Cardiac valves disorder classification based on active valves appearance periodic sequences tree of murmurs. (March 2020)

• Record Type: Journal Article
• Authors: Saeidi, Azra; Almasganj, Farshad
• Is Part Of: Biomedical signal processing and control. Volume 57(2020)
• Publication Date: 2020-03
• Subjects: Heart sound classification -- Source localization -- Power spectra density -- Heart murmur; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.101775
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A proper automatic heart murmur detection has been developed. Heart sound murmurs; aortic, mitral, Tricuspid, and pulmonary stenosis and regurgitation, and combinations of them. The spatial information of active heart valves were achieved by subspace based method to detect active heart valves in time. Recording normal heart sound from healthy subjects and abnormal heart sounds by a microphone array. Abstract: Heart sound auscultation and interpretation is a primary diagnosis and cardiac physical examination method. Heart sound classification becomes a challenging issue in the present of complicated heart sound or multiple valvular heart diseases. Unlike the existence automatic heart sound classification techniques, a powerful heart sound classification method utilizing spatial-temporal information is proposed to determine the heart murmur type when multiple heart murmurs are occurred. First of all, normal and abnormal heart sounds are discriminated via power spectra density of heart sound feature extraction along with Support Vector Machine classifier. Spatial-temporal information of heart valves are extracted by microphone array recording and recursively sound source localization with high resolution. A tree of active heart valves appearance sequences of heart murmurs are obtained by mining locations of active heart valves to model heart murmurs. Due to the heart cyclostationary nature, all sequences of this murmur tree are periodic. Normal heart sound and abnormal heart sound containing various valve regurgitation and stenosis are collected by a rectangular array of 2 × 3 microphones. To evaluate the benefits of the proposed method, it is compared with a murmur classification method based on power spectra density feature extraction. The proposed method achieves 89.8 % accuracy which is superior to mentioned method.