基于高斯拟合的第二心音分裂评价方法
Anovel Evaluation Method of S2 Split Based on Gaussian Fitting
DOI: 10.12677/MD.2023.132035, PDF,    科研立项经费支持
作者: 刘 超, 刘熠辉, 何 勇, 刘 智, 张宇欣, 何杵壕, 曾文华, 贺家俊：湖南理工学院信息科学与工程学院，湖南 岳阳
关键词: 第二心音；第二心音分裂系数；高斯拟合；重叠率；S2；S2split； GMM； Overlapping Rate
摘要: 鉴于利用第二心音主动脉瓣关闭(A2)和肺动脉瓣关闭(P2)的时间间隔检测心音分裂程度易受心跳影响而使检测精度低，本研究提出一种基于高斯拟合的第二心音分裂系数(S2split )用于检测第二心音分裂评估新方法。其主要贡献如下：① 基于高斯拟合的A2和P2统计量的评估方法；② 基于高斯成分重叠率(OLR)的第二心音分裂系数(S2split )定义。本研究通过对标准和临床数据库的2908个心音周期进行分析，在总体精度为1的前提下，得S2split统计和分裂对应关系为：μS2split＞0.4，且σS2split+μS2split＞0.45为异常分裂；0＜μS2split＜0.4，且σS2split+μS2split＜0.45为正常分裂；μS2split=0为单一无分裂第二心音。
Abstract: Due to the fact that the time interval (TA2→P2 ) between the sounds produced by aortic valve closure (A2) and pulmonary valve closure (P2) can be easily influenced by the heartbeat,it cannot accurately judge the second heart sound split (S2). This study proposes a novel evaluation methodology for de-tecting the wide splitting of S2 using the second heart sound splitting coefficient ( S2split ) based on Gaussian fitting.The main contributions are as follows: ① An evaluation method of A2 and P2 statis-tics based on Gaussian fitting; ② A definition of the second heart sound splitting coefficient ( S2split) based on the Gaussian components overlapping rate (OLR).This study analyzed 2908 heart sound cycles from standard and clinical databases. Based on the overall accuracy of 1, the S2split statistics and splitting corresponding relationship is that: if μS2split＞0.4 and σS2split+μS2split＞0.45, it is an abnormal split; if 0＜μS2split＜0.4 and σS2split+μS2split＜0.45, it is a normal split; if μS2split=0, it is a single S2 with no splitting.
文章引用：刘超, 刘熠辉, 何勇, 刘智, 张宇欣, 何杵壕, 曾文华, 贺家俊. 基于高斯拟合的第二心音分裂评价方法[J]. 医学诊断, 2023, 13(2): 205-217. https://doi.org/10.12677/MD.2023.132035

参考文献

[1] Boutana, D., Djeddi, M. and Benidir, M. (2007) Identification of Aortic Stenosis and Mitral Regurgitation by Heart Sound Segmenta-tion on Time-Frequency Domain. Proceedings of 2007 5th International Symposium on Image and Signal Processing and Analysis, Istanbul, 27-29 September 2007, 1-6. [Google Scholar] [CrossRef] 
[2] Coviello, J.S. (2015) Auscultation Skills: Breath & Heart Sounds. LWW, Philadelphia.
[3] Debbal, S.M. and Bereksi-Reguig, F. (2007) Automatic Measure of the Split in the Second Cardiac Sound by Using the Wavelet Transform Technique. Computers in Biology and Medicine, 37, 269-276. [Google Scholar] [CrossRef] [PubMed]
[4] Yildirim, I. and Ansari, R. (2007) A Robust Method to Estimate Time Split in Second Heart Sound Using Instantaneous Frequency Analysis. Proceedings of 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, 22-26 August 2007, 1855-1858. [Google Scholar] [CrossRef] 
[5] Benedetto, J.J., Mcclellan, J. and Cochran, D. (2005) Time-Frequency and Time­Scale Methods. Birkhäuser, Boston.
