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

A cardiac cycle with aortic regurgitation and its envelope signal.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 6: A cardiac cycle with aortic regurgitation and its envelope signal.

Mentions: Segmentation is even more difficult in the case of heart sound with murmur. Figure 6 shows a cardiac cycle with aortic regurgitation murmur and its envelope signal. Aortic regurgitation is characterized by diastolic murmur, in addition to diminished S1 sound [7]. From the figure it can be seen that just one cardiac cycle contains 4 peaks, the largest of which corresponds to S2. However, there is no clear location of S1 as can be seen from the top panel, where S1 appears to have been "squashed". Therefore the envelope signal has 3 peaks that can not be labelled because the location of S1 is uncertain. For this reason, segmentation using the envelope analysis approach needs to eliminate extra peaks while retaining the ones that correspond to FHS. This is called "peak conditioning". In general, peak conditioning is based on "minimum peak interval". That is, if an interval between consecutive peaks fall below the minimum interval, it indicates that one of them must be an extra peak; and a common procedure is to eliminate the one with smaller magnitude. Peak conditioning can become a very tedious process due to several reasons:


A framework for automatic heart sound analysis without segmentation.

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

A cardiac cycle with aortic regurgitation and its envelope signal.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 6: A cardiac cycle with aortic regurgitation and its envelope signal.
Mentions: Segmentation is even more difficult in the case of heart sound with murmur. Figure 6 shows a cardiac cycle with aortic regurgitation murmur and its envelope signal. Aortic regurgitation is characterized by diastolic murmur, in addition to diminished S1 sound [7]. From the figure it can be seen that just one cardiac cycle contains 4 peaks, the largest of which corresponds to S2. However, there is no clear location of S1 as can be seen from the top panel, where S1 appears to have been "squashed". Therefore the envelope signal has 3 peaks that can not be labelled because the location of S1 is uncertain. For this reason, segmentation using the envelope analysis approach needs to eliminate extra peaks while retaining the ones that correspond to FHS. This is called "peak conditioning". In general, peak conditioning is based on "minimum peak interval". That is, if an interval between consecutive peaks fall below the minimum interval, it indicates that one of them must be an extra peak; and a common procedure is to eliminate the one with smaller magnitude. Peak conditioning can become a very tedious process due to several reasons:

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