Phonocardiogram