AUTHOR=Li Chunsheng , Liu Shiyue , Wang Zeyu , Yuan Guanqian 

TITLE=Classifying epileptic phase-amplitude coupling in SEEG using complex-valued convolutional neural network

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.1085530

DOI=10.3389/fphys.2022.1085530

ISSN=1664-042X

ABSTRACT=EEG phase-amplitude coupling (PAC), the amplitude of high-frequency oscillations modulated by the phase of low-frequency oscillations (LFOs), is a useful biomarker to localize epileptogenic tissue. It is commonly represented in a comodulogram of coupling strength but without coupled phase information. The PAC is also found in the normal brain, and it is difficult to discriminate pathological PACs from normal ones. This study proposes a novel approach based on complex-valued PAC (CV-PAC) for classifying epileptic PAC. The CV-PAC combines both the coupling strengths and the coupled phases of LFOs. The complex-valued convolutional neural network (CV-CNN) is then used to classify epileptic CV-PAC. Stereo-electroencephalography (SEEG) recordings from nine intractable epilepsy patients were analyzed. The leave-one-out cross-validation is performed, and the area-under-cure (AUC) value is used as the indicator of the performance of different measures. Our result shows that the AUC value is 0.92 for classifying epileptic CV-PAC using CV-CNN. The AUC value decreases to 0.89, 0.80, and 0.88 while using traditional CNN, support vector machine, and random forest, respectively. The phases of delta (1 - 4 Hz) and alpha (8 - 10 Hz) bands are different between epileptic and normal CV-PAC. The phase information of CV-PAC is important for improving classification performance. The proposed approach of CV-PAC/CV-CNN promises to identify more accurate epileptic brain activities for potential surgical intervention.