STMHT-based heart sound segmentation(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2020年第12期
- Page:
- 1553-1559
- Research Field:
- 医学信号处理与医学仪器
- Publishing date:
Info
- Title:
- STMHT-based heart sound segmentation
- Author(s):
- SUN Shuping; WU Yue; HUANG Tingting; ZHANG Biqiang; DU Xiaoyu; HE Peiguang; YANG Wenbo
- Nanyang Institute of Technology, Nanyang 473000, China
- Keywords:
- heart sound wavelet decomposition envelope extraction short time modified Hilbert transform algorithm
- PACS:
- R318
- DOI:
- DOI:10.3969/j.issn.1005-202X.2020.12.016
- Abstract:
- When using heart sound analysis to diagnose heart diseases, the locations and extractions of the first heart sound (S1) and the second heart sound (S2) are primary task. Herein a heart sound segmentation method based on short-time modified Hilbert transform (STMHT) is proposed for separately extracting S1 and S2. The study is arranged as the following 3 stages. Wavelet decomposition is firstly employed to preprocess heart sound signals and remain the efficient component of heart sound signals (21.5-689.0 Hz), and then the envelope for heart sound signals is extracted using Viola integral waveform. Finally, S1 and S2 are automatically located and extracted by STMHT algorithm. The performance is evaluated by 30 cases of heart sound signals, and the results show that the accuracy of the S1 and S2 extraction is up to 97.37％, which is higher than that obtained by other methods.
Last Update: 2020-12-30