Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Hessam Ahmadi; Emad Fatemizadeh; Alimotie Nasrabadi
Volume 14, Issue 3 , October 2020, , Pages 235-249
Abstract
Functional Magnetic Resonance Imaging (fMRI) is a non-invasive neuroimaging technique for analyzing the brain functions through low-frequency fluctuations called the Blood-Oxygen-Level-Dependent (BOLD) signals. Measurement of the functional connectivity in brain networks is usually done by the fMRI time-series ...
Read More
Functional Magnetic Resonance Imaging (fMRI) is a non-invasive neuroimaging technique for analyzing the brain functions through low-frequency fluctuations called the Blood-Oxygen-Level-Dependent (BOLD) signals. Measurement of the functional connectivity in brain networks is usually done by the fMRI time-series through Pearson Correlation Coefficients (PCC). As the PCC shows linear dependencies, in this study, non-linear relationships in the fMRI signals of the patients with Alzheimer's Disease (AD) were investigated using the kernel trick method. Kernel trick approach maps the input information into a higher dimension space and implements the linear calculations in a new space that is proportionate to the non-linear relationships in the primary space. After generating the weighted undirected brain graphs based on the Automated Anatomical Labeling (AAL) atlas, different kernel functions with different parameters were applied. Then the graph global measures including degree, strength, small-worldness, modularity, and efficiencies features were computed and the non-parametric permutation test was performed. According to the results, the kernel trick method showed more significant differences with AD and healthy subjects in comparison with the simple PCC and it could be because of the non-linear correlations that are not captured by the PCC. Among different kernel functions, the Polynomial function had the best performance. Applying this kernel, the classification was done by the Support Vector Machine (SVM) classifier. The achieved accuracy was equal to 98.68±0.79%. The Occipital and Temporal lobes and also the Default Mode Network (DMN) were analyzed and the kernel trick method showed more significant differences in all of them. It is worthwhile to mention that the right and left Angular areas of DMN showed no significant changes in none of the methods and it could be concluded that the AD does not affect this areas effectively.
Biomedical Image Processing / Medical Image Processing
Ali Taalimi; Emadoddin Fatemizadeh
Volume 4, Issue 3 , June 2010, , Pages 231-248
Abstract
Functional magnetic resonance imaging (fMRI) is widely used for investigation of brain neural activity. This imaging technique obtains signals and images from human brain’s response to prescheduled tasks. Several studies on blood oxygenation level-dependent (BOLD) signal responses demonstrate nonlinear ...
Read More
Functional magnetic resonance imaging (fMRI) is widely used for investigation of brain neural activity. This imaging technique obtains signals and images from human brain’s response to prescheduled tasks. Several studies on blood oxygenation level-dependent (BOLD) signal responses demonstrate nonlinear behavior in response to a stimulus. In this paper we investigate nonlinear modeling of BOLD signal activity to model the nonlinear and time variant behaviors of this physiological system. For this purpose two categories of nonlinear methods are considered, first those one with emphasis on physiological parameters which affect BOLD response and methods model the input and output of system without any refer to all the hidden state variables (physiological parameters. Balloon model is analzyed and a new approach for activation detection based on this model is introduced. In addition, the Hammerstein-Wiener, NARMA and Volterra kernels are investigated as nonlinear and nonphysiological methods and their ability in detection of activation detection are compared. The Activation detection methods have been applied on the two data sets (real and synthetic). For synthetic data and threshold equal to 0.45, the Jaccard index for Wiener- Hammerstein, NARMA, and Volterra model was 0.9, 1.0, and 0.91, respectively. In real dataset and for optimal threshold (0.35, 0.4, and 0.45) the same index was 0.85, 0.90, and 0.87, respectively.
