Detection of systolic ejection click using time growing neural network

被引:23
作者
Gharehbaghi, Arash [1 ]
Dutoit, Thierry [2 ]
Ask, Per [1 ]
Sornmo, Leif [3 ]
机构
[1] Linkoping Univ, Dept Biomed Engn, Physiol Measurements IMT, Linkoping, Sweden
[2] Univ Mons, Fac Polytech, B-7000 Mons, Belgium
[3] Lund Univ, Ctr Integrat Electrocardiol, Dept Elect & Informat Technol, Lund, Sweden
基金
瑞典研究理事会;
关键词
Systolic ejection click; Time growing neural network; Time delay neural network; Heart sound; 1ST HEART-SOUND; MURMURS; CLASSIFICATION; AUSCULTATION; CHILDREN;
D O I
10.1016/j.medengphy.2014.02.011
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In this paper, we present a novel neural network for classification of short-duration heart sounds: the time growing neural network (TGNN). The input to the network is the spectral power in adjacent frequency bands as computed in time windows of growing length. Children with heart systolic ejection click (SEC) and normal children are the two groups subjected to analysis. The performance of the TGNN is compared to that of a time delay neural network (TDNN) and a multi-layer perceptron (MLP), using training and test datasets of similar sizes with a total of 614 normal and abnormal cardiac cycles. From the test dataset, the classification rate/sensitivity is found to be 97.0%/98.1% for the TGNN, 85.1%/76.4% for the TDNN, and 92.7%/85.7% for the MLP. The results show that the TGNN performs better than do TDNN and MLP when frequency band power is used as classifier input. The performance of TGNN is also found to exhibit better immunity to noise. (C) 2014 IPEM. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页码:477 / 483
页数:7
相关论文
共 24 条
  • [1] Assessing aortic stenosis using sample entropy of the phonocardiographic signal in dogs
    Ahlstrom, C.
    Hoglund, K.
    Hult, P.
    Haggstrom, J.
    Kvart, C.
    Ask, P.
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2008, 55 (08) : 2107 - 2109
  • [2] NONINVASIVE DIAGNOSIS OF CORONARY-ARTERY DISEASE USING A NEURAL NETWORK ALGORITHM
    AKAY, M
    [J]. BIOLOGICAL CYBERNETICS, 1992, 67 (04) : 361 - 367
  • [3] [Anonymous], 1993, An introduction to the bootstrap
  • [4] [Anonymous], 1995, INTRO NEURAL NETWORK, DOI DOI 10.7551/MITPRESS/3905.001.0001
  • [5] Innocent murmurs
    Biancaniello, T
    [J]. CIRCULATION, 2005, 111 (03) : E20 - E22
  • [6] Automated pediatric cardiac auscultation
    de Vos, Jacques P.
    Blanckenberg, Mike M.
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (02) : 244 - 252
  • [7] DeGroff CG, 2001, CIRCULATION, V103, P2711
  • [8] Heart sound classification using wavelet transform and incremental self-organizing map
    Dokur, Zuemray
    Olmer, Tamer
    [J]. DIGITAL SIGNAL PROCESSING, 2008, 18 (06) : 951 - 959
  • [9] Heart sound cancellation based on multiscale products and linear prediction
    Flores-Tapia, Daniel
    Moussavi, Zahra A. K.
    Thomas, Gabriel
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (02) : 234 - 243
  • [10] Neural network classification of homomorphic segmented heart sounds
    Gupta, Cota Navin
    Palaniappan, Ramaswamy
    Swaminathan, Sundaram
    Krishnan, Shankar M.
    [J]. APPLIED SOFT COMPUTING, 2007, 7 (01) : 286 - 297