Orthogonal subspace projection based framework to extract heart cycles from SCG signal. (April 2019)

• Record Type: Journal Article
• Authors: Choudhary, Tilendra; Bhuyan, M.K.; Sharma, L.N.
• Is Part Of: Biomedical signal processing and control. Volume 50(2019)
• Page Start: 45
• Page End: 51
• Publication Date: 2019-04
• Subjects: Seismocardiogram -- Electrocardiogram -- Heart cycle extraction -- Orthogonal subspace projection; 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.2019.01.005
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Heart cycle is extracted from SCG signal using two important fiducial points of systole and diastole profiles. These fiducial points are AO and postAC peaks, which are detected using our proposed method. The AO peaks are detected using orthogonal subspace projection based proposed framework, which uses ECG signal as a reference. The postAC peaks are estimated on intervals between consecutive AO peaks using our simple windowing technique. The proposed method is evaluated using temporal error analysis between detected and manually annotated peaks for AO and postAC instants. The proposed heart cycle extractions with the help of AO and postAC peaks are compared to R-peaks of concurrent ECG signal. The metric used for comparison is normalized cross correlation (NCC). The quantitative analysis of the proposed method enables its applicability in the direction of heart cycle extraction and heart rate variability analysis. Abstract: Early diagnosis and prediction of heart diseases are essential to reduce the cardiac risks. Change in heart cycle morphologies is a vital diagnostic feature for cardiac clinical systems. A seismocardiogram (SCG) signal provides more detailed information of different cardiac phases in a heart cycle compared to other cardiac signals. Hence, heart cycle extraction using SCG is very important to examine cardiac activities. In this manuscript, an orthogonal subspace projection based framework is proposed to extract heart cycles from a SCG signal. The heart cycle is estimated by calculating intervals between consecutive aortic valve opening (AO) instants, and post aortic valve closing (postAC) instants. Orthogonal subspace projection is applied to the SCG signal on ECG subspace for AO peak detection. The signal generated from projection gives the locations of AO peaks in the SCG signal. The postAC peaks are determined on intervals between consecutive AO peaks using segmentation, FIR based smoothing, Butterworth high pass filtering, and finding maxima point. The performance of the proposed method is evaluated using SCG signals from CEBS database, publicly available at Physionet archive. The performance results show that the proposed method produces an acceptable detection rate with a minimal detection error. The evaluation results of the proposed method show its extendibility in heart rate variability analysis and hemodynamic parameter extraction.