Related Experiment Videos
Separation of discontinuous adventitious sounds from vesicular sounds using a wavelet-based filter
L J Hadjileontiadis1, S M Panas
1Department of EE and CE, Aristotle University of Thessaloniki, Greece. leontios@ccf.auth.gr
IEEE Transactions on Bio-Medical Engineering
|December 24, 1997
Summary
This study introduces an automated filter to separate pathological lung sounds (discontinuous adventitious sounds) from normal breathing sounds. The novel wavelet transform-based filter accurately identifies and isolates these abnormal sounds for improved pulmonary diagnostics.
Area of Science:
- Pulmonary Medicine
- Biomedical Engineering
- Signal Processing
Background:
- Discontinuous adventitious sounds (DAS) are critical indicators of pulmonary pathologies.
- Accurate separation of DAS from vesicular sounds (VS) is essential for lung sound analysis.
- Existing methods for lung sound separation can be complex and computationally intensive.
Purpose of the Study:
- To develop an automated method for separating pathological discontinuous adventitious sounds (DAS) from vesicular sounds (VS).
- To leverage the nonstationary characteristics of DAS for improved diagnostic analysis.
- To present a computationally efficient and clinically applicable tool for lung sound analysis.
Main Methods:
- Development of a wavelet transform-based stationary-nonstationary filter (WTST-NST).
- The algorithm combines multiresolution analysis with hard thresholding.
- Application of the WTST-NST filter to crackles and squawks from multiple lung sound databases.
Main Results:
- The WTST-NST filter successfully revealed the coherent structure of DAS, separating them from VS.
- The filter demonstrated higher accuracy and objectivity compared to existing separation tools.
- The method achieved a lower computational cost, indicating efficiency.
Conclusions:
- The proposed WTST-NST filter provides an accurate and objective method for separating pathological lung sounds.
- The algorithm's efficiency and simple implementation make it suitable for clinical medicine.
- This tool can enhance the diagnostic capabilities in pulmonary auscultation.