A Comparative Study of Correlation Methods in Functional Connectivity Analysis Using fMRI Data of Alzheimer's Patients.

Background: Functional Magnetic Resonance Imaging (fMRI) is a non-invasive neuroimaging tool, used in brain function research and is also a low-frequency signal, showing brain activation by means of Oxygen consumption. Objective: One of the reliable methods in brain functional connectivity analysis is the correlation method. In correlation analysis, the relationship between two time-series has been investigated. In fMRI analysis, the Pearson correlation is used while there are other methods. This study aims to investigate the different correlation methods in functional connectivity analysis. Material and Methods: In this analytical research, based on fMRI signals of Alzheimer's Disease (AD) and healthy individuals from the ADNI database, brain functional networks were generated using correlation techniques, including Pearson, Kendall, and Spearman. Then, the global and nodal measures were calculated in the whole brain and in the most important resting-state network called Default Mode Network (DMN). The statistical analysis was performed using non-parametric permutation test. Results: Results show that although in nodal analysis, the performance of correlation methods was almost similar, in global features, the Spearman and Kendall were better in distinguishing AD subjects. Note that, nodal analysis reveals that the functional connectivity of the posterior areas in the brain was more damaged because of AD in comparison to frontal areas. Moreover, the functional connectivity of the dominant hemisphere was disrupted more. Conclusion: Although the Pearson method has limitations in capturing non-linear relationships, it is the most prevalent method. To have a comprehensive analysis, investigating non-linear methods such as distance correlation is recommended.

Identifying brain functional connectivity alterations during different stages of Alzheimer's disease.

Purpose: Alzheimer's disease (AD) starts years before its signs and symptoms including the dementia become apparent. Diagnosis of the AD in the early stages is important to reduce the speed of brain decline. Aim of the study: Identifying the alterations in the functional connectivity of the brain during the disease stages is among the main important issues in this regard. Therefore, in this study, the changes in the functional connectivity during the AD stages were analyzed.Materials and methods: By employing the functional magnetic resonance imaging (fMRI) data and graph theory, weighted undirected graphs of the whole-brain and default mode network (DMN) network were investigated individually in the early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), AD, and control subjects. Results: In the whole-brain analysis, during one year of disease progression, no significant changes were observed in none of the study groups. However, the intergroup comparison showed that in different stages (from healthy to AD) the efficiencies, clustering coefficient, transitivity, and modularity of the brain network have significantly changed. In the DMN network analysis, the EMCI subjects demonstrated significant alterations but no significant changes were observed in other study groups. In the nodal analysis of the DMN, the participation, clustering, and degree were among the measures significantly changed with the AD progression. Conclusions: Functional connectivity alterations are more in the first stage of AD. Since AD progresses slowly whole brain alterations are not significant in one year but DMN exhibits significant changes. Cingulum anterior and posterior areas were the first affected regions of interest (ROI) in the DMN network afterwards, the frontal superior medial ROI was declined in the functional connectivity.

Deep sparse graph functional connectivity analysis in AD patients using fMRI data.

Functional magnetic resonance imaging (fMRI) is a non-invasive method that helps to analyze brain function based on BOLD signal fluctuations. Functional Connectivity (FC) catches the transient relationship between various brain regions usually measured by correlation analysis. The elements of the correlation matrix are between -1 to 1. Some of them are very small values usually related to weak and spurious correlations due to noises and artifacts. They can not be concluded as real strong correlations between brain regions and their existence could make a misconception and leads to fake results. It is crucial to make a conclusion based on reliable and informative correlations. In order to eliminate weak correlations, thresholding is a common method. In this routine, by adjusting a threshold the values below the threshold turn to zero and the rest remains. In this paper, in addition to thresholding, two other methods including spectral sparsification based on Effective Resistance (ER) and autoencoders are investigated for sparsing the correlation matrices. Autoencoders are based on deep learning neural networks and ER considers the network as a resistive circuit. The fMRI data of the study correspond to Alzheimer's patients and control subjects. Graph global measures are calculated and a non-parametric permutation test is reported. Results show that the autoencoder and spectral sparsification achieved more distinctive brain graphs between healthy and AD subjects. Also, more graph global features were significantly different from these two methods due to better elimination of weak correlations and preserve more informative ones. Regardless of the sparsification method features including average strength, clustering, local efficiency, modularity, and transitivity are significantly different (P-value=0.05). On the other hand, the measures radius, diameter, and eccentricity showed no significant differences in none of the methods. In addition, according to three different methods, the brain regions show fragile and solid FCs are determined.

