Classification of fMRI independent components using IC-fingerprints and support vector machine classifiers

A survey of brain functional network extraction methods using fMRI data

Functional network (FN) analyses play a pivotal role in uncovering insights into brain function and understanding the pathophysiology of various brain disorders. This paper focuses on classical and advanced methods for deriving brain FNs from functional magnetic resonance imaging (fMRI) data. We systematically review their foundational principles, advantages, shortcomings, and interrelations, encompassing both static and dynamic FN extraction approaches. In the context of static FN extraction, we present hypothesis-driven methods such as region of interest (ROI)-based approaches as well as data-driven methods including matrix decomposition, clustering, and deep learning. For dynamic FN extraction, both window-based and windowless methods are surveyed with respect to the estimation of time-varying FN and the subsequent computation of FN states. We also discuss the scope of application of the various methods and avenues for future improvements.

Evaluating the effect of denoising submillimeter auditory fMRI data with NORDIC

Functional magnetic resonance imaging (fMRI) has emerged as an essential tool for exploring human brain function. Submillimeter fMRI, in particular, has emerged as a tool to study mesoscopic computations. The inherently low signal-to-noise ratio (SNR) at submillimeter resolutions warrants the use of denoising approaches tailored at reducing thermal noise - the dominant contributing noise component in high resolution fMRI. NORDIC PCA is one of such approaches, and has been benchmarked against other approaches in several applications. Here, we investigate the effects that two versions of NORDIC denoising have on auditory submillimeter data. As investigating auditory functional responses poses unique challenges, we anticipated that the benefit of this technique would be especially pronounced. Our results show that NORDIC denoising improves the detection sensitivity and the reliability of estimates in submillimeter auditory fMRI data. These effects can be explained by the reduction of the noise-induced signal variability. However, we also observed a reduction in the average response amplitude (percent signal), which may suggest that a small amount of signal was also removed. We conclude that, while evaluating the effects of the signal reduction induced by NORDIC may be necessary for each application, using NORDIC in high resolution auditory fMRI studies may be advantageous because of the large reduction in variability of the estimated responses.

Brain perfusion imaging by multi-delay arterial spin labeling: Impact of modeling dispersion and interaction with denoising strategies and pathology

PURPOSE

Arterial spin labeling (ASL) acquisitions at multiple post-labeling delays may provide more accurate quantification of cerebral blood flow (CBF), by fitting appropriate kinetic models and simultaneously estimating relevant parameters such as the arterial transit time (ATT) and arterial cerebral blood volume (aCBV). We evaluate the effects of denoising strategies on model fitting and parameter estimation when accounting for the dispersion of the label bolus through the vasculature in cerebrovascular disease.

METHODS

We analyzed multi-delay ASL data from 17 cerebral small vessel disease patients (50 ± 9 y) and 13 healthy controls (52 ± 8 y), by fitting an extended kinetic model with or without bolus dispersion. We considered two denoising strategies: removal of structured noise sources by independent component analysis (ICA) of the control-label image timeseries; and averaging the repetitions of the control-label images prior to model fitting.

RESULTS

Modeling bolus dispersion improved estimation precision and impacted parameter values, but these effects strongly depended on whether repetitions were averaged before model fitting. In general, repetition averaging improved model fitting but adversely affected parameter values, particularly CBF and aCBV near arterial locations in patients. This suggests that using all repetitions allows better noise estimation at the earlier delays. In contrast, ICA denoising improved model fitting and estimation precision while leaving parameter values unaffected.

CONCLUSION

Our results support the use of ICA denoising to improve model fitting to multi-delay ASL and suggest that using all control-label repetitions improves the estimation of macrovascular signal contributions and hence perfusion quantification near arterial locations. This is important when modeling flow dispersion in cerebrovascular pathology.

Aortic valve Replacement compared to Transcatheter Implant and its relationship with COgnitive Impairment (ARTICO) evaluated with neuropsychological and advanced neuroimaging: a longitudinal cohort study

BACKGROUND

Aortic stenosis is the most common valvulopathy in Western countries. The treatment of choice had been surgery aortic valve replacement (SAVR), but the improvement in endovascular approaches as transcatheter aortic valve implantation (TAVI), initially reserved for patients with very high surgical risk, has been extended to high and intermediate, and recently also to low-risk patients. Stroke and vascular cognitive impairment are the most important complications. It is not entirely clear which technique is best to avoid these complications as well as their impact. Our goal is to evaluate changes in cognitive performance in the early (1-month) and late (1-year) postoperative period in patients undergoing SAVR or TAVI, by extensive neuropsychological study (NRP) and advanced Magnetic Resonance Imaging (MRI). Specifically, to compare early and late cognitive changes after the intervention between both groups, the occurrence of stroke during follow-up and to compare the appearance of silent vascular lesions and changes in brain activity and functional connectivity with functional MRI during follow-up between both groups.

METHODS/DESIGN

Prospective longitudinal cohort study. A non-selected representative sample of 80 subjects, 40 SAVR and 40 TAVI to obtain a final sample of 36 eligible subjects in each group, ranging from 70 to 85 years old, with indication for aortic replacement and intermediate or high surgical risk will be studied. At baseline, within one month before the treatment, all individuals will undergo an extensive NRP and advanced MRI study. These studies will also be performed 1-month and 1-year after treatment, to assess the appearance of new vascular lesions, as well as changes in cognitive performance with respect to baseline.

DISCUSSION

This study aims to evaluate changes in cognitive performance as well as both clinical and silent vascular events occurring in the early (1-month) and late (1-year) periods after SAVR and TAVI. We will also analyze the correlation between neuropsychological and neuroimaging approaches in order to evaluate cognition. Therefore, it may provide high-quality data of cognitive changes and vascular events for both techniques, and be useful to tailor interventions to individual characteristics and ultimately aiding in decision-making.

TRIAL REGISTRATION

This study is register in Clinicaltrials.gov (NCT05235529) on 11th February 2022.

Detection of autism spectrum disorder using graph representation learning algorithms and deep neural network, based on fMRI signals

Introduction

Can we apply graph representation learning algorithms to identify autism spectrum disorder (ASD) patients within a large brain imaging dataset? ASD is mainly identified by brain functional connectivity patterns. Attempts to unveil the common neural patterns emerged in ASD are the essence of ASD classification. We claim that graph representation learning methods can appropriately extract the connectivity patterns of the brain, in such a way that the method can be generalized to every recording condition, and phenotypical information of subjects. These methods can capture the whole structure of the brain, both local and global properties.

Methods

The investigation is done for the worldwide brain imaging multi-site database known as ABIDE I and II (Autism Brain Imaging Data Exchange). Among different graph representation techniques, we used AWE, Node2vec, Struct2vec, multi node2vec, and Graph2Img. The best approach was Graph2Img, in which after extracting the feature vectors representative of the brain nodes, the PCA algorithm is applied to the matrix of feature vectors. The classifier adapted to the features embedded in graphs is an LeNet deep neural network.

Results and discussion

Although we could not outperform the previous accuracy of 10-fold cross-validation in the identification of ASD versus control patients in this dataset, for leave-one-site-out cross-validation, we could obtain better results (our accuracy: 80%). The result is that graph embedding methods can prepare the connectivity matrix more suitable for applying to a deep network.

A comprehensive investigation of physiologic noise modeling in resting state fMRI; time shifted cardiac noise in EPI and its removal without external physiologic signal measures

Hemodynamic cardiac and respiratory-cycle fluctuations are a source of unwanted non-neuronal signal components, often called physiologic noise, in resting state (rs-) fMRI studies. Here, we use image-based retrospective correction of physiological motion (RETROICOR) with externally measured physiologic signals to investigate cardiac and respiratory hemodynamic phase functions reflected in rs-fMRI data. We find that the cardiac phase function is time shifted locally, while the respiratory phase function is described as single, fixed phase form across the brain. In light of these findings, we propose an update to Physiologic EStimation by Temporal ICA (PESTICA), our publically available software package that estimates physiologic signals when external physiologic measures are not available. This update incorporates: 1) auto-selection of slicewise physiologic regressors and generation of physiologic fixed phase regressors with total slices/TR sampling rate, 2) Fourier series expansion of the cardiac fixed phase regressor to account for time delayed cardiac noise 3) removal of cardiac and respiratory noise in imaging data. We compare the efficacy of the updated method to RETROICOR.

