Identification of cognitive load-dependent activation patterns using working memory task-based fMRI at various levels of difficulty.

Working memory, which is regarded as the foundation of cognitive processes, is a system that stores, processes, and manipulates information in short intervals of time that are actually needed for daily functioning. This study aimed to assess the brain activity of healthy controls (HC) while performing the N-back task, which is one of the most popularly used tests for evaluating working memory along with functional magnetic resonance imaging (fMRI). In this regard, we collected fMRI data from right-handed individuals in a 3.0 T scanner during the Persian version of the visual variant N-back task performance with three levels of complexity varied throughout the experiment (1, 2, and 3-back conditions) to increase the cognitive demands. The statistical parametric mapping (SPM12) software was used to analyze fMRI data for the identification of cognitive load-dependent activation patterns based on contrast images obtained from different levels of task difficulty. Our findings showed that as cognitive complexity increased, the number of significant activation clusters and cluster extent increased in several areas distributed in the cerebellum, frontoparietal lobes, insula, SMA, and lenticular nucleus, the majority of which are recognized for their role in working memory. Furthermore, deactivation patterns during 1-, 2-, and 3-back vs. 0-back contrasts revealed significant clusters in brain regions that are mostly described as being part of the default mode network (DMN). Based on previous research, our results supported the recognized involvement of the mentioned cortical and subcortical areas in various types or levels of N-back tasks. This study found that altering activation patterns by increasing task difficulty could aid in evaluating the various stages of cognitive dysfunction in many brain diseases such as multiple sclerosis (MS) and Alzheimer's disease by comparing controls in future studies to apply early appropriate treatment strategies.

Early MS Identification Using Non-linear Functional Connectivity and Graph-theoretic Measures of Cognitive Task-fMRI Data.

Introduction: Functional neuroimaging has developed a fundamental ground for understanding the physical basis of the brain. Recent studies have extracted invaluable information from the underlying substrate of the brain. However, cognitive deficiency has insufficiently been assessed by researchers in multiple sclerosis (MS). Therefore, extracting the brain network differences among relapsing-remitting MS (RRMS) patients and healthy controls as biomarkers of cognitive task functional magnetic resonance imaging (fMRI) data and evaluating such biomarkers using machine learning were the aims of this study. Methods: In order to activate cognitive functions of the brain, blood-oxygen-level-dependent (BOLD) data were collected throughout the application of a cognitive task. Accordingly, a nonlinear-based brain network was established using kernel mutual information based on the automated anatomical labeling atlas (AAL). Subsequently, a statistical test was carried out to determine the variation in brain network measures between the two groups on binary adjacency matrices. We also found the prominent graph features by merging the Wilcoxon rank-sum test with the Fisher score as a hybrid feature selection method. Results: The results of the classification performance measures showed that the construction of a brain network using a new nonlinear connectivity measure in task-fMRI performs better than the linear connectivity measures in terms of classification. The Wilcoxon rank-sum test also demonstrated a superior result for clinical applications. Conclusion: We believe that non-linear connectivity measures, like KMI, outperform linear connectivity measures, like correlation coefficient in finding the biomarkers of MS disease according to classification performance metrics. Highlights: The performance of some brain regions (the hippocampus, parahippocampus, cuneus, pallidum, and two segments of the cerebellum) is different between healthy and MS people.Non-linear connectivity measures, such as Kernel mutual information, perform better than linear connectivity measures, such as correlation coefficient, in finding the biomarkers of MS disease. Plain Language Summary: Multiple sclerosis (MS) can disrupt the function of the central nervous system. The function of brain network is impaired in these patients. In this study, we evaluated the change in brain network based on a non-linear connectivity measure using cognitive task-based fMRI data between MS patients and healthy controls. We used Kernel mutual information (KMI) and designed a graph network based on the results of connectivity analysis. The the paced auditory serial addition test was used to activate cognitive functions of the brain. The classification was employed for the results using different decision tree -based technique and support vector machine. KMI can be considered a valid measure of connectivity over linear measures, like the correlation coefficient. KMI does not have the drawbacks of mutual information technique. However, further studies should be implemented on brain data of MS patients to draw more definite conclusions.

