Accurate classification of schizophrenia patients based on novel resting-state fMRI features.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:6691-6694
Authors: Arbabshirani MR, Castro E, Calhoun VD
There is a growing interest in automatic classification of mental disorders such as schizophrenia based on neuroimaging data. Most previous studies considered structural MRI, diffusion tensor imaging and task-based fMRI for this purpose. However, resting-state fMRI data has not been used much to evaluate discrimination of schizophrenia patients from healthy controls. Resting data are of great interest, since they are relatively easy to collect, and not confounded by behavioral performance on a task. In this study, we extract two types of features from resting-state fMRI data: functional network connectivity features that capture internetwork connectivity patterns and autoconnectivity features capturing temporal connectivity of each brain network. Autoconnectivity is a novel concept we have recently proposed. We used minimum redundancy maximum relevancy to select features. Classification results using support vector machine shows that combining these two types of features can improve the classification on a large resting fMRI dataset consisting of 195 patients with schizophrenia and 175 healthy controls. We achieved the accuracy of 85% which is very promising.
PMID: 25571531 [PubMed - as supplied by publisher]
A unified machine learning method for task-related and resting state fMRI data analysis.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:6426-6429
Authors: Xiaomu Song, Nan-Kuei Chen
Functional magnetic resonance imaging (fMRI) aims to localize task-related brain activation or resting-state functional connectivity. Most existing fMRI data analysis techniques rely on fixed thresholds to identify active voxels under a task condition or functionally connected voxels in the resting state. Due to fMRI non-stationarity, a fixed threshold cannot adapt to intra- and inter-subject variation and provide a reliable mapping of brain function. In this work, a machine learning method is proposed for a unified analysis of both task-related and resting state fMRI data. Specifically, the mapping of brain function in a task condition or resting state is formulated as an outlier detection process. Support vector machines are used to provide an initial mapping and refine mapping results. The method does not require a fixed threshold for the final decision, and can adapt to fMRI non-stationarity. The proposed method was evaluated using experimental data acquired from multiple human subjects. The results indicate that the proposed method can provide reliable mapping of brain function, and is applicable to various quantitative fMRI studies.
PMID: 25571467 [PubMed - as supplied by publisher]
Local Sparse Component Analysis for Blind Source Separation: An application to resting state FMRI.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:5611-5614
Authors: Vieira G, Amaro E, Baccala LA
We propose a new Blind Source Separation technique for whole-brain activity estimation that best profits from FMRI's intrinsic spatial sparsity. The Local Sparse Component Analysis (LSCA) combines wavelet analysis, group-separable regularizers, contiguity-constrained clusterization and principal components analysis (PCA) into a unique spatial sparse representation of FMRI images towards efficient dimensionality reduction without sacrificing physiological characteristics by avoiding artificial stochastic model constraints. The LSCA outperforms classical PCA source reconstruction for artificial data sets over many noise levels. A real FMRI data illustration reveals resting-state activities in regions hard to observe, such as thalamus and basal ganglia, because of their small spatial scale.
PMID: 25571267 [PubMed - as supplied by publisher]
Classification of borderline personality disorder based on spectral power of resting-state fMRI.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:5036-5039
Authors: Tingting Xu, Cullen KR, Houri A, Lim KO, Schulz SC, Parhi KK
Borderline personality disorder (BPD) is a serious mental illness that can cause significant suffering and carries a risk of suicide. Assigning an accurate diagnosis is critical to guide treatment. Currently, the diagnosis of BPD is made exclusively through the use of clinical assessment; no objective test is available to assist with its diagnosis. Thus, it is highly desirable to explore quantitative biomarkers to better characterize this illness. In this study, we extract spectral power features from the power spectral density and cross spectral density of resting-state fMRI data, covering 20 brain regions and 5 frequency bands. Machine learning approaches are employed to select the most discriminating features to identify BPD. Following a leave-one-out cross validation procedure, the proposed approach achieves 93.55% accuracy (100% specificity and 90.48% sensitivity) in classifying 21 BPD patients from 10 healthy controls based on the top ranked features. The most discriminating features are selected from the 0.1~0.15Hz frequency band, and are located at the left medial orbitofrontal cortex, the left thalamus, and the right rostral anterior cingulate cortex. The high classification accuracy indicates the discriminating power of the spectral power features in BPD identification. The proposed machine learning approach may be used as an objective test to assist clinical diagnosis of BPD.
