks shown to be important for classification covaried with verbal communication impairments in Autism. Conclusion: Multi-site data harmonization using ComBat improves neuroimaging-based diagnostic classification of mental disorders. Significance: ComBat has the potential to make AI-based clinical decision-support systems more feasible in psychiatry.

Body dysmorphic disorder (BDD) is marked by preoccupation with misperceived appearance flaws. Previous functional magnetic resonance imaging (fMRI) studies have found reduced neural activity and connectivity of visual areas specialized for global/holistic visual processing in BDD [[1], [2], [3]], suggesting that aberrant dorsal visual system functioning might contribute to distorted perception. In this proof-of-concept study we tested if intermittent theta-burst stimulation (iTBS), a form of excitatory repetitive transcranial magnetic stimulation (rTMS), would enhance dorsal visual system utilization as quantified through dynamic effective connectivity (DEC) modeling [4]. This is a single-session study with the application of iTBS and an fMRI scan immediately afterwards (within 15 min after the stimulation). We hypothesized that those undergoing active iTBS would show enhanced connectivity in dorsal visual areas responsible for global/holistic visual processing compared with sham.

Various machine-learning classification techniques have been employed previously to classify brain states in healthy and disease populations using functional magnetic resonance imaging (fMRI). These methods generally use supervised classifiers that are sensitive to outliers and require labeling of training data to generate a predictive model. Density-based clustering, which overcomes these issues, is a popular unsupervised learning approach whose utility for high-dimensional neuroimaging data has not been previously evaluated. Its advantages include insensitivity to outliers and ability to work with unlabeled data. Unlike the popular k-means clustering, the number of clusters need not be specified. In this study, we compare the performance of two popular density-based clustering methods, DBSCAN and OPTICS, in accurately identifying individuals with three stages of cognitive impairment, including Alzheimer’s disease. We used static and dynamic functional connectivity features for clustering, which captures the strength and temporal variation of brain connectivity respectively. To assess the robustness of clustering to noise/outliers, we propose a novel method called recursive-clustering using additive-noise (R-CLAN). Results demonstrated that both clustering algorithms were effective, although OPTICS with dynamic connectivity features outperformed in terms of cluster purity (95.46%) and robustness to noise/outliers. This study demonstrates that density-based clustering can accurately and robustly identify diagnostic classes in an unsupervised way using brain connectivity.

Autism spectrum disorder (ASD) is a brain-based disorder characterized by social deficits and repetitive behaviors. Fast diagnostic prediction of ASD is important due to its prevalence: CDC estimates that 1 in 68 children has been identified with autism spectrum disorder. With the advancement in neuroimaging technology and AI, researchers have begun to build machine learning models that take the brain image of a patient as input, and predict whether he/she has ASD. A typical workflow is to preprocess a brain image into a network of connected brain regions, where indicative features are extracted using simple linear or convolutional models to be used for prediction. Recently, graph convolutional networks (GCNs) have become popular which can directly operate on graph data, such as the brain network. However, the recent work applying GCN for ASD prediction used a static population network which is not easy to use when the subject population updates. In this paper, we propose an ASD predictive model that applies GCN directly on a population-averaged brain network along with self-attention graph pooling, which can be easily applied to new patient diagnosis once trained, and it beats all existing models by a large margin in terms of accuracy (78% compared with the prior best, 70%, on the ABIDE-I database).

Objective Our study aimed to quantify structural changes in relation to metabolic abnormalities in the cerebellum, thalamus, and parietal cortex of patients with late-onset GM2-gangliosidosis (LOGG), which encompasses late-onset Tay-Sachs disease (LOTS) and Sandhoff disease (LOSD). Methods We enrolled 10 patients with LOGG (7 LOTS, 3 LOSD) who underwent a neurological assessment battery and 7 age-matched controls. Structural MRI and MRS were performed on a 3 T scanner. Structural volumes were obtained from FreeSurfer and normalized by total intracranial volume. Quantified metabolites included N-acetylaspartate (NAA), choline (Cho), myo-inositol (mI), creatine (Cr), and combined glutamate-glutamine (Glx). Metabolic concentrations were corrected for partial volume effects. Results Structural analyses revealed significant cerebellar atrophy in the LOGG cohort, which was primarily driven by LOTS patients. NAA was lower and mI higher in LOGG, but this was also significantly driven by the LOTS patients. Clinical ataxia deficits (via the Scale for the Assessment and Rating of Ataxia) were associated with neuronal injury (via NAA), neuroinflammation (via mI), and volumetric atrophy in the cerebellum. Interpretation The decrease of NAA in the cerebellum suggests that, in addition to cerebellar atrophy, there is ongoing impaired neuronal function and/or loss, while an increase in mI indicates possible neuroinflammation in LOGG (more so within the LOTS subvariant). Quantifying cerebellar atrophy in relation to neurometabolic differences in LOGG may lead to improvements in assessing disease severity, progression, and pharmacological efficacy. Lastly, additional neuroimaging studies in LOGG are required to contrast LOTS and LOSD more accurately.

