模式识别与人工智能
2025年1月11日 星期六   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2021, Vol. 34 Issue (4): 333-342    DOI: 10.16451/j.cnki.issn1003-6059.202104005
“智能医疗与医学图像处理”专辑 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于深度神经网络的个性化睡眠癫痫发作预测
程晨晨1,3, 尤波1,2, 刘燕2,3,4, 戴亚康3,4
1.哈尔滨理工大学 机械动力工程学院 哈尔滨 150080
2.哈尔滨理工大学 自动化学院 哈尔滨 150080
3.中国科学院苏州生物医学工程技术研究所 医学影像技术研究室 苏州 215163
4.苏州市医疗健康信息技术重点实验室 苏州 215163
A Patient-Specific Method for Epileptic Seizure Prediction During Sleep Based on Deep Neural Network
CHENG Chenchen1,3, YOU Bo1,2, LIU Yan2,3,4, DAI Yakang3,4
1. School of Mechanical and Power Engineering, Harbin University of Science and Technology, Harbin 150080
2. School of Automation, Harbin University of Science and Technology, Harbin 150080
3. Medical Imaging Technology Laboratory, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163
4. Suzhou Key Laboratory of Medical and Health Information Technology, Suzhou 215163

全文: PDF (886 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 现有癫痫发作预测方法存在精度较低、错误报警率较高、癫痫患者睡眠脑电特异性、致痫灶位置和类型不同导致脑电信号存在差异的问题.文中提出基于深度神经网络的个性化睡眠癫痫发作预测方法,帮助医生和患者采取及时有效的治疗措施,降低患者患并发症和猝死的概率.对原始脑电信号滤波和分段以去除噪声,保证短时间内触发警报,利用离散小波变换分解信号并提取统计特征表征脑电信号时频特征.再应用双向长短期记忆网络挖掘最具鉴别能力的特征并结合留一法分类,经过决策过程优化得到预测结果.在不同频带限制条件下的实验表明,与睡眠癫痫相关的δ频带信号是影响发作预测性能的重要因素.相比现有睡眠癫痫预测方法,文中方法性能较优.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
程晨晨
尤波
刘燕
戴亚康
关键词 癫痫发作预测睡眠脑电(EEG)深度神经网络个性化    
Abstract:The existing epileptic seizure prediction methods present the problems of low accuracy, high false alarm rate, sleep electroencephalogram(EEG) specificity of epileptic patients and differences in EEG signals caused by differences in the location and type of epileptic foci . In this paper, a patient-specific method for epileptic seizure prediction during sleep based on deep neural network is proposed to help doctors and patients to take timely and effective treatment measures. Consequently, the probability of patients suffering from complications and sudden death is reduced. The original EEG signals are filtered and segmented to remove noise and trigger the alarm in a short time. Discrete wavelet transform is utilized to decompose the EEG, and statistical features are extracted to reveal the time-frequency characteristics of EEG signals. Then, the bi-direction long-short term memory(Bi-LSTM) is employed to mine the most discriminative features combined with the leave-one-out method for classification. The prediction results are obtained after the optimization of the decision-making process. Experiments with different frequency band restrictions show that the δ band signal related to sleep epilepsy affects the prediction performance and the performance of the proposed method is better than the existing sleep epileptic seizure prediction methods.
Key wordsEpileptic Seizure Prediction    Sleep Electroencephalogram(EEG)    Deep Neural Network    Patient-Specific   
收稿日期: 2020-06-01     
ZTFLH: R 318  
通讯作者: 戴亚康,博士,研究员,主要研究方向为智能医学影像处理分析.E-mail:daiyk@sibet.ac.cn.   
作者简介: 程晨晨,博士研究生,主要研究方向为神经电生理信号分析、机器学习、模式识别.E-mail:chengchenchen2018@163.com. 尤 波,博士,教授,主要研究方向为机器人、神经电生理信号分析、机器学习、模式识别等.E-mail:youbo@hrbust.edu.cn. 刘 燕,博士,副研究员,主要研究方向为多模态神经影像智能处理分析.E-mail:liuyan@sibet.ac.cn.
引用本文:   
程晨晨, 尤波, 刘燕, 戴亚康. 基于深度神经网络的个性化睡眠癫痫发作预测[J]. 模式识别与人工智能, 2021, 34(4): 333-342. CHENG Chenchen, YOU Bo, LIU Yan, DAI Yakang. A Patient-Specific Method for Epileptic Seizure Prediction During Sleep Based on Deep Neural Network. , 2021, 34(4): 333-342.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202104005      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I4/333
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn