Qiao Weizheng, Bi Xiaojun, Han Lu, Zhang Yulin
Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing 100081, China.
College of Information Engineering, Minzu University of China, Beijing 100081, China.
Sensors (Basel). 2024 Dec 25;25(1):51. doi: 10.3390/s25010051.
Epilepsy is a group of neurological disorders characterized by epileptic seizures, and it affects tens of millions of people worldwide. Currently, the most effective diagnostic method employs the monitoring of brain activity through electroencephalogram (EEG). However, it is critical to predict epileptic seizures in patients prior to their onset, allowing for the administration of preventive medications before the seizure occurs. As a pivotal application of artificial intelligence in medical treatment, learning the features of EEGs for epilepsy prediction and detection remains a challenging problem, primarily due to the presence of intra-class and inter-class variations in EEG signals. In this study, we propose the spatio-temporal EEGNet, which integrates contractive slab and spike convolutional deep belief network (CssCDBN) with a self-attention architecture, augmented by dual-task learning to address this issue. Initially, our model was designed to extract high-order and deep representations from EEG spectrum images, enabling the simultaneous capture of spatial and temporal information. Furthermore, EEG-based verification aids in reducing intra-class variation by considering the time correlation of the EEG during the fine-tuning stage, resulting in easier inference and training. The results demonstrate the notable efficacy of our proposed method. Our method achieved a sensitivity of 98.5%, a false-positive rate (FPR) of 0.041, a prediction time of 50.92 min during the epilepsy prediction task, and an accuracy of 94.1% during the epilepsy detection task, demonstrating significant improvements over current state-of-the-art methods.
癫痫是一组以癫痫发作为特征的神经系统疾病，全球数以千万计的人受其影响。目前，最有效的诊断方法是通过脑电图（EEG）监测大脑活动。然而，在癫痫发作前对患者进行预测至关重要，这样可以在发作前给予预防性药物治疗。作为人工智能在医学治疗中的一个关键应用，学习脑电图的特征以进行癫痫预测和检测仍然是一个具有挑战性的问题，主要是因为脑电图信号中存在类内和类间差异。在本研究中，我们提出了时空脑电图网络（spatio - temporal EEGNet），它将收缩平板和尖峰卷积深度信念网络（CssCDBN）与自注意力架构相结合，并通过双任务学习进行增强以解决这个问题。最初，我们的模型旨在从脑电图频谱图像中提取高阶和深度特征表示，能够同时捕捉空间和时间信息。此外，基于脑电图的验证通过在微调阶段考虑脑电图的时间相关性来减少类内差异，从而使推理和训练更容易。结果证明了我们提出的方法具有显著效果。我们的方法在癫痫预测任务中的灵敏度达到了98.5%，误报率（FPR）为0.041，预测时间为50.92分钟，在癫痫检测任务中的准确率为94.1%，与当前最先进的方法相比有显著改进。
