[1]艾海明,张清利,宋现涛,等.基于深度学习的桡动脉脉搏波重构方法[J].中国医学物理学杂志,2024,41(4):472-478.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.012]
　AI Haiming,ZHANG Qingli,SONG Xiantao,et al.Reconstruction method for radial artery pulse wave based on deep learning[J].Chinese Journal of Medical Physics,2024,41(4):472-478.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.012]
点击复制

基于深度学习的桡动脉脉搏波重构方法()
分享到：

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

卷:
41卷
期数:
2024年第4期
页码:
472-478
栏目:
医学信号处理与医学仪器
出版日期:
2024-04-25

文章信息/Info

Title:
Reconstruction method for radial artery pulse wave based on deep learning
文章编号:
1005-202X（2024）04-0472-07
作者:
艾海明1; 张清利1; 宋现涛2; 王野3; 张松3; 杨益民3
1.北京开放大学科学技术学院， 北京 100081； 2.首都医科大学附属北京安贞医院心内科， 北京 100029； 3.北京工业大学环境与生命学部， 北京 100124
Author(s):
AI Haiming1;  ZHANG Qingli1;  SONG Xiantao2;  WANG Ye3;  ZHANG Song3;  YANG Yimin3
1. College of Science and Technology, Beijing Open University, Beijing 100081, China 2. Department of Cardiology, Beijing Anzhen Hospital, Capital Medical University, Beijing 100029, China 3. Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
关键词:
深度学习; 脉搏波; 波形重构; 模型优化; 变分自编码器
Keywords:
Keywords: deep learning pulse wave wave reconstruction model optimization variational auto-encoder
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2024.04.012
文献标志码:
A
摘要:
目的：针对从指端脉搏波重构出桡动脉脉搏波的难题，提出一种基于深度学习的重构方法。方法：使用四通道数据采集系统PowerLab分别无创采集指端脉搏波和桡动脉脉搏波，对脉搏波信号噪声源进行分析，利用去基线算法、小波变换去噪算法、归一化预处理算法，得到稳定的信号波形。设计变分自编码器（VAE）网络模型结构参数，利用十折交叉验证法对744例受试者数据进行训练，建立桡动脉脉搏波预测模型。设置学习率、随机失活、正则化项共3项超参数，对VAE网络模型进行优化。结果：186例受试者桡动脉脉搏波重构和同步检测结果表明：低阻型和高阻型指端脉搏波经VAE网络模型建模后5%K差、20%K差、K差总方差、[FIT]分别为49.10%、96.70%、89.74和75.80%；低阻型和高阻型指端脉搏波经VAE网络优化模型建模后5%K差、20%K差、K差总方差、[FIT]分别为48.50%、94.50%、73.74和66.30%。结论：VAE网络模型建模及其优化方法可用于桡动脉脉搏波重构，重构精度较高，并具有较强的鲁棒性和泛化能力。
Abstract:
Abstract: Objective To propose a reconstruction method based on deep learning for addressing the challenge of reconstructing radial artery pulse wave from fingertip pulse wave. Methods A four-channel data acquisition system PowerLab was used to non-invasively acquire finger pulse waves and radial artery pulse waves. The noise source in the pulse wave signals were analyzed, and the stable signal waveforms were obtained after baseline removal, wavelet transform denoising, and normalization preprocessing. The structure and parameters of the variational auto-encoder (VAE) network model were designed. The model was trained using 10-fold cross-validation on data from 744 subjects to establish a prediction model for radial artery pulse waves and the VAE network model was optimized by adjusting hyperparameter settings of learning rate, dropout, and regularization term. Results The results from the reconstruction and synchronous detection of radial artery pulse waves in 186 subjects showed that for reconstructing radial artery pulse waves from low- and high-resistance fingertip pulse waves, the 5% K difference, 20% K difference, total variance of K difference, and FIT were 49.10%, 96.70%, 89.74, and 75.80% when using VAE network model, and those were 48.50%, 94.50%, 73.74, and 66.30% when using VAE optimization model. Conclusion The VAE network model and its optimization method can be used for radial artery pulse wave reconstruction, with high reconstruction accuracy, strong robustness and generalization ability.

相似文献/References:

[1]郭垚垚,陈兆学.一种脉搏波和心电信号时域基线漂移消除方法[J].中国医学物理学杂志,2016,33(2):167.[doi:10.3969/j.issn.1005-202X.2016.02.012]
　[J].Chinese Journal of Medical Physics,2016,33(4):167.[doi:10.3969/j.issn.1005-202X.2016.02.012]
[2]陶源,王佳飞,杜俊龙,等.基于卷积神经网络的细胞识别[J].中国医学物理学杂志,2017,34(1):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
　[J].Chinese Journal of Medical Physics,2017,34(4):53.[doi:10.3969/j.issn.1005-202X.2017.01.011]
[3]苏志刚,朱海玲,郝敬堂. 基于高斯混合模型的脉搏波特征提取方法[J].中国医学物理学杂志,2018,35(1):76.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.014]
　SU Zhigang,ZHU Hailing,HAO Jingtang. Gaussian mixture model-based method for extracting the features of pulse wave[J].Chinese Journal of Medical Physics,2018,35(4):76.[doi:DOI:10.3969/j.issn.1005-202X.2018.01.014]
[4]门阔,戴建荣. 利用深度反卷积神经网络自动勾画放疗危及器官[J].中国医学物理学杂志,2018,35(3):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
　MEN Kuo,DAI Jianrong. Automatic segmentation of organs at risk in radiotherapy using deep deconvolutional neural network[J].Chinese Journal of Medical Physics,2018,35(4):256.[doi:DOI:10.3969/j.issn.1005-202X.2018.03.002]
[5]邓金城,彭应林,刘常春,等. 深度卷积神经网络在放射治疗计划图像分割中的应用[J].中国医学物理学杂志,2018,35(6):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
　DENG Jincheng,PENG Yinglin,LIU Changchun,et al. Application of deep convolution neural network in radiotherapy planning image segmentation[J].Chinese Journal of Medical Physics,2018,35(4):621.[doi:DOI:10.3969/j.issn.1005-202X.2018.06.001]
[6]苏志刚,吕江波,郝敬堂. 基于平滑先验法去除脉搏波基线漂移[J].中国医学物理学杂志,2018,35(10):1197.[doi:DOI:10.3969/j.issn.1005-202X.2018.10.017]
　SU Zhigang,LÜ,Jiangbo,et al. Removal of baseline drift of pulse wave based on smoothness prior[J].Chinese Journal of Medical Physics,2018,35(4):1197.[doi:DOI:10.3969/j.issn.1005-202X.2018.10.017]
[7]查雪帆,杨丰,吴俣南,等. 结合迁移学习与深度卷积网络的心电分类研究[J].中国医学物理学杂志,2018,35(11):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
　ZHA Xuefan,YANG Feng,WU Yunan,et al. ECG classification based on transfer learning and deep convolution neural network[J].Chinese Journal of Medical Physics,2018,35(4):1307.[doi:DOI:10.3969/j.issn.1005-202X.2018.11.013]
[8]陈倩蓉,梁永波,赵飞骏,等. 基于心电-脉搏波的心血管疾病识别研究[J].中国医学物理学杂志,2019,36(2):210.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.017]
　CHEN Qianrong,LIANG Yongbo,ZHAO Feijun,et al. Cardiovascular disease recognition based on electrocardiogram data and pulse wave[J].Chinese Journal of Medical Physics,2019,36(4):210.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.017]
[9]程敏,陈兆学. 基于指端脉搏波视频信号的心率稳定检测算法[J].中国医学物理学杂志,2019,36(2):215.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.018]
　CHENG Min,CHEN Zhaoxue. An algorithm based on video signals of pulse waves on the finger tip for stable detection of heart rates[J].Chinese Journal of Medical Physics,2019,36(4):215.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.018]
[10]宫进昌,赵尚义,王远军. 基于深度学习的医学图像分割研究进展[J].中国医学物理学杂志,2019,36(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
　GONG Jinchang,ZHAO Shangyi,WANG Yuanjun.Research progress on deep learning-based medical image segmentation[J].Chinese Journal of Medical Physics,2019,36(4):420.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.010]
[11]周韡鼎,陈兆学.基于深度学习的指-桡端脉搏波信号转换方法[J].中国医学物理学杂志,2023,40(2):202.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.013]
　ZHOU Weiding,CHEN Zhaoxue.Deep learning-based method for finger-radial PPG signal transferring[J].Chinese Journal of Medical Physics,2023,40(4):202.[doi:DOI:10.3969/j.issn.1005-202X.2023.02.013]
[12]张瑞芳,梁永波,崔谋,等.结合多模态融合方式的脉搏波房颤识别[J].中国医学物理学杂志,2023,40(10):1260.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.013]
　ZHANG Ruifang,LIANG Yongbo,,et al.Multimodal fusion approach to detect atrial fibrillation using PPG[J].Chinese Journal of Medical Physics,2023,40(4):1260.[doi:DOI:10.3969/j.issn.1005-202X.2023.10.013]

备注/Memo

备注/Memo:
【收稿日期】2023-11-10 【基金项目】国家重点研发计划（2019YFC0119700）；科技部科技创新2030-“新一代人工智能”重大项目（2020AAA0105800）；比尔?琳达盖茨基金（OPP1148910）；北京市教委科技项目（KM201951160001） 【作者简介】艾海明，博士，副教授，研究方向：生物医学信息检测与处理、生物医学电子与医疗仪器，E-mail: aihm@bjou.edu.cn 【通信作者】杨益民，研究生导师，研究方向：心血管血流参数无损伤检测，E-mail: yym@bjut.edu.cn
更新日期/Last Update: 2024-04-25