[6] Rhif, M., Ben Abbes, A., Farah, I.R., et al. (2019) Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A Review. Applied Sciences, 9, Article 1345. [Google Scholar] [CrossRef] 
[7] Tang, H., Park, Y. and Ruan, C. (2015) Nonlinear Time Domain Relation between Res-piratory Phase and Timing of the First Heart Sound. Computational and Mathematical Methods in Medicine, 2015, Article ID: 410102. [Google Scholar] [CrossRef] [PubMed]
[8] Barma, S., Chen, B.W., Ji, W., et al. (2015) Measurement of Duration, Energy of In-stantaneous Frequencies, and Splits of Subcomponents of the Second Heart Sound. IEEE Transactions on Instrumentation and Meas-urement, 64, 1958-1967. [Google Scholar] [CrossRef] 
[9] Reed, T.R., Reed, N.E. and Fritzson, P. (2004) Heart Sound Analysis for Symptom Detection and Computer-Aided Diagnosis. Simulation Modelling Practice and Theory, 12, 129-146. [Google Scholar] [CrossRef] 
[10] Cherif, L.H. and Debbal, S.M. (2018) The Impact of Valvular Pathologies on Heart Rate, the Second Heart Sound Split, and Systolic Pulmonary Arterial Pressure. Journal of Mechanics in Medicine and Biology, 18, Article ID: 1850008. [Google Scholar] [CrossRef] 
[11] Luisada, A.A. (1971) The Second Heart Sound in Normal and Abnormal Con-ditions. The American Journal of Cardiology, 28, 150-161. [Google Scholar] [CrossRef] [PubMed]
[12] Tang, H., Chen, H. and Li, T. (2017) Quantitative Measurement of Respiratory Split in the Second Heart Sound. Computing in Cardiology, 44, 1-4. [Google Scholar] [CrossRef] 
[13] Tang, H., Gao, J., Ruan, C., et al. (2013) Modeling of Heart Sound Morphol-ogy and Analysis of the Morphological Variations Induced by Respiration. Computers in Biology and Medicine, 43, 1637-1644. [Google Scholar] [CrossRef] [PubMed]
[14] Will, C., Shi, K., Schellenberger, S., et al. (2018) Radar-Based Heart Sound Detection. Scientific Reports, 8, Article No. 11551. [Google Scholar] [CrossRef] [PubMed]
[15] de Lima Hedayioglu, F. (2014) Looking at the Second Heart Sound: A Multi-Facet Study. Universidade do Porto, Porto. (In Portugal)
[16] Zheng, Y., Guo, X., Jiang, H. and Zhou, B. (2017) An Innovative Multi-Level Singular Value Decomposition and Compressed Sensing Based Frame-work for Noise Removal from Heart Sounds. Biomedical Signal Processing and Control, 38, 34-43. [Google Scholar] [CrossRef] 
[17] Sun, S., Wang, H., Cheng, C., et al. (2017) PCA-Based Heart Sound Feature Generation for a Ventricular Septal Defect Discrimination. Proceedings of 2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, 15-17 December 2017, 128-133. [Google Scholar] [CrossRef] 
[18] 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. [Google Scholar] [CrossRef] 
[19] Chen, Y., Luo, Y., Huang, W., et al. (2017) Machine-Learning-Based Classifi-cation of Real-Time Tissue Elastography for Hepatic Fibrosis in Patients with Chronic Hepatitis B. Computers in Biology and Medicine, 89, 18-23. [Google Scholar] [CrossRef] [PubMed]
[20] Hamidi, M., Ghassemian, H. and Imani, M. (2018) Classification of Heart Sound Signal Using Curve Fitting and Fractal Dimension. Biomedical Signal Processing and Control, 39, 351-359. [Google Scholar] [CrossRef] 
[21] Sun, S., Wang, H., Chang, Z., et al. (2018) On the Mahalanobis Distance Classi-fication Criterion for a Ventricular Septal Defect Diagnosis System. IEEE Sensors Journal, 19, 2665-2674. [Google Scholar] [CrossRef] 