Deep Attentive Spatio-Temporal Feature Learning for Automatic Resting-State fMRI Denoising

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive functional neuroimaging modality that has been widely used to investigate functional connectomes in the brain. Since noise and artifacts generated by non-neuronal physiological activities are predominant in raw rs-fMRI data, effective noise removal is one of the most important preprocessing steps prior to any subsequent analysis. For rs-fMRI denoising, a common trend is to decompose rs-fMRI data into multiple components and then regress out noise-related components. Therefore, various machine learning techniques have been used in such analyses with predefined procedures and manually engineered features. However, the lack of a universal definition of a noise-related source or artifact complicates manual feature engineering. Manual feature selection can result in the failure to capture unknown types of noise. Furthermore, the possibility that the hand-crafted features will only work for the broader population (e.g., healthy adults) but not for "outliers" (e.g., infants or subjects that belong to a disease cohort) is quite high. In practice, we have limited knowledge of which features should be extracted; thus, multi-classifier assembly must be implemented to improve performance, although this process is quite time-consuming. However, in real rs-fMRI applications, fast and accurate automatic identification of noise-related components on different datasets is critical. To solve this problem, we propose a novel, automatic, and end-to-end deep learning framework dedicated to noise-related component identification via a faster and more effective multi-layer feature extraction strategy that learns deeply embedded spatio-temporal features of the components. In this study, we achieved remarkable performance on various rs-fMRI datasets, including multiple adult rs-fMRI datasets from different rs-fMRI studies and an infant rs-fMRI dataset, which is quite heterogeneous and differs from that of adults. Our proposed framework also dramatically increases the noise detection speed owing to its inherent ability for deep learning (< 1s for single-component classification). It can be easily integrated into any preprocessing pipeline, even those that do not use standard procedures but depend on alternative toolboxes.

Associations between childhood chronic stress and dynamic functional connectivity in drug-naïve, first-episode adolescent MDD

BACKGROUND

We explored the associations between chronic stress and dynamic working patterns of the whole brain using resting state MRI data in drug-naïve, first-episode adolescents with major depressive disorder (MDD).

METHODS

We compared dynamic functional connectivity (dyn-FC) and screen out networks with difference in whole brain between 45 healthy controls (HC) and 60 adolescent MDD patients using dynamic independent components analysis. In each of these networks with difference between groups, hub brain regions were selected as functionally connected to more than 30 brain regions at the same time. Then we extracted the dyn-FC coefficients of each hub brain region with other brain regions in each component at different time points and calculated the average value of the entire scan time. Finally, we explored correlations between these average values of the entire scan time and scores on the Childhood Chronic Stress Questionnaire (CCSQ).

RESULTS

We found three networks as well as some hub brain regions with different dyn-FC patterns between adolescent MDD and HC. Scores on the CCSQ were found to correlate with dynamic FC between hub brain areas and certain other brain areas in MDD patients.

LIMITATIONS

our cross-sectional study design does not allow us to speculate about causality between chronic stress and depression. Prospective cohort studies should explore in detail how the changes in dynamic FC appear and evolve during MDD.

CONCLUSIONS

Chronic stress is related with the brain dynamic working patterns in adolescent MDD.

Beyond Massive Univariate Tests: Covariance Regression Reveals Complex Patterns of Functional Connectivity Related to Attention-Deficit/Hyperactivity Disorder, Age, Sex, and Response Control

Background

Studies of brain functional connectivity (FC) typically involve massive univariate tests, performing statistical analysis on each individual connection. In this study, we apply a novel whole-matrix regression approach referred to as covariate assisted principal regression to identify resting-state FC brain networks associated with attention-deficit/hyperactivity disorder (ADHD) and response control.

Methods

Participants included 8- to 12-year-old children with ADHD (n = 115; 29 girls) and typically developing control children (n = 102; 35 girls) who completed a resting-state functional magnetic resonance imaging scan and a Go/NoGo task. We modeled three sets of covariates to identify resting-state networks associated with an ADHD diagnosis, sex, and response inhibition (commission errors) and variability (ex-Gaussian parameter tau).

Results

The first network includes FC between striatal-cognitive control (CC) network subregions and thalamic-default mode network (DMN) subregions and is positively related to age. The second consists of FC between CC-visual-somatomotor regions and between CC-DMN subregions and is positively associated with response variability in boys with ADHD. The third consists of FC within the DMN and between DMN-CC-visual regions and differs between boys with and without ADHD. The fourth consists of FC between visual-somatomotor regions and between visual-DMN regions and differs between girls and boys with ADHD and is associated with response inhibition and variability in boys with ADHD. Unique networks were also identified in each of the three models, suggesting some specificity to the covariates of interest.

Conclusions

These findings demonstrate the utility of our novel covariance regression approach to studying functional brain networks relevant for development, behavior, and psychopathology.

Locked-in Intact Functional Networks in Children with Autism Spectrum Disorder: A Case-Control Study

Resting-state functional magnetic resonance imaging (rs-fMRI) has the potential to investigate abnormalities in brain network structure and connectivity on an individual level in neurodevelopmental disorders, such as autism spectrum disorder (ASD), paving the way toward using this technology for a personalized, precision medicine approach to diagnosis and treatment. Using a case-control design, we compared five patients with severe regressive-type ASD to five patients with temporal lobe epilepsy (TLE) to examine the association between brain network characteristics and diagnosis. All children with ASD and TLE demonstrated intact motor, language, and frontoparietal (FP) networks. However, aberrant networks not usually seen in the typical brain were also found. These aberrant networks were located in the motor (40%), language (80%), and FP (100%) regions in children with ASD, while children with TLE only presented with aberrant networks in the motor (40%) and language (20%) regions, in addition to identified seizure onset zones. Fisher's exact test indicated a significant relationship between aberrant FP networks and diagnosis (p = 0.008), with ASD and atypical FP networks co-occurring more frequently than expected by chance. Despite severe cognitive delays, children with regressive-type ASD may demonstrate intact typical cortical network activation despite an inability to use these cognitive facilities. The functions of these intact cognitive networks may not be fully expressed, potentially because aberrant networks interfere with their long-range signaling, thus creating a unique "locked-in network" syndrome.

Semantic verbal fluency brain network: delineating a physiological basis for the functional hubs using dual-echo ASL and graph theory approach

Objective. Semantic verbal fluency (SFV) is a cognitive process that engages and modulates specific brain areas related to language comprehension and production, decision making, response inhibition, and memory retrieval. The impairment of the brain network responsible for these functions is related to various neurological conditions, and different strategies have been proposed to assess SVF-related deficits in such diseases. In the present study, the concomitant changes of brain perfusion and functional connectivity were investigated during the resting state and SVF task performance.Approach. Arterial spin labeling (ASL), a perfusion-based magnetic resonance imaging (MRI) method, was used with a pseudocontinuous labeling approach and dual-echo readout in 28 healthy right-handed Brazilian Portuguese speakers. The acquisition was performed in a resting state condition and during the performance of a SVF task.Main results. During task performance, a significant increase in cerebral blood flow (CBF) was observed in language-related regions of the frontal lobe, including Brodmann's areas 6, 9, 45, and 47, associated with semantic processing, word retrieval, and speech motor programming. Such regions, along with the posterior cingulate, showed a crucial role in the SVF functional network, assessed by seed-to-voxel and graph analysis. Our approach successfully overcame the generalization problem regarding functional MRI (fMRI) graph analysis with cognitive, task-based paradigms. Moreover, the CBF maps enabled the functional assessment of orbital frontal and temporal regions commonly affected by magnetic susceptibility artifacts in conventional T2*-weighted fMRI approaches.Significance. Our results demonstrated the capability of ASL to evaluate perfusion alterations and functional patterns simultaneously regarding the SVF network providing a quantitative physiological basis to functional hubs in this network, which may support future clinical studies.

