[1]范振华,刘志琴,常家铭,等.基于GWO-VMD-DLSTM框架的心磁信号降噪方法[J].中国医学物理学杂志,2026,43(3):330-337.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.008]
　FAN Zhenhua,LIU Zhiqin,CHANG Jiaming,et al.Magnetocardiography signal denoising method based on the GWO-VMD-DLSTM framework[J].Chinese Journal of Medical Physics,2026,43(3):330-337.[doi:DOI:10.3969/j.issn.1005-202X.2026.03.008]
点击复制

基于GWO-VMD-DLSTM框架的心磁信号降噪方法()

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

卷:
43卷
期数:
2026年第3期
页码:
330-337
栏目:
医学信号处理与医学仪器
出版日期:
2026-03-27

文章信息/Info

Title:
Magnetocardiography signal denoising method based on the GWO-VMD-DLSTM framework
文章编号:
1005-202X（2026）03-0330-08
作者:
范振华1; 刘志琴2; 常家铭1; 段俊萍1; 王佳云1; 张斌珍1
1.中北大学极限环境光电动态测试技术与仪器全国重点实验室， 山西 太原 030051； 2.山西师范大学化学与材料科学学院， 山西 太原 030031
Author(s):
FAN Zhenhua1;  LIU Zhiqin2;  CHANG Jiaming1;  DUAN Junping1;  WANG Jiayun1;  ZHANG Binzhen1
1. State Key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instruments, North University of China, Taiyuan 030051, China 2. School of Chemistry and Material Science, Shanxi Normal University, Taiyuan 030031, China
关键词:
心磁信号; 变分模态分解; 长短期记忆网络; 双头注意力机制; 信号降噪; 深度学习
Keywords:
Keywords: magnetocardiography signal variational mode decomposition long short-term memory network dual-head attention mechanism signal denoising deep learning
分类号:
R318；TN312
DOI:
DOI:10.3969/j.issn.1005-202X.2026.03.008
文献标志码:
A
摘要:
针对心磁信号在采集过程中易受多源噪声干扰、病理特征被淹没等问题，提出一种基于变分模态分解与双头注意力长短期记忆网络的联合降噪算法。该方法首先通过灰狼优化算法优化的变分模态分解对原始心磁信号进行自适应分解，获得一系列本征模态函数分量，有效抑制模态混叠现象，实现噪声与有效信号的精准分离；随后构建具有双头注意力机制的长短期记忆网络，自适应学习各模态分量中的噪声与信号特征，实现分量级滤波与信号的端到端重构，克服传统方法依赖人工经验筛选模态分量的局限性。实验结果表明，在复杂噪声与基线漂移环境下，所提方法在信噪比（23.58 dB）和余弦相似度（0.99）等关键指标上均优于传统降噪算法，同时能有效保留心磁信号中的病理特征，为心磁图技术在心血管疾病早期诊断中的临床应用提供可靠技术支撑。
Abstract:
Abstract: To address the challenge that magnetocardiographic (MCG) signals are susceptible to contamination by various noise sources during acquisition, which in turn obscures critical pathological features, a novel denoising algorithm integrating variational mode decomposition (VMD) and a dual-head attention long short-term memory (LSTM) network is proposed. This method utilizes the grey wolf optimization algorithm-optimized VMD to adaptively decompose the raw MCG signal into a series of intrinsic mode functions (IMFs), thereby effectively suppressing mode mixing and achieving precise separation between noise and clinically relevant features. Next, a LSTM network with dual-head attention module is constructed to adaptively capture the noise and signal features on the IMFs, which enables component-wise filtering and end-to-end signal reconstruction without the need for manual IMFs selection. Experimental results demonstrate that in environments with complex noise and baseline drift, the proposed method achieves superior performance compared to conventional algorithms, with a signal-to-noise ratio of 23.58 dB and a cosine similarity of 0.99, and meanwhile effectively preserves diagnostically relevant features. This study provides a robust technical foundation for enhancing the clinical utility of MCG in the early screening and diagnosis of cardiovascular diseases.

相似文献/References:

[1]赵丽,崔立杰.基于变分模态分解的眼电伪迹去除[J].中国医学物理学杂志,2020,37(2):237.[doi:DOI:10.3969/j.issn.1005-202X.2020.02.018]
　ZHAO Li,CUI Lijie.Electrooculogram artifacts removal based on variational mode decomposition[J].Chinese Journal of Medical Physics,2020,37(3):237.[doi:DOI:10.3969/j.issn.1005-202X.2020.02.018]
[2]郁伟,李正权,邢松.改进WOA-VMD算法的心电信号去噪[J].中国医学物理学杂志,2023,40(9):1143.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.014]
　YU Wei,LI Zhengquan,XING Song,et al.ECG signal denoising using improved WOA-VMD algorithm[J].Chinese Journal of Medical Physics,2023,40(3):1143.[doi:DOI:10.3969/j.issn.1005-202X.2023.09.014]
[3]孙文慧,张乙鹏,林冬梅,等.基于变分模态分解的肺音去噪算法[J].中国医学物理学杂志,2024,41(4):479.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.013]
　SUN Wenhui,ZHANG Yipeng,et al.Lung sound denoising algorithm based on variational mode decomposition[J].Chinese Journal of Medical Physics,2024,41(3):479.[doi:DOI:10.3969/j.issn.1005-202X.2024.04.013]
[4]艾海明,董哲,葛静茹,等.超导心磁信号测量技术及冠心病筛查[J].中国医学物理学杂志,2024,41(10):1265.[doi:DOI:10.3969/j.issn.1005-202X.2024.10.011]
　AI Haiming,DONG Zhe,GE Jingru,et al.Superconducting magnetocardiography signal measurement technology and coronary heart disease screening[J].Chinese Journal of Medical Physics,2024,41(3):1265.[doi:DOI:10.3969/j.issn.1005-202X.2024.10.011]
[5]薛栋超,朱俊杰.针对心磁信号的HISSA优化多模态协同降噪算法[J].中国医学物理学杂志,2025,42(9):1201.[doi:DOI:10.3969/j.issn.1005-202X.2025.09.012]
　XUE Dongchao,ZHU Junjie,et al.HISSA-optimized multi-level cooperative denoising algorithm for magnetocardiogram signals[J].Chinese Journal of Medical Physics,2025,42(3):1201.[doi:DOI:10.3969/j.issn.1005-202X.2025.09.012]

备注/Memo

备注/Memo:
【收稿日期】2025-08-21 【基金项目】山西省归国留学人员科研项目（2022-143） 【作者简介】范振华，硕士研究生，研究方向：心磁信号处理，E-mail: 15635460976@163.com 【通信作者】张斌珍，教授，研究方向：微纳机电系统下的动态测试技术、微弱信号检测与处理等，E-mail: zhangbinzhen@nuc.edu.cn
更新日期/Last Update: 2026-03-30