Wang Xiaojia, Liu Yanchao, Yang Chunfeng
Wuxi Vocational College of Science and Technology, Wuxi, 214028, China.
School of computer science and engineering, Southeast University, Nanjing, 210096, China.
Brain Inform. 2024 Aug 23;11(1):22. doi: 10.1186/s40708-024-00233-y.
Epilepsy is one of the most common clinical diseases of the nervous system. The occurrence of epilepsy will bring many serious consequences, and some patients with epilepsy will develop drug-resistant epilepsy. Surgery is an effective means to treat this kind of patients, and lesion localization can provide a basis for surgery. The purpose of this study was to explore the functional types and connectivity evolution patterns of relevant regions of the brain during seizures. We used intracranial EEG signals from patients with epilepsy as the research object, and the method used was GRU-GC. The role of the corresponding area of each channel in the seizure process was determined by the introduction of group analysis. The importance of each area was analysed by introducing the betweenness centrality and PageRank centrality. The experimental results show that the classification method based on effective connectivity has high accuracy, and the role of the different regions of the brain could also change during the seizures. The relevant methods in this study have played an important role in preoperative assessment and revealing the functional evolution patterns of various relevant regions of the brain during seizures.
癫痫是神经系统最常见的临床疾病之一。癫痫的发生会带来许多严重后果，一些癫痫患者会发展为药物难治性癫痫。手术是治疗这类患者的有效手段，而病灶定位可为手术提供依据。本研究的目的是探索癫痫发作期间大脑相关区域的功能类型和连接演变模式。我们将癫痫患者的颅内脑电图信号作为研究对象，采用的方法是GRU-GC。通过引入组分析确定每个通道对应区域在癫痫发作过程中的作用。通过引入介数中心性和PageRank中心性分析每个区域的重要性。实验结果表明，基于有效连接性的分类方法具有较高的准确性，并且大脑不同区域的作用在癫痫发作期间也可能发生变化。本研究中的相关方法在术前评估以及揭示癫痫发作期间大脑各个相关区域的功能演变模式方面发挥了重要作用。
