南方医科大学学报

南方医科大学学报 ›› 2022, Vol. 42 ›› Issue (3): 375-383.doi: 10.12122/j.issn.1673-4254.2022.03.09

• • 上一篇    下一篇

可穿戴式心电信号R峰检测的心拍感知卷积网络

谭慧欣，赖杰伟，王 祚，季 磊，张一行，王进亮，宋育章，阳 维   

  1. 南方医科大学生物医学工程学院，广东 广州 510515；广东省医学图像处理重点实验室，广东 广州 510515；中国人民解放军总医院医疗保障中心信息科，北京 100853；心韵恒安医疗科技（北京）有限公司，北京 100142；美国加州大学河滨分校，美国加利福尼亚州 河滨 92521
  • 出版日期:2022-03-20 发布日期:2022-04-12

Heartbeat-aware convolutional neural network for R-peak detection of wearable device ECG data

TAN Huixin, LAI Jiewei, WANG Zuo, JI Lei, ZHANG Yihang, WANG Jinliang, SONG Yuzhang, YANG Wei   

  1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China; Information Department, Medical Security Center, Chinese PLA General Hospital, Beijing 100853, China; CardioCloud Medical Technology (Beijing) Co. Ltd, Beijing 100084, China; University of California, Riverside, Riverside 92521, USA
  • Online:2022-03-20 Published:2022-04-12

RichHTML

27

PDF

371

摘要： 目的 实现可穿戴式心电信号的R峰检测，为准确估计心率、心率变异性等生理参数提供基础。方法 采用全卷积网络预测R峰热图，对热图进行峰值定位获得R峰位置。引入心拍感知模块，联合心拍数量预测任务和R峰热图预测任务进行学习，提高卷积网络对全局上下文信息的提取能力。心拍感知模块预测的心拍数量还可估计R-R间期，用作峰值定位的峰间最小水平距离。为满足移动端的实时应用，采用深度可分离卷积减小模型的参数量和计算量。结果 实验仅使用可穿戴式心电数据训练模型。测试中定位误差容忍度设置为150 ms时，本文方法在可穿戴式心电数据集和公开数据集LUDB上的R峰检测灵敏度均高达100%，真阳率均超过99.9%；对于时长10 s的ECG信号，R峰检测CPU耗时约为23.2 ms。结论 本文方法对可穿戴式和常规心电信号的R峰检测均可达到良好效果，且满足R峰检测的实时性需求。

关键词: 可穿戴式心电信号；R峰检测；心拍感知；卷积网络

Abstract: Objective To develop a method for R-peak detection of ECG data from wearable devices to allow accurate estimation of the physiological parameters including heart rate and heart rate variability. Methods A fully convolutional neural network was applied to predict the R-peak heatmap of ECG data and locate the R-peak positions. The heartbeat-aware (HA) module was introduced to enable the model to learn to predict the heartbeat number and R-peak heatmap simultaneously, thereby improving the capability of the model for extraction of the global context. The R-R interval estimated by the predicted heartbeat number was adopted to calculate the minimum horizontal distance for peak positioning. To achieve real-time R-peak detection on mobile devices, the deep separable convolution was adopted to reduce the number of parameters and the computational complexity of the model. Results The proposed model was trained only with ECG data from wearable devices. At a tolerance window interval of 150 ms, the proposed method achieved R peak detection sensitivities of 100% for both wearable device ECG dataset and a public dataset (i.e. LUDB), and the true positivity rates exceeded 99.9%. As for the ECG signal of a 10 s duration, the CPU time of the proposed method for R-peak detection was about 23.2 ms. Conclusion The proposed method has good performance for R-peak detection of both wearable device ECG data and routine ECG data and also allows real-time R-peak detection of the ECG data.

Key words: wearable device ECG data; R-peak detection; heartbeat-aware; convolutional neural network