Stable Meta-Networks, Noise, and Artifacts in the Human Connectome: Low- to High-Dimensional Independent Components Analysis as a Hierarchy of Intrinsic Connectivity Networks

Connectivity within the human connectome occurs between multiple neuronal systems-at small to very large spatial scales. Independent component analysis (ICA) is potentially a powerful tool to facilitate multi-scale analyses. However, ICA has yet to be fully evaluated at very low (10 or fewer) and ultra-high dimensionalities (200 or greater). The current investigation used data from the Human Connectome Project (HCP) to determine the following: (1) if larger networks, or meta-networks, are present at low dimensionality, (2) if nuisance sources increase with dimensionality, and (3) if ICA is prone to overfitting. Using bootstrap ICA, results suggested that, at very low dimensionality, ICA spatial maps consisted of Visual/Attention and Default/Control meta-networks. At fewer than 10 components, well-known networks such as the Somatomotor Network were absent from results. At high dimensionality, nuisance sources were present even in denoised high-quality data but were identifiable by correlation with tissue probability maps. Artifactual overfitting occurred to a minor degree at high dimensionalities. Basic summary statistics on spatial maps (maximum cluster size, maximum component weight, and average weight outside of maximum cluster) quickly and easily separated artifacts from gray matter sources. Lastly, by using weighted averages of bootstrap stability, even ultra-high dimensional ICA resulted in highly reproducible spatial maps. These results demonstrate how ICA can be applied in multi-scale analyses, reliably and accurately reproducing the hierarchy of meta-networks, large-scale networks, and subnetworks, thereby characterizing cortical connectivity across multiple spatial scales.

"Impact of ICA Dimensionality on the Test-Retest Reliability of Resting-State Functional Connectivity

As resting-state functional connectivity (rsFC) research moves toward the study of individual differences, test-retest reliability is increasingly important to understand. Previous literature supports the test-retest reliability of rsFC derived with independent component analysis (ICA) and dual regression, yet the impact of dimensionality (i.e., the number of components to extract from group-ICA) remained obscure in the current context of large-scale datasets. To provide principled guidelines on this issue, ICA at dimensionalities varying from 25 to 350 was applied to the cortical surface with resting-state functional magnetic resonance imaging data from 1003 participants in the Human Connectome Project. The reliability of two rsFC measures: (within-component) coherence and (between-component) connectivity was estimated. Reliability and its change with dimensionality varied by network: the cognitive (frontoparietal, cingulo-opercular, dorsal attention, and default) networks were measured with the highest reliability which improved with increased dimensionality until at least 150; the visual and somatomotor networks were measured with lower reliability which benefited mildly from increased dimensionality; the temporal pole/orbitofrontal cortex (TP/OFC) network was measured with the lowest reliability. Overall, ICA reliability was optimized at dimensionalities of 150 or above. Compared with two popular binary, non-overlapping cortical atlases, ICA and dual regression resulted in higher reliability for the cognitive networks, lower reliability for the somatomotor network, and similar reliability for the visual and TP/OFC networks. These findings highlight analytical decisions that maximize the reliability of rsFC measures and how they depend on one's networks of interest.

A novel spatiotemporal tool for the automatic classification of fMRI noise based on Independent Component Analysis

In this study, a semi-automatic, easy-to-use classification method for the identification and removal of fMRI noise is proposed and tested. The method relies on subject-level spatial independent component analysis (ICA) of fMRI data. Starting from a reference set of labeled independent components (ICs), novel ICs are classified as physiological/artefactual by combining a spatial correlation (SC) analysis with the reference ICs and relative power spectral (PS) analysis. Here, ICs from a task-based fMRI dataset were used as reference. SC and SP thresholds were set using a test dataset (5 subjects, same fMRI protocol) based on Receiving Operating Characteristic curves. The tool performance and versatility were measured on a resting-state fMRI dataset (5 subjects). Our results show that the method can automatically identify noise-related ICs with accuracy, specificity and sensitivity higher than 80% across different fMRI protocols. These findings also suggest that the reference set provided in the present study might be used to mark ICs coming from independent taskrelated or resting-state fMRI datasets.Clinical relevance- The new method will be included in a userfriendly, open-source tool for removal of noisy contributions from fMRI datasets to be used in clinical and research practices.

Aberrant functional connectivity in resting state networks of ADHD patients revealed by independent component analysis

Background

ADHD is one of the most common psychiatric disorders in children and adolescents. Altered functional connectivity has been associated with ADHD symptoms. This study aimed to investigate abnormal changes in the functional connectivity of resting-state brain networks (RSNs) among adolescent patients with different subtypes of ADHD.

Methods

The data were obtained from the ADHD-200 Global Competition, including fMRI data from 88 ADHD patients (56 patients of ADHD-Combined, ADHD-C and 32 patients of ADHD-Inattentive, ADHD-I) and 67 typically developing controls (TD-C). Group ICA was utilized to research aberrant brain functional connectivity within the different subtypes of ADHD.

Results

In comparison with the TD-C group, the ADHD-C group showed clusters of decreased functional connectivity in the left inferior occipital gyrus (p = 0.0041) and right superior occipital gyrus (p = 0.0011) of the dorsal attention network (DAN), supplementary motor area (p = 0.0036) of the executive control network (ECN), left supramarginal gyrus (p = 0.0081) of the salience network (SN), middle temporal gyrus (p = 0.0041), and superior medial frontal gyrus (p = 0.0055) of the default mode network (DMN), while the ADHD-I group showed decreased functional connectivity in the right superior parietal gyrus (p = 0.0017) of the DAN and left middle temporal gyrus (p = 0.0105) of the DMN. In comparison with the ADHD-I group, the ADHD-C group showed decreased functional connectivity in the superior temporal gyrus (p = 0.0062) of the AN, inferior temporal gyrus (p = 0.0016) of the DAN, and the dorsolateral superior frontal gyrus (p = 0.0082) of the DMN. All the clusters surviving at p < 0.05 (AlphaSim correction).

Conclusion

The results suggested that decreased functional connectivity within the DMN and DAN was responsible, at least in part, for the symptom of inattention in ADHD-I patients. Similarly, we believed that the impaired functional connectivity within networks may contribute to the manifestations of ADHD-C patients, including inattention, hyperactivity/impulsivity, and unconscious movements.

Effects of Maternal Fish Oil and/or 5-Methyl-Tetrahydrofolate Supplementation during Pregnancy on Offspring Brain Resting-State at 10 Years Old: A Follow-Up Study from the NUHEAL Randomized Controlled Trial

Recent studies have shown that maternal supplementation with folate and long-chain polyunsaturated fatty acids (LC-PUFAs) during pregnancy may affect children's brain development. We aimed at examining the potential long-term effect of maternal supplementation with fish oil (FO) and/or 5-methyl-tetrahydrofolate (5-MTHF) on the brain functionality of offspring at the age of 9.5-10 years. The current study was conducted as a follow-up of the Spanish participants belonging to the Nutraceuticals for a Healthier Life (NUHEAL) project; 57 children were divided into groups according to mother's supplementation and assessed through functional magnetic resonance imaging (fMRI) scanning and neurodevelopment testing. Independent component analysis and double regression methods were implemented to investigate plausible associations. Children born to mothers supplemented with FO (FO and FO + 5-MTHF groups, n = 33) showed weaker functional connectivity in the default mode (DM) (angular gyrus), the sensorimotor (SM) (motor and somatosensory cortices) and the fronto-parietal (FP) (angular gyrus) networks compared to the No-FO group (placebo and 5-MTHF groups, n = 24) (PFWE < 0.05). Furthermore, no differences were found regarding the neuropsychological tests, except for a trend of better results in an object recall (memory) test. Considering the No-FO group, the aforementioned networks were associated negatively with attention and speed-processing functions. Mother's FO supplementation during pregnancy seems to be able to shape resting-state network functioning in their children at school age and appears to produce long-term effects on children´s cognitive processing.

Anomalous intrinsic connectivity within and between visual and auditory networks in major depressive disorder

OBJECTIVE

Major depressive disorder (MDD) is a ubiquitous mental illness with heterogeneous symptoms, however, the pathophysiology mechanisms are still not fully understood. Clinical and preclinical studies suggested that depression could cause disturbances in sensory perception systems, disruptions in auditory and visual functions may serve as an essential clinical features underlying MDD.

METHODS

The current study investigated the abnormal intrinsic connectivity within and between visual and auditory networks in 95 MDD patients and 97 age-, gender-, education level-matched healthy controls (HCs) by using resting-state functional magnetic resonance imaging (fMRI). One auditory network (AN) and three visual components including visual component 1 (VC1), VC2, and VC3 were identified by using independent component analysis method based on the fMRI networks during the resting state with the largest spatial correlations, combining with brain regions and specific network templates.

