Computer Science

Computer Science ›› 2024, Vol. 51 ›› Issue (6A): 230800091-7.doi: 10.11896/jsjkx.230800091

• Image Processing & Multimedia Technolog • Previous Articles     Next Articles

Classification Model of Heart Sounds in Pulmonary Hypertension Based on Time-Frequency Fusion Features

WANG Yanlin1, SUN Jing1, YANG Hongbo2, GUO Tao2, PAN Jiahua2, WANG Weilian1   

  1. 1 School of Information Science and Engineering,Yunnan University,Kunming 650500,China
    2 Kunming Medical University Affiliated Cardiovascular Hospital,Kunming 650102,China
  • Published:2024-06-06
  • About author:WANG Yanlin,born in 1998,postgra-duate.Her main research interests include signal processing and machine learning.
    WANG Weilian,born in 1947,bachelor,professor.His main research interests include signal processing and pattern recognition,biological signal proces-sing,digital-analog hybrid IC and ASIC design.
  • Supported by:
    National Natural Science Foundation of China(81960067)and Major Science and Technology Projects of Yunnan Province in 2018(2018ZF017).

PDF (PC)

282

Abstract: Pulmonary hypertension associated with congenital heart disease has a high mortality rate,and early screening and identification of it is particularly important for cure.At present,diagnosis is made by right heart catheterization,which is an invasive examination,it is not easy to use in screening,and has high risk and high cost.Therefore,it is urgent to study a non-invasive and convenient method for identification.In this paper,a time-frequency fusion heart sound classification model is established.First,the heart sound signal is preprocessed,then the signal is converted,and the dynamic time-frequency characteristics are obtained by using the fusion filter bank.Finally,the obtained fusion feature parameters are input into the TabPFN network for classification and recognition.Experimental results indicate that the algorithm has average accuracy,precision,sensitivity,specificity,and F1 scores of 92.21%,92.15%,92.15%,96.11%,and 92.14% respectively in normal,CHD-PAH,and CHD.It is important for the early screening and identification of pulmonary hypertension associated with congenital heart disease.

Key words: Heart sound, Congenital heart disease-associated pulmonary arterial hypertension, Dynamic feature extraction, Time-Frequency feature fusion, Tabular prior-data fitted network(TabPFN)

CLC Number: 