This article provides data for five different neuropsychiatric disorders—Attention Deficit Hyperactivity Disorder, Alzheimer's Disease, Autism Spectrum Disorder, Post-Traumatic Stress Disorder, and Post-Concussion Syndrome–along with healthy controls. The data includes clinical diagnostic labels, phenotypic variables, and resting-state functional magnetic resonance imaging connectivity features obtained from individuals. In addition, it provides the source MATLAB codes used for data analyses. Three existing clustering methods have been incorporated into the provided code, which do not require a priori specification of the number of clusters. A genetic algorithm based feature selection method has also been included to find the relevant subset of features and clustering the subset of data simultaneously. Findings from this data set and further detailed interpretations are available in our recent research study (Zhao et al., 2017) [1]. This contribution is a valuable asset for performing unsupervised machine learning on fMRI data to investigate the correspondence of clinical diagnostic grouping with the underlying neurobiological/phenotypic clusters. Keywords: Functional magnetic resonance imaging, Functional connectivity, Effective connectivity, Unsupervised learning, Clustering, Genetic algorithm, Psychiatric disorders

Cognitive and emotional functions are supported by the coordinated activity of a distributed network of brain regions. This coordinated activity may be disrupted by psychosocial stress, resulting in the dysfunction of cognitive and emotional processes. Graph theory is a mathematical approach to assess coordinated brain activity that can estimate the efficiency of information flow and determine the centrality of brain regions within a larger distributed neural network. However, limited research has applied graph-theory techniques to the study of stress. Advancing our understanding of the impact stress has on global brain networks may provide new insight into factors that influence individual differences in stress susceptibility. Therefore, the present study examined the brain connectivity of participants that completed the Montreal Imaging Stress Task (Goodman et al., 2016; Wheelock et al., 2016). Salivary cortisol, heart rate, skin conductance response, and self-reported stress served as indices of stress, and trait anxiety served as an index of participant's disposition toward negative affectivity. Psychosocial stress was associated with a decrease in the efficiency of the flow of information within the brain. Further, the centrality of brain regions that mediate emotion regulation processes (i.e., hippocampus, ventral prefrontal cortex, and cingulate cortex) decreased during stress exposure. Interestingly, individual differences in cortisol reactivity were negatively correlated with the efficiency of information flow within this network, whereas cortisol reactivity was positively correlated with the centrality of the amygdala within the network. These findings suggest that stress reduces the efficiency of information transfer and leaves the function of brain regions that regulate the stress response vulnerable to disruption. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

BackgroundIn individuals with body dysmorphic disorder (BDD), selective attention biases and aberrant visual scanning patterns may cause imbalances in global vs. detailed visual processing, contributing to perceptual distortions for appearance. The mechanistic effects of modifying visual attention on brain function in BDD, which may be critical to developing perceptual-based treatments, have not been explored. This study tested the effects of visual-attention modulation on dorsal and ventral visual stream activation and connectivity, and eye behaviors.MethodsWe acquired functional magnetic resonance imaging data in 37 unmedicated adults with BDD and 30 controls. Participants viewed their faces under two conditions: a) unconstrained (naturalistically), and b) holding their gaze on the center of the image (visual-attention modulation), monitored with an eye-tracking camera. We analyzed activation and dynamic effective connectivity in dorsal and ventral visual streams and visual fixation duration.ResultsVisual-attention modulation resulted in longer fixation duration and reduced activation in dorsal and ventral visual streams in both groups compared with naturalistic viewing. Longer fixation duration was associated with greater effective connectivity from V1 to early dorsal visual stream during the second naturalistic viewing, across groups. During naturalistic viewing, there was greater V1 to early dorsal visual stream connectivity after, compared with before, visual-attention modulation.ConclusionsWhen viewing one’s face, longer visual fixation may confer greater communication in dorsal visual system, facilitating global/holistic visual processing. The finding that reduction in visual scanning while viewing one’s face results in persistent effects during unconstrained viewing has implications for perceptual retraining treatment design for BDD.

Highlights • Participants with ALS exhibited impaired function between the cortex and cerebellum. • The cerebellum is associated with complex motor and cognitive processing tasks. • These findings add to the growing number of ALS reports implicating the cerebellum., Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease of the central nervous system that results in a progressive loss of motor function and ultimately death. It is critical, yet also challenging, to develop non-invasive biomarkers to identify, localize, measure and/or track biological mechanisms implicated in ALS. Such biomarkers may also provide clues to identify potential molecular targets for future therapeutic trials. Herein we report on a pilot study involving twelve participants with ALS and nine age-matched healthy controls who underwent high-resolution resting state functional magnetic resonance imaging at an ultra-high field of 7 Tesla. A group-level whole-brain analysis revealed a disruption in long-range functional connectivity between the superior sensorimotor cortex (in the precentral gyrus) and bilateral cerebellar lobule VI. Post hoc analyses using atlas-derived left and right cerebellar lobule VI revealed decreased functional connectivity in ALS participants that predominantly mapped to bilateral postcentral and precentral gyri. Cerebellar lobule VI is a transition zone between anterior motor networks and posterior non-motor networks in the cerebellum, and is associated with a wide range of key functions including complex motor and cognitive processing tasks. Our observation of the involvement of cerebellar lobule VI adds to the growing number of studies implicating the cerebellum in ALS. Future avenues of scientific investigation should consider how high-resolution imaging at 7T may be leveraged to visualize differences in functional connectivity disturbances in various genotypes and phenotypes of ALS along the ALS-frontotemporal dementia spectrum.

The hemodynamic response function (HRF) represents the transfer function linking neural activity with the functional MRI (fMRI) signal, modeling neurovascular coupling. Since HRF is influenced by non-neural factors, to date it has largely been considered as a confound or has been ignored in many analyses. However, underlying biophysics suggests that the HRF may contain meaningful correlates of neural activity, which might be unavailable through conventional fMRI metrics. Here, we estimated the HRF by performing deconvolution on resting-state fMRI data from a longitudinal sample of 25 healthy controls scanned twice and 44 adults with obsessive-compulsive disorder (OCD) before and after 4-weeks of intensive cognitive-behavioral therapy (CBT). HRF response height, time-to-peak and full-width at half-maximum (FWHM) in OCD were abnormal before treatment and normalized after treatment in regions including the caudate. Pre-treatment HRF predicted treatment outcome (OCD symptom reduction) with 86.4% accuracy, using machine learning. Pre-treatment HRF response height in the caudate head and time-to-peak in the caudate tail were top-predictors of treatment response. Time-to-peak in the caudate tail, a region not typically identified in OCD studies using conventional fMRI activation or connectivity measures, may carry novel importance. Additionally, pre-treatmentresponse height in caudate head predicted post-treatment OCD severity (R = -0.48, P = 0.001), and was associated with treatment-related OCD severity changes (R = -0.44, P = 0.0028), underscoring its relevance. With HRF being a reliable marker sensitive to brain function, OCD pathology, and intervention-related changes, these results could guide future studies towards novel discoveries not possible through conventional fMRI approaches like standard BOLD activation or connectivity.

