Phonocardiogram Segmentation and Abnormal Phonocardiogram Screening Algorithm Based on Cardiac Cycle Estimation
ZHAO Zhan①② ZHANG Xuru①② FANG Zhen①② CHEN Xianxiang① DU Lidong① LI Tianchang③
①(Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China) ②(University of Chinese Academy of Sciences, Beijing 100049, China) ③(Navy General Hospital, Beijing 100048, China)
Abstract：Heart disease is of highest morbidity and mortality. The cardiac structure and mechanical characteristics can be reflected by auscultation. Compared with echocardiography and nuclear magnetic resonance, auscultation gets the advantages of fast, low cost and easy to use. The composition of phonocardiogram is complex, and the auscultation is easy to be affected by the subjectivity of the doctor, various noise and disturbances, which limits the application of auscultation. The algorithm of phonocardiogram segmentation and abnormal phonocardiogram screening is presented. For the reason that the heart cycle is estimated in advance, 80% cardiac cycle can be recognition correctly when random disturbances exist. The diagnostic indexes of time and frequency domain with high discrimination are also presented, and the abnormal heart sounds are recognized by Support Vector Machine (SVM) with the accuracy about 92%. The algorithm can be used for assisting doctors or portable phonocardiogram monitoring device.
RANDHAWA S K and SINGH M. Classification of heart sound signals using multi-modal features[J]. Procedia Computer Science, 2015, 58: 165-171. doi: 10.1016/j.procs. 2015.08.045.
[2]
KIM S and HWANG D. Murmur-adaptive compression technique for phonocardiogram signals[J]. Electronics Letters, 2016, 52(3): 183-184. doi: 10.1049/el.2015.3449.
[3]
Bank I, VLIEGEN H W, and BRUSCHKE A V. The 200th anniversary of the stethoscope: Can this low-tech device survive in the high-tech 21st century[J]. European Heart Journal, 2016, 37(47): 3536-3543. doi: 10.1093/eurheartj /ehw034.
ZHAO Caihua, LIU Ju, SUN Jiande, et al. Blind separation of noisy speech mixtures based on wavelet transform and independent component analysis[J]. Journal of Electronics & Information Technology, 2006, 28(9): 1565-1568.
[5]
SAFARA F. Cumulant-based trapezoidal basis selection for heart sound classification[J]. Medical & Biological Engineering & Computing, 2015, 53(11): 1153-1164. doi: 10. 1007/s11517-015-1394-4.
[6]
JATUPAIBOON N, PAN-NGUM S, and ISRASENA P. Electronic stethoscope prototype with adaptive noise cancellation[C]. 8th International Conference on ICT and Knowledge Engineering, Bangkok, Thailand, 2010: 32-36.
[7]
CHENG Xiefeng and LI Wei. Research on heart-sound graphical processing methods based on heart-sounds window function[J]. Acta Physica Sinica, 2015, 64(5): 58703. doi: 10.7498/aps.64.058703.
[8]
VARGHEES V N and RAMACHANDRAN K I. A novel heart sound activity detection framework for automated heart sound analysis[J]. Biomedical Signal Processing & Control, 2014, 13(1): 174-188. doi: 10.1016/j.bspc.2014.05. 002.
[9]
CHAKRABARTI T, SAHA S, ROY S, et al. Phonocardiogram signal analysis-practices, trends and challenges: A critical review[C]. International Conference and Workshop on Computing and Communication, Vancouver, Canada, 2015: 1-4.
[10]
SHARMA L N. Multiscale analysis of heart sound for segmentation using multiscale hilbert envelope[C]. International Conference on ICT and Knowledge Engineering, Bangkok, Thailand, 2015: 33-37.
[11]
SPRINGER D, TARASSENKO L, and CLIFFORD G. Logistic regression-HSMM-based heart sound segmentation [J]. IEEE Transactions on Biomedical Engineering, 2016, 63(4): 822-832. doi: 10.1109/TBME.2015.2475278.
[12]
HOYOS C C, MURILLO-RENDON S, and CASTELLANOS- DOMINGUEZ C G. Heart Sound Segmentation in Noisy Environments[M]. Berlin: Springer, 2013: 254-263.
[13]
PAPADANIIL C D and HADJILEONTIADIS L J. Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features[J]. IEEE Journal of Biomedical & Health Informatics, 2014, 18(4): 1138-1152. doi: 10.1109/JBHI.2013.2294399.
[14]
MOHAMAD M M, SH-HUSSAIN H, TING C M, et al. Heart sound monitoring system[J]. Journal of Engineering & Applied Sciences, 2016, 11(7): 4748-4755.
[15]
BRUSCO M and NAZERAN H. Development of an intelligent PDA-based wearable digital phonocardiograph[C]. Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, 2005: 3506-3509.
[16]
CLIFFORD G D, LIU C, MOODY B, et al. Classification of normal/abnormal heart sound recordings: the physioNet/ computing in cardiology challenge 2016[C]. Computing in Cardiology, Vancouver, Canada, 2016: 609-612.
[17]
MOHAMMAD A, ABTAHI M, CONSTANT N, et al. Mobile phonocardiogram diagnosis in newborns using support vector machine[J]. Healthcare, 2017, 5(1): 16-26. doi: 10.3390/ healthcare5010016.
[18]
ZHANG W, HAN J, and DENG S. Heart sound classification based on scaled spectrogram and partial least squares regression[J]. Biomedical Signal Processing & Control, 2017, 32(2): 20-28. doi: 10.1016/j.bspc.2016.10.004.
[19]
KAO W C and WEI C C. Automatic phonocardiograph signal analysis for detecting heart valve disorders[J]. Expert Systems with Applications, 2011, 38(6): 6458-6468. doi: 10.1016/j.eswa.2010.11.100.
PU Xiujuan, ZENG Xiaoping, HAN Liang, et al. Extraction of fetal electrocardiogram signal using least squares support vector machines[J]. Journal of Electronics & Information Technology, 2009, 31(12): 2941-2947.
[22]
BENTLEY P, NORDEHN G, COIMBRA M, et al. Classifying heart sounds challenge[OL]. http://www. peterjbentley.com/heartchallenge/index.html. 2016.6.
[23]
KRISTOMO D, HIDAYAT R, SOESANTI I, et al. Heart sound feature extraction and classification using autoregressive power spectral density (AR-PSD) and statistics features[C]. Advances of Science and Technology for Society: Proceedings of the International Conference on Science and Technology, Yogyakarta, Indonesia, 2016: (090007-1-090007-7).
