Title :
Heart sound segmentation of pediatric auscultations using wavelet analysis
Author :
Castro, A. ; Vinhoza, Tiago T. V. ; Mattos, Sandra S. ; Coimbra, M.T.
Author_Institution :
Dept. de Cienc. de Comput., Univ. do Porto, Porto, Portugal
Abstract :
Auscultation is widely applied in clinical activity, nonetheless sound interpretation is dependent on clinician training and experience. Heart sound features such as spatial loudness, relative amplitude, murmurs, and localization of each component may be indicative of pathology. In this study we propose a segmentation algorithm to extract heart sound components (S1 and S2) based on it´s time and frequency characteristics. This algorithm takes advantage of the knowledge of the heart cycle times (systolic and diastolic periods) and of the spectral characteristics of each component, through wavelet analysis. Data collected in a clinical environment, and annotated by a clinician was used to assess algorithm´s performance. Heart sound components were correctly identified in 99.5% of the annotated events. S1 and S2 detection rates were 90.9% and 93.3% respectively. The median difference between annotated and detected events was of 33.9 ms.
Keywords :
bioacoustics; cardiology; feature extraction; haemodynamics; medical signal detection; medical signal processing; paediatrics; patient diagnosis; wavelet transforms; S1 detection rates; S2 detection rates; diastolic periods; heart cycle times; heart sound segmentation; murmurs; pediatric auscultations; relative amplitude; spatial loudness; systolic periods; time-frequency characteristics; wavelet analysis; Estimation; Feature extraction; Heart rate; Phonocardiography; Signal processing algorithms; Stethoscope;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE
Conference_Location :
Osaka
DOI :
10.1109/EMBC.2013.6610399