Resting-state functional Magnetic Resonance Imaging (rs-fMRI) has been extensively used for diagnostic classification because it does not require task compliance and is easier to pool data from multiple imaging sites, thereby increasing the sample size. A MATLAB-based toolbox called Machine Learning in NeuroImaging (MALINI) for feature extraction and disease classification is presented. The MALINI toolbox extracts functional and effective connectivity features from preprocessed rs-fMRI data and performs classification between healthy and disease groups using any of 18 popular and widely used machine learning algorithms that are based on diverse principles. A consensus classifier combining the power of multiple classifiers is also presented. The utility of the toolbox is illustrated by accompanying data consisting of resting-state functional connectivity features from healthy controls and subjects with various brain-based disorders: autism spectrum disorder from autism brain imaging data exchange (ABIDE), Alzheimer's disease and mild cognitive impairment from Alzheimer's disease neuroimaging initiative (ADNI), attention deficit hyperactivity disorder from ADHD-200, and post-traumatic stress disorder and post-concussion syndrome acquired in-house. Results of classification performed on the above datasets can be obtained from the main article titled “Supervised machine learning for diagnostic classification from large-scale neuroimaging datasets” [1]. The data was divided into homogeneous and heterogeneous splits, such that 80% could be used for training, model building and cross-validation, while the remaining 20% of the data could be used as a hold-out independent test data for replication of the classification performance, to ensure the robustness of the classifiers to population variance in image acquisition site and age of the sample. Keywords: Resting-state functional MRI, Supervised machine learning, Diagnostic classification, Functional connectivity, Autism, ADHD, Alzheimer's disease, PTSD

Objective Schizophrenia spectrum disorders (SSD) and psychotic bipolar disorder share a number of genetic and neurobiological features, despite a divergence in clinical course and outcome trajectories. We studied the diagnostic classification potential that can be achieved on the basis of the structure and connectivity within a triple network system (the default mode, salience and central executive network) in patients with SSD and psychotic bipolar disorder. Methods Directed static connectivity and its dynamic variance was estimated among 8 nodes of the three large-scale networks. Multivariate autoregressive models of deconvolved resting state functional magnetic resonance imaging time series were obtained from 57 patients (38 with SSD and 19 with bipolar disorder and psychosis). We used 2/3 of the patients for training and validation of the classifier and the remaining 1/3 as an independent hold-out test data for performance estimation. Results A high level of discrimination between bipolar disorder with psychosis and SSD (combined balanced accuracy = 96.2%; class accuracies 100% for bipolar and 92.3% for SSD) was achieved when effective connectivity and morphometry of the triple network nodes was combined with symptom scores. Patients with SSD were discriminated from patients with bipolar disorder and psychosis as showing higher clinical severity of disorganization and higher variability in the effective connectivity between salience and executive networks. Conclusions Our results support the view that the study of network-level connectivity patterns can not only clarify the pathophysiology of SSD but also provide a measure of excellent clinical utility to identify discrete diagnostic/prognostic groups among individuals with psychosis.

Objective It is important to identify brain-based biomarkers that progressively deteriorate from healthy to mild cognitive impairment (MCI) to Alzheimer’s disease (AD). Cortical thickness, amyloid-ß deposition, and graph measures derived from functional connectivity (FC) networks obtained using functional MRI (fMRI) have been previously identified as potential biomarkers. Specifically, in the latter case, betweenness centrality (BC), a nodal graph measure quantifying information flow, is reduced in both AD and MCI. However, all such reports have utilized BC calculated from undirected networks that characterize synchronization rather than information flow, which is better characterized using directed networks. Methods Therefore, we estimated BC from directed networks using Granger causality (GC) on resting-state fMRI data (N = 132) to compare the following populations (p Results MP detected more brain regions than BC that progressively deteriorated from NC to EMCI to LMCI to AD, as well as exhibited significant associations with behavioral measures. Additionally, graph measures obtained from conventional FC networks could not identify a single node, underscoring the relevance of GC. Conclusion Our findings demonstrate the superiority of MP over BC as well as GC over FC in our case. MP obtained from GC networks could serve as a potential biomarker for progressive deterioration of MCI and AD.

In Functional magnetic resonance imaging (fMRI), the blood oxygen level dependent (BOLD) signal is modeled as a convolution of the hemodynamic response function (HRF) and the unmeasured latent neural signal. Although most cortical and subcortical brain regions share the canonical shape of the HRF, the temporal structure of HRFs are variable across brain regions and subjects. This variability is induced by both neural and non-neural factors. The variability between subjects can be examined by three parameters that characterize the HRF: response height (RH), time-to-peak (TTP) and full-width at half-max (FWHM). This data provides three HRF parameters at every voxel, obtained from Autism Spectrum Disorder (ASD) patients (N = 531), and matched healthy controls (N = 571). Since ongoing studies suggest that non-standard populations have important differences in their HRFs when compared with healthy control, this data set is valuable in studying variability of HRF in ASD group and inferring the underlying pathology that also affects the HRF. It also has implications for fMRI analyses like resting-sate connectivity analysis.

