[1]张乙鹏,孙文慧,陈扶明.基于小波变换和CNN-LSTM的肺音分类算法[J].中国医学物理学杂志,2024,41(3):356-364.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.014]
 ZHANG Yipeng,SUN Wenhui,et al.Lung sound classification algorithm based on wavelet transform and CNN-LSTM[J].Chinese Journal of Medical Physics,2024,41(3):356-364.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.014]
点击复制

基于小波变换和CNN-LSTM的肺音分类算法()
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3期
页码:
356-364
栏目:
医学信号处理与医学仪器
出版日期:
2024-03-27

文章信息/Info

Title:
Lung sound classification algorithm based on wavelet transform and CNN-LSTM
文章编号:
1005-202X(2024)03-0356-09
作者:
张乙鹏12孙文慧12陈扶明2
1.甘肃中医药大学信息工程学院, 甘肃 兰州 730000; 2.中国人民解放军联勤保障部队第940医院医疗保障中心,甘肃 兰州 730050
Author(s):
ZHANG Yipeng1 2 SUN Wenhui1 2 CHEN Fuming2
1. School of Information Engineering, Gansu University of Chinese Medicine, Lanzhou 730000, China 2. Medical Security Center, The 940th Hospital of Joint Logistics Support Force of Chinese Peoples Liberation Army, Lanzhou Gansu, 730050, China
关键词:
肺音分类小波变换卷积神经网络长短期记忆网络
Keywords:
Keywords: lung sound classification wavelet transform convolutional neural network long short-term memory
分类号:
R318;TP912.35
DOI:
DOI:10.3969/j.issn.1005-202X.2024.03.014
文献标志码:
A
摘要:
目的:针对如何建立有助于电子听诊诊断的肺音分类模型,提出一种基于卷积神经网络(CNN)-长短期记忆网络(LSTM)的混合深度学习肺音分类模型方法。方法:首先使用小波变换对数据集进行特征提取,使肺音信号转化为能量熵、峰值等特征;在此基础上构建CNN和LSTM的混合算法分类模型,其中将小波变换提取的特征先输入CNN模块,能够获得数据的空间维度特征,再通过LSTM模块获得数据的时间维度特征,融合两类特征,通过模型可以将肺音分类,从而达到辅助判断患者的肺部疾病。结果:CNN-LSTM混合模型准确率、F1分数均明显高于其他单一模型,可达到0.948和0.950。结论:提出的CNN-LSTM混合模型分类准确率更高,在智能听诊领域具有广泛的潜在应用价值。
Abstract:
Abstract: Objective To establish a hybrid deep learning lung sound classification model based on convolutional neural network (CNN)-long short-term memory (LSTM) for electronic auscultation. Methods Wavelet transform was used to extract features from the dataset, transforming lung sound signals into energy entropy, peak value and other features. On this basis, a classification model based on hybrid algorithm incorporating CNN and LSTM neural network was constructed. The features extracted by wavelet transform were input into CNN module to obtain the spatial features of the data, and then the temporal features were detected through LSTM module. The fusion of the two types of features enabled the classification of lung sounds through the model, thereby assisting in the diagnosis of pulmonary diseases. Results The accuracy rate and F1 score of CNN-LSTM hybrid model were significantly higher than those of other single models, reaching 0.948 and 0.950. Conclusion The proposed CNN-LSTM hybrid model demonstrates higher accuracy and more precise classification, showcasing broad potential application value in intelligent auscultation.

相似文献/References:

[1]韩庆阳,李丙玉,王晓东,等.一种同时消除脉搏波信号中呼吸基线漂移和高频噪声的方法[J].中国医学物理学杂志,2014,31(02):4801.[doi:10.3969/j.issn.1005-202X.2014.02.019]
[2]樊晓燕,陈兆学.基于小波变换的尿沉渣粘连细胞分割算法的研究与实现[J].中国医学物理学杂志,2013,30(01):3881.[doi:10.3969/j.issn.1005-202X.2013.01.011]
[3]杨杰,张胜,余顺,等.一种基于二次样条母小波函数的心电QRS复合波检测算法[J].中国医学物理学杂志,2013,30(02):4036.[doi:10.3969/j.issn.1005-202X.2013.02.018]
[4]朱柏辉,黄业开,王静,等.LMS自适应噪声抵消算法的DSP脉搏血氧监测研究[J].中国医学物理学杂志,2013,30(02):4041.[doi:10.3969/j.issn.1005-202X.2013.02.019]
[5]王红敏,聂生东,王远军,等.低场核磁共振信号降噪方法研究进展[J].中国医学物理学杂志,2013,30(04):4261.[doi:10.3969/j.issn.1005-202X.2013.04.012]
[6]褚晶辉,刘静媛,吕卫,等.一种基于小波变换的乳腺X线图肿块分割方法[J].中国医学物理学杂志,2013,30(06):4519.[doi:10.3969/j.issn.1005-202X.2013.06.013]
[7]王远军,姜博宇,靳珍怡,等.基于小波变换的医学图像融合方法综述[J].中国医学物理学杂志,2013,30(06):4530.[doi:10.3969/j.issn.1005-202X.2013.06.016]
[8]袁野,王夏天,张子辰,等.基于小波变换和改进的瞬态独立成分分析融合算法的心电信号降噪方法[J].中国医学物理学杂志,2016,33(4):415.[doi:10.3969/j.issn.1005-202X.2016.04.019]
 [J].Chinese Journal of Medical Physics,2016,33(3):415.[doi:10.3969/j.issn.1005-202X.2016.04.019]
[9]靳珍怡,王远军.基于非下采样轮廓波变换的多模态医学图像融合[J].中国医学物理学杂志,2016,33(5):445.[doi:10.3969/j.issn.1005-202X.2016.05.004]
 [J].Chinese Journal of Medical Physics,2016,33(3):445.[doi:10.3969/j.issn.1005-202X.2016.05.004]
[10]蒋曲博,甘永进,张翠娜.反射式血氧饱和度检测系统研制[J].中国医学物理学杂志,2017,34(1):58.[doi:10.3969/j.issn.1005-202X.2017.01.012]
 [J].Chinese Journal of Medical Physics,2017,34(3):58.[doi:10.3969/j.issn.1005-202X.2017.01.012]

备注/Memo

备注/Memo:
【收稿日期】2023-12-11 【基金项目】国家自然科学基金(61901515,62361038);甘肃省自然科学基金(22JR5RA002) 【作者简介】张乙鹏,硕士,研究方向:生物医学信号检测与处理,E-mail: zyp731964329@qq.com 【通信作者】陈扶明,高级工程师,博士,研究方向:生物医学信号检测与处理,E-mail: cfm5762@126.com
更新日期/Last Update: 2024-03-27