  • TN912
[1]KEARNEY K,KOTLYAR E,LAU E M T.Pulmonary vascular disease as a systemic and multisystem disease[J].Clinics in Chest Medicine,2021,42(1):167-177.
[2]NAEJIE R,RICHTER M J,RUBIN L J.The physiological basis of pulmonary arterial hypertension[J].European Respiratory Journal,2022,59(6):2334-2354.
[3]GALIE N,HUMBERT M,VACHIERY J L,et al.2015 ESC/ERS guidelines for the diagnosis and treatment of pulmonary hypertension:the joint task force for the diagnosis and treatment of pulmonary hypertension of the European Society of Cardiology(ESC) and the European Respiratory Society(ERS):endorsed by:Association for European Paediatric and Congenital Cardio-logy(AEPC),International Society for Heart and Lung Transplantation(ISHLT)[J].European Heart Journal,2016,37(1):67-119.
[4]YAGHI S,NOVIKOV A,TRANDAFIRESCU T.Clinical up-date on pulmonary hypertension[J].Journal of Investigative Medicine,2020,68(4):821-827.
[5]MARON B A,KOVACS G,VAIDYA A,et al.Cardiopulmonary hemodynamics in pulmonary hypertension and heart failure:JACC review topic of the week[J].Journal of the American College of Cardiology,2020,76(22):2671-2681.
[6]THOMAS C A,ANDERSON R J,CONDON D F,et al.Diagno-sis and management of pulmonary hypertension in the modern era:insights from the 6th world symposium[J].Pulmonary Therapy,2020,6(1):9-22.
[7]SOMMER N,GHOFRANI H A,PAK O,et al.Current and future treatments of pulmonary arterial hypertension[J].British Journal of Pharmacology,2021,178(1):6-30.
[8]PASCALL E,TULLOH R M R.Pulmonary hypertension incongenital heart disease[J].Future Cardiology,2018,14(4):343-353.
[9]SIMONNEAU G,MONTANI D,CELERMAJER D S,et al.Haemodynamic definitions and updated clinical classification of pulmonary hypertension[J].European Respiratory Journal,2019,53(1):1913-1926.
[10]SHUVO S B,ALAM SS,AYMAN S U,et al.NRC-Net:Automated noise robust cardio net for detecting valvular cardiac diseases using optimum transformation method with heart sound signals[J].Biomedical Signal Processing and Control,2023,86(1):105272.
[11]TANG H,RONG Y,CHAI L,et al.Deep Learning Radar forHigh-Fidelity Heart Sound Recovery in Real-World Scenarios[J].IEEE Sensors Journal,2023,23:17803-17814.
[12]WANG W B,QIN D M,WANG S B,et al.A multi-channelUNet framework based on SNMF-DCNN for robust heart-lung-sound separation[J].Computers in Biology and Medicine,2023,164:10.
[13]ELOLA A,ARAMENDI E,OLIVEIRA J,et al.Beyond Heart Murmur Detection:Automatic Murmur Grading From Phonocardiogram[J].IEEE Journal of Biomedical and Health Informatics,2023,27:3856-3866.
[14]GE B B,YANG H B,MA P Y,et al.Detection of pulmonary hypertension associated with congenital heart disease based on time-frequency domain and deep learning features[J].Biome-dical Signal Processing and Control,2023,81:11.
[15]WANG X Z,YANG H B,ZONG R,et al.Heart sound classification based on sub-band envelope and convolution neural network[J].Journal of Biomedical Engineering,2021,38(5):969-978.
[16]NIZAM N B,NUHASH S I S K,HASAN T.Hilbert-envelopefeatures for cardiac disease classification from noisy phonocardiograms[J].Biomedical Signal Processing and Control,2022,78(1):253-262.
[17]KAMSON A P,SHARMA L N,DANDAPAT S.Multi-centroid diastolic duration distribution based HSMM for heart sound segmentation[J].Biomedical Signal Processing and Control,2019,48(1):265-272.
[18]YILDIRIM M.Automatic classification and diagnosis of heartvalve diseases using heart sounds with MFCC and proposed deep model[J/OL].Concurrency and Computation:Practice and Experience(2022-07-25).https://onlinelibrary.wiley.com/doi/10.1002/cpe.7232.
[19]CHEN P,ZHANG Q.Classification of heart sounds using discrete time-frequency energy feature based on S transform and the wavelet threshold denoising[J].Biomedical Signal Proces-sing and Control,2020,57(1):348-358.
[20]DAR J A,SRIVASTAVA K K.,LONE S A.Spectral features and optimal Hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals[J].Biomedical Signal Processing and Control,2022,78(1):355-372.
[21]KUI H,PAN J,ZONG R,et al.Heart sound classification based on log Mel-frequency spectral coefficients features and convolutional neural networks[J].Biomedical Signal Processing and Control,2021,69(1):175-190.
[22]GUPTA C N,PALANIAPPAN R,SWAMINATHAN S,et al.Neural network classification of homomorphic segmented heart sounds[J].Applied Soft Computing,2007,7(1):286-297.
[23]TANG H,JIANG Y,LI T,et al.Identification of pulmonary hypertension using entropy measure analysis of heart sound signal[J].Entropy,2018,20(5):389-405.
[24]LI W H,WANG W B,GONG W G.Acoustic feature extraction of anomalous sounds in public spaces under low signal-to-noise ratio[J].Acta Acustica,2019,44(5):934-944.
[25]GHAFFAR M S B A,KHAN U S,IQBAL J,et al.Improving classification performance of four class FNIRS-BCI using Mel Frequency Cepstral Coefficients(MFCC)[J].Infrared Physics & Technology,2021,112(1):425-436.
[26]HOLLMANN N,MULLER S,EGGENSPERGER K,et al.TabPFN:A transformer that solves small tabular classification problems in a second[J/OL](2022-11-29).https://arxiv.org/abs/2207.01848.
[1] ZHANG Xin, SUN Jing, YANG Hong-bo, PAN Jia-hua, GUO Tao, WANG Wei-lian. Heart Sound Segmentation Algorithm Based on TK Energy Operator and Envelope Fusion [J]. Computer Science, 2022, 49(11A): 210900135-6.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.