Purpose fMRI is the convolution of the hemodynamic response function (HRF) and unmeasured neural activity. HRF variability (HRFv) across the brain could, in principle, alter functional connectivity (FC) estimates from resting-state fMRI (rs-fMRI). Given that HRFv is driven by both neural and non-neural factors, it is problematic when it confounds FC. However, this aspect has remained largely unexplored even though FC studies have grown exponentially. We hypothesized that HRFv confounds FC estimates in the brain's default-mode-network. Methods We tested this hypothesis using both simulations (where the ground truth is known and modulated) as well as rs-fMRI data obtained in a 7T MRI scanner (N = 47, healthy). FC was obtained using 2 pipelines: data with hemodynamic deconvolution (DC) to estimate the HRF and minimize HRFv, and data with no deconvolution (NDC, HRFv-ignored). DC and NDC FC networks were compared, along with regional HRF differences, revealing potential false connectivities that resulted from HRFv. Results We found evidence supporting our hypothesis using both simulations and experimental data. With simulations, we found that HRFv could cause a change of up to 50% in FC. With rs-fMRI, several potential false connectivities attributable to HRFv, with majority connections being between different lobes, were identified. We found a double exponential relationship between the magnitude of HRFv and its impact on FC, with a mean/median error of 30.5/11.5% caused in FC by HRF confounds. Conclusion HRFv, if ignored, could cause identification of false FC. FC findings from HRFv-ignored data should be interpreted cautiously. We suggest deconvolution to minimize HRFv.

Functional MRI (fMRI) is modeled as a convolution of the hemodynamic response function (HRF) and an unmeasured latent neural signal. However, HRF itself is variable across brain regions and subjects. This variability is induced by both neural and non-neural factors. Aberrations in underlying neurochemical mechanisms, which control HRF shape, have been reported in autism spectrum disorders (ASD). Therefore, we hypothesized that this will lead to voxel-specific, yet systematic differences in HRF shape between ASD and healthy controls. As a corollary, we also hypothesized that such alterations will lead to differences in estimated functional connectivity in fMRI space compared to latent neural space. To test these hypotheses, we performed blind deconvolution of resting-state fMRI time series acquired from large number of ASD and control subjects obtained from the Autism Brain Imaging Data Exchange (ABIDE) database (N = 1102). Many brain regions previously implicated in autism showed systematic differences in HRF shape in ASD. Specifically, we found that precuneus had aberrations in all HRF parameters. Consequently, we obtained precuneus-seed-based functional connectivity differences between ASD and controls using fMRI as well as using latent neural signals. We found that non-deconvolved fMRI data failed to detect group differences in connectivity between precuneus and certain brain regions that were instead observed in deconvolved data. Our results are relevant for the understanding of hemodynamic and neurochemical aberrations in ASD, as well as have methodological implications for resting-state functional connectivity studies in Autism, and more generally in disorders that are accompanied by neurochemical alterations that may impact HRF shape., Highlights • We demonstrate that HRF variability negatively impacts fMRI functional connectivity. • HRF variability confounds functional connectivity differences between groups. • We provide evidence for this in Autism Spectrum Disorders using the ABIDE database. • Most studies do not account for this HRF variability: implications in neuroimaging.

The brain is a highly interconnected neurobiological system. Network-level characterization is thus largely performed to understand brain functioning. Brain activity can be captured through modalities like functional magnetic resonance imaging (fMRI) and electroencephalogram (EEG). Brain networks are then estimated through pairwise relationships between brain regions using brain connectivity. Functional connectivity, which measures the degree of coactivation between two brain regions, is estimated from pairwise EEG (or fMRI) time series using a measure of synchronization like Pearson's correlation. However, all such measures suffer from the fact that they are continuous variables, with values often lying in the ambiguous range (say 0.3–0.7) wherein it is difficult to infer whether the two time series are actually synchronized or not. This makes the interpretation of findings challenging. Synchronization measures are also largely corrupted by noise. In this paper, a novel autocorrelation-based iterative synchronization (ABIS) technique is proposed, which provides binary synchronization values (0 = not synchronized, 1 = synchronized). It is entirely data driven with no assumptions, input parameters, or arbitrary choices. We demonstrate that ABIS resolves ambiguous synchronizations and provides reliable, robust, and neurobiologically meaningful binary synchronization values. ABIS also performs better than conventional synchronization on all these faculties. This technique has tremendous applications in brain functional connectivity analysis. Complex network modeling of the brain using graph theoretic techniques largely require binary connectivity matrices, which are often obtained by arbitrarily thresholding continuous connectivity matrices. Such practice usually sophisticates the analysis or yields unreliable results. The use of ABIS could entirely eliminate these issues since it provides binary connectivity matrices in a single step, without assumptions or arbitrary choices. Additionally, it resolves ambiguous connectivities to provide a set of sure-connections and sure no-connections, which improves the interpretability of connectivity results and enhances noise robustness (which plagues connectivity analysis). This study has potential applications in network modeling of the brain, and graph-theoretic analysis in general.

Brain connectivity studies report group differences in pairwise connection strengths. While informative, such results are difficult to interpret since our understanding of the brain relies on region-based properties, rather than on connection information. Given that large disruptions in the brain are often caused by a few pivotal sources, we propose a novel framework to identify the sources of functional disruption from effective connectivity networks. Our approach integrates static and time-varying effective connectivity modeling in a probabilistic framework, to identify aberrant foci and the corresponding aberrant connectomics network. Using resting-state fMRI, we illustrate the utility of this novel approach in U.S. Army soldiers (N = 87) with posttraumatic stress disorder (PTSD), mild traumatic brain injury (mTBI) and combat controls. Additionally, we employed machine-learning classification to identify those significant connectivity features that possessed high predictive ability. We identified three disrupted foci (middle frontal gyrus [MFG], insula, hippocampus), and an aberrant prefrontal-subcortical-parietal network of information flow. We found the MFG to be the pivotal focus of network disruption, with aberrant strength and temporal-variability of effective connectivity to the insula, amygdala and hippocampus. These connectivities also possessed high predictive ability (giving a classification accuracy of 81%); and they exhibited significant associations with symptom severity and neurocognitive functioning. In summary, dysregulation originating in the MFG caused elevated and temporally less-variable connectivity in subcortical regions, followed by a similar effect on parietal memory-related regions. This mechanism likely contributes to the reduced control over traumatic memories leading to re-experiencing, hyperarousal and flashbacks observed in soldiers with PTSD and mTBI. Hum Brain Mapp 39:264-287, 2018. © 2017 Wiley Periodicals, Inc.

