基于生成对抗网络的动态心电信号QRS波检测  

QRS wave detection algorithm of dynamic ECG signal based on generative adversarial networks

作　　者：于婷婷 冯鹏[1] 漆伟 郑冬 何鹏[1] 魏彪[1] YU Ting-ting;FENG Peng;QI Wei;ZHENG Dong;HE Peng;WEI Biao(Chongqing University Key Laboratory of Optoelectronic Technology and System of Ministry of Education,Cho昭qing,China,400044)

机构地区：[1]重庆大学光电技术及系统教育部重点实验室,重庆400044

出　　处：《光电子．激光》2021年第2期186-193,共8页Journal of Optoelectronics·Laser

基　　金：科技部2019国家重点研发计划(2019YFC0605203);重庆市基础研究和前沿探索项目(cstc2020jcyj-msxmX0553);中央高校基本科研业务费(2020CDJ-LHZZ-075);重庆市教委科学技术研究计划项目(KJQN201904007)联合资助项目。

摘　　要：心电信号分析是预防心血管疾病的重要举措,QRS波的精确检测不仅是心电信号处理的关键步骤且对心率计算和异常情况分析具有重要作用。针对动态心电信号存在信号质量差或异常节奏波形导致常用QRS波检测方法精度较低的问题,本文提出了一种基于生成对抗网络新型QRS波检测算法。该算法以Pix2Pix网络为基础,生成网络采用U-Net结构,判别网络运用Patch-GAN思想,利用U-Net结构的跳跃连接方式,实现了心电数据至R波波峰位置数据的映射,并通过对原始信号的去噪和重组,提升输入信号信噪比。使用ICBEB动态心电数据库2000组单导联心电信号进行算法验证,并与P&T算法和基于CNN的算法作对比,结果表明,本文算法的R波检测准确率达到99.13%,显著优于P&T算法和CNN算法。在灵敏度和阳性预测方面,本文算法获得最优结果,说明了本文算法的有效性。ECG signal detection is an important measure to prevent cardiovascular diseases.The accurate detection of QRS wave is not only a key step in ECG signal processing,but also plays an important role in heart rate calculation and abnormal situation analysis.In order to solve the problem of poor signal quality or abnormal rhythm waveforms in dynamic ECG signals,which results in low accuracy of commonly used QRS wave detection methods,therefore this paper proposes a new QRS wave detection based on our proposed algorithm.The algorithm is based on the Pix2 Pix network.The Generative network adopts the U-Net structure,the Discriminant network uses the Patch-GAN idea,and makes full use of the jump connection structure of the U-Net structure to realize the mapping of ECG data to R wave peak position data,and improve the signal-to-noise ratio of the input signal by denoising and reorganizing the original signal.Using 2000 groups of single-lead ECG signals about ICBEB dynamic ECG database for algorithm verification,comparing with the other two algorithms,the results show that the accuracy rate of QRS wave detection algorithm based on our proposed algorithm reaches 99.13%,which is significantly better than the other two algorithms.Our algorithm also gets the best results on Se and+P criteria,which shows the effectiveness of the algorithm in this paper.

关 键 词：心电信号 对抗生成网络 QRS波检测 R波波峰位置 

分 类 号：TH841[机械工程—仪器科学与技术]