Liu Xin, Li Chunyang, Lou Xicheng, Kong Haohuan, Li Xinwei, Li Zhangyong, Zhong Lisha
Research Center of Biomedical Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.
School of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China.
Front Neuroinform. 2024 Mar 19;18:1354436. doi: 10.3389/fninf.2024.1354436. eCollection 2024.
Epileptic seizures are characterized by their sudden and unpredictable nature, posing significant risks to a patient's daily life. Accurate and reliable seizure prediction systems can provide alerts before a seizure occurs, as well as give the patient and caregivers provider enough time to take appropriate measure. This study presents an effective seizure prediction method based on deep learning that combine with handcrafted features. The handcrafted features were selected by Max-Relevance and Min-Redundancy (mRMR) to obtain the optimal set of features. To extract the epileptic features from the fused multidimensional structure, we designed a P3D-BiConvLstm3D model, which is a combination of pseudo-3D convolutional neural network (P3DCNN) and bidirectional convolutional long short-term memory 3D (BiConvLstm3D). We also converted EEG signals into a multidimensional structure that fused spatial, manual features, and temporal information. The multidimensional structure is then fed into a P3DCNN to extract spatial and manual features and feature-to-feature dependencies, followed by a BiConvLstm3D input to explore temporal dependencies while preserving the spatial features, and finally, a channel attention mechanism is implemented to emphasize the more representative information in the multichannel output. The proposed has an average accuracy of 98.13%, an average sensitivity of 98.03%, an average precision of 98.30% and an average specificity of 98.23% for the CHB-MIT scalp EEG database. A comparison of the proposed model with other baseline methods was done to confirm the better performance of features through time-space nonlinear feature fusion. The results show that the proposed P3DCNN-BiConvLstm3D-Attention3D method for epilepsy prediction by time-space nonlinear feature fusion is effective.
癫痫发作具有突然性和不可预测性，对患者的日常生活构成重大风险。准确可靠的癫痫发作预测系统可以在发作前发出警报，并为患者和护理人员提供足够的时间采取适当措施。本研究提出了一种基于深度学习并结合手工特征的有效癫痫发作预测方法。通过最大相关性和最小冗余性（mRMR）选择手工特征，以获得最优特征集。为了从融合的多维结构中提取癫痫特征，我们设计了一个P3D-BiConvLstm3D模型，它是伪3D卷积神经网络（P3DCNN）和双向卷积长短期记忆3D（BiConvLstm3D）的组合。我们还将脑电图信号转换为融合了空间、手工特征和时间信息的多维结构。然后将该多维结构输入到P3DCNN中，以提取空间和手工特征以及特征间的依赖关系，接着输入到BiConvLstm3D中，在保留空间特征的同时探索时间依赖关系，最后，实现通道注意力机制以强调多通道输出中更具代表性的信息。对于CHB-MIT头皮脑电图数据库，所提出的方法平均准确率为98.13%，平均灵敏度为98.03%，平均精确率为98.30%，平均特异性为98.23%。通过与其他基线方法进行比较，以确认通过时空非线性特征融合得到的特征具有更好的性能。结果表明，所提出的通过时空非线性特征融合进行癫痫预测的P3DCNN-BiConvLstm3D-Attention3D方法是有效的。
