Sparse modeling of heart sounds and murmurs based on orthogonal matching pursuit
ABSTRACT In this paper, we address the Heart Sound signal modeling problem. The approach taken is based on sparse and redundant representations on an overcomplete dictionary. We apply matching pursuit (MP) and orthogonal matching pursuit (OMP) on two sets of normal and pathological phonocardiograms (PCGs). The dictionary includes classical Gabor wavelets or time-frequency atoms which are the product of a sinusoid and a Gaussian window function. The normalized root-mean-square error (NRMSE) was computed between the original and the reconstructed signals. The results show that the OMP method is very suitable to the transient and complex properties of the PCG's, as it yielded excellent NRMSE's around 1.61% for normal sounds and 5.19% for pathological murmurs.
- SourceAvailable from: udel.edu[show abstract] [hide abstract]
ABSTRACT: Skilled cardiologists perform cardiac auscultation, acquiring and interpreting heart sounds, by implicitly carrying out a sequence of steps. These include discarding clinically irrelevant beats, selectively tuning in to particular frequencies and aggregating information across time to make a diagnosis. In this paper, we formalize a series of analytical stages for processing heart sounds, propose algorithms to enable computers to approximate these steps, and investigate the effectiveness of each step in extracting relevant information from actual patient data. Through such reasoning, we provide insight into the relative difficulty of the various tasks involved in the accurate interpretation of heart sounds. We also evaluate the contribution of each analytical stage in the overall assessment of patients. We expect our framework and associated software to be useful to educators wanting to teach cardiac auscultation, and to primary care physicians, who can benefit from presentation tools for computer-assisted diagnosis of cardiac disorders. Researchers may also employ the comprehensive processing provided by our framework to develop more powerful, fully automated auscultation applications.IEEE Transactions on Biomedical Engineering 04/2007; 54(4):651-62. · 2.35 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: The matching pursuit method of Mallat and Zhang (1993) is applied to the analysis and synthesis of phonocardiograms (PCGs). The method is based on a classical Gabor wavelet or time-frequency atom which is the product of a sinusoid and a Gaussian window function, it decomposes a signal into a series of time-frequency atoms by an iterative process based on selecting the largest inner product of the signal (and the subsequent residues) with atoms from a redundant dictionary. The Gaussian window controls the envelope duration and time position of each atom; and the sinusoid represents the frequency. The method was applied to two sets of PCGs: one with very low-noise level and the other with 10% noise energy. Each database includes 11 PCGs representing the normal and the pathological conditions of the heart. The normalized root-mean-square error (NRMSE) was computed between the original and the reconstructed signals. The results show that the matching pursuit method is very suitable to the transient and complex properties of the PCGs, as it yielded excellent NRMSEs around 2.2% for the two sets of 11 PCGs tested.IEEE Transactions on Biomedical Engineering 09/1998; · 2.35 Impact Factor
- [show abstract] [hide abstract]
ABSTRACT: It is acknowledged that the first heart sound S1 consists of two major, high-frequency components M1 and T1, corresponding, respectively, to the vibrations of the mitral and tricuspid valves and their surrounding tissues following valve closure in early systole. In this study, the matching pursuit (MP) method was used to decompose S1 into a series of time-frequency atoms. M1 and T1 were separated from the parameterised atoms of S1. The first two dominant frequencies of M1 were identified and used as features of a linear classifier to diagnose mitral valve abnormality. This method was applied to two sets of S1 data recorded from 15 patients with normal, and 15 patients with abnormal, bioprosthetic mitral valves, respectively. It was found that the two features exhibit significant differences between the normal and abnormal sets (p< 0.001). Using these two features, a correct classification of 93% was obtained. In addition, when the Wigner distribution of S1 was calculated from the decomposed atoms and compared with a spectrogram, the MP method provided better results. The study demonstrates that the MP method may be a promising technique for heart sound analysis.Medical & Biological Engineering & Computing 11/2001; 39(6):644-8. · 1.79 Impact Factor