Spontaneous State Detection Using Time-Frequency and Time-Domain Features Extracted From Stereo-Electroencephalography Traces

Huanpeng Ye; Zhen Fan; Guangye Li; Zehan Wu; Jie Hu; Xinjun Sheng; Liang Chen; Xiangyang Zhu

doi:10.3389/fnins.2022.818214

Spontaneous State Detection Using Time-Frequency and Time-Domain Features Extracted From Stereo-Electroencephalography Traces

Front Neurosci. 2022 Mar 17:16:818214. doi: 10.3389/fnins.2022.818214. eCollection 2022.

Authors

Huanpeng Ye¹, Zhen Fan², Guangye Li¹, Zehan Wu², Jie Hu², Xinjun Sheng¹, Liang Chen², Xiangyang Zhu¹

Affiliations

¹ State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.
² Department of Neurosurgery of Huashan Hospital, Fudan University, Shanghai, China.

Abstract

As a minimally invasive recording technique, stereo-electroencephalography (SEEG) measures intracranial signals directly by inserting depth electrodes shafts into the human brain, and thus can capture neural activities in both cortical layers and subcortical structures. Despite gradually increasing SEEG-based brain-computer interface (BCI) studies, the features utilized were usually confined to the amplitude of the event-related potential (ERP) or band power, and the decoding capabilities of other time-frequency and time-domain features have not been demonstrated for SEEG recordings yet. In this study, we aimed to verify the validity of time-domain and time-frequency features of SEEG, where classification performances served as evaluating indicators. To do this, using SEEG signals under intermittent auditory stimuli, we extracted features including the average amplitude, root mean square, slope of linear regression, and line-length from the ERP trace and three traces of band power activities (high-gamma, beta, and alpha). These features were used to detect the active state (including activations to two types of names) against the idle state. Results suggested that valid time-domain and time-frequency features distributed across multiple regions, including the temporal lobe, parietal lobe, and deeper structures such as the insula. Among all feature types, the average amplitude, root mean square, and line-length extracted from high-gamma (60-140 Hz) power and the line-length extracted from ERP were the most informative. Using a hidden Markov model (HMM), we could precisely detect the onset and the end of the active state with a sensitivity of 95.7 ± 1.3% and a precision of 91.7 ± 1.6%. The valid features derived from high-gamma power and ERP in this work provided new insights into the feature selection procedure for further SEEG-based BCI applications.

Keywords: brain-computer interface; feature evaluation; high-gamma; stereo-electroencephalography; time-domain feature.