摘要
面向心脏疾病计算机辅助诊断,本文提出一种基于一维卷积神经网络和循环神经网络混合深度学习结构的心音分析方法.本结构首先利用卷积神经网络学习心脏病症在心音信号上的表征,然后通过循环神经网络处理心音信号中的时序信息进行分类,在提升心音分类正确率的同时,大幅度降低了网络参数.为验证本深度学习结构所学特征的有效性,除已有的成人心音数据集外,本文还专门构建了一个面向婴幼儿先天性心脏病的心音数据集,并通过端到端的类别响应图证明了本方法在室缺诊断时学习到的心音信号特征符合临床医师的心音听诊经验.实验结果表明,本文方法能在3153例成人心音数据分类上达到92.56%的正确率,在528例婴幼儿心音数据分类上达到97.48%正确率,模型参数仅有0.05 M.
For the computer-aided heart disease diagnosis,this paper proposes a method of heart sound analysis based on the mixed structure of one-dimensional convolutional neural network and recurrent neural network.The proposed structure uses the convolutional neural network to learn the representation of heart disease on the heart sound signal,and then processes the time sequence information in the heart sound signal through the recurrent neural network for classifica⁃tion,which greatly reduces the network parameters while improving the accuracy of heart sound classification.The experi⁃mental results show that the proposed method can achieve the accuracy of 92.56%on the classification of 3153 cases of nor⁃mal and abnormal heart sounds for adults,and 97.48%on the classification of 528 cases of normal and abnormal heart sounds for infants and children.The parameter of the proposed method is 0.05M,which is suitable for portable application situations.
作者
肖斌
陈嘉博
毕秀丽
张俊辉
李伟生
王国胤
马旭
XIAO Bin;CHEN Jia-bo;BI Xiu-li;ZHANG Jun-hui;LI Wei-sheng;WANG Guo-yin;MA Xu(Chongqing Key Laboratory of Image Cognition,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;The First Affiliated Hospital of Chongqing Medical University,Chongqing 400042,China;Institute of Science and Technology,National Health Commission,Beijing 100081,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2022年第10期2425-2432,共8页
Acta Electronica Sinica
基金
国家自然科学基金(No.61806032,No.61976031)
国家重点研发计划(No.2016YFC1000307-3)
重庆市基础与前沿项目(No.cstc2018jcy⁃jAX0117)
重庆市教委科学技术研究计划重点项目(No.KJZD-K201800601)。
关键词
心音听诊
一维卷积神经网络
循环神经网络
类别响应图
heart sound analysis
one-dimensional convolutional neural network
recurrent neural network
class ac⁃tivation map