[22] Sweldens, W.W. (1996) Wavelets: What Next? Proceedings of the IEEE, 84, 680-685. [Google Scholar] [CrossRef] 
[23] Sun, S. (2015) An Innovative Intelligent System Based on Automatic Diagnostic Feature Extraction for Diagnosing Heart Diseases. Knowledge-Based Systems, 75, 224-238. [Google Scholar] [CrossRef] 
[24] Varghees, V.N. and Ramachandran, K.I. (2014) A Novel Heart Sound Activity Detection Framework for Automated Heart Sound Analysis. Biomedical Signal Processing and Control, 13, 174-188. [Google Scholar] [CrossRef] 
[25] Sun, S., Wang, H., Jiang, Z., et al. (2014) Segmentation-Based Heart Sound Feature Extraction Combined with Classifier Models for a VSD Diagnosis System. Expert Systems with Applications, 41, 1769-1780. [Google Scholar] [CrossRef] 
[26] Pole, A., West, M. and Harrison, J. (2005) Time Series: Modeling, Computation and Inference (Chapman & Hall/CRC Texts in Statistical Science). Chapman and Hall/CRC, London.
[27] Leblanc-Hotte, A., Chabot-Roy, G., Odagiu, L., et al. (2018) High-Throughput Refractive Index-Based Microphotonic Sensor for Enhanced Cellular Dis-crimination. Sensors and Actuators B: Chemical, 266, 255-262. [Google Scholar] [CrossRef] 
[28] Prodigious (2018) Abnormally Wide Split Second Sound—Heart Sounds Collec-tion.
https://www.youtube.com/watch?v=D5SYn26JsFI
[29] Sun, H. and Wang, S. (2011) Measuring the Component Overlapping in the Gaussian Mixture Model. Data Mining and Knowledge Discovery, 23, 479-502. [Google Scholar] [CrossRef] 
[30] Yan, J., Zhang, Z., Wang, W., et al. (2019) A Hybrid Data and Model Transfer Framework for Distributed Machine Learning. Proceedings of 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP), Xi’an, 23-25 October 2019, 1-7. [Google Scholar] [CrossRef] 
[31] Sokolova, M., Japkowicz, N. and Szpakowicz, S. (2006) Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation. In: Sattar, A. and Kang, B., Eds., AI 2006: AI 2006: Advances in Artificial Intelligence, Lecture Notes in Computer Science, Vol. 4304, Springer, Berlin, 1015-1021. [Google Scholar] [CrossRef] 
[32] Cohen, J. (1960) A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement, 20, 37-46. [Google Scholar] [CrossRef] 
[33] Phung, V.H. and Rhee, E.J. (2019) A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets. Applied Sciences, 9, Article No. 4500. [Google Scholar] [CrossRef] 
[34] Luo, H., Westphal, P., Shahmohammadi, M., Heckman, L.I., Kuiper, M., Cornelussen, R.N., Delhaas, T. and Prinzen, F.W. (2021) Second Heart Sound Splitting as an Indicator of Interventricular Mechanical Dyssynchrony Using a Novel Splitting Detection Algorithm, Physiological Reports, 9, e14687. [Google Scholar] [CrossRef] [PubMed]
[35] Tang, H., Chen, H. and Li, T. (2017) Discrimination of Aortic and Pulmonary Components from the Second Heart Sound Using Respiratory Modulation and Measurement of Respiratory Split. Applied Sciences, 7, Article No. 690. [Google Scholar] [CrossRef] 
[36] Djebbari, A. and Bereksi-Reguig, F. (2013) Detection of the Valvular Split within the Second Heart Sound Using the Reassigned Smoothed Pseudo Wigner-Ville Distribution. Biomedical Engineering Online, 12, Article No. 37. [Google Scholar] [CrossRef]