Zhao Wei, Li Zhenqi, Hu Jing, Ma Yunju
Central Research Institute, Guangzhou Shiyuan Electronics Co., Ltd., Guangzhou, China.
Front Physiol. 2024 Jul 15;15:1384356. doi: 10.3389/fphys.2024.1384356. eCollection 2024.
The QRS complex is the most prominent waveform within the electrocardiograph (ECG) signal. The accurate detection of the QRS complex is an essential step in the ECG analysis algorithm, which can provide fundamental information for the monitoring and diagnosis of the cardiovascular diseases. Seven public ECG datasets were used in the experiments. A simple and effective QRS complex detection algorithm based on the deep neural network (DNN) was proposed. The DNN model was composed of two parts: a feature pyramid network (FPN) based backbone with dual input channels to generate the feature maps, and a location head to predict the probability of point belonging to the QRS complex. The depthwise convolution was applied to reduce the parameters of the DNN model. Furthermore, a novel training strategy was developed. The target of the DNN model was generated by using the points within 75 milliseconds and beyond 150 milliseconds from the closest annotated QRS complexes, and artificial simulated ECG segments with high heart rates were generated in the data augmentation. The number of parameters and floating point operations (FLOPs) of our model was 26976 and 9.90M, respectively. The proposed method was evaluated through a cross-dataset test and compared with the sophisticated state-of-the-art methods. On the MITBIH NST, the proposed method demonstrated slightly better sensitivity (95.59% vs. 95.55%) and lower presicion (91.03% vs. 92.93%). On the CPSC 2019, the proposed method have similar sensitivity (95.15% vs.95.13%) and better precision (91.75% vs. 82.03%). Experimental results show the proposed algorithm achieved a comparable performance with only a few parameters and FLOPs, which would be useful for the application of ECG analysis on the wearable device.
QRS波群是心电图（ECG）信号中最突出的波形。准确检测QRS波群是ECG分析算法中的关键步骤，可为心血管疾病的监测和诊断提供基础信息。实验使用了七个公开的ECG数据集。提出了一种基于深度神经网络（DNN）的简单有效的QRS波群检测算法。DNN模型由两部分组成：一个基于特征金字塔网络（FPN）的主干网络，具有双输入通道以生成特征图，以及一个定位头，用于预测点属于QRS波群的概率。应用深度卷积来减少DNN模型的参数。此外，还开发了一种新颖的训练策略。DNN模型的目标是通过使用距离最近标注的QRS波群75毫秒以内和150毫秒以外的点生成的，并且在数据增强中生成了高心率的人工模拟ECG片段。我们模型的参数数量和浮点运算次数（FLOPs）分别为26976和990万。通过跨数据集测试对所提出的方法进行了评估，并与先进的现有方法进行了比较。在MITBIH NST数据集上，所提出的方法显示出略高的灵敏度（95.59%对95.55%）和较低的精度（91.03%对92.93%）。在CPSC 2019数据集上，所提出的方法具有相似的灵敏度（95.15%对95.13%）和更高的精度（91.75%对82.03%）。实验结果表明，所提出的算法仅用少量参数和FLOPs就实现了可比的性能，这将有助于在可穿戴设备上应用ECG分析。