PMID: 25571124 [PubMed - as supplied by publisher]
Simultaneous blind separation and clustering of coactivated EEG/MEG sources for analyzing spontaneous brain activity.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:4932-4935
Authors: Hirayama J, Ogawa T, Hyvarinen A
Analysis of the dynamics (non-stationarity) of functional connectivity patterns has recently received a lot of attention in the neuroimaging community. Most analysis has been using functional magnetic resonance imaging (fMRI), partly due to the inherent technical complexity of the electro- or magnetoencephalography (EEG/MEG) signals, but EEG/MEG holds great promise in analyzing fast changes in connectivity. Here, we propose a method for dynamic connectivity analysis of EEG/MEG, combining blind source separation with dynamic connectivity analysis in a single probabilistic model. Blind source separation is extremely useful for interpretation of the connectivity changes, and also enables rejection of artifacts. Dynamic connectivity analysis is performed by clustering the coactivation patterns of separated sources by modeling their variances. Experiments on resting-state EEG show that the obtained clusters correlate with physiologically meaningful quantities.
PMID: 25571098 [PubMed - as supplied by publisher]
Combination of FMRI-SMRI-EEG data improves discrimination of schizophrenia patients by ensemble feature selection.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:3889-3892
Authors: Jing Sui, Castro E, Hao He, Bridwell D, Yuhui Du, Pearlson GD, Jiang T, Calhoun VD
Multimodal brain imaging data fusion is a scientifically interesting and clinically important topic; however, there is relatively little work on N-way data fusion. In this paper, we applied multi-set canonical correlation analysis (MCCA) to combine data of resting state fMRI, EEG and sMRI, in order to elucidate the abnormalities that underlie schizophrenia patients and also covary across multiple modalities. We also tested whether the identified group-discriminative components can be used for feature selection in group classification. MCCA is demonstrated to be an effective feature selection technique, especially in multimodal fusion. We also proposed an ensemble feature selection scheme by combining two sample t-test, MCCA and support vector machine with recursive feature elimination (SVM-RFE), resulting in optimal group-discriminating features for each modality. Finally, we compared the classifying power between two groups based on the above selected features via 7 modality-combinations. Results show that the fMRI-sMRI-EEG combination derives the best classification accuracy in training (91%) and predication rate (100%) in testing data, validating the effectiveness and advantages of multimodal fusion in discriminating schizophrenia.
PMID: 25570841 [PubMed - as supplied by publisher]
Higher dimensional analysis shows reduced dynamism of time-varying network connectivity in schizophrenia patients.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:3837-3840
Authors: Miller RL, Yaesoubi M, Calhoun VD
Assessments of functional connectivity between brain networks is a fixture of resting state fMRI research. Until very recently most of this work proceeded from an assumption of stationarity in resting state network connectivity. In the last few years however, interest in moving beyond this simplifying assumption has grown considerably. Applying group temporal independent component analysis (tICA) to a set of time-varying functional network connectivity (FNC) matrices derived from a large multi-site fMRI dataset (N=314; 163 healthy, 151 schizophrenia patients), we obtain a set of five basic correlation patterns (component spatial maps (SMs)) from which observed FNCs can be expressed as mutually independent linear combinations, i.e., the coefficient on each SM in the linear combination is maximally independent of the others. We study dynamic properties of network connectivity as they are reflected in this five-dimensional space, and report stark differences in connectivity dynamics between schizophrenia patients and healthy controls. We also find that the most important global differences in FNC dynamism between patient and control groups are replicated when the same dynamical analysis is performed on sets of correlation patterns obtained from either PCA or spatial ICA, giving us additional confidence in the results.
