Processing of the Phonocardiographic Signal: methods for the intelligent stethoscope

Phonocardiographic signals contain bioacoustic information reflecting the operation of the heart. Normally there are two heart sounds, and additional sounds indicate disease. If a third heart sound is present it could be a sign of heart failure whereas a murmur indicates defective valves or an orifice in the septal wall. The primary aim of this thesis is to use signal processing tools to improve the diagnostic value of this information. More specifically, three different methods have been developed…

Contents

1. INTRODUCTION
1.1. AIM OF THE THESIS
1.2. THESIS OUTLINE
2. PRELIMINARIES ON HEART SOUNDS AND HEART MURMURS
2.1. PHYSICS OF SOUND
2.2. PHYSIOLOGY OF THE HEART
2.3. HEART SOUNDS
2.4. HEART MURMURS
2.5. AUSCULTATION AND THE PHONOCARDIOGRAM
2.6. ACQUISITION OF PHONOCARDIOGRAPHIC SIGNALS
2.6.1. Sensors
2.6.2. Pre-processing, digitalization and storage
3. SIGNAL ANALYSIS FRAMEWORK
3.1. MEASURING CHARACTERISTICS THAT VARY IN TIME
3.1.1. Intensity
3.1.2. Frequency
3.2. NONLINEAR SYSTEMS AND EMBEDOLOGY
3.3. NONLINEAR ANALYSIS TOOLS
3.3.1. Non-integer dimensions
3.3.2. Recurrence quantification analysis
3.3.3. Higher order statistics
3.4. NONLINEAR PREDICTION
4. PROPERTIES OF PHONOCARDIOGRAPHIC SIGNALS
4.1. TIME AND FREQUENCY
4.1.1. Murmurs from stenotic semilunar valves
4.1.2. Murmurs from regurgitant atrioventricular valves
4.1.3. Murmurs caused by septal defects
4.1.4. Quantifying the results
4.2. HIGHER ORDER STATISTICS
4.3. RECONSTRUCTED STATE SPACES
4.3.1. Quantifying the reconstructed state space
4.3.2. Recurrence time statistics
4.4. FRACTAL DIMENSION
5. APPLICATIONS IN PHONOCARDIOGRAPHIC SIGNAL PROCESSING
5.1. SEGMENTATION OF THE PHONOCARDIOGRAPHIC SIGNAL
5.2. FINDING S3
5.3. FILTERING OUT SIGNAL COMPONENTS
5.4. CLASSIFICATION OF MURMURS
5.4.1. Feature extraction
5.4.2. Finding relevant features
5.4.3. Classifying murmurs
6. DISCUSSION
6.1. CONTEXT OF THE PAPERS
6.2. PATIENTS AND DATA SETS
6.2.1. Measurement noise
6.3. METHODOLOGY
6.4. FUTURE WORK
6.4.1. Clinical validation
6.4.2. Multi-sensor approach
6.4.3. Dimension reduction
6.4.4. Choosing an appropriate classifier
7. REVIEW OF PAPERS
7.1. PAPER I, HEART SOUND CANCELLATION
7.2. PAPER II, DETECTION OF THE 3RD
HEART SOUND
7.3. PAPER III, FEATURE EXTRACTION FROM SYSTOLIC MURMURS
REFERENCES

Author: Ahlström, Christer

Source: Linköping University

Download URL 2: Visit Now