基于分割的自适应特征提取诊断心音方法
Segmentation-Based Adaptive Feature Extraction Methodology for Discriminating Heart Sounds

DOI: 10.12677/CSA.2021.118210, PP. 2051-2063

Keywords: 心音，心音分割，(CS₁)，(CS₂ )，短时修正希尔伯特变换，主成分分析法
Heart Sound, Heart Sound Segmentation, (CS₁)，(CS₂ ), STMHT, Principal Component Analysis

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对心音特征具有随其可分割性而改变的性质，提出一种基于心音分割的自适应特征提取算法，进而创建一种创新型的心脏病诊断系统。其创新点主要体现在：基于短时修正希尔伯特变换的第一复杂心音(CS₁)，第二复杂心音(CS₂)或完整心音(CS)的自适应分割提取；基于分割心音的自适应频率特征FF1或FF2提取；基于主成分分析的多尺度特征[γ₁₁、γ₁₂]和[γ₂₁、γ₂₂、γ₂₃]降维处理。实现此研究目标的2个阶段概括为：① 自动统计分析两个连续峰值之间的时间间隔，以此来确定心音的可分割特性；② 基于心音分割的自适应特征提取以及降维处理。通过在线数据库和临床数据库中提取的心音特征的散点图对系统性能进行初步评估验证。
An adaptive feature extraction algorithm based on heart sound segmentation is proposed to create an innovative heart disease diagnosis system, which based on the nature of heart sound features that change with their segment. The innovations of this methodology are primarily reflected in the automatic segmentation and extraction of the first complex heart sound (CS₁), the second complex heart sound (CS₂) or each cardiac sound (CS) based on the short-time modified Hilbert transform; adaptive frequency feature FF1 or FF2 extraction based on the segmented heart sounds; and dimensionality reduction of the multiscale features [γ₁₁、γ₁₂] and [γ₂₁、γ₂₂、γ₂₃] based on principal component analysis. The two phases of this study are summarized as: ① automatic statistical analysis of the time interval between two consecutive peaks to determine the segmental characteristics of the heart sounds; ② adaptive feature extraction and dimensionality reduction based on heart sound segmentation. A preliminary evaluation of the performance of the system is validated by scatter plots of heart sound features extracted from the online and clinical databases.