Functional magnetic resonance imaging (fMRI) is an indirect measure of brain activity, i.e. it is a convolution of the latent (unmeasured) neural signal and the hemodynamic response function (HRF). As such, the HRF has been shown to vary across brain regions and individuals. The shape of the HRF is controlled by both neural and non-neural factors. The shape of the HRF can be characterized by three parameters (response height, time-to-peak and full-width at half-max). The data presented here provides the three HRF parameters at every voxel, obtained from U.S. Army soldiers (N=87) diagnosed with posttraumatic stress disorder (PTSD), with comorbid PTSD and mild-traumatic brain injury (mTBI), and matched healthy combat controls. Findings from this data and further interpretations are available in our recent research study (Rangaprakash et al., 2017) [1]. This data is a valuable asset in studying the impact of HRF variability on fMRI data analysis, specifically resting state functional connectivity.

Using resting-state functional magnetic resonance imaging, we test the hypothesis that subjects with post-traumatic stress disorder (PTSD) are characterized by reduced temporal variability of brain connectivity compared to matched healthy controls. Specifically, we test whether PTSD is characterized by elevated static connectivity, coupled with decreased temporal variability of those connections, with the latter providing greater sensitivity toward the pathology than the former. Static functional connectivity (FC; nondirectional zero-lag correlation) and static effective connectivity (EC; directional time-lagged relationships) were obtained over the entire brain using conventional models. Dynamic FC and dynamic EC were estimated by letting the conventional models to vary as a function of time. Statistical separation and discriminability of these metrics between the groups and their ability to accurately predict the diagnostic label of a novel subject were ascertained using separate support vector machine classifiers. Our findings support our hypothesis that PTSD subjects have stronger static connectivity, but reduced temporal variability of connectivity. Further, machine learning classification accuracy obtained with dynamic FC and dynamic EC was significantly higher than that obtained with static FC and static EC, respectively. Furthermore, results also indicate that the ease with which brain regions engage or disengage with other regions may be more sensitive to underlying pathology than the strength with which they are engaged. Future studies must examine whether this is true only in the case of PTSD or is a general organizing principle in the human brain. Hum Brain Mapp 38:4479-4496, 2017. © 2017 Wiley Periodicals, Inc.

Functional MRI (fMRI) is an indirect measure of neural activity as a result of the convolution of the hemodynamic response function (HRF) and latent (unmeasured) neural activity. Recent studies have shown variability of HRF across brain regions (intra-subject spatial variability) and between subjects (inter-subject variability). Ignoring this HRF variability during data analysis could impair the reliability of such fMRI results. Using whole-brain resting-state fMRI (rs-fMRI), we employed hemodynamic deconvolution to estimate voxel-wise HRF. Studying the impact of mental disorders on HRF variability, we identified HRF aberrations in soldiers (N = 87) with posttraumatic stress disorder (PTSD) and mild-traumatic brain injury (mTBI) compared to combat controls. Certain subcortical and default-mode regions were found to have significant HRF aberrations in the clinical groups. These brain regions have been previously associated with neurochemical alterations in PTSD, which are known to impact the shape of the HRF. We followed-up these findings with seed-based functional connectivity (FC) analysis using regions-of-interest (ROIs) whose HRFs differed between the groups. We found that part of the connectivity group differences reported from traditional FC analysis (no deconvolution) were attributable to HRF variability. These findings raise the question of the degree of reliability of findings from conventional rs-fMRI studies (especially in psychiatric populations like PTSD and mTBI), which are corrupted by HRF variability. We also report and discus, for the first time, voxel-level HRF alterations in PTSD and mTBI. To the best of our knowledge, this is the first study to report evidence for the impact of HRF variability on connectivity group differences. Our work has implications for rs-fMRI connectivity studies. We encourage researchers to incorporate hemodynamic deconvolution during pre-processing to minimize the impact of HRF variability., Highlights • We demonstrate the impact of HRF variability on fMRI functional connectivity. • Such HRF variability results in inaccuracies in functional connectivity differences • We provide evidence for this in a psychiatric cohort of soldiers with PTSD and mTBI. • Neurochemical alterations in the clinical groups could be leading to change in HRF. • Most studies do not account for this HRF variability: implications in neuroimaging.

Background: There is a significant number of military personnel with a history of mild traumatic brain injury (mTBI) who suffer from comorbid posttraumatic stress symptoms (PTS). Although there is evidence of disruptions of the default mode network (DMN) associated with PTS and mTBI, previous studies have only studied static connectivity while ignoring temporal variability of connectivity. Objective: To assess DMN disrupted or dysregulated neurocircuitry, cognitive functioning, and psychological health of active-duty military with mTBI and PTS. Method: U.S. Army soldiers with PTS (n = 14), mTBI + PTS (n = 25), and healthy controls (n = 21) voluntarily completed a cognitive and symptom battery. In addition, participants had magnetic resonance imaging (MRI) to assess both static functional connectivity (SFC) and variance of dynamic functional connectivity (vDFC) of the DMN. Results: Both the PTS and mTBI + PTS groups had significant symptoms, but only the comorbid group had significant decrements in cognitive functioning. Both groups showed less stable and disrupted neural signatures of the DMN, mainly constituting the cingulate-frontal-temporal-parietal attention network. Specifically, the PTS group showed a combination of both reduced contralateral strength and reduced unilateral variability of frontal- cingulate- temporal connectivities, as well as increased variability of frontal- parietal connectivities. The mTBI + PTS group had fewer abnormal connectives than the PTS group, all of which included reduced strength of frontal- temporal regions and reduced variability frontal- cingulate- temporal regions. Greater SFC and vDFC connectivity of the left dorsolateral prefrontal cortex (dlPFC) ↔ precuneus was associated with higher cognitive scores and lower symptom scores. Conclusions: Findings suggest that individuals with PTS and mTBI + PTS have a propensity for accentuated generation of thoughts, feelings, sensations, and/or images while in a resting state. Compared with controls, only the PTS group was associated with accentuated variability of the frontal- parietal attention network. While there were no significant differences in DMN connectivity strength between the mTBI + PTS and PTS groups, variability of connectivity was able to distinguish them.

