基于多特征融合网络的心音分割方法研究  

A heart sound segmentation method based on multi-feature fusion network

作　　者：田翩 何培宇[1] 蔡杰[2] 赵启军 李莉[4] 钱永军[2] 潘帆[1] TIAN Pian;HE Peiyu;CAI Jie;ZHAO Qijun;LI Li;QIAN Yongjun;PAN Fan(School of Electronic Information,Sichuan University,Chengdu,610065,P.R.China;Department of Cardiovascular Surgery,West China Hospital,Sichuan University,Chengdu,610041,P.R.China;School of Computer Science,Sichuan University,Chengdu,610065,P.R.China;Department of Pediatric Cardiology,West China Second University Hospital,Sichuan University,Chengdu,610041,P.R.China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]四川大学华西医院心脏大血管外科,成都610041 [3]四川大学计算机学院(软件学院),成都610065 [4]四川大学华西第二医院儿童心血管科,成都610041

出　　处：《中国胸心血管外科临床杂志》2024年第5期672-681,共10页Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

基　　金：国家自然科学基金(62066042);四川省重点研发计划(2022YFG0045);中央高校基本科研业务费(2022SCU12008)。

摘　　要：目的 提出一种基于多特征融合网络的心音分割方法。方法 研究资料来源于2016 CinC/PhysioNet数据集(来自764例患者的3 153段记录,男性约占91.93%,平均年龄30.36岁)。首先从时域与时频域中分别对心音进行特征提取,再通过特征降维的方法减少输入的冗余特征;然后经过特征选择分别找到两个特征空间中性能最佳的特征;利用多尺度空洞卷积、协同融合和通道注意力机制实现多特征融合;最后,将得到的融合特征送入双向门控循环网络(BiGRU)实现心音分割。结果 本方法在测试集上得到的心音分割精确率、召回率与F1值分别能达到96.70%、96.99%与96.84%。结论 本文提出的多特征融合网络具有较好的心音分割性能,能够为设计以心音为基础的心脏疾病自动分析提供高准确率的心音分割技术支持。Objective To propose a heart sound segmentation method based on multi-feature fusion network.Methods Data were obtained from the CinC/PhysioNet 2016 Challenge dataset(a total of 3153 recordings from 764 patients,about 91.93%of whom were male,with an average age of 30.36 years).Firstly the features were extracted in time domain and time-frequency domain respectively,and reduced redundant features by feature dimensionality reduction.Then,we selected optimal features separately from the two feature spaces that performed best through feature selection.Next,the multi-feature fusion was completed through multi-scale dilated convolution,cooperative fusion,and channel attention mechanism.Finally,the fused features were fed into a bidirectional gated recurrent unit(BiGRU)network to heart sound segmentation results.Results The proposed method achieved precision,recall and F1 score of 96.70%,96.99%,and 96.84%respectively.Conclusion The multi-feature fusion network proposed in this study has better heart sound segmentation performance,which can provide high-accuracy heart sound segmentation technology support for the design of automatic analysis of heart diseases based on heart sounds.

关 键 词：心音分割 BiGRU网络 主成分分析 特征选择 多特征融合 

分 类 号：TN912.3[电子电信—通信与信息系统] R318[电子电信—信息与通信工程]