References

[1]	WHO (2020) Cardiovascular Diseases. https://www.who.int/health-topics/cardiovascular-diseases/#tab=tab_1
[2]	Malik, A.S., Boyko, O., Atkar, N. and Young, W.F. (2001) A Comparative Study of MR Imaging Profile of Titanium Pedicle Screws. Acta Radiologica, 42, 291-293. https://doi.org/10.1080%2F028418501127346846
[3]	Vos, T., Barber, R.M., Bell, B., et al. (2015) Global, Regional, and National Incidence, Prevalence, and Years Lived with Disability for 301 Acute and Chronic Dis-eases and Injuries in 188 Countries, 1990-2013: A Systematic Analysis for the Global Burden of Disease Study 2013. The Lancet, 386, 743-800. https://doi.org/10.1016/S0140-6736(15)60692-4
[4]	Sun, S., Wang, H., Chang, Z., Mao, B. and Liu, Y. (2019) On the Mahalanobis Distance Classification Criterion for a Ventricular Septal Defect Diagnosis System. IEEE Sensors Journal, 19, 2665-2674. https://doi.org/10.1109/JSEN.2018.2882582
[5]	谭朝文, 王威廉, 宗容, 潘家华, 杨宏波. 基于卷积神经网络的先心病心音信号分类算法[J]. 生物医学工程学杂志, 2019, 36(5): 728-736, 744. https://doi.org/10.7507/1001-5515.201806031
[6]	Notario, P.M., Gentile, E., Amidon, M., Angst, D., Lefaiver, C. and Webster, K. (2019) Home-Based Telemedicine for Children with Medical Complexity. Telemedicine and e-Health, 25, 1123-1132. https://doi.org/10.1089/tmj.2018.0186
[7]	Coviello, J.S. (2013) Auscultation Skills: Breath & Heart Sounds. 5th Edition, Lippincott Williams & Wilkins, Philadelphia.
[8]	Liu, Q., Wu, X. and Ma, X. (2018) An Automatic Segmentation Method for Heart Sounds. BioMedical Engineering OnLine, 17, Article No. 106. https://doi.org/10.1186/s12938-018-0538-9
[9]	Messner, E., Z？hrer, M. and Pernkopf, F. (2018) Heart Sound Segmentation—Anevent Detection Approach Using Deep Recurrent Neural Networks. IEEE Transactions on Biomedi-cal Engineering, 65, 1964-1974. https://doi.org/10.1109/TBME.2018.2843258
[10]	Sun, S.P. (2015) An Innovative Intelligent System Based on Automatic Diagnostic Feature Extraction for Diagnosing Heart Diseases. Knowledge-Based Systems, 75, 224-238. https://doi.org/10.1016/j.knosys.2014.12.001
[11]	Sun, S. and Wang, H. (2018) Principal Component Analy-sis-Based Features Generation Combined with Ellipse Models-Based Classification Criterion for a Ventricular Septal Defect Diagnosis System. Australasian Physical & Engineering Sciences in Medicine, 41, 821-836. http://link.springer.com/10.1007/s13246-018-0676-1 https://doi.org/10.1007/s13246-018-0676-1
[12]	Sun, S., Wang, H., Jiang, Z., Fang, Y. and Tao, T. (2014) Seg-mentation-Based Heart Sound Feature Extraction Combined with Classifier Models for a VSD Diagnosis System. Expert Systems with Applications, 41, 1769-1780. http://www.sciencedirect.com/science/article/pii/S0957417413006970 https://doi.org/10.1016/j.eswa.2013.08.076
[13]	Choi, S. and Jiang, Z. (2010) Cardiac Sound Murmurs Classifica-tion with Autoregressive Spectral Analysis and Multi-Support Vector Machine Technique. Computers in Biology and Medicine, 40, 8-20. http://www.sciencedirect.com/science/article/pii/S0010482509001796 https://doi.org/10.1016/j.compbiomed.2009.10.003
[14]	Ali, M.N., El Dahshan, E.-S.A. and Yahia, A.H. (2017) Denoising of Heart Sound Signals Using Discrete Wavelet Transform. Circuits, Systems, and Signal Processing, 36, 4482-4497. https://doi.org/10.1007/s00034-017-0524-7
[15]	Continuing Medical Implementation (2019) Heart Sounds Databases-Continuing Medical Implementation. http://www.cvtoolbox.com/index.html
[16]	MacWalter, D. and MacWalter, G. (2019) Human Heart Sounds and Mur-murs. https://libguides.dundee.ac.uk/medicine/databases
[17]	Máttar, J.A., Shoemaker, W.C., Diament, D., Lomar, A., Lopes, A.C., De Freitas, E., Stella, F.P. and Factore, L.A. (1991) Systolic and Diastolic Time Intervals in the Critically Ill Patient. Critical Care Medicine, 19, 1382-1386. http://www.ncbi.nlm.nih.gov/pubmed/1935158 https://doi.org/10.1097/00003246-199111000-00014
