基于生成对抗网络的PPG⁃ECG信号转换方法

Method of Transferring PPG to ECG Based on Generative Adversarial Network

心电(Electrocardiogram,ECG)信号的长期检测与评估对心血管疾病的诊断和预防至关重要。心电信号的检测通常需要在患者身上安装电极,易使受试者产生不适感,适用范围有限。相对而言,使用光电容积描记法(Photoplethysmography,PPG)检测得到的脉搏波(Pulse wave)信号不仅包含丰富的心血管生理和病理信息,而且易于测量。考虑到PPG与ECG信号间存在固有的映射关系,本文基于生成对抗网络(Generative adversarial network,GAN)提出了一种将PPG转换为ECG信号的模型。该模型生成器由Unet模型组成,并且在特征图融合方面参考了Unet++的结构,而其判别器由卷积神经网络组成。在训练过程中,采用梯度惩罚方式增加了生成模型的稳定性。基于公用数据集进行了实验,通过对比53名受试者样本的处理结果,新模型所生成ECG信号的均方根误差(Root mean square error,RMSE)、Pearson相关系数(ρ)和Fréchet距离(Fréchet distance,FD)三个指标分别提升了3.4%、5.5%和0.4%,证明新模型具有更好的PPG⁃ECG转换效果。

Long-term detection and evaluation of electrocardiogram(ECG)signals is crucial for the diagnosis and prevention of cardiovascular disease.However,the detection of ECG signals usually needs to install electrodes on the patient,which can easily cause discomfort to the subject,and the scope of application is thus limited.In contrast,pulse wave signals detected by photoplethysmography(PPG)not only contains rich cardiovascular physiological and pathological information,but also is easy to be measured.Considering the inherent mapping relationship between PPG and ECG signals,a model of transferring PPG to ECG signals based on generative adversarial network(GAN)is proposed.The generator network is composed of the Unet model,the structure of Unet++is referenced in the feature map fusion,and the discriminator network is composed of a convolutional neural network.During the training process,gradient penalty is utilized to increase the stability of the model.The experiment is conducted based on public datasets.By comparing the processing results of a sample of 53 subjects,the root mean square error(RMSE),Pearson correlation coefficient(ρ)and Fréchet distance(FD)of the ECG signal generated by the new model are improved by 3.4%,5.5%and 0.4%,respectively,proving that the new model has better PPG-ECG transfer effect.