RESULTS

We found that MDD could be characterized by the following disrupted network model relative to HCs: (i) reduced within-network connectivity in the AN, VC2, and VC3; (ii) reduced between-network connectivity between the AN and the VC3. Furthermore, aberrant functional connectivity (FC) within the visual network was linked to the clinical symptoms.

CONCLUSIONS

Overall, our results demonstrated that abnormalities of FC in perception systems including intrinsic visual and auditory networks may explain neurobiological mechanisms underlying MDD and could serve as a potential effective biomarker.

Decreased effective connection from the parahippocampal gyrus to the prefrontal cortex in Internet gaming disorder: A MVPA and spDCM study

OBJECTIVES

Understanding the neural mechanisms underlying Internet gaming disorder (IGD) is essential for the condition's diagnosis and treatment. Nevertheless, the pathological mechanisms of IGD remain elusive at present. Hence, we employed multi-voxel pattern analysis (MVPA) and spectral dynamic causal modeling (spDCM) to explore this issue.

METHODS

Resting-state fMRI data were collected from 103 IGD subjects (male = 57) and 99 well-matched recreational game users (RGUs, male = 51). Regional homogeneity was calculated as the feature for MVPA based on the support vector machine (SVM) with leave-one- out cross-validation. Mean time series data extracted from the brain regions in accordance with the MVPA results were used for further spDCM analysis.

RESULTS

Results display a high accuracy of 82.67% (sensitivity of 83.50% and specificity of 81.82%) in the classification of the two groups. The most discriminative brain regions that contributed to the classification were the bilateral parahippocampal gyrus (PG), right anterior cingulate cortex (ACC), and middle frontal gyrus (MFG). Significant correlations were found between addiction severity (IAT and DSM scores) and the ReHo values of the brain regions that contributed to the classification. Moreover, the results of spDCM showed that compared with RGU, IGD showed decreased effective connectivity from the left PG to the right MFG and from the right PG to the ACC and decreased self-connection in the right PG.

CONCLUSIONS

These results show that the weakening of the PG and its connection with the prefrontal cortex, including the ACC and MFG, may be an underlying mechanism of IGD.

Prospective motion correction of fMRI: Improving the quality of resting state data affected by large head motion

The quality of functional MRI (fMRI) data is affected by head motion. It has been shown that fMRI data quality can be improved by prospectively updating the gradients and radio-frequency pulses in response to head motion during image acquisition by using an MR-compatible optical tracking system (prospective motion correction, or PMC). Recent studies showed that PMC improves the temporal Signal to Noise Ratio (tSNR) of resting state fMRI data (rs-fMRI) acquired from subjects not moving intentionally. Besides that, the time courses of Independent Components (ICs), resulting from Independent Component Analysis (ICA), were found to present significant temporal correlation with the motion parameters recorded by the camera. However, the benefits of applying PMC for improving the quality of rs-fMRI acquired under large head movements and its effects on resting state networks (RSN) and connectivity matrices are still unknown. In this study, subjects were instructed to cross their legs at will while rs-fMRI data with and without PMC were acquired, which generated head motion velocities ranging from 4 to 30 ​mm/s. We also acquired fMRI data without intentional motion. Independent component analysis of rs-fMRI was performed to evaluate IC maps and time courses of RSNs. We also calculated the temporal correlation among different brain regions and generated connectivity matrices for the different motion and PMC conditions. In our results we verified that the crossing leg movements reduced the tSNR of sessions without and with PMC by 45 and 20%, respectively, when compared to sessions without intentional movements. We have verified an interaction between head motion speed and PMC status, showing stronger attenuation of tSNR for acquisitions without PMC than for those with PMC. Additionally, the spatial definition of major RSNs, such as default mode, visual, left and right central executive networks, was improved when PMC was enabled. Furthermore, motion altered IC-time courses by decreasing power at low frequencies and increasing power at higher frequencies (typically associated with artefacts). PMC partially reversed these alterations of the power spectra. Finally, we showed that PMC provides temporal correlation matrices for data acquired under motion conditions more comparable to those obtained by fMRI sessions where subjects were instructed not to move.

Heart rate variability as a biomarker in health and affective disorders: A perspective on neuroimaging studies

The dynamic embodiment of psychological processes is evident in the association of health outcomes, behavioural traits and psychological functioning with Heart Rate Variability (HRV). The dominant high-frequency component of HRV is an index of the central neural control of heart rhythm, mediated via the parasympathetic vagus nerve. HRV provides a potential objective measure of action policies for the adaptive and predictive allostatic regulation of homeostasis within the cardiovascular system. In its support, a network of brain regions (referred to as the 'central autonomic network') maps internal state, and controls autonomic responses. This network includes regions of prefrontal cortex, anterior cingulate cortex, insula, amygdala, periaqueductal grey, pons and medulla. Human neuroimaging studies of neural activation and functional connectivity broadly endorse this architecture, and its link with cardiac regulation at rest and dysregulation in clinical states that include affective disorders. In this review, we appraise neuroimaging research and related evidence for HRV as an informative marker of autonomic integration with affect and cognition, taking a perspective on function and organisation. We consider evidence for the utility of HRV as a metric to inform targeted interventions to improve autonomic and affective dysregulation, and suggest research questions for further investigation.

Somatic symptoms disorders in Parkinson's disease are related to default mode and salience network dysfunction

Background

Somatic Symptoms Disorder (SSD) has been shown to have a clinically very high prevalence in Parkinson's Disease (PD) with frequencies ranging from 7.0% to 66.7%, higher than in the general population (10%- 25%).

SSD has been associated with dysfunction in Default Mode and Salience network.

Aim

With the present study we aim to verify by means of resting state functional MRI whether possible specific abnormalities in the activation and functional connectivity of the default mode network (DMN) and salience network in cognitively intact PD patients may be more prominent in PD patients with somatic symptoms (SSD-PD) as compared with patients without SSD (PD).

Methods

Eighteen SSD-PD patients (61% male), 18 PD patients (83% male) and 22 healthy age-matched subjects (59% male) were enrolled in the study and underwent resting state functional MRI.

Results

fractional amplitude of low-frequency fluctuation (fALFF) showed reduced activity in bilateral lateral parietal cortex and in left anterior insula in both SSD-PD and PD compared to control group. Functional connectivity (FC) values in the DMN areas and between DMN and salience network areas were found to be lower in SSD-PD than in control group and PD. No significant correlation was found between fMRI results and demographic and clinical variables, excluding the effect of possible confounders on fMRI results.

The present study, showing reduced activity in bilateral parietal areas and in the left anterior insula as compared to healthy controls, suggests a dysfunction of the DMN and salience network in PD, either with or without SSD.

The FC reduction within DMN areas and between DMN and salience network areas in SSD-PD patients suggests a role of dysfunctional connectivity in the resting state network of patients with SSD.

•

Reduced activity in parietal areas and in anterior insula in Parkinson's Disease.

•

Functional connectivity is lower in Parkinson's disease with somatic symptoms.

•

Somatic Symptoms in PD are related to default mode and salience network alterations.

ICA-based denoising for ASL perfusion imaging

Arterial Spin Labelling (ASL) imaging derives a perfusion image by tracing the accumulation of magnetically labeled blood water in the brain. As the image generated has an intrinsically low signal to noise ratio (SNR), multiple measurements are routinely acquired and averaged, at a penalty of increased scan duration and opportunity for motion artefact. However, this strategy alone might be ineffective in clinical settings where the time available for acquisition is limited and patient motion are increased. This study investigates the use of an Independent Component Analysis (ICA) approach for denoising ASL data, and its potential for automation.

72 ASL datasets (pseudo-continuous ASL; 5 different post-labeling delays: 400, 800, 1200, 1600, 2000 m s; total volumes = 60) were collected from thirty consecutive acute stroke patients. The effects of ICA-based denoising (manual and automated) where compared to two different denoising approaches, aCompCor, a Principal Component-based method, and Enhancement of Automated Blood Flow Estimates (ENABLE), an algorithm based on the removal of corrupted volumes. Multiple metrics were used to assess the changes in the quality of the data following denoising, including changes in cerebral blood flow (CBF) and arterial transit time (ATT), SNR, and repeatability. Additionally, the relationship between SNR and number of repetitions acquired was estimated before and after denoising the data.

