Detection of coronary artery atherosclerotic disease using novel features from synchrosqueezing transform of phonocardiogram. (September 2020)

• Record Type: Journal Article
• Authors: Pathak, Akanksha; Samanta, Pranab; Mandana, Kayapanda; Saha, Goutam
• Is Part Of: Biomedical signal processing and control. Volume 62(2020)
• Publication Date: 2020-09
• Subjects: CAD coronary artery disease -- CWT continuous wavelet transform -- MA midaxillary -- MIT mitral -- PCG phonocardiogram -- PUL pulmonary -- RE Renyi entropy -- SE Shannon entropy -- SST synchrosqueezing transform -- T-F time-frequency -- TFE time frequency entropy -- TFR time frequency representation -- TRI tricuspid; Atherosclerosis -- Coronary artery disease -- Phonocardiogram -- Renyi entropy -- Shannon entropy -- Synchrosqueezing transform; 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.2020.102055
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A multichannel phonocardiogram (PCG) based atherosclerotic coronary artery disease (CAD) detection system is proposed. Novel feature representation using synchrosqueezing transform and entropy of PCG is employed for CAD detection. Proposed fusion of features derived from time-frequency and spectrum methods for CAD diagnosis. Comparison of continuous wavelet transform and synchrosqueezing transform in CAD detection. Improved performance compared to existing state-of-the art methods. Abstract: Objective: Atherosclerotic coronary artery disease (CAD) detection through a simple, non-invasive approach will be useful in point-of-care diagnosis. Though numerous studies have addressed CAD detection using phonocardiogram (PCG) signal, none of the studies yet have explored time-varying frequency characteristics of both systolic and diastolic phases of PCG. In this study, we propose a novel method to detect CAD using synchrosqueezing transform (SST) of cardiac cycle. Method: Experiments are performed on 960 PCG collected from four positions/channels on the left anterior chest of 40 CAD and 40 normal subjects. Initially, the temporal variation of subband entropy in SST is analyzed for each channel. Later, their complementary aspect with spectral features is exploited in a fusion framework. Decision from multiple channels are combined to further improve the performance. Results: The proposed entropy features from SST resulted in maximum accuracy of 81.92% in multichannel framework. Fusion with spectral features was found to improve the accuracy to 83.48%. Relative improvement of 15.81% and 6.91% in accuracy is obtained over two recently proposed techniques that considered bag-of-features and sub-band based spectral power, respectively. Conclusion: SST can capture useful time-frequency information from PCG to facilitate CAD detection. The proposed fusion framework using SST and spectral features in a multichannel PCG acquisition platform performs better than other PCG based approaches. Significance: The work shows the potential of developing a non-invasive, inexpensive, point-of-care diagnostic CAD detection system using PCG. Such a system is expected to improve healthcare accessibility in general and reach out to the marginalized in particular.