Phase-synchrony evaluation of EEG signals for Multiple Sclerosis diagnosis based on bivariate empirical mode decomposition during a visual task

Spatial synchrony evaluation among neural networks of the brain would play an important role in decoding of complicated brain interactions in healthy subjects and the ones with neurological disease such as Multiple Sclerosis (MS). Despite the widespread prevalence of this disease, as well as the importance of identifying any MS-related damage in the central nervous system, the study of brain interactions is still poorly investigated. Moreover, there has always been a vital need to automate the MS diagnosis procedure. This automation would yield to eliminate the evaluation errors and, consequently, improve its consistency and reliability. To address these issues, in this work, we proposed a robust pattern recognition algorithm as a computer-aided diagnosis system. This method is based on the calculation of pairwise phase-synchrony of EEG recordings during a visual task. In order to calculate the phase-synchrony, the bivariate empirical mode decomposition (BEMD) was applied to extract the intrinsic mode functions (IMFs). The phases of these IMFs were obtained using the Hilbert transform to be utilized in the mean phase coherence (MPC), a measure for phase-synchrony calculation. After construction of the feature space using MPC values, the ReliefF algorithm was applied for dimension reduction, which results in lower compu
tational complexity and cost. Finally, the best distinguishing features were fed to the K-Nearest Neighbors (KNN) classifier. The results demonstrated a higher level of networks synchronization in the posterior regions of the brain and desynchronization in the anterior regions among MS group in comparison with the normal subjects. In the validation phase, the leave-one-subject-out cross-validation (LOOCV) method was used to assess the validity of the proposed algorithm. This led to the accuracy, sensitivity and specificity of 93.09%, 91.07% and 95.24% for red-green, 90.44%, 88.39% and 92.62% for luminance and 87.44%, 87.05% and 87.86% for blue-yellow tasks. Using the proposed algorithm, the pairwise phase-synchrony differences of EEG signals between MS and normal subjects were extracted. The experimental results demonstrate the reliability of the presented method to be generalized in the field of early and automated MS diagnosis systems.