A multi-domain feature fusion epilepsy seizure detection method based on spike matching and PLV functional networks

Qikai Fan; Lurong Jiang; Amira M El Gohary; Fang Dong; Duanpo Wu; Tiejia Jiang; Chen Wang; Junbiao Liu

doi:10.1088/1741-2552/adaef3

A multi-domain feature fusion epilepsy seizure detection method based on spike matching and PLV functional networks

J Neural Eng. 2025 Jan 27. doi: 10.1088/1741-2552/adaef3. Online ahead of print.

Authors

Qikai Fan¹, Lurong Jiang², Amira M El Gohary³, Fang Dong⁴, Duanpo Wu⁵, Tiejia Jiang⁶, Chen Wang¹, Junbiao Liu⁷

Affiliations

¹ School of Information Science and Engineering, Zhejiang Sci-Tech University, Zhejiang Sci-Tech University, Hangzhou, Hangzhou, Zhejiang, 310018, CHINA.
² School of Information Science and Technology, Zhejiang Sci-Tech University, Zhejiang Sci-Tech University, Hangzhou, Hangzhou, Zhejiang, 310018, CHINA.
³ Cairo University, Cairo University, Cario, Giza, Giza, 12311, EGYPT.
⁴ College of Information and Electric Engineering, Hangzhou City University, Hangzhou City University, Hangzhou, Hangzhou, Zhejiang, 310015, CHINA.
⁵ Hangzhou Dianzi University, Hangzhou Dianzi University, Hangzhou, Hangzhou, 310018, CHINA.
⁶ Zhejiang University School of Medicine Children's Hospital Binjiang Campus, Department of Neurology, The Children's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, 310052, CHINA.
⁷ Hangzhou Dianzi University, School of Automation, Hangzhou Dianzi University, Hangzhou 310052, China, Hangzhou, Zhejiang, 310018, CHINA.

PMID: 39870038
DOI: 10.1088/1741-2552/adaef3

Abstract

The identification of spikes, as a typical characteristic wave of epilepsy, is crucial for diagnosing and locating the epileptogenic region. The traditional seizure detection methods lack spike features and have low sample richness. This paper proposes a seizure detection method with spike-based phase locking value (PLV) functional brain networks and multi-domain fused features. Approach. In the spiking detection part, brain functional networks based on PLV are constructed to explore the changes in brain functional states during spiking discharge, from the perspective of microscopic neuronal activity to macroscopic brain region interactions. Then, in the epilepsy seizure detection task, multi-domain fused feature sequences are constructed using time-domain, frequency-domain, inter-channel correlation, and the spike detection features. Finally, Bi-LSTM and Transformer encoders and their optimized models are used to verify the effectiveness of the proposed method. Main results. Experimental results achieve the best seizure detection metrics on Bi-LSTM Attention, with accuracy, sensitivity, and specificity reaching 98.40%, 98.94%, and 97.86%, respectively. Significance. The method is significant as it innovatively applies multi channel spike network features to seizure detection. It can potentially improve the diagnosis and location of the epileptogenic region by accurately detecting seizures through the identification of spikes, which is a crucial characteristic wave of epilepsy.

Keywords: EEG; brain network; multi-domain features; seizure detection; spike.