Qu Rongrong, Song Tingqiang, Wei Guozheng, Wei Lili, Cao Wenjuan, Song Jiale
College of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, 266100, China.
Office of the Dean, The Affiliated Hospital of Oingdao University, Qingdao, 266000, China.
Pediatr Cardiol. 2024 Sep 2. doi: 10.1007/s00246-024-03633-3.
Fetal electrocardiogram (FECG) contains crucial information about the fetus during pregnancy, making the extraction of FECG signal essential for monitoring fetal health. However, extracting FECG signal from abdominal electrocardiogram (AECG) poses several challenges: (1) FECG signal is often contaminated by noise, and (2) FECG signal is frequently overshadowed by high-amplitude maternal electrocardiogram (MECG). To address these issues and enhance the accuracy of signal extraction, this paper proposes an improved Cycle Generative Adversarial Networks (CycleGAN) with integrated contrastive learning for FECG signal extraction. The model introduces a dual-attention mechanism in the generator of the generative adversarial network, incorporating a multi-head self-attention (MSA) module and a channel-wise self-attention (CSA) module to enhance the quality of generated signals. Additionally, a contrastive triplet loss is integrated into the CycleGAN loss function, optimizing training to increase the similarity between the extracted FECG signal and the scalp fetal electrocardiogram. The proposed method is evaluated using the ADFECG dataset and the PCDB dataset both from the Physionet. In terms of signal extraction quality, Mean Squared Error is reduced to 0.036, Mean Absolute Error (MAE) to 0.009, and Pearson Correlation Coefficient reaches 0.924. When validating the model performance, Structural Similarity Index achieves 95.54%, Peak Signal-to-Noise Ratio (PSNR) reaches 38.87 dB, and R-squared (R) attains 95.12%. Furthermore, the positive predictive value (PPV), sensitivity (SEN) and F1-score for QRS wave cluster detection on the ADFECG dataset also reached 99.56%, 99.43% and 99.50%, respectively. On the PCDB dataset, the positive predictive value (PPV), sensitivity (SEN) and F1-score for QRS wave cluster detection also reached 98.24%, 98.60% and 98.42%, respectively. All of them are higher than other methods. Therefore, the proposed model has important applications in effective monitoring of fetal health during pregnancy.
胎儿心电图（FECG）包含孕期胎儿的关键信息，因此提取FECG信号对于监测胎儿健康至关重要。然而，从腹部心电图（AECG）中提取FECG信号面临诸多挑战：（1）FECG信号常被噪声污染；（2）FECG信号常被高幅度的母体心电图（MECG）掩盖。为解决这些问题并提高信号提取的准确性，本文提出一种改进的循环生成对抗网络（CycleGAN），并集成对比学习用于FECG信号提取。该模型在生成对抗网络的生成器中引入了双注意力机制，包括多头自注意力（MSA）模块和通道自注意力（CSA）模块，以提高生成信号的质量。此外，对比三元组损失被集成到CycleGAN损失函数中，优化训练以增加提取的FECG信号与头皮胎儿心电图之间的相似度。所提出的方法使用来自Physionet的ADFECG数据集和PCDB数据集进行评估。在信号提取质量方面，均方误差降至0.036，平均绝对误差（MAE）降至0.009，皮尔逊相关系数达到0.924。在验证模型性能时，结构相似性指数达到95.54%，峰值信噪比（PSNR）达到38.87 dB，决定系数（R）达到95.12%。此外，在ADFECG数据集上进行QRS波群检测的阳性预测值（PPV）、灵敏度（SEN）和F1分数也分别达到99.56%、99.43%和99.50%。在PCDB数据集上，QRS波群检测的阳性预测值（PPV）、灵敏度（SEN）和F1分数也分别达到98.24%、98.60%和98.42%。所有这些指标均高于其他方法。因此，所提出的模型在孕期有效监测胎儿健康方面具有重要应用。
