[1]徐柏林,蔡文杰,杨明菲,等.基于改进U-Net模型的心电波形分割[J].中国医学物理学杂志,2022,39(10):1274-1279.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.016]
　XU Bolin,CAI Wenjie,YANG Mingfei,et al.ECG waveform segmentation based on improved U-Net model[J].Chinese Journal of Medical Physics,2022,39(10):1274-1279.[doi:DOI:10.3969/j.issn.1005-202X.2022.10.016]
点击复制

基于改进U-Net模型的心电波形分割()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
39卷
期数:
2022年第10期
页码:
1274-1279
栏目:
医学信号处理与医学仪器
出版日期:
2022-11-02

文章信息/Info

Title:
ECG waveform segmentation based on improved U-Net model
文章编号:
1005-202X（2022）10-1274-06
作者:
徐柏林; 蔡文杰; 杨明菲; 张标
上海理工大学健康科学与工程学院， 上海 200093
Author(s):
XU Bolin;  CAI Wenjie;  YANG Mingfei;  ZHANG Biao
School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
关键词:
心电图; 改进U-Net模型; 算法验证; 分割
Keywords:
Keywords: electrocardiogram improved U-Net model algorithm verification segmentation
分类号:
R318；TP391
DOI:
DOI:10.3969/j.issn.1005-202X.2022.10.016
文献标志码:
A
摘要:
基于U-Net框架提出一种新的算法用于心电波形的分割。该方法将一定长度的心电信号作为输入，输出P波、QRS波和T波的分割图像，同时定位各个特征波的起始点和终止点，创新性地提出了多通道空洞卷积加上注意力机制的模型结构，并设计了一种数据增强公式用于增加数据的多样性。本研究提出的方法在LUDB上进行训练测试，在QTDB上验证算法的泛化能力。实验结果表明，所提的算法在LUDB的平均灵敏度、平均阳性预测率、平均F1分数分别为99.41%、98.90%、98.75%；在QTDB的平均灵敏度、平均阳性预测率、平均F1分数分别为98.65%、98.43%、98.23%，这说明本文算法效果更好，并具有优异的泛化性能。
Abstract:
Abstract: A new algorithm based on U-Net framework is proposed for ECG waveform segmentation, taking the ECG signal of fixed length as the input, and then outputting the images of P wave, QRS wave and T wave. The method can locate the starting and ending points of each characteristic wave. A novel model structure of multi-channel dilated convolution with attention mechanism is put forward, and a data enhancement formula is designed to increase the diversity of data. The proposed method is trained and tested on LUDB, and the generalization ability of the algorithm is verified on QTDB. The experimental results show that the average sensitivity, average positive prediction rate, and average F1 score of the proposed algorithm are 99.41%, 98.90%, 98.75% on LUDB, and 98.65%, 98.43%, 98.23% on QTDB, indicating that the proposed algorithm performs better and has excellent generalization performance.

相似文献/References:

[1]武会江,黄启俊,常胜,等.基于多项式参数拟合和支持向量机的心肌梗死识别算法[J].中国医学物理学杂志,2017,34(7):736.[doi:10.3969/j.issn.1005-202X.2017.07.017]
　[J].Chinese Journal of Medical Physics,2017,34(10):736.[doi:10.3969/j.issn.1005-202X.2017.07.017]
[2]王凯,杨枢. 基于自适应学习的心律失常心拍分类方法[J].中国医学物理学杂志,2019,36(1):92.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.018]
　WANG Kai,YANG Shu. Adaptive learning-based method for classification of arrhythmic heartbeats[J].Chinese Journal of Medical Physics,2019,36(10):92.[doi:DOI:10.3969/j.issn.1005-202X.2019.01.018]
[3]梁伟玲,吴超,林建斌,等. 基于Arduino的无线心电信号采集系统设计与实现[J].中国医学物理学杂志,2019,36(6):715.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.019]
　LIANG Weiling,WU Chao,LIN Jianbin,et al. Design and implementation of wireless ECG signal acquisition system based on Arduino[J].Chinese Journal of Medical Physics,2019,36(10):715.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.019]
[4]王凯,杨枢,李超. 一种基于ECG的多层共轭对称Hadamard特征变换的房颤异常信号分类方法[J].中国医学物理学杂志,2019,36(9):1068.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.014]
　WANG Kai,YANG Shu,LI Chao. ECG-based multi-level conjugate symmetric Hadamard feature transformation for classification of abnormal signals of atrial fibrillation[J].Chinese Journal of Medical Physics,2019,36(10):1068.[doi:DOI:10.3969/j.issn.1005-202X.2019.09.014]
[5]蔚文婧,王寻,张鹏远,等.一种基于多层感知器的房颤心电图检测方法[J].中国医学物理学杂志,2020,37(3):332.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.015]
　WEI Wenjing,WANG Xun,ZHANG Pengyuan,et al.Multilayer perceptron-based method for atrial fibrillation ECG detection[J].Chinese Journal of Medical Physics,2020,37(10):332.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.015]
[6]文翠,赵新军,张震洪,等.冠心病患者心电图ST段改变与多排螺旋CT冠状动脉成像的关系分析[J].中国医学物理学杂志,2020,37(8):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
　WEN Cui,ZHAO Xinjun,ZHANG Zhenhong,et al.Relationships between ECG ST-segment changes and multi-slice spiral CT coronary angiography in patients with coronary heart disease[J].Chinese Journal of Medical Physics,2020,37(10):1035.[doi:DOI:10.3969/j.issn.1005-202X.2020.08.018]
[7]胡丹琴,蔡文杰.QRS复合波检测技术综述[J].中国医学物理学杂志,2020,37(9):1208.[doi:10.3969/j.issn.1005-202X.2020.09.024]
　HU Danqin,CAI Wenjie.Review on technologies for QRS complex detection[J].Chinese Journal of Medical Physics,2020,37(10):1208.[doi:10.3969/j.issn.1005-202X.2020.09.024]
[8]林卓琛,张晋昕.基于非参数相关系数的心肌病自动诊断[J].中国医学物理学杂志,2021,38(1):80.[doi:10.3969/j.issn.1005-202X.2021.01.014]
　LIN Zhuochen,ZHANG Jinxin.Automatic diagnosis of cardiomyopathy based on nonparametric correlation coefficient[J].Chinese Journal of Medical Physics,2021,38(10):80.[doi:10.3969/j.issn.1005-202X.2021.01.014]
[9]王新峰,漆梦玲,徐洪智.基于心电图的心肌梗死识别分类研究[J].中国医学物理学杂志,2022,39(8):992.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.013]
　WANG Xinfeng,QI Mengling,et al.ECG-based identification and classification of myocardial infarction[J].Chinese Journal of Medical Physics,2022,39(10):992.[doi:DOI:10.3969/j.issn.1005-202X.2022.08.013]
[10]刘建华,吕建峰,蔡金丹.基于卷积神经网络和长短时记忆网络的心肌梗死检测[J].中国医学物理学杂志,2022,39(11):1448.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.020]
　LIU Jianhua,L?Jianfeng,CAI Jindan.Screening for myocardial infarction using convolutional neural network and long short-term memory network[J].Chinese Journal of Medical Physics,2022,39(10):1448.[doi:DOI:10.3969/j.issn.1005-202X.2022.11.020]

备注/Memo

备注/Memo:
【收稿日期】2022-05-17 【基金项目】国家自然科学基金（31830042） 【作者简介】徐柏林，硕士研究生，研究方向：医学人工智能，E-mail: 1649800018@qq.com 【通信作者】蔡文杰，副教授，研究方向：医学人工智能，E-mail: wjcai@usst.edu.cn
更新日期/Last Update: 2022-10-27