The use of an ICA-based denoising approach resulted in significantly higher mean CBF and ATT values (p < 0.001), lower CBF and ATT variance (p < 0.001), increased SNR (p < 0.001), and improved repeatability (p < 0.05) when compared to the raw data. The performance of manual and automated ICA-based denoising was comparable. These results went beyond the effects of aCompCor or ENABLE. Following ICA-based denoising, the SNR was higher using only 50% of the ASL-dataset collected than when using the whole raw data.

The results show that ICA can be used to separate signal from noise in ASL data, improving the quality of the data collected. In fact, this study suggests that the acquisition time could be reduced by 50% without penalty to data quality, something that merits further study. Independent component classification and regression can be carried out either manually, following simple criteria, or automatically.

•

ICA can be used to separate signal from noise in ASL data, improving data quality.

•

Automated denoising reproduces the improvement seen by a manual approach.

•

ICA based denoising is superior to PCA or volume censoring approaches.

•

ASL acquisition time could be reduced by 50% without penalty to data quality.

The potential of MR-Encephalography for BCI/Neurofeedback applications with high temporal resolution

Real-time functional magnetic resonance imaging (rt-fMRI) enables the update of various brain-activity measures during an ongoing experiment as soon as a new brain volume is acquired. However, the recorded Blood-oxygen-level dependent (BOLD) signal also contains physiological artifacts such as breathing and heartbeat, which potentially cause misleading false positive effects especially problematic in brain-computer interface (BCI) and neurofeedback (NF) setups. The low temporal resolution of echo planar imaging (EPI) sequences (which is in the range of seconds) prevents a proper separation of these artifacts from the BOLD signal. MR-Encephalography (MREG) has been shown to provide the high temporal resolution required to unalias and correct for physiological fluctuations and leads to increased specificity and sensitivity for mapping task-based activation and functional connectivity as well as for detecting dynamic changes in connectivity over time. By comparing a simultaneous multislice echo planar imaging (SMS-EPI) sequence and an MREG sequence using the same nominal spatial resolution in an offline analysis for three different experimental fMRI paradigms (perception of house and face stimuli, motor imagery, Stroop task), the potential of this novel technique for future BCI and NF applications was investigated. First, adapted general linear model pre-whitening which accounts for the high temporal resolution in MREG was implemented to calculate proper statistical results and be able to compare these with the SMS-EPI sequence. Furthermore, the respiration- and cardiac pulsation-related signals were successfully separated from the MREG signal using independent component analysis which were then included as regressors for a GLM analysis. Only the MREG sequence allowed to clearly separate cardiac pulsation and respiration components from the signal time course. It could be shown that these components highly correlate with the recorded respiration and cardiac pulsation signals using a respiratory belt and fingertip pulse plethysmograph. Temporal signal-to-noise ratios of SMS-EPI and MREG were comparable. Functional connectivity analysis using partial correlation showed a reduced standard error in MREG compared to SMS-EPI. Also, direct time course comparisons by down-sampling the MREG signal to the SMS-EPI temporal resolution showed lower variance in MREG. In general, we show that the higher temporal resolution is beneficial for fMRI time course modeling and this aspect can be exploited in offline application but also, is especially attractive, for real-time BCI and NF applications.

Support Vector Machine for Analyzing Contributions of Brain Regions During Task-State fMRI

The mainstream method used for the analysis of task functional Magnetic Resonance Imaging (fMRI) data, is to obtain task-related active brain regions based on generalized linear models. Machine learning as a data-driven technical method is increasingly used in fMRI data analysis. The language task data, including math task and story task, of the Human Connectome Project (HCP) was used in this work. We chose a linear support vector machine as a classifier to classify math and story tasks and compared them with the activated brain regions of a SPM statistical analysis. As a result, 13 of the 25 regions used for classification in SVM were activated regions, and 12 were non-activated regions. In particular, the right Paracentral Lobule and right Rolandic Operculum which belong to non-activated regions, contributed most to the classification. Therefore, the differences found in machine learning can provide a new understanding of the physiological mechanisms of brain regions under different tasks.

ADHD-related sex differences in fronto-subcortical intrinsic functional connectivity and associations with delay discounting

Background

Attention-deficit/hyperactivity disorder (ADHD) is associated with atypical fronto-subcortical neural circuitry and heightened delay discounting, or a stronger preference for smaller, immediate rewards over larger, delayed rewards. Recent evidence of ADHD-related sex differences in brain structure and function suggests anomalies in fronto-subcortical circuitry may differ among girls and boys with ADHD. The current study examined whether the functional connectivity (FC) within fronto-subcortical neural circuitry differs among girls and boys with ADHD compared to same-sex typically developing (TD) controls and relates to delay discounting.

Methods

Participants include 8–12-year-old children with ADHD (n = 72, 20 girls) and TD controls (n = 75, 21 girls). Fronto-subcortical regions of interest were functionally defined by applying independent component analysis to resting-state fMRI data. Intrinsic FC between subcortical components, including the striatum and amygdala, and prefrontal components, including ventromedial prefrontal cortex (vmPFC), anterior cingulate cortex (ACC), and anterior dorsolateral prefrontal cortex (dlPFC), was compared across diagnostic groups overall and within sex. Correlations between intrinsic FC of the six fronto-subcortical pairs and delay discounting were also examined.

Results

Both girls and boys with ADHD show atypical FC between vmPFC and subcortical regions including the striatum (stronger positive FC in ADHD) and amygdala (weaker negative FC in ADHD), with the greatest diagnostic effects among girls. In addition, girls with ADHD show atypical intrinsic FC between the striatum and dlPFC components, including stronger positive FC with ACC and stronger negative FC with dlPFC. Further, girls but not boys, with ADHD, show heightened real-time delay discounting. Brain–behavior correlations suggest (1) stronger negative FC between the striatal and dlPFC components correlated with greater money delay discounting across all participants and (2) stronger FC between the amygdala with both the dlPFC and ACC components was differentially related to heightened real-time discounting among girls and boys with and without ADHD.

Conclusions

Our findings suggest fronto-subcortical functional networks are affected in children with ADHD, particularly girls, and relate to delay discounting. These results also provide preliminary evidence of greater disruptions in fronto-subcortical FC among girls with ADHD that is not due to elevated inattention symptom severity, intellectual reasoning ability, age, or head motion.

Electronic supplementary material

The online version of this article (10.1186/s11689-018-9254-9) contains supplementary material, which is available to authorized users.

Interaction of Developmental Venous Anomalies with Resting-State Functional MRI Measures

BACKGROUND AND PURPOSE

Functional MR imaging of the brain, used for both clinical and neuroscientific applications, relies on measuring fluctuations in blood oxygenation. Such measurements are susceptible to noise of vascular origin. The purpose of this study was to assess whether developmental venous anomalies, which are frequently observed normal variants, can bias fMRI measures by appearing as true neural signal.

MATERIALS AND METHODS

Large developmental venous anomalies (1 in each of 14 participants) were identified from a large neuroimaging cohort (n = 814). Resting-state fMRI data were decomposed using independent component analysis, a data-driven technique that creates distinct component maps representing aspects of either structured noise or true neural activity. We searched all independent components for maps that exhibited a spatial distribution of their signals following the topography of developmental venous anomalies.

RESULTS

Of the 14 developmental venous anomalies identified, 10 were clearly present in 17 fMRI independent components in total. While 9 (52.9%) of these 17 independent components were dominated by venous contributions and 2 (11.8%) by motion artifacts, 2 independent components (11.8%) showed partial neural signal contributions and 5 independent components (29.4%) unambiguously exhibited typical neural signal patterns.

CONCLUSIONS

Developmental venous anomalies can strongly resemble neural signal as measured by fMRI. They are thus a potential source of bias in fMRI analyses, especially when present in the cortex. This could impede interpretation of local activity in patients, such as in presurgical mapping. In scientific studies with large samples, developmental venous anomaly confounds could be mainly addressed using independent component analysis-based denoising.

