期刊
IEEE ACCESS
卷 11, 期 -, 页码 23085-23096出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3252897
关键词
Epilepsy; Correlation; Deep learning; mutual information; factor graphs; convolutional neural network; deep learning; seizure; EEG; neural mutual information estimator
We propose a hybrid model-based data-driven seizure detection algorithm called MICAL, which utilizes neural MI estimators, 1D CNN, and factor graph inference to improve the detection of seizures from EEG signals. The method successfully captures inter-channel statistical dependence and temporal correlation, leading to state-of-the-art performance.
We develop a hybrid model-based data-driven seizure detection algorithm called Mutual Information-based CNN-Aided Learned factor graphs (MICAL) for detection of eclectic seizures from EEG signals. Our proposed method contains three main components: a neural mutual information (MI) estimator, 1D convolutional neural network (CNN), and factor graph inference. Since during seizure the electrical activity in one or more regions in the brain becomes correlated, we use neural MI estimators to measure inter-channel statistical dependence. We also design a 1D CNN to extract additional features from raw EEG signals. Since the soft estimates obtained as the combined features from the neural MI estimator and the CNN do not capture the temporal correlation between different EEG blocks, we use them not as estimates of the seizure state, but to compute the function nodes of a factor graph. The resulting factor graphs allows structured inference which exploits the temporal correlation for further improving the detection performance. On public CHB-MIT database, We conduct three evaluation approaches using the public CHB-MIT database, including 6-fold leave-four-patients-out cross-validation, all patient training; and per patient training. Our evaluations systematically demonstrate the impact of each element in MICAL through a complete ablation study and measuring six performance metrics. It is shown that the proposed method obtains state-of-the-art performance specifically in 6-fold leave-four-patients-out cross-validation and all patient training, demonstrating a superior generalizability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据