Automatic seizure detection based on Gray Level Co-occurrence Matrix of STFT imaged-EEG. (January 2023)

• Record Type: Journal Article
• Authors: Shayeste, Haniye; Asl, Babak Mohammadzadeh
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 1
• Publication Date: 2023-01
• Subjects: Epileptic seizure detection -- Imaged-EEG -- Gray Level Co-occurrence Matrix -- Short time Fourier transform -- Electroencephalogram; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104109
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Epilepsy is a complicated neurological disorder, that features recurrent seizures. During a seizure, the repetitive action potentials lead to a high-frequency burst, and a hyper synchronization happens among the activities of a population of cortical neurons concurrently. In this study, we propose a repetition-based seizure detection method, using Gray Level Co-occurrence Matrix (GLCM) and Electroencephalogram (EEG) signals. In this method, imaged-EEGs are made from the Short Time Fourier Transform (STFT) coefficients of two sequential epochs. The GLCMs of these images are calculated and one feature named d i a g G L C M is extracted from each co-occurrence matrix. This feature demonstrates the repetition of the STFT coefficient of a frequency band in two sequential epochs, which are used for a classification task between ictal (during a seizure) and inter-ictal (between seizures) time segments. Using one frequency band's STFT repetition, a patient-specific seizure detection algorithm is developed with an accuracy of 99.56%, a sensitivity of 99.52%, and specificity of 99.62%. This accurate classification shows the efficiency of the extracted feature which can be a biomarker for the ictal repetitive action potentials. Highlights: Converting EEG features in successive epochs into imaged-EEGs. Gray Level Co-occurrence Matrix for imaged-EEGs processing. STFT coefficients repetition in sequential epochs as a biomarker of epileptic seizures. 99.56% accuracy of seizure detection using CHB-MIT dataset.