Many brain-based disorders are traditionally diagnosed based on clinical interviews and behavioral assessments, which are recognized to be largely imperfect. Therefore, it is necessary to establish neuroimaging-based biomarkers to improve diagnostic precision. Resting-state functional magnetic resonance imaging (rs-fMRI) is a promising technique for the characterization and classification of varying disorders. However, most of these classification methods are supervised, i.e., they require a priori clinical labels to guide classification. In this study, we adopted various unsupervised clustering methods using static and dynamic rs-fMRI connectivity measures to investigate whether the clinical diagnostic grouping of different disorders is grounded in underlying neurobiological and phenotypic clusters. In order to do so, we derived a general analysis pipeline for identifying different brain-based disorders using genetic algorithm-based feature selection, and unsupervised clustering methods on four different datasets; three of them—ADNI, ADHD-200, and ABIDE—which are publicly available, and a fourth one—PTSD and PCS—which was acquired in-house. Using these datasets, the effectiveness of the proposed pipeline was verified on different disorders: Attention Deficit Hyperactivity Disorder (ADHD), Alzheimer’s Disease (AD), Autism Spectrum Disorder (ASD), Post-Traumatic Stress Disorder (PTSD), and Post-Concussion Syndrome (PCS). For ADHD and AD, highest similarity was achieved between connectivity and phenotypic clusters, whereas for ASD and PTSD/PCS, highest similarity was achieved between connectivity and clinical diagnostic clusters. For multi-site data (ABIDE and ADHD-200), we report site-specific results. We also reported the effect of elimination of outlier subjects for all four datasets. Overall, our results suggest that neurobiological and phenotypic biomarkers could potentially be used as an aid by the clinician, in additional to currently available clinical diagnostic standards, to improve diagnostic precision. Data and source code used in this work is publicly available at https://github.com/xinyuzhao/identification-of-brain-based-disorders.git.

Anorexia nervosa (AN) and body dysmorphic disorder (BDD) share distorted perceptions of appearance with extreme negative emotion, yet the neural phenotypes of emotion processing remain underexplored in them, and they have never been directly compared. We sought to determine if shared and disorder-specific fronto-limbic connectivity patterns characterize these disorders. FMRI data was obtained from three unmedicated groups: BDD (n = 32), weight-restored AN (n = 25), and healthy controls (HC; n = 37), while they viewed fearful faces and rated their own degree of fearfulness in response. We performed dynamic effective connectivity modeling with medial prefrontal cortex (mPFC), rostral anterior cingulate cortex (rACC), and amygdala as regions-of-interest (ROI), and assessed associations between connectivity and clinical variables. HCs exhibited significant within-group bidirectional mPFC-amygdala connectivity, which increased across the blocks, whereas BDD participants exhibited only significant mPFC-to-amygdala connectivity (P < 0.05, family-wise error corrected). In contrast, participants with AN lacked significant prefrontal-amygdala connectivity in either direction. AN showed significantly weaker mPFC-to-amygdala connectivity compared to HCs (P = 0.0015) and BDD (P = 0.0050). The mPFC-to-amygdala connectivity was associated with greater subjective fear ratings (R2 = 0.11, P = 0.0016), eating disorder symptoms (R2 = 0.33, P = 0.0029), and anxiety (R2 = 0.29, P = 0.0055) intensity scores. Our findings, which suggest a complex nosological relationship, have implications for understanding emotion regulation circuitry in these related psychiatric disorders, and may have relevance for current and novel therapeutic approaches.

Functional magnetic resonance imaging (fMRI), being an indirect measure of brain activity, is mathematically defined as a convolution of the unmeasured latent neural signal and the hemodynamic response function (HRF). The HRF is known to vary across the brain and across individuals, and it is modulated by neural as well as nonneural factors. Three parameters characterize the shape of the HRF, which is obtained by performing deconvolution on resting-state fMRI data: response height, time-to-peak and full-width at half-max. The data provided here, obtained from 47 healthy adults, contains these three HRF parameters at every voxel in the brain, as well as HRF parameters from the default-mode network (DMN). In addition, we have provided functional connectivity (FC) data from the same DMN regions, obtained for two cases: data with deconvolution (HRF variability minimized) and data with no deconvolution (HRF variability corrupted). This would enable researchers to compare regional changes in HRF with corresponding FC differences, to assess the impact of HRF variability on FC. Importantly, the data was obtained in a 7T MRI scanner. While most fMRI studies are conducted at lower field strengths, like 3T, ours is the first study to report HRF data obtained at 7T. FMRI data at ultra-high fields contains larger contributions from small vessels, consequently HRF variability is lower for small vessels at higher field strengths. This implies that findings made from this data would be more conservative than from data acquired at lower fields, such as 3T. Results obtained with this data and further interpretations are available in our recent research study (Rangaprakash et al., in press) [1]. This is a valuable dataset for studying HRF variability in conjunction with FC, and for developing the HRF profile in healthy individuals, which would have direct implications for fMRI data analysis, especially resting-state connectivity modeling. This is the first public HRF data at 7T. (C) 2018 The Authors. Published by Elsevier Inc.