A computer-aided approach for automatic detection of breast masses in digital mammogram via spectral clustering and support vector machine.

Breast cancer continues to be a widespread health concern all over the world. Mammography is an important method in the early detection of breast abnormalities. In recent years, using an automatic Computer-Aided Detection (CAD) system based on image processing techniques has been a more reliable interpretation in the illustration of breast distortion. In this study, a fully process-integrated approach with developing a CAD system is presented for the detection of breast masses based on texture description, spectral clustering, and Support Vector Machine (SVM). To this end, breast Regions of Interest (ROIs) are automatically detected from digital mammograms via gray-scale enhancement and data cleansing. The ROIs are segmented as labeled multi-sectional patterns using spectral clustering by the means of intensity descriptors relying on the region's histogram and texture descriptors based on the Gray Level Co-occurrence Matrix (GLCM). In the next step, shape and probabilistic features are derived from the segmented sections and given to the Genetic Algorithm (GA) to do the feature selection. The optimal feature vector comprising a fusion of selected shape and probabilistic features is submitted to linear kernel SVM for robust and reliable classification of mass tissues from the non-mass. Linear discrimination analysis (LDA) is also performed to ascertain the significance of the nominated feature space. The classification results of the proposed approach are presented by sensitivity, specificity, and accuracy measures, which are 89.5%, 91.2%, and 90%, respectively.

EEG signal analysis during Ishihara's test in subjects with normal vision and color vision deficiency.

Color Vision Deficiency (CVD) is one of the most common types of vision deficiency. People with CVD have difficulty seeing color spectra depending on what types of retina photoreceptors are impaired. In this paper, the Ishihara test with 38 plates was used to examine the Electroencephalogram (EEG) of ten subjects with CVD plus ten healthy individuals. The recording was performed according to the 10-20 international system. The C-based software was programmed so that subjects could select the number or path in each test plate in the software options while recording EEG. Frequency features in different frequency bands were extracted from the EEG signals of the two groups during the Ishihara test. Statistically significant differences (P < 0.05) between features were assessed by independent samples t-test with False Discovery Rate (FDR) correction. Also, the K-nearest neighbor classifier (KNN) was used to classify the two groups. The results revealed that the most significant difference between the two groups in the Ishihara test images occurred for the electrodes located in the right temporoparietal areas (P4 and T6) of the brain in the Delta, Theta, Beta1, and Beta2 frequency bands. The KNN classifier, using the signals that reported the greatest statistical difference between the two groups, showed that the two groups were distinguishable with 85.2% accuracy. In this way, images from the Ishihara test that would provide the most accurate classification were identified. In conclusion, this research provided new insights into EEG signals of subjects with CVD and healthy subjects based on the Ishihara color vision test.

Multiclass classification of patients during different stages of Alzheimer's disease using fMRI time-series.

Alzheimer's Disease (AD) begins several years before the symptoms develop. It starts with Mild Cognitive Impairment (MCI) which can be separated into Early MCI and Late MCI (EMCI and LMCI). Functional connectivity analysis and classification are done among the different stages of illness with Functional Magnetic Resonance Imaging (fMRI). In this study, in addition to the four stages including healthy, EMCI, LMCI, and AD, the patients have been tracked for a year. Indeed, the classification has been done among 7 groups to analyze the functional connectivity changes in one year in different stages. After generating the functional connectivity graphs for eliminating the weak links, three different sparsification methods were used. In addition to simple thresholding, spectral sparsification based on effective resistance and sparse autoencoder were performed in order to analyze the effect of sparsification routine on classification results. Also, instead of extracting common features, the correlation matrices were reshaped to a correlation vector and used as a feature vector to enter the classifier. Since the correlation matrix is symmetric, in another analysis half of the feature vector was used, moreover, the Genetic Algorithm (GA) also utilized for feature vector dimension reduction. The non-linear SVM classifier with a polynomial kernel applied. The results showed that the autoencoder sparsification method had the greatest discrimination power with the accuracy of 98.35% for classification when the feature vector was the full correlation matrix.

Analysis of central venous pressure (CVP) signals using mathematical methods.

Central venous pressure (CVP) is an important clinical parameter for physicians but only the absolute CVP value is typically monitored in the intensive care unit (ICU). In this study, we propose a novel mathematical method to present and analyze CVP signals. A total of 44 suitable samples were chosen from a total of 65 collected in an ICU. Pre-processing of the samples included rate reduction and digital filtering. The statistical features of time and frequency domain, wavelet, and empirical mode decomposition of these signals were extracted. We found no significant difference among the CVP signals regarding sex, smoking, coronary disease, and respiration mode of the samples.