Limits...
A framework for automatic heart sound analysis without segmentation.

Yuenyong S, Nishihara A, Kongprawechnon W, Tungpimolrut K - Biomed Eng Online (2011)

Bottom Line: Geometric mean was used as performance index.Average classification performance using ten-fold cross-validation was 0.92 for noise free case, 0.90 under white noise with 10 dB signal-to-noise ratio (SNR), and 0.90 under impulse noise up to 0.3 s duration.Further work include building a new training set recorded from actual patients, then further evaluate the method based on this new training set.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Communication and Integrated Systems, Tokyo Institute of Technology, Japan 2-12-1-W9-108 Ookayama, Meguro-ku, Tokyo, Japan. toey123@gmail.com

ABSTRACT

Background: A new framework for heart sound analysis is proposed. One of the most difficult processes in heart sound analysis is segmentation, due to interference form murmurs.

Method: Equal number of cardiac cycles were extracted from heart sounds with different heart rates using information from envelopes of autocorrelation functions without the need to label individual fundamental heart sounds (FHS). The complete method consists of envelope detection, calculation of cardiac cycle lengths using auto-correlation of envelope signals, features extraction using discrete wavelet transform, principal component analysis, and classification using neural network bagging predictors.

Result: The proposed method was tested on a set of heart sounds obtained from several on-line databases and recorded with an electronic stethoscope. Geometric mean was used as performance index. Average classification performance using ten-fold cross-validation was 0.92 for noise free case, 0.90 under white noise with 10 dB signal-to-noise ratio (SNR), and 0.90 under impulse noise up to 0.3 s duration.

Conclusion: The proposed method showed promising results and high noise robustness to a wide range of heart sounds. However, more tests are needed to address any bias that may have been introduced by different sources of heart sounds in the current training set, and to concretely validate the method. Further work include building a new training set recorded from actual patients, then further evaluate the method based on this new training set.

Show MeSH

Related in: MedlinePlus

Comparison of DWT denoising on heart sounds with different murmur intensity. (a) Heart sound with relatively mild aortic stenosis. (b) Reconstructed signal from d5 DWT coefficients. The murmur had been attenuated significantly. (c) Heart sound with severe aortic stenosis. (d) Reconstructed signal from d5 DWT coefficients. Murmur is still largely present.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3045988&req=5

Figure 7: Comparison of DWT denoising on heart sounds with different murmur intensity. (a) Heart sound with relatively mild aortic stenosis. (b) Reconstructed signal from d5 DWT coefficients. The murmur had been attenuated significantly. (c) Heart sound with severe aortic stenosis. (d) Reconstructed signal from d5 DWT coefficients. Murmur is still largely present.

Mentions: 1. Often murmur can be eliminated by DWT decomposition and reconstruction. However, when a murmur is very loud, it overlaps with the FHS both in time and in frequency, and hence cannot be eliminated by the DWT method. Figure 7 compares the result of applying the DWT method described in [15] on a heart sound with moderate murmur and that with a very loud murmur. It can be seen in the left column that the murmur has been significantly removed. On the other hand, in the right column, the murmur is still largely present.


A framework for automatic heart sound analysis without segmentation.

Yuenyong S, Nishihara A, Kongprawechnon W, Tungpimolrut K - Biomed Eng Online (2011)

Comparison of DWT denoising on heart sounds with different murmur intensity. (a) Heart sound with relatively mild aortic stenosis. (b) Reconstructed signal from d5 DWT coefficients. The murmur had been attenuated significantly. (c) Heart sound with severe aortic stenosis. (d) Reconstructed signal from d5 DWT coefficients. Murmur is still largely present.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3045988&req=5

Figure 7: Comparison of DWT denoising on heart sounds with different murmur intensity. (a) Heart sound with relatively mild aortic stenosis. (b) Reconstructed signal from d5 DWT coefficients. The murmur had been attenuated significantly. (c) Heart sound with severe aortic stenosis. (d) Reconstructed signal from d5 DWT coefficients. Murmur is still largely present.
Mentions: 1. Often murmur can be eliminated by DWT decomposition and reconstruction. However, when a murmur is very loud, it overlaps with the FHS both in time and in frequency, and hence cannot be eliminated by the DWT method. Figure 7 compares the result of applying the DWT method described in [15] on a heart sound with moderate murmur and that with a very loud murmur. It can be seen in the left column that the murmur has been significantly removed. On the other hand, in the right column, the murmur is still largely present.

Bottom Line: Geometric mean was used as performance index.Average classification performance using ten-fold cross-validation was 0.92 for noise free case, 0.90 under white noise with 10 dB signal-to-noise ratio (SNR), and 0.90 under impulse noise up to 0.3 s duration.Further work include building a new training set recorded from actual patients, then further evaluate the method based on this new training set.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Communication and Integrated Systems, Tokyo Institute of Technology, Japan 2-12-1-W9-108 Ookayama, Meguro-ku, Tokyo, Japan. toey123@gmail.com

ABSTRACT

Background: A new framework for heart sound analysis is proposed. One of the most difficult processes in heart sound analysis is segmentation, due to interference form murmurs.

Method: Equal number of cardiac cycles were extracted from heart sounds with different heart rates using information from envelopes of autocorrelation functions without the need to label individual fundamental heart sounds (FHS). The complete method consists of envelope detection, calculation of cardiac cycle lengths using auto-correlation of envelope signals, features extraction using discrete wavelet transform, principal component analysis, and classification using neural network bagging predictors.

Result: The proposed method was tested on a set of heart sounds obtained from several on-line databases and recorded with an electronic stethoscope. Geometric mean was used as performance index. Average classification performance using ten-fold cross-validation was 0.92 for noise free case, 0.90 under white noise with 10 dB signal-to-noise ratio (SNR), and 0.90 under impulse noise up to 0.3 s duration.

Conclusion: The proposed method showed promising results and high noise robustness to a wide range of heart sounds. However, more tests are needed to address any bias that may have been introduced by different sources of heart sounds in the current training set, and to concretely validate the method. Further work include building a new training set recorded from actual patients, then further evaluate the method based on this new training set.

Show MeSH
Related in: MedlinePlus