Interpretation of Heart Sound Signal through Automated Artifact-Free Segmentation

Abstract

Purpose: Digital recording of heart sounds commonly known as Phonocardiogram (PCG)
signal, is a convenient primary diagnostic tool for analyzing condition of heart. Phonocardiogram
aids physicians to visualize the acoustic energies that results from mechanical
aspect of cardiac activity. PCG signal cycle segmentation is an essential processing step towards
heart sound signal analysis. Sound artifacts due to inappropriate placement of stethoscope,
body movement, cough etc. makes segmentation difficult. Artifact-free segmented heart
sound cycles are convenient for physicians to interpret and it is also useful for computerized
automated classification of abnormality.
Methods: We have developed a framework which selects good quality heart sound subsequences
which are artifact-free and reused the features involved in this processing in segmentation.
In this work, we have used information contained in frequency subbands by decomposing
the signal using Discrete Wavelet Packet Transform (DWPT). The algorithm identifies the
parts of the signal where artifacts are prominent and it also detects major events in heart sound
cycles.
Results: The algorithm shows good results when tested on normal and five commonly occurring
pathological heart sound signals. An average accuracy of 93.71% is registered for artifactfree
subsequence selection process. The cycle segmentation algorithm gives an accuracy of
98.36%, 98.18% and 93.97% respectively for three databases used in the experiment.
Conclusions: The work provides a solution for artifact-free segmentation of heart sound cycles
to assist interpretation of heart sound by physicians in objective analysis through recording
in a computer. It is also useful for development of an automated decision support system on
heart sound abnormality.

MAIN KEY FINDINGS
• Artifact free subsequence detection is preferable over attempt to reduce the effect of artifacts
due to overlap of information content.
• DWPT is useful for detection of artifact contaminated subsequences due to its ability to provide
for more detailed information of higher frequency components.
• DWPT features of subsequence detection can be reused for automatic segmentation of heart
sound.
• The artifact-free segmented heart sound cycle detection system can work in real-time.