A Brain-Computer Interface (BCI) is a setup permitting the control of external devices by decoding brain activity. Electroencephalography (EEG) has been extensively used for decoding brain activity since it is non-invasive, cheap, portable, and has high temporal resolution to allow real-time operation. Due to its poor spatial specificity, BCIs based on EEG can require extensive training and multiple trials to decode brain activity (consequently slowing down the operation of the BCI). On the other hand, BCIs based on functional magnetic resonance imaging (fMRI) are more accurate owing to its superior spatial resolution and sensitivity to underlying neuronal processes which are functionally localized. However, due to its relatively low temporal resolution, high cost, and lack of portability, fMRI is unlikely to be used for routine BCI. We propose a new approach for transferring the capabilities of fMRI to EEG, which includes simultaneous EEG/fMRI sessions for finding a mapping from EEG to fMRI, followed by a BCI run from only EEG data, but driven by fMRI-like features obtained from the mapping identified previously. Our novel data-driven method is likely to discover latent linkages between electrical and hemodynamic signatures of neural activity hitherto unexplored using model-driven methods, and is likely to serve as a template for a novel multi-modal strategy wherein cross-modal EEG-fMRI interactions are exploited for the operation of a unimodal EEG system, leading to a new generation of EEG-based BCIs.

Objectives Military service members risk acquiring posttraumatic stress disorder (PTSD) and mild-traumatic brain injury (mTBI), with high comorbidity. Owing to overlapping symptomatology in chronic mTBI or postconcussion syndrome (PCS) and PTSD, it is difficult to assess the etiology of a patient's condition without objective measures. Using resting-state functional MRI in a novel framework, we tested the hypothesis that their neural signatures are characterized by functionally hyperconnected brain regions which are less variable over time. Additionally, we predicted that such connectivities possessed the highest ability in predicting the diagnostic membership of a novel subject (top-predictors) in addition to being statistically significant. Methods U.S. Army Soldiers (N = 87) with PTSD and comorbid PCS + PTSD were recruited along with combat controls. Static and dynamic functional connectivities were evaluated. Group differences were obtained in accordance with our hypothesis. Machine learning classification (MLC) was employed to determine top predictors. Results From whole-brain connectivity, we identified the hippocampus-striatum connectivity to be significantly altered in accordance with our hypothesis. Diffusion tractography revealed compromised white-matter integrity between aforementioned regions only in the PCS + PTSD group, suggesting a structural etiology for the PCS + PTSD group rather than being an extreme subset of PTSD. Employing MLC, connectivities provided worst-case accuracy of 84% (9% more than psychological measures). Additionally, the hippocampus-striatum connectivities were found to be top predictors and thus a potential biomarker of PTSD/mTBI. Conclusions PTSD/mTBI are associated with hippocampal-striatal hyperconnectivity from which it is difficult to disengage, leading to a habit-like response toward episodic traumatic memories, which fits well with behavioral manifestations of combat-related PTSD/mTBI. Hum Brain Mapp 38:2843-2864, 2017. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

a b s t r a c t Complex biological systems such as the human brain can be expected to be inherently nonlinear and hence difficult to model. Most of the previous studies on investigations of brain function have either used linear models or parametric nonlinear models. In this paper, we propose a novel application of a nonlinear measure of phase synchronization based on recurrences, correlation between probabilities of recurrence (CPR), to study seizures in the brain. The advantage of this nonparametric method is that it makes very few assumptions thus making it possible to investigate brain functioning in a data-driven way. We have demonstrated the utility of CPR measure for the study of phase synchronization in multichannel seizure EEG recorded from patients with global as well as focal epilepsy. For the case of global epilepsy, brain synchronization using thresholded CPR matrix of multichannel EEG signals showed clear differences in results obtained for epileptic seizure and pre-seizure. Brain headmaps obtained for seizure and pre- seizure cases provide meaningful insights about synchronization in the brain in those states. The headmap in the case of focal epilepsy clearly enables us to identify the focus of the epilepsy which provides certain diagnostic value. Comparative studies with linear correlation have shown that the nonlinear measure CPR outperforms the linear correlation measure. © 2014 Elsevier Ltd. All rights reserved.

Real world biological systems such as the human brain are inherently nonlinear and difficult to model. However, most of the previous studies have either employed linear models or parametric nonlinear models for investigating brain function. In this paper, a novel application of a nonlinear measure of phase synchronization based on recurrences, correlation between probabilities of recurrence (CPR), to study connectivity in the brain has been proposed. Being non-parametric, this method makes very few assumptions, making it suitable for investigating brain function in a data-driven way. CPR's utility with application to multichannel electroencephalographic (EEG) signals has been demonstrated. Brain connectivity obtained using thresholded CPR matrix of multichannel EEG signals showed clear differences in the number and pattern of connections in brain connectivity between (a) epileptic seizure and pre-seizure and (b) eyes open and eyes closed states. Corresponding brain headmaps provide meaningful insights about synchronization in the brain in those states. K-means clustering of connectivity parameters of CPR and linear correlation obtained from global epileptic seizure and pre-seizure showed significantly larger cluster centroid distances for CPR as opposed to linear correlation, thereby demonstrating the superior ability of CPR for discriminating seizure from pre-seizure. The headmap in the case of focal epilepsy clearly enables us to identify the focus of the epilepsy which provides certain diagnostic value. (C) 2013 Elsevier Ltd. All rights reserved.