Granger causality analysis in combination with directed network measures for classification of MS patients and healthy controls using task-related fMRI.

Several studies have already assessed brain network variations in multiple sclerosis (MS) patients and healthy controls (HCs). The underlying neural system's functioning is apparently too complicated, however. Therefore, the neural time series' analysis through new methods is the aim of any recent research. Functional magnetic resonance imaging (fMRI) is a prominent modality for investigating the human brain's neural substrate, especially when cognitive impairment occurs. The present study was an attempt to investigate the brain network's differences between MS patients and HCs using graph-theoretic measures constructed by an effective connectivity measure through statistical tests. The results of the significant measures were then evaluated through machine learning methods. To this end, we gathered blood-oxygen level dependent (BOLD) fMRI data of the participants during the execution of paced auditory serial addition test (PASAT). Granger causality analysis (GCA) was then employed between brain regions' time series on each subject in order to construct a brain network. Afterward, the Wilcoxon rank-sum test was implemented to find the alteration of brain networks between the mentioned groups. According to the results, Global flow coefficient was significantly different between HCs and patients. Moreover, MS disease impacted several areas of the brain including Hippocampus, Para Hippocampal, Thalamus, Cuneus, Superior temporal gyrus, Heschl, Caudate, Medial Frontal Superior Gyrus, Fusiform, Pallidum, and several parts of Cerebellum in centrality measures and local flow coefficient. Most of the obtained regions were related to the cognitive impacts of the disease. We also found the best subset of graph features by means of Fisher score, and classified them to evaluate the features strength for the discrimination of MS patients from HCs via several machine learning methods. Having used the combination of Wilcoxon rank-sum test and Fisher score, we were able to classify MS patients from HCs using linear support vector machine (SVM) with an accuracy of 95%. With regard to the few existing studies on brain network of MS patients, especially during a cognitive task execution, our findings showed that the selected graph measures by Wilcoxon rank-sum test and Fisher score from the GCA-based brain networks resulted in a promising classification accuracy.

Analysis of brain functional connectivity network in MS patients constructed by modular structure of sparse weights from cognitive task-related fMRI.

Cognitive dysfunction in multiple sclerosis (MS) seems to be the result of neural disconnections, leading to a wide range of brain functional network alterations. It is assumed that the analysis of the topological structure of brain connectivity network can be used to assess cognitive impairments in MS disease. We aimed to identify these brain connectivity pattern alterations and detect the significant features for the distinction of MS patients from healthy controls (HC). In this regard, the importance of functional brain networks construction for better exhibition of changes, inducing the improved reflection of functional organization structure should be precisely considered. In this paper, we strove to introduce a framework for modeling the functional connectivity network by considering the two most important intrinsic sparse and modular structures of brain. For the proposed approach, we first derived group-wise sparse representation via learning a common over-complete dictionary matrix from the aggregated cognitive task-based functional magnetic resonance imaging (fMRI) data of all subjects of the two groups to be able to investigate between-group differences. We then applied the modularity concept on achieved sparse coefficients to compute the connectivity strength between the two brain regions. We examined the changes in network topological properties between relapsing-remitting MS (RRMS) and matched HC groups by considering the pairwise connections of regions of the resulted weighted networks and extracting graph-based measures. We found that the informative brain regions were related to their important connectivity weights, which could distinguish MS patients from the healthy controls. The experimental findings also proved the discrimination ability of the modularity measure among all the global features. In addition, we identified such local feature subsets as eigenvector centrality, eccentricity, node strength, and within-module degree, which significantly differed between the two groups. Moreover, these nodal graph measures have been served as the detectors of brain regions, affected by different cognitive deficits. In general, our findings illustrated that integration of sparse representation, modular structure, and pairwise connectivity strength in combination with the graph properties could help us with the early diagnosis of cognitive alterations in the case of MS.