[18]	Yeo, T.C., Dujardin, K.S., Tei, C., Mahoney, D.W., McGoon, M.D. and Seward, J.B. (1998) Value of a Doppler-Derived Index Combining Systolic and Diastolic Time In-tervals in Predicting Outcome in Primary Pulmonary Hypertension. The American Journal of Cardiology, 81, 1157-1161. https://doi.org/10.1016/S0002-9149(98)00140-4 http://www.sciencedirect.com/science/article/pii/S0002914998001404
[19]	Cui, W., Roberson, D.A., Chen, Z., Madro-nero, L.F. and Cuneo, B.F. (2008) Systolic and Diastolic Time Intervals Measured from Doppler Tissue Imaging: Nor-mal Values and Z-Score Tables, and Effects of Age, Heart Rate, and Body Surface Area. Journal of the American Society of Echocardiography, 21, 361-370. http://www.sciencedirect.com/science/article/pii/S0894731707004403
[20]	Medical Sound Library (2019) Auscultate: Learn Heart Sounds, Murmurs and Medical Auscultation. https://www.medzcool.com/auscultate
[21]	Sun, S. (2020) A Novel Method-Based Secondary Envelope Extraction for Heart Sound Analysis.
[22]	Solanki, D.S. (2020) Aortic Regurgitation. Rated Medicine. https://ratedmedicine.wordpress.com/aortic-regurgitation/
[23]	AMBOSS (2020) AMBOSS: Medical Knowledge Distilled YouTube. https://www.youtube.com/channel/UC8xEQrU6VhJU6pDZd-GkJWg
[24]	Auscultation Sound (2019) Heart Murmur-Mitral Regurgitation Auscultation Sound!!! Complete. https://www.medzcool.com/auscultate
[25]	Patkar, R. (2020) Heart Sounds: Atrial Septal Defect. https://www.youtube.com/watch?v=bArVgcBgp4M
[26]	Thinklabs (2019) Thinklabs Heart Sound Library. https://www.thinklabs.com/heart-sounds?hclocation=ufi
[27]	Last Second Medicine (2017). https://www.youtube.com/channel/UCPnja4taYSqY8Ydk1W4fN8w
[28]	Easy Auscultation (2021) Easy Auscul-tation Training—Heart and Lung Sounds. https://www.easyauscultation.com/
[29]	3M Database (2019) 50 Heart and Lung Sounds Library. http://solutions.3m.com/wps/portal/3M/enEU/3M-Littmann-EMEA/stethoscope/littmann-learning-institute/heart-lung-sounds/heart-lung-sound-library/
[30]	AMBOSSMed (2019) AMBOSS: Medical Knowledge Distilled. https://www.medzcool.com/auscultate
[31]	Heart Sound & Murmur Library (2019). http://www.med.umich.edu/lrc/psb/heartsounds/index.htm
[32]	Mohseni, S.S. and Mohamadyari, M. (2016) Heart Ar-rhythmias Classification via a Sequential Classifier Using Neural Network, Principal Component Analysis and Heart Rate Variation. 2016 IEEE 8th International Conference on Intelligent Systems, Sofia, 4-6 September 2016, 715-722. https://doi.org/10.1109/IS.2016.7737390
[33]	Kavitha, R. and Kannan, E. (2016) An Efficient Framework for Heart Disease Classification Using Feature Extraction and Feature Selection Technique in Data Mining. Proceedings of the 1st International Conference on Emerging Trends in Engineering, Technology and Science, Pudukkottai, 24-26 Feb-ruary 2016, 1-5. https://doi.org/10.1109/ICETETS.2016.7603000
[34]	Guo, H.-W., Huang, Y.-S., Lin, C.-H., Chien, J.-C., Haraikawa, K. and Shieh, J.-S. (2016) Heart Rate Variability Signal Features for Emotion Recognition by Using Principal Component Analysis and Support Vectors Machine. 2016 IEEE 16th International Conference on Bioinformatics and Bioengineering, Taichung, 31 October-2 November 2016, 274-277. https://doi.org/10.1109/BIBE.2016.40
[35]	Motin, M.A., Karmakar, C.K. and Palaniswami, M. (2018) Prin-cipal Component Analysis: A Novel Approach for Extracting Respiratory Rate and Heart Rate from Photoplethysmo-graphic Signal. IEEE Journal of Biomedical and Health Informatics, 22, 766-774. https://doi.org/10.1109/JBHI.2017.2679108
[36]	El-Saadawy, H., Tantawi, M., Shedeed, H.A. and Tolba, M.F. (2017) Electrocardiogram (ECG) Heart Disease Diagnosis Using PNN, SVM and Softmax Regression Classifiers. 2017 8th International Conference on Intelligent Computing and Information Systems, Cairo, 5-7 December 2017, 106-110. https://doi.org/10.1109/INTELCIS.2017.8260040
[37]	Johnson, R.A. and Wichern, D.W. (2007) Applied Multi-variate Statistical Analysis. 6th Edition, Pearson, London. http://docshare04.docshare.tips/files/12598/125983744.pdf

Full-Text