Clustering is one of the most important methods for organizing database into groups. In this paper, Ordering Points To Identify Clustering Structure (OPTICS) algorithm has been used to perform clustering of functional Magnetic Resonance Imaging (fMRI) data. Dynamic functional connectivity features on fMRI data (ADNI database) obtained from subjects with early mild cognitive impairment (E-MCI), late mild cognitive impairment (L-MCI), Alzheimer's disease and healthy controls has been used for the study. On performing clustering, it has been observed that OPTICS is able to cluster the subjects into four inherent groups with a very high success rate. This result gives rise to applications in determining latent groups indicating various brain disorders.

Wrist pulse signals contain information about the status of health of a person and hence diagnosis using these signals is of great importance since long time. In this paper the efficacy of signal processing techniques in extracting useful information from wrist pulse signals has been demonstrated by using signals recorded before lunch and after lunch conditions. We have used correlation between probabilities of recurrence which is a recent nonlinear measure of synchronization, as well as Pearson's correlation coefficient, which is a traditionally used measure of synchronization. Statistical analysis using two-sample t-test is performed, which shows that there is significantly different synchronizations between signals acquired before lunch and those acquired after lunch. Moreover, upon performing RCE-SVM classification, the nonlinear synchronization measure showed a classification accuracy of 91.6% against the accuracy of 80.5% for correlation. These results show that the new nonlinear synchronization measure is effective in distinguishing the changes taking place after having lunch. This paper also demonstrates the ability of the wrist pulse signals in detecting changes occurring under two different conditions. This study is significant given that analysis of wrist pulse signals in case of food intake is less explored in literature and also that it has potential applications in healthcare.

Automated recognition and classification of brain diseases are of tremendous value to society. Attention deficit hyperactivity disorder (ADHD) is a diverse spectrum disorder whose diagnosis is based on behavior and hence will benefit from classification utilizing objective neuroimaging measures. Toward this end, an international competition was conducted for classifying ADHD using functional magnetic resonance imaging data acquired from multiple sites worldwide. Here, we consider the data from this competition as an example to illustrate the utility of fully connected cascade (FCC) artificial neural network (ANN) architecture for performing classification. We employed various directional and nondirectional brain connectivity-based methods to extract discriminative features which gave better classification accuracy compared to raw data. Our accuracy for distinguishing ADHD from healthy subjects was close to 90% and between the ADHD subtypes was close to 95%. Further, we show that, if properly used, FCC ANN performs very well compared to other classifiers such as support vector machines in terms of accuracy, irrespective of the feature used. Finally, the most discriminative connectivity features provided insights about the pathophysiology of ADHD and showed reduced and altered connectivity involving the left orbitofrontal cortex and various cerebellar regions in ADHD.

Wrist pulse signals contain important information about the health of a person and hence diagnosis based on pulse signals has assumed great importance. In this paper we demonstrate the efficacy of a two term Gaussian model to extract information from pulse signals. Results have been obtained by conducting experiments on several subjects to record wrist pulse signals for the cases of before exercise and after exercise. Parameters have been extracted from the recorded signals using the model and a paired t-test is performed, which shows that the parameters are significantly different between the two groups. Further, a recursive cluster elimination based support vector machine is used to perform classification between the groups. An average classification accuracy of 99.46% is obtained, along with top classifiers. It is thus shown that the parameters of the Gaussian model show changes across groups and hence the model is effective in distinguishing the changes taking place due to the two different recording conditions. The study has potential applications in healthcare.

Wrist pulse signal contains more important information about the health status of a person and pulse signal diagnosis has been employed in oriental medicine since very long time. In this paper we have used signal processing techniques to extract information from wrist pulse signals. For this purpose we have acquired radial artery pulse signals at wrist position noninvasively for different cases of interest. The wrist pulse waveforms have been analyzed using spatial features. Results have been obtained for the case of wrist pulse signals recorded for several subjects before exercise and after exercise. It is shown that the spatial features show statistically significant changes for the two cases and hence they are effective in distinguishing the changes taking place due to exercise. Support vector machine classifier is used to classify between the groups, and a high classification accuracy of 99.71% is achieved. Thus this paper demonstrates the utility of the spatial features in studying wrist pulse signals obtained under various recording conditions. The ability of the model to distinguish changes occurring under two different recording conditions can be potentially used for health care applications.

It is well known that wrist pulse signals contain information about the status of health of a person and hence diagnosis based on pulse signals has assumed great importance since long time. In this paper the efficacy of signal processing techniques in extracting useful information from wrist pulse signals has been demonstrated by using signals recorded under two different experimental conditions viz. before lunch condition and after lunch condition. We have used Pearson's product-moment correlation coefficient, which is an effective measure of phase synchronization, in making a statistical analysis of wrist pulse signals. Contour plots and box plots are used to illustrate various differences. Two-sample t-tests show that the correlations show statistically significant differences between the groups. Results show that the correlation coefficient is effective in distinguishing the changes taking place after having lunch. This paper demonstrates the ability of the wrist pulse signals in detecting changes occurring under two different conditions. The study assumes importance in view of limited literature available on the analysis of wrist pulse signals in the case of food intake and also in view of its potential health care applications.

It is increasingly being recognized that resting state brain connectivity derived from functional magnetic resonance imaging (fMRI) data is an important marker of brain function both in healthy and clinical populations. Though linear correlation has been extensively used to characterize brain connectivity, it is limited to detecting first order dependencies. In this study, we propose a framework where in phase synchronization (PS) between brain regions is characterized using a new metric "correlation between probabilities of recurrence" (CPR) and subsequent graph-theoretic analysis of the ensuing networks. We applied this method to resting state fMRI data obtained from human subjects with and without administration of propofol anesthetic. Our results showed decreased PS during anesthesia and a biologically more plausible community structure using CPR rather than linear correlation. We conclude that CPR provides an attractive nonparametric method for modeling interactions in brain networks as compared to standard correlation for obtaining physiologically meaningful insights about brain function.