Classification and Prediction of Brain Disorders Using Functional Connectivity: Promising but Challenging

Brain functional imaging data, especially functional magnetic resonance imaging (fMRI) data, have been employed to reflect functional integration of the brain. Alteration in brain functional connectivity (FC) is expected to provide potential biomarkers for classifying or predicting brain disorders. In this paper, we present a comprehensive review in order to provide guidance about the available brain FC measures and typical classification strategies. We survey the state-of-the-art FC analysis methods including widely used static functional connectivity (SFC) and more recently proposed dynamic functional connectivity (DFC). Temporal correlations among regions of interest (ROIs), data-driven spatial network and functional network connectivity (FNC) are often computed to reflect SFC from different angles. SFC can be extended to DFC using a sliding-window framework, and intrinsic connectivity states along the time-varying connectivity patterns are typically extracted using clustering or decomposition approaches. We also briefly summarize window-less DFC approaches. Subsequently, we highlight various strategies for feature selection including the filter, wrapper and embedded methods. In terms of model building, we include traditional classifiers as well as more recently applied deep learning methods. Moreover, we review representative applications with remarkable classification accuracy for psychosis and mood disorders, neurodevelopmental disorder, and neurological disorders using fMRI data. Schizophrenia, bipolar disorder, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease and mild cognitive impairment (MCI) are discussed. Finally, challenges in the field are pointed out with respect to the inaccurate diagnosis labeling, the abundant number of possible features and the difficulty in validation. Some suggestions for future work are also provided.

Non-linear ICA Analysis of Resting-State fMRI in Mild Cognitive Impairment

Compared to linear independent component analysis (ICA), non-linear ICA is more suitable for the decomposition of mixed components. Existing studies of functional magnetic resonance imaging (fMRI) data by using linear ICA assume that the brain's mixed signals, which are caused by the activity of brain, are formed through the linear combination of source signals. But the application of the non-linear combination of source signals is more suitable for the mixed signals of brain. For this reason, we investigated statistical differences in resting state networks (RSNs) on 32 healthy controls (HC) and 38 mild cognitive impairment (MCI) patients using post-nonlinear ICA. Post-nonlinear ICA is one of the non-linear ICA methods. Firstly, the fMRI data of all subjects was preprocessed. The second step was to extract independent components (ICs) of fMRI data of all subjects. In the third step, we calculated the correlation coefficient between ICs and RSN templates, and selected ICs of the largest spatial correlation coefficient. The ICs represent the corresponding RSNs. After finding out the eight RSNs of MCI group and HC group, one sample t-tests were performed. Finally, in order to compare the differences of RSNs between MCI and HC groups, the two-sample t-tests were carried out. We found that the functional connectivity (FC) of RSNs in MCI patients was abnormal. Compared with HC, MCI patients showed the increased and decreased FC in default mode network (DMN), central executive network (CEN), dorsal attention network (DAN), somato-motor network (SMN), visual network(VN), MCI patients displayed the specifically decreased FC in auditory network (AN), self-referential network (SRN). The FC of core network (CN) did not reveal significant group difference. The results indicate that the abnormal FC in RSNs is selective in MCI patients.

Correlating Resting-State Functional Magnetic Resonance Imaging Connectivity by Independent Component Analysis-Based Epileptogenic Zones with Intracranial Electroencephalogram Localized Seizure Onset Zones and Surgical Outcomes in Prospective Pediatric Intractable Epilepsy Study

The purpose of this study was to prospectively investigate the agreement between the epileptogenic zone(s) (EZ) localization by resting-state functional magnetic resonance imaging (rs-fMRI) and the seizure onset zone(s) (SOZ) identified by intracranial electroencephalogram (ic-EEG) using novel differentiating and ranking criteria of rs-fMRI abnormal independent components (ICs) in a large consecutive heterogeneous pediatric intractable epilepsy population without an a priori alternate modality informing EZ localization or prior declaration of total SOZ number. The EZ determination criteria were developed by using independent component analysis (ICA) on rs-fMRI in an initial cohort of 350 pediatric patients evaluated for epilepsy surgery over a 3-year period. Subsequently, these rs-fMRI EZ criteria were applied prospectively to an evaluation cohort of 40 patients who underwent ic-EEG for SOZ identification. Thirty-seven of these patients had surgical resection/disconnection of the area believed to be the primary source of seizures. One-year seizure frequency rate was collected postoperatively. Among the total 40 patients evaluated, agreement between rs-fMRI EZ and ic-EEG SOZ was 90% (36/40; 95% confidence interval [CI], 0.76-0.97). Of the 37 patients who had surgical destruction of the area believed to be the primary source of seizures, 27 (73%) rs-fMRI EZ could be classified as true positives, 7 (18%) false positives, and 2 (5%) false negatives. Sensitivity of rs-fMRI EZ was 93% (95% CI 78-98%) with a positive predictive value of 79% (95% CI, 63-89%). In those with cryptogenic localization-related epilepsy, agreement between rs-fMRI EZ and ic-EEG SOZ was 89% (8/9; 95% CI, 0.52-99), with no statistically significant difference between the agreement in the cryptogenic and symptomatic localization-related epilepsy subgroups. Two children with negative ic-EEG had removal of the rs-fMRI EZ and were seizure free 1 year postoperatively. Of the 33 patients where at least 1 rs-fMRI EZ agreed with the ic-EEG SOZ, 24% had at least 1 additional rs-fMRI EZ outside the resection area. Of these patients with un-resected rs-fMRI EZ, 75% continued to have seizures 1 year later. Conversely, among 75% of patients in whom rs-fMRI agreed with ic-EEG SOZ and had no anatomically separate rs-fMRI EZ, only 24% continued to have seizures 1 year later. This relationship between extraneous rs-fMRI EZ and seizure outcome was statistically significant (p = 0.01). rs-fMRI EZ surgical destruction showed significant association with postoperative seizure outcome. The pediatric population with intractable epilepsy studied prospectively provides evidence for use of resting-state ICA ranking criteria, to identify rs-fMRI EZ, as developed by the lead author (V.L.B.). This is a high yield test in this population, because no seizure nor particular interictal epilepiform activity needs to occur during the study. Thus, rs-fMRI EZ detected by this technique are potentially informative for epilepsy surgery evaluation and planning in this population. Independent of other brain function testing modalities, such as simultaneous EEG-fMRI or electrical source imaging, contextual ranking of abnormal ICs of rs-fMRI localized EZs correlated with the gold standard of SOZ localization, ic-EEG, across the broad range of pediatric epilepsy surgery candidates, including those with cryptogenic epilepsy.

Reprint of 'Noise contributions to the fMRI signal: An Overview'

The ability to discriminate signal from noise plays a key role in the analysis and interpretation of functional magnetic resonance imaging (fMRI) measures of brain activity. Over the past two decades, a number of major sources of noise have been identified, including system-related instabilities, subject motion, and physiological fluctuations. This article reviews the characteristics of the various noise sources as well as the mechanisms through which they affect the fMRI signal. Approaches for distinguishing signal from noise and the associated challenges are also reviewed. These challenges reflect the fact that some noise sources, such as respiratory activity, are generated by the same underlying brain networks that give rise to functional signals that are of interest.

Automatic Removal of Physiological Artifacts in EEG: The Optimized Fingerprint Method for Sports Science Applications

Data contamination due to physiological artifacts such as those generated by eyeblinks, eye movements, and muscle activity continues to be a central concern in the acquisition and analysis of electroencephalographic (EEG) data. This issue is further compounded in EEG sports science applications where the presence of artifacts is notoriously difficult to control because behaviors that generate these interferences are often the behaviors under investigation. Therefore, there is a need to develop effective and efficient methods to identify physiological artifacts in EEG recordings during sports applications so that they can be isolated from cerebral activity related to the activities of interest. We have developed an EEG artifact detection model, the Fingerprint Method, which identifies different spatial, temporal, spectral, and statistical features indicative of physiological artifacts and uses these features to automatically classify artifactual independent components in EEG based on a machine leaning approach. Here, we optimized our method using artifact-rich training data and a procedure to determine which features were best suited to identify eyeblinks, eye movements, and muscle artifacts. We then applied our model to an experimental dataset collected during endurance cycling. Results reveal that unique sets of features are suitable for the detection of distinct types of artifacts and that the Optimized Fingerprint Method was able to correctly identify over 90% of the artifactual components with physiological origin present in the experimental data. These results represent a significant advancement in the search for effective means to address artifact contamination in EEG sports science applications.

A new ICA-based fingerprint method for the automatic removal of physiological artifacts from EEG recordings

Background

EEG may be affected by artefacts hindering the analysis of brain signals. Data-driven methods like independent component analysis (ICA) are successful approaches to remove artefacts from the EEG. However, the ICA-based methods developed so far are often affected by limitations, such as: the need for visual inspection of the separated independent components (subjectivity problem) and, in some cases, for the independent and simultaneous recording of the inspected artefacts to identify the artefactual independent components; a potentially heavy manipulation of the EEG signals; the use of linear classification methods; the use of simulated artefacts to validate the methods; no testing in dry electrode or high-density EEG datasets; applications limited to specific conditions and electrode layouts.

