[1]潘嘉婷,梁丽诗,陈真诚.基于Bi-UNet的无创动脉血压波形重建算法[J].中国医学物理学杂志,2024,41(1):66-71.[doi:DOI:10.3969/j.issn.1005-202X.2024.01.010]
　PAN Jiating,LIANG Lishi,CHEN Zhencheng,et al.Non-invasive arterial blood pressure waveform reconstruction algorithm based on Bi-UNet[J].Chinese Journal of Medical Physics,2024,41(1):66-71.[doi:DOI:10.3969/j.issn.1005-202X.2024.01.010]
点击复制

基于Bi-UNet的无创动脉血压波形重建算法()
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1期
页码:
66-71
栏目:
医学信号处理与医学仪器
出版日期:
2024-01-23

文章信息/Info

Title:
Non-invasive arterial blood pressure waveform reconstruction algorithm based on Bi-UNet
文章编号:
1005-202X（2024）01-0066-06
作者:
潘嘉婷1; 梁丽诗2; 陈真诚1; 2; 3; 4
1.桂林电子科技大学电子工程与自动化学院， 广西 桂林 541000； 2.桂林电子科技大学生命与环境科学学院， 广西 桂林 541000； 3.广西高校生物传感与仪器重点实验室， 广西 桂林541000； 4.广西人体生理信息无创检测工程技术研究中心， 广西 桂林 541000
Author(s):
PAN Jiating1;  LIANG Lishi2;  CHEN Zhencheng1;  2;  3;  4
1. School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541000, China 2. School of Life and Environmental Science, Guilin University of Electronic Technology, Guilin 541000, China 3. Guangxi Colleges and Universities Key Laboratory of Biomedical Sensors and Intelligent Instruments, Guilin 541000, China 4. Guangxi Engineering Technology Research Center of Human Physiological Information Noninvasive Detection, Guilin 541000, China
关键词:
信号重建; 无创; 动脉血压波形; 光电容积脉搏波; 深度学习
Keywords:
Keywords: signal reconstruction non-invasive arterial blood pressure waveform photoplethysmogram deep learning
分类号:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2024.01.010
文献标志码:
A
摘要:
提出了一种非侵入性的深度学习方法，用于光电容积脉搏波信号重构动脉血压信号。设计的Bi-UNet模型采用U-Net作为特征提取器，设计了双向时间处理器模块，用于提取基于个体模型的时间依赖信息。双向时间处理器模块利用BiLSTM网络有效地分析正向和反向的时间序列数据。此外，笔者采用了深度监督方法，即训练模型关注数据的各个层面特征，以提高预测波形的准确性。本文模型在重要的动脉血压波形指标收缩压、舒张压和平均动脉血压上的平均绝对误差分别达到了2.89、1.55和1.52 mmHg，标准差分别达到了2.43、1.79和1.47 mmHg。这些结果表明本文方法相比现有技术的优越性，并展示了其在实施和应用中的潜力。
Abstract:
Abstract: A non-invasive deep learning method is proposed for reconstructing arterial blood pressure signals from photoplethysmography signals. The method employs U-Net as a feature extractor, and a module referred to as bidirectional temporal processor is designed to extract time-dependent information on an individual model basis. The bidirectional temporal processor module utilizes a BiLSTM network to effectively analyze time series data in both forward and backward directions. Furthermore, a deep supervision approach which involves training the model to focus on various aspects of data features is adopted to enhance the accuracy of the predicted waveforms. The differences between actual and predicted values are 2.89±2.43, 1.55±1.79 and 1.52±1.47 mmHg on systolic blood pressure, diastolic blood pressure and mean arterial pressure, respectively, suggesting the superiority of the proposed method over the existing techniques, and demonstrating its application potential.

相似文献/References:

[1]杨骏,张海生,金贵,等.基于磁感应的闭合性颅脑撞击伤脑出血早期检测实验研究[J].中国医学物理学杂志,2018,35(9):1069.[doi:10.3969/j.issn.1005-202X.2018.09.014]
　YANG Jun,ZHANG Haisheng,JIN Gui,et al.Experimental research of early detection of cerebral hemorrhage in closed craniocerebralinjury based on magnetic induction[J].Chinese Journal of Medical Physics,2018,35(1):1069.[doi:10.3969/j.issn.1005-202X.2018.09.014]
[2]武陆琪,程云章,边俊杰.基于脉搏波的心输出量监测技术研究进展[J].中国医学物理学杂志,2020,37(3):355.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.019]
　WU Luqi,CHENG Yunzhang,BIAN Junjie.Advances in cardiac output monitoring technology based on pulse wave[J].Chinese Journal of Medical Physics,2020,37(1):355.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.019]
[3]徐晓慧,李晖,王彬,等.可穿戴式持续葡萄糖监测设备的研究现状[J].中国医学物理学杂志,2020,37(4):473.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.014]
　XU Xiaohui,LI Hui,et al.Research status of wearable continuous glucose monitoring devices[J].Chinese Journal of Medical Physics,2020,37(1):473.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.014]

备注/Memo

备注/Memo:
【收稿日期】2023-09-02 【基金项目】国家重大科研仪器研制项目（61627807）；广西创新驱动发展项目（2019AA12005）；国家自然科学基金联合基金项目（U22A2092） 【作者简介】潘嘉婷，硕士研究生，研究方向：医学与信息处理，E-mail: kkmuggle666@gmail.com 【通信作者】陈真诚，博士，教授，研究生导师，研究方向：生物医学传感与智能仪器，E-mail: chenzhcheng@guet.edu.cn
更新日期/Last Update: 2024-01-23