PMID: 25570828 [PubMed - as supplied by publisher]
Impact of multivariate granger causality analyses with embedded dimension reduction on network modules.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:2797-2800
Authors: Schmidt C, Pester B, Nagarajan M, Witte H, Leistritz L, Wismueller A
High dimensional functional MRI data in combination with a low temporal resolution imposes computational limits on classical Granger Causality analyses with respect to a large-scale representations of functional interactions in the brain. To overcome these limitations and exploit information inherent in resulting brain connectivity networks at the large scale, we propose a multivariate Granger Causality approach with embedded dimension reduction. Using this approach, we computed binary connectivity networks from resting state fMRI images and analyzed them with respect to network module structure, which might be linked to distinct brain regions with an increased density of particular interaction patterns as compared to inter-module regions. As a proof of concept, we show that the modular structure of these large-scale connectivity networks can be recovered. These results are promising since further analysis of large-scale brain network partitions into modules might prove valuable for understanding and tracing changes in brain connectivity at a more detailed resolution level than before.
PMID: 25570572 [PubMed - as supplied by publisher]
A method for functional network connectivity using distance correlation.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:2793-2796
Authors: Rudas J, Guaje J, Demertzi A, Heine L, Tshibanda L, Soddu A, Laureys S, Gomez F
In this paper, we present a novel approach for functional network connectivity in fMRI resting activity using distance correlation. The proposed method accounts for nonlinear relationships between the resting state networks and can be used for both single subject and group level analyses. We showed that the new strategy improves the capacity of characterization of pathological populations, such as, patients with disorder of consciousness, when compared to related approaches.
PMID: 25570571 [PubMed - as supplied by publisher]
Exploring difference and overlap between schizophrenia, schizoaffective and bipolar disorders using resting-state brain functional networks.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:1517-1520
Authors: Yuhui Du, Jingyu Liu, Jing Sui, Hao He, Pearlson GD, Calhoun VD
Schizophrenia, schizoaffective and bipolar disorders share some common symptoms. However, the biomarkers underlying those disorders remain unclear. In fact, there is still controversy about the schizoaffective disorder with respect to its validity of independent category and its relationship with schizophrenia and bipolar disorders. In this paper, based on brain functional networks extracted from resting-state fMRI using a recently proposed group information guided ICA (GIG-ICA) method, we explore the biomarkers for discriminating healthy controls, schizophrenia patients, bipolar patients, and patients with two symptom defined subsets of schizoaffective disorder, and then investigate the relationship between different groups. The results demonstrate that the discriminating regions mainly including frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insular and supramarginal cortices perform well in distinguishing the different diagnostic groups. The results also suggest that schizoaffective disorder may be an independent disorder, although its subtype characterized by depressive episodes shares more similarity with schizophrenia.
PMID: 25570258 [PubMed - as supplied by publisher]
Computation of resting state networks from fMRI through a measure of phase synchrony.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:1456-1459
Authors: Villafane-Delgado M, Zhu DC, Aviyente S
Resting-state fMRI (rs-fMRI) studies of the human brain have demonstrated that low-frequency fluctuations can define functionally relevant resting state networks (RSNs). The majority of these methods rely on Pearson's correlation for quantifying the functional connectivity between the time series from different regions. However, it is well-known that correlation is limited to quantifying only linear relationships between the time series and assumes stationarity of the underlying processes. Many empirical studies indicate nonstationarity of the BOLD signals. In this paper, we adapt a measure of time-varying phase synchrony to quantify the functional connectivity and modify it to distinguish between synchronization and desynchronization. The proposed measure is compared to the conventional Pearson's correlation method for rs-fMRI analyses on two subjects (six scans per subject) in terms of their reproducibility.
PMID: 25570243 [PubMed - as supplied by publisher]
Differences in hemispherical thalamo-cortical causality analysis during resting-state fMRI.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:990-993
Authors: Anwar AR, Muthalib M, Perrey S, Wolff S, Deuschl G, Heute U, Muthuraman M
Thalamus is a very important part of the human brain. It has been reported to act as a relay for the messaging taking place between the cortical and sub-cortical regions of the brain. In the present study, we analyze the functional network between both hemispheres of the brain with the focus on thalamus. We used conditional Granger causality (CGC) and time-resolved partial directed coherence (tPDC) to investigate the functional connectivity. Results of CGC analysis revealed the asymmetry between connection strengths of the bilateral thalamus. Upon testing the functional connectivity of the default-mode network (DMN) at low-frequency fluctuations (LFF) and comparing coherence vectors using Spearman's rank correlation, we found that thalamus is a better source for the signals directed towards the contralateral regions of the brain, however, when thalamus acts as sink, it is a better sink for signals generated from ipsilateral regions of the brain.
