曹玉珍 ,高晨阳,余 辉,王 江
AuthorsHTML:曹玉珍 ¹ ，高晨阳 ¹ ，余 辉 ¹ ，王 江 ²
AuthorsListE:Cao Yuzhen,Gao Chenyang,Yu Hui ,Wang Jiang
AuthorsHTMLE:Cao Yuzhen¹，Gao Chenyang¹，Yu Hui ¹，Wang Jiang ²
Unit:1. 天津大学精密仪器与光电子工程学院，天津 300072；
2. 天津大学电气自动化与信息工程学院，天津 300072

Unit_EngLish:1. School of Precision Instruments and Optoelectronics Engineering，Tianjin University，Tianjin 300072，China；
2. School of Electrical and Information Engineering，Tianjin University，Tianjin 300072，China

Abstract_Chinese:随着对癫痫状态神经元电活动研究的不断深入，针对癫痫患者的电磁刺激疗法备受关注，自动准确地识别 癫痫发作状态是及时准确地实施电磁刺激的关键．因此，构建了一种由通用模型向个性化模型迁移的癫痫发作状态 识别方法．首先，基于多个病患的脑电数据，采用一维卷积神经网络建立癫痫状态识别的通用模型，学习不同病患 癫痫发作时脑电状态的共性特征，以实现对不同病患癫痫发作状态的通用识别；其次，基于单个病患的脑电数据， 通过迁移学习将通用模型的参数迁移到个性化模型之中以简化模型训练、加速收敛，讨论了通用模型参数向个性化 模型迁移的全面迁移方式和卷积层参数迁移方式的性能．使用 CHB-MIT 数据库中 17 例病患的长程脑电记录数据对 算法进行验证，最终所有病患个性化模型的平均准确率达到了 91.04%．基于个性化模型对病患的长程脑电记录进行 癫痫发作起止时间判断，模型对癫痫发作和结束状态的检出率达到了 96.43%和 89.29%．结果表明，该模型发挥了 深度学习无需手动提取、选择特征的优势，为癫痫状态识别方法用于癫痫治疗方案的开发提供了参考与依据．
Abstract_English:With the deepening of research on the electrical activity of epileptic neurons，electromagnetic stimulation therapy for epileptic patients has attracted considerable attention. Automatic and accurate identification of epileptic seizure status is the key to the timely and accurate implementation of electromagnetic stimulation. In this study，a novel patient-specific seizure state recognition technique based on convolutional neural network(CNN)and transfer learning is proposed. First，on the basis of the electroencephalogram(EEG)recordings from multiple patients，the one-dimensional CNN is used to establish a general model for epileptic seizure state recognition. The general model is used to learn the common characteristics of EEG during seizures in different patients to achieve general recognition of seizure states. Then，on the basis of the EEG recordings from individual patients，the parameters of the general model are transferred to the personalized model using transfer learning to simplify model training and accelerate con\u0002vergence. The model performance of the overall migration and convolution layer parameter migration modes of uni\u0002versal model parameters to the personalized model is also discussed. Finally，the algorithm is applied to long-term scalp EEG recordings of 17 patients in the CHB-MIT database. The average accuracy of all patient personalized mod-els reaches 91.04%. On the basis of the personalized model，the patients’ long-term EEG recordings are used to judge the onset and end of seizures. The detection rates of the onset and end of seizure states reach 96.43% and 89.29%， respectively，in the test dataset. Thus，the EEG-based seizure state recognition model using CNN and transfer learning could be used in the development of treatment programs for patients with epilepsy.
Keyword_Chinese:癫痫；卷积神经网络；迁移学习；个性化模型
Keywords_English:epilepsy；convolutional neural network；transfer learning；personalized model

PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=6697