Methods

Our fingerprint method automatically identifies EEG ICs containing eyeblinks, eye movements, myogenic artefacts and cardiac interference by evaluating 14 temporal, spatial, spectral, and statistical features composing the IC fingerprint. Sixty-two real EEG datasets containing cued artefacts are recorded with wet and dry electrodes (128 wet and 97 dry channels). For each artefact, 10 nonlinear SVM classifiers are trained on fingerprints of expert-classified ICs. Training groups include randomly chosen wet and dry datasets decomposed in 80 ICs. The classifiers are tested on the IC-fingerprints of different datasets decomposed into 20, 50, or 80 ICs. The SVM performance is assessed in terms of accuracy, False Omission Rate (FOR), Hit Rate (HR), False Alarm Rate (FAR), and sensitivity (p). For each artefact, the quality of the artefact-free EEG reconstructed using the classification of the best SVM is assessed by visual inspection and SNR.

Results

The best SVM classifier for each artefact type achieved average accuracy of 1 (eyeblink), 0.98 (cardiac interference), and 0.97 (eye movement and myogenic artefact). Average classification sensitivity (p) was 1 (eyeblink), 0.997 (myogenic artefact), 0.98 (eye movement), and 0.48 (cardiac interference). Average artefact reduction ranged from a maximum of 82% for eyeblinks to a minimum of 33% for cardiac interference, depending on the effectiveness of the proposed method and the amplitude of the removed artefact. The performance of the SVM classifiers did not depend on the electrode type, whereas it was better for lower decomposition levels (50 and 20 ICs).

Discussion

Apart from cardiac interference, SVM performance and average artefact reduction indicate that the fingerprint method has an excellent overall performance in the automatic detection of eyeblinks, eye movements and myogenic artefacts, which is comparable to that of existing methods. Being also independent from simultaneous artefact recording, electrode number, type and layout, and decomposition level, the proposed fingerprint method can have useful applications in clinical and experimental EEG settings.

EEG-Informed fMRI: A Review of Data Analysis Methods

The simultaneous acquisition of electroencephalography (EEG) with functional magnetic resonance imaging (fMRI) is a very promising non-invasive technique for the study of human brain function. Despite continuous improvements, it remains a challenging technique, and a standard methodology for data analysis is yet to be established. Here we review the methodologies that are currently available to address the challenges at each step of the data analysis pipeline. We start by surveying methods for pre-processing both EEG and fMRI data. On the EEG side, we focus on the correction for several MR-induced artifacts, particularly the gradient and pulse artifacts, as well as other sources of EEG artifacts. On the fMRI side, we consider image artifacts induced by the presence of EEG hardware inside the MR scanner, and the contamination of the fMRI signal by physiological noise of non-neuronal origin, including a review of several approaches to model and remove it. We then provide an overview of the approaches specifically employed for the integration of EEG and fMRI when using EEG to predict the blood oxygenation level dependent (BOLD) fMRI signal, the so-called EEG-informed fMRI integration strategy, the most commonly used strategy in EEG-fMRI research. Finally, we systematically review methods used for the extraction of EEG features reflecting neuronal phenomena of interest.

Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity

Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algorithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification methods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The variation in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of principal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the dataset. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback.

Support Vector Machine Classification of Obsessive-Compulsive Disorder Based on Whole-Brain Volumetry and Diffusion Tensor Imaging

Magnetic resonance imaging (MRI) methods have been used to detect cerebral anatomical distinction between obsessive-compulsive disorder (OCD) patients and healthy controls (HC). Machine learning approach allows for the possibility of discriminating patients on the individual level. However, few studies have used this automatic technique based on multiple modalities to identify potential biomarkers of OCD. High-resolution structural MRI and diffusion tensor imaging (DTI) data were acquired from 48 OCD patients and 45 well-matched HC. Gray matter volume (GMV), white matter volume (WMV), fractional anisotropy (FA), and mean diffusivity (MD) were extracted as four features were examined using support vector machine (SVM). Ten brain regions of each feature contributed most to the classification were also estimated. Using different algorithms, the classifier achieved accuracies of 72.08, 61.29, 80.65, and 77.42% for GMV, WMV, FA, and MD, respectively. The most discriminative gray matter regions that contributed to the classification were mainly distributed in the orbitofronto-striatal "affective" circuit, the dorsolateral, prefronto-striatal "executive" circuit and the cerebellum. For WMV feature and the two feature sets of DTI, the shared regions contributed the most to the discrimination mainly included the uncinate fasciculus, the cingulum in the hippocampus, corticospinal tract, as well as cerebellar peduncle. Based on whole-brain volumetry and DTI images, SVM algorithm revealed high accuracies for distinguishing OCD patients from healthy subjects at the individual level. Computer-aided method is capable of providing accurate diagnostic information and might provide a new perspective for clinical diagnosis of OCD.

Two-Dimensional Temporal Clustering Analysis for Patients with Epilepsy: Detecting Epilepsy-Related Information in EEG-fMRI Concordant, Discordant and Spike-Less Patients

EEG acquired simultaneously with fMRI (EEG-fMRI) is a multimodal method that has shown promise in mapping the seizure onset zone in patients with focal epilepsy. However, there are many instances when this method is unsuccessful or not applicable, and other data driven fMRI methods may be utilized. One such method is the two-dimensional temporal clustering analysis (2dTCA). In this study we compared the classic EEG-fMRI and 2dTCA performance in mapping regions related to the seizure onset region in 18 focal epilepsy patients (12 presenting interictal epileptiform discharges (IEDs), during EEG-fMRI acquisition) with Engel I or II surgical outcome. Activation maps of both 2dTCA timing outputs (positive and negative histograms) and EEG detected IEDs were computed and compared to the region of epilepsy surgical resection. Patients were evaluated in three categories based on frequency of EEG detected spiking during the MRI. EEG-fMRI maps were concordant to the epilepsy region in 5/12 subjects, four with frequent IEDs on EEG. The 2dTCA was successful in mapping 13/18 patients including 3/6 with no IEDs detected (10/12 with IEDs detected). The epilepsy-related activities were successfully mapped by both methods in only 4/12 patients. This work suggests that the epilepsy-related information detected by each method may be different: while EEG-fMRI is more accurate in patients with high rather than lower numbers of EEG detected IEDs; 2dTCA can be useful in evaluating patients even when no concurrent EEG spikes are detected or EEG-fMRI is not effective. Therefore, our results support that 2dTCA might be an alternative for mapping epilepsy-related BOLD activity in negative EEG-fMRI (6/7 patients) and spike-less patients.

Dual-echo ASL contributes to decrypting the link between functional connectivity and cerebral blow flow

Arterial spin labeling (ASL) MRI with a dual-echo readout module (DE-ASL) enables noninvasive simultaneous acquisition of cerebral blood flow (CBF)-weighted images and blood oxygenation level dependent (BOLD) contrast. Up to date, resting-state functional connectivity (FC) studies based on CBF fluctuations have been very limited, while the BOLD is still the method most frequently used. The purposes of this technical report were (i) to assess the potentiality of the DE-ASL sequence for the quantification of resting-state FC and brain organization, with respect to the conventional BOLD (cvBOLD) and (ii) to investigate the relationship between a series of complex network measures and the CBF information. Thirteen volunteers were scanned on a 3 T scanner acquiring a pseudocontinuous multislice DE-ASL sequence, from which the concomitant BOLD (ccBOLD) simultaneously to the ASL can be extracted. In the proposed comparison, the brain FC and graph-theoretical analysis were used for quantifying the connectivity strength between pairs of regions and for assessing the network model properties in all the sequences. The main finding was that the ccBOLD part of the DE-ASL sequence provided highly comparable connectivity results compared to cvBOLD. As expected, because of its different nature, ASL sequence showed different patterns of brain connectivity and graph indices compared to BOLD sequences. To conclude, the resting-state FC can be reliably detected using DE-ASL, simultaneously to CBF quantifications, whereas a single fMRI experiment precludes the quantitative measurement of BOLD signal changes. Hum Brain Mapp 38:5831-5844, 2017. © 2017 Wiley Periodicals, Inc.

