Suppr
超能文献

基于 R 波峰对齐生成对抗网络的肢体导联心电图 V 导联信号合成。

Synthesis of Electrocardiogram V-Lead Signals From Limb-Lead Measurement Using R-Peak Aligned Generative Adversarial Network.

出版信息

IEEE J Biomed Health Inform. 2020 May;24(5):1265-1275. doi: 10.1109/JBHI.2019.2936583. Epub 2019 Aug 21.

DOI:10.1109/JBHI.2019.2936583

Abstract

Recently, portable electrocardiogram (ECG) hardware devices have been developed using limb-lead measurements. However, portable ECGs provide insufficient ECG information because of limitations in the number of leads and measurement positions. Therefore, in this study, V-lead ECG signals were synthesized from limb leads using an R-peak aligned generative adversarial network (GAN). The data used the Physikalisch-Technische Bundesanstalt (PTB) dataset provided by PhysioNet. First, R-peak alignment was performed to maintain the physiological information of the ECG. Second, time domain ECG was converted to bi-dimensional space by ordered time-sequence embedding. Finally, the GAN was learned through the pairs between the modified limb II (MLII) lead and each chest (V) lead. The result showed that the mean structural similarity index (SSIM) was 0.92, and the mean error rate of the percent mean square difference (PRD) of the chest leads was 7.21%.

摘要

最近，已经开发出了使用肢体导联测量的便携式心电图（ECG）硬件设备。然而，由于导联数量和测量位置的限制，便携式 ECG 提供的 ECG 信息不足。因此，在这项研究中，使用 R 波对齐生成对抗网络（GAN）从肢体导联合成 V 导联 ECG 信号。所使用的数据来自 PhysioNet 提供的 Physikalisch-Technische Bundesanstalt（PTB）数据集。首先，进行 R 波对齐以保持 ECG 的生理信息。其次，通过有序时间序列嵌入将时域 ECG 转换为二维空间。最后，通过修改后的肢体 II（MLII）导联和每个胸部（V）导联之间的对来学习 GAN。结果表明，平均结构相似性指数（SSIM）为 0.92，胸部导联的平均均方根差（PRD）误差率为 7.21%。