PMID: 25570127 [PubMed - as supplied by publisher]
Cluster-based analysis for characterizing dynamic functional connectivity.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:982-985
Authors: Shakil S, Magnuson ME, Keilholz SD, Chin-Hui Lee
Different regions in the resting brain exhibit non-stationary functional connectivity (FC) over time. In this paper, a simple and efficient framework of clustering the variability in FC of a rat's brain at rest is proposed. This clustering process reveals areas that are always connected with a chosen region, called seed voxel, along with the areas exhibiting variability in the FC. This addresses an issue common to most dynamic FC analysis techniques, which is the assumption that the spatial extent of a given network remains constant over time. We increase the voxel size and reduce the spatial resolution to analyze variable FC of the whole resting brain. We hypothesize that the adjacent voxels in resting state functional magnetic resonance imaging (rsfMRI), just as in task-based fMRI, exhibit similar intensities, so they can be averaged to obtain larger voxels without any significant loss of information. Sliding window correlation is used to compute variable patterns of the rat's whole brain FC with the seed voxel in the sensorimotor cortex. These patterns are grouped based on their spatial similarities using binary transformed feature vectors in k-means clustering, not only revealing the variable and nonvariable portions of FC in the resting brain but also detecting the extent of the variability of these patterns.
PMID: 25570125 [PubMed - as supplied by publisher]
A comparative analysis of functional connectivity data in resting and task-related conditions of the brain for disease signature of OCD.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:978-981
Authors: Shenas SK, Halici U, Cicek M
Obsessive Compulsive Disorder (OCD) is a frequent, chronic disorder producing intrusive thoughts which results in repetitive behaviors. It is thought that this psychological disorder occurs due to abnormal functional connectivity in certain regions of the brain called Default Mode Network (DMN) mainly. Recently, functional MRI (FMRI) studies were performed in order to compare the differences in brain activity between patients with OCD and healthy individuals through different conditions of the brain. Our previous study on extraction of disease signature for OCD that is determining the features for discrimination of OCD patients from healthy individuals based on their resting-sate functional connectivity (rs-FC) data had given encouraging results. In the present study, functional data extracted from FMRI images of subjects under imagination task (maintaining an image in mind, im-FC) is considered. The aim of this study is to compare classification results achieved from both resting and task-related (imagination) conditions. This research has shown quite interesting and promising results using the same classification (SVM) method.
PMID: 25570124 [PubMed - as supplied by publisher]
Using functional MRI alone for localization in focal epilepsy.
Conf Proc IEEE Eng Med Biol Soc. 2014 Aug;2014:730-733
Authors: Zhang CH, Yunfeng Lu, Brinkmann B, Welker K, Worrell G, Bin He
In the present study, we developed a method for the purpose of localizing epilepsy related hemodynamic foci for patients suffering intractable focal epilepsy using resting state fMRI alone. We studied two groups of subjects: five patients with intractable focal epilepsy, and ten healthy volunteers performing motor tasks. Spatial independent component analysis (ICA) was performed on the fMRI alone data and a set of independent component (IC) selection criteria was developed to identify epilepsy related ICs. The method was then evaluated in the healthy group with motor tasks. In all five surgery patients, there was at least one identified IC concordant with surgical resection. In the motor task study of healthy subjects, our method revealed components with concordant spatial and temporal features as expected from the unilateral motor tasks. These results suggest the lateralization and localization value of fMRI alone in presurgical evaluation for patients with intractable unilateral focal epilepsy. The proposed method is noninvasive in nature and easy to implement. It has the potential to be incorporated in current presurgical workup for the diagnosis of intractable focal epilepsy patients.