Ten Key Observations on the Analysis of Resting-state Functional MR Imaging Data Using Independent Component Analysis

For more than 20 years, the powerful, flexible family of independent component analysis (ICA) techniques has been used to examine spatial, temporal, and subject variation in functional magnetic resonance (fMR) imaging data. This article provides an overview of 10 key principles in the basic and advanced application of ICA to resting-state fMR imaging. ICA's core advantages include robustness to artifact; false-positives and autocorrelation; adaptability to variant study designs; agnosticism to the temporal evolution of fMR imaging signals; and ability to extract, identify, and analyze neural networks. ICA remains in the vanguard of fMRI methods development.

Sedation of Patients With Disorders of Consciousness During Neuroimaging: Effects on Resting State Functional Brain Connectivity

BACKGROUND

To reduce head movement during resting state functional magnetic resonance imaging, post-coma patients with disorders of consciousness (DOC) are frequently sedated with propofol. However, little is known about the effects of this sedation on the brain connectivity patterns in the damaged brain essential for differential diagnosis. In this study, we aimed to assess these effects.

METHODS

Using resting state functional magnetic resonance imaging 3T data obtained over several years of scanning patients for diagnostic and research purposes, we employed a seed-based approach to examine resting state connectivity in higher-order (default mode, bilateral external control, and salience) and lower-order (auditory, sensorimotor, and visual) resting state networks and connectivity with the thalamus, in 20 healthy unsedated controls, 8 unsedated patients with DOC, and 8 patients with DOC sedated with propofol. The DOC groups were matched for age at onset, etiology, time spent in DOC, diagnosis, standardized behavioral assessment scores, movement intensities, and pattern of structural brain injury (as assessed with T1-based voxel-based morphometry).

RESULTS

DOC were associated with severely impaired resting state network connectivity in all but the visual network. Thalamic connectivity to higher-order network regions was also reduced. Propofol administration to patients was associated with minor further decreases in thalamic and insular connectivity.

CONCLUSIONS

Our findings indicate that connectivity decreases associated with propofol sedation, involving the thalamus and insula, are relatively small compared with those already caused by DOC-associated structural brain injury. Nonetheless, given the known importance of the thalamus in brain arousal, its disruption could well reflect the diminished movement obtained in these patients. However, more research is needed on this topic to fully address the research question.

Methods for cleaning the BOLD fMRI signal

Blood oxygen-level-dependent functional magnetic resonance imaging (BOLD fMRI) has rapidly become a popular technique for the investigation of brain function in healthy individuals, patients as well as in animal studies. However, the BOLD signal arises from a complex mixture of neuronal, metabolic and vascular processes, being therefore an indirect measure of neuronal activity, which is further severely corrupted by multiple non-neuronal fluctuations of instrumental, physiological or subject-specific origin. This review aims to provide a comprehensive summary of existing methods for cleaning the BOLD fMRI signal. The description is given from a methodological point of view, focusing on the operation of the different techniques in addition to pointing out the advantages and limitations in their application. Since motion-related and physiological noise fluctuations are two of the main noise components of the signal, techniques targeting their removal are primarily addressed, including both data-driven approaches and using external recordings. Data-driven approaches, which are less specific in the assumed model and can simultaneously reduce multiple noise fluctuations, are mainly based on data decomposition techniques such as principal and independent component analysis. Importantly, the usefulness of strategies that benefit from the information available in the phase component of the signal, or in multiple signal echoes is also highlighted. The use of global signal regression for denoising is also addressed. Finally, practical recommendations regarding the optimization of the preprocessing pipeline for the purpose of denoising and future venues of research are indicated. Through the review, we summarize the importance of signal denoising as an essential step in the analysis pipeline of task-based and resting state fMRI studies.

Impact of automated ICA-based denoising of fMRI data in acute stroke patients

Different strategies have been developed using Independent Component Analysis (ICA) to automatically de-noise fMRI data, either focusing on removing only certain components (e.g. motion-ICA-AROMA, Pruim et al., 2015a) or using more complex classifiers to remove multiple types of noise components (e.g. FIX, Salimi-Khorshidi et al., 2014 Griffanti et al., 2014). However, denoising data obtained in an acute setting might prove challenging: the presence of multiple noise sources may not allow focused strategies to clean the data enough and the heterogeneity in the data may be so great to critically undermine complex approaches. The purpose of this study was to explore what automated ICA based approach would better cope with these limitations when cleaning fMRI data obtained from acute stroke patients. The performance of a focused classifier (ICA-AROMA) and a complex classifier (FIX) approaches were compared using data obtained from twenty consecutive acute lacunar stroke patients using metrics determining RSN identification, RSN reproducibility, changes in the BOLD variance, differences in the estimation of functional connectivity and loss of temporal degrees of freedom. The use of generic-trained FIX resulted in misclassification of components and significant loss of signal (< 80%), and was not explored further. Both ICA-AROMA and patient-trained FIX based denoising approaches resulted in significantly improved RSN reproducibility (p < 0.001), localized reduction in BOLD variance consistent with noise removal, and significant changes in functional connectivity (p < 0.001). Patient-trained FIX resulted in higher RSN identifiability (p < 0.001) and wider changes both in the BOLD variance and in functional connectivity compared to ICA-AROMA. The success of ICA-AROMA suggests that by focusing on selected components the full automation can deliver meaningful data for analysis even in population with multiple sources of noise. However, the time invested to train FIX with appropriate patient data proved valuable, particularly in improving the signal-to-noise ratio.

fMRI capture of auditory hallucinations: Validation of the two-steps method

Our purpose was to validate a reliable method to capture brain activity concomitant with hallucinatory events, which constitute frequent and disabling experiences in schizophrenia. Capturing hallucinations using functional magnetic resonance imaging (fMRI) remains very challenging. We previously developed a method based on a two-steps strategy including (1) multivariate data-driven analysis of per-hallucinatory fMRI recording and (2) selection of the components of interest based on a post-fMRI interview. However, two tests still need to be conducted to rule out critical pitfalls of conventional fMRI capture methods before this two-steps strategy can be adopted in hallucination research: replication of these findings on an independent sample and assessment of the reliability of the hallucination-related patterns at the subject level. To do so, we recruited a sample of 45 schizophrenia patients suffering from frequent hallucinations, 20 schizophrenia patients without hallucinations and 20 matched healthy volunteers; all participants underwent four different experiments. The main findings are (1) high accuracy in reporting unexpected sensory stimuli in an MRI setting; (2) good detection concordance between hypothesis-driven and data-driven analysis methods (as used in the two-steps strategy) when controlled unexpected sensory stimuli are presented; (3) good agreement of the two-steps method with the online button-press approach to capture hallucinatory events; (4) high spatial consistency of hallucinatory-related networks detected using the two-steps method on two independent samples. By validating the two-steps method, we advance toward the possible transfer of such technology to new image-based therapies for hallucinations. Hum Brain Mapp 38:4966-4979, 2017. © 2017 Wiley Periodicals, Inc.

Automatic Recognition of fMRI-Derived Functional Networks Using 3-D Convolutional Neural Networks

Current functional magnetic resonance imaging (fMRI) data modeling techniques, such as independent component analysis and sparse coding methods, can effectively reconstruct dozens or hundreds of concurrent interacting functional brain networks simultaneously from the whole brain fMRI signals. However, such reconstructed networks have no correspondences across different subjects. Thus, automatic, effective, and accurate classification and recognition of these large numbers of fMRI-derived functional brain networks are very important for subsequent steps of functional brain analysis in cognitive and clinical neuroscience applications. However, this task is still a challenging and open problem due to the tremendous variability of various types of functional brain networks and the presence of various sources of noises. In recognition of the fact that convolutional neural networks (CNN) has superior capability of representing spatial patterns with huge variability and dealing with large noises, in this paper, we design, apply, and evaluate a deep 3-D CNN framework for automatic, effective, and accurate classification and recognition of large number of functional brain networks reconstructed by sparse representation of whole-brain fMRI signals. Our extensive experimental results based on the Human Connectome Project fMRI data showed that the proposed deep 3-D CNN can effectively and robustly perform functional networks classification and recognition tasks, while maintaining a high tolerance for mistakenly labeled training instances. This study provides a new deep learning approach for modeling functional connectomes based on fMRI data.