Automatic detection of HFOs based on singular value decomposition and improved fuzzy c-means clustering for localization of seizure onset zones

Abstract This paper devises a new detector based on singular value decomposition (SVD) and improved fuzzy c-means (FCM) clustering for automatically detecting high-frequency oscillations (HFOs) that are used for localizing seizure onset zones (SOZs) in epilepsy. First, HFO candidates (HFOCs) are obtained by the root mean square method. Next, a time-frequency analysis method is applied to eliminate spikes from HFOCs, which consists of the Stockwell transform, SVD combined with the k-medoids clustering algorithm, Stockwell inverse transform, and threshold method. Then, four kinds of distinctive features, i.e. mean singular values, line lengths, power ratios and spectral centroid of the rest of HFOCs, are extracted and augmented as feature vectors. These vectors are used as the input of the improved FCM clustering algorithm optimized by the simulated annealing algorithm combined with the genetic algorithm. Finally, the localization of SOZs is accomplished based on the concentrations of the detected HFOs. The superiority of the devised detector over other five existing ones is demonstrated by comparing their localization performance.