Manuscript received June 9, 2024; revised July 5, 2024; accepted September 6, 2024; published January 27, 2025.

Abstract—High-Frequency Oscillations (HFOs) have been considered as a potentially useful biomarker for localizing epileptogenic areas in drug-resistant patients requiring presurgical intervention, exploiting intracranial electroencephalographic iEEG. Consequently, it’s important to create accurate strategies for detecting epileptic seizures. Predicting seizures requires classifying appropriate indicators, which is difficult due to their time-frequency overlap. Convolutional Neural Networks (CNN), one of the deep learning approaches, have demonstrated promising results in analyzing and classifying epilepsy-related iEEG biomarkers. In our study, we proposed to explore three global methods: multiclass of Support Vector Machine (SVM), multiple architecture CNN, and CNN-SVM, on a simulated iEEG dataset and then on a real iEEG signal. Our best results for the studied three models in the classification of HFO have yielded high accuracy rates: GoogLeNet-SVM achieves approximately 99.63% and 94.07% for simulated data (1) and real data (2), respectively, SVM multiclass achieves 98.14% and 88.51% for (1) and (2), respectively, and GoogLeNet achieves 98.52% and 91.85% for (1) and (2), respectively. Hence, we found that our proposed model performs better than other current techniques. These results suggest that deep learning models could be a successful strategy for classifying epilepsy biomarkers and may improve seizure prediction techniques, and hence can enhance epileptic patient’s well-being.

Keywords—High-Frequency Oscillations (HFOs), Convolutional Neural Networks (CNN), multiclass Support Vector Machine (SVM), CNN-SVM, GoogLeNet-SVM

Cite: Zayneb Sadek, Abir Hadriche, Rahma Maalej, and Nawel Jmail, "Multi-classification of High-Frequency Oscillations Using iEEG Signals and Deep Learning Models," Journal of Image and Graphics, Vol. 13, No. 1, pp. 52-63, 2025.

Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC-BY-4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.