Identification of Abnormal Heart Sounds

Abstract

As a part of 2016 Physionet/CinC callenge, this work aims at the detection of abnormal phonocardiogram (PCG) recordings. Heart sound signal analysis has been an active research topic over the past decades with various studies such as heart sound segmentation and classification. We used the Physionet/CinC2016 challenge PCG database, which contains a large public collection of PCG recordings from a variety of clinical and nonclinical environments. The PCG classification in this work is performed in two steps. PCG heartbeats are first segmented and various heart sound markers are delineated. Then, a series of beat-specific features are extracted from the segmented heartbeats. Finally, PCG recordings are classified into normal and abnormal groups by performing classification based on tape-long features and by analyzing beatextracted features from the PCG. Our method achieved an overall score of 80 in the unofficial phase of the challenge. In the official phase, the overall score of the proposed method was 82, with a sensitivity of 89%. IntroductionMechanical activity of the heart, which is triggered by the propagation of electrical activity within the heart, is audible at different locations on the chest wall. Phonocardiogram (PCG) is an audio recording of these mechanical activities recorded at the chest surface. Heat sounds provide valuable information which can help in the diagnosis of heart valve disorders. PCG comprises fundamental heart sounds from which S1 and S2 are the most prominent in normal recordings, respectively representing the beginning of ventricular contraction and the beginning of diastole [1]. In abnormal cases, various markers maybe present beside the fundamental heart sounds such as murmurs. Murmurs are noise-like high frequency sounds and long systolic murmurs as well as diastolic and continuous murmurs are generally pathologic [2].Auscultation is a common cost-effective technique that provides valuable information about heart valve problems. However, by listening to mechanical activity of the heart with a stethoscope, physicians cannot examine all physical characteristics of heart sounds, as it has been shown that only limited activity of heart sounds and murmurs are within human audibility range [1] [3].Over the years, various heart sound classification methods have been proposed. Generally, the analysis of heart sounds is performed on the heart cycle. To this end many PCG heart sound segmentation methods have been developed, enabling the detection of fundamental heart sound markers such as the beginning/end of S1, systole, S2 and diastole. These segmentation techniques use different approaches such as signal envelopes With the segmented cardiac cycles, the classification of heart sound pathologies is made possible and several methods have been proposed over the last decades. Among these studies, artificial neural networks [13], support vector machines [14] and HMM based [15] approaches are common. Classification based on clustering has also been shown to be effective in heart sound...

Classification of Phonocardiogram Signals Using the Wavelet Scattering Transform and Equilibrium Optimization Approach

“…The effectiveness of the Equilibrium Optimization technique, which utilizes the wavelet scattering transform, has been evaluated by comparing its classi cation performance with other recently published methods listed in Table 2. These techniques consist of using a tape classi er to extract time features [9], utilizing a neural network to extract time-frequency features [13], [21], and applying Wavelet transform features with SVM [12] and CNN [6], [20]. Moreover, High-order statistics can also be used in combination with CNN as mentioned in [11].…”

“…For a long time, researchers and developers have focused on studying and advancing the categorization of PCG signals into two groups: healthy and diseased [7]. Numerous techniques exist for analyzing heart sounds, primarily emphasizing feature extraction and classi cation methods [3], [9]. The features of the PCG signal were obtained by applying various methods including Fourier Transform (FT), Wavelet Transform (WT), and statistical and morphological features to the entire PCG signals.…”