PMID: 25570062 [PubMed - as supplied by publisher]
The smarter, the stronger: Intelligence level correlates with brain resilience to systematic insults.
Cortex. 2014 Dec 2;64C:293-309
Authors: Santarnecchi E, Rossi S, Rossi A
Neuroimaging evidences posit human intelligence as tightly coupled with several structural and functional brain properties, also suggesting its potential protective role against aging and neurodegenerative conditions. However, whether higher order cognition might in fact lead to a more resilient brain has not been quantitatively demonstrated yet. Here we document a relationship between individual intelligence quotient (IQ) and brain resilience to targeted and random attacks, as measured through resting-state fMRI graph-theoretical analysis in 102 healthy individuals. In this modeling context, enhanced brain robustness to targeted attacks (TA) in individuals with higher IQ is supported by an increased distributed processing capacity despite the systematic loss of the most important node(s) of the system. Moreover, brain resilience in individuals with higher IQ is supported by a set of neocortical regions mainly belonging to language and memory processing network(s), whereas regions related to emotional processing are mostly responsible for lower IQ individuals. Results suggest intelligence level among the predictors of post-lesional or neurodegenerative recovery, also promoting the evolutionary role of higher order cognition, and simultaneously suggesting a new framework for brain stimulation interventions aimed at counteract brain deterioration over time.
PMID: 25569764 [PubMed - as supplied by publisher]
Early-course unmedicated schizophrenia patients exhibit elevated prefrontal connectivity associated with longitudinal change.
J Neurosci. 2015 Jan 7;35(1):267-86
Authors: Anticevic A, Hu X, Xiao Y, Hu J, Li F, Bi F, Cole MW, Savic A, Yang GJ, Repovs G, Murray JD, Wang XJ, Huang X, Lui S, Krystal JH, Gong Q
Strong evidence implicates prefrontal cortex (PFC) as a major source of functional impairment in severe mental illness such as schizophrenia. Numerous schizophrenia studies report deficits in PFC structure, activation, and functional connectivity in patients with chronic illness, suggesting that deficient PFC functional connectivity occurs in this disorder. However, the PFC functional connectivity patterns during illness onset and its longitudinal progression remain uncharacterized. Emerging evidence suggests that early-course schizophrenia involves increased PFC glutamate, which might elevate PFC functional connectivity. To test this hypothesis, we examined 129 non-medicated, human subjects diagnosed with early-course schizophrenia and 106 matched healthy human subjects using both whole-brain data-driven and hypothesis-driven PFC analyses of resting-state fMRI. We identified increased PFC connectivity in early-course patients, predictive of symptoms and diagnostic classification, but less evidence for "hypoconnectivity." At the whole-brain level, we observed "hyperconnectivity" around areas centered on the default system, with modest overlap with PFC-specific effects. The PFC hyperconnectivity normalized for a subset of the sample followed longitudinally (n = 25), which also predicted immediate symptom improvement. Biologically informed computational modeling implicates altered overall connection strength in schizophrenia. The initial hyperconnectivity, which may decrease longitudinally, could have prognostic and therapeutic implications.
PMID: 25568120 [PubMed - in process]
Spatial and temporal characteristics of error-related activity in the human brain.
J Neurosci. 2015 Jan 7;35(1):253-66
Authors: Neta M, Miezin FM, Nelson SM, Dubis JW, Dosenbach NU, Schlaggar BL, Petersen SE
A number of studies have focused on the role of specific brain regions, such as the dorsal anterior cingulate cortex during trials on which participants make errors, whereas others have implicated a host of more widely distributed regions in the human brain. Previous work has proposed that there are multiple cognitive control networks, raising the question of whether error-related activity can be found in each of these networks. Thus, to examine error-related activity broadly, we conducted a meta-analysis consisting of 12 tasks that included both error and correct trials. These tasks varied by stimulus input (visual, auditory), response output (button press, speech), stimulus category (words, pictures), and task type (e.g., recognition memory, mental rotation). We identified 41 brain regions that showed a differential fMRI BOLD response to error and correct trials across a majority of tasks. These regions displayed three unique response profiles: (1) fast, (2) prolonged, and (3) a delayed response to errors, as well as a more canonical response to correct trials. These regions were found mostly in several control networks, each network predominantly displaying one response profile. The one exception to this "one network, one response profile" observation is the frontoparietal network, which showed prolonged response profiles (all in the right hemisphere), and fast profiles (all but one in the left hemisphere). We suggest that, in the place of a single localized error mechanism, these findings point to a large-scale set of error-related regions across multiple systems that likely subserve different functions.
PMID: 25568119 [PubMed - in process]
Abnormal Resting State fMRI Activity Predicts Processing Speed Deficits in First-Episode Psychosis.
Neuropsychopharmacology. 2015 Jan 8;
Authors: Argyelan M, Gallego JA, Robinson DG, Ikuta T, Sarpal D, John M, Kingsley PB, Kane J, Malhotra AK, Szeszko PR
Little is known regarding the neuropsychological significance of resting state functional magnetic resonance imaging (rs-fMRI) activity early in the course of psychosis. Moreover, no studies have used different approaches for analysis of rs-fMRI activity and examined gray matter thickness in the same cohort. In this study 41 patients experiencing a first-episode of psychosis (including N=17 who were antipsychotic drug-naïve at the time of scanning) and 41 individually age- and sex-matched healthy volunteers completed rs-fMRI and structural magnetic resonance imaging exams and neuropsychological assessments. We computed correlation matrices for 266 regions-of-interest across the brain to assess global connectivity. In addition, independent component analysis (ICA) was used to assess group differences in the expression of rs-fMRI activity within 20 predefined publicly available templates. Patients demonstrated lower overall rs-fMRI global connectivity compared to healthy volunteers without associated group differences in gray matter thickness assessed within the same regions-of-interest used in this analysis. Similarly, ICA revealed worse rs-fMRI expression scores across all 20 networks in patients compared to healthy volunteers with posthoc analyses revealing significant (p <.05; corrected) abnormalities within the caudate nucleus and planum temporale. Worse processing speed correlated significantly with overall lower global connectivity using the region-of-interest approach and lower expression scores within the planum temporale using ICA. Our findings implicate dysfunction in rs-fMRI activity in first-episode psychosis prior to extensive antipsychotic treatment using different analytic approaches (in the absence of concomitant gray matter structural differences) that predict processing speed.Neuropsychopharmacology accepted article preview online, 08 January 2015. doi:10.1038/npp.2015.7.
PMID: 25567423 [PubMed - as supplied by publisher]
Frequency-specific network topologies in the resting human brain.
Front Hum Neurosci. 2014;8:1022
Authors: Sasai S, Homae F, Watanabe H, Sasaki AT, Tanabe HC, Sadato N, Taga G
A community is a set of nodes with dense inter-connections, while there are sparse connections between different communities. A hub is a highly connected node with high centrality. It has been shown that both "communities" and "hubs" exist simultaneously in the brain's functional connectivity network (FCN), as estimated by correlations among low-frequency spontaneous fluctuations in functional magnetic resonance imaging (fMRI) signal changes (0.01-0.10 Hz). This indicates that the brain has a spatial organization that promotes both segregation and integration of information. Here, we demonstrate that frequency-specific network topologies that characterize segregation and integration also exist within this frequency range. In investigating the coherence spectrum among 87 brain regions, we found that two frequency bands, 0.01-0.03 Hz (very low frequency [VLF] band) and 0.07-0.09 Hz (low frequency [LF] band), mainly contributed to functional connectivity. Comparing graph theoretical indices for the VLF and LF bands revealed that the network in the former had a higher capacity for information segregation between identified communities than the latter. Hubs in the VLF band were mainly located within the anterior cingulate cortices, whereas those in the LF band were located in the posterior cingulate cortices and thalamus. Thus, depending on the timescale of brain activity, at least two distinct network topologies contributed to information segregation and integration. This suggests that the brain intrinsically has timescale-dependent functional organizations.
PMID: 25566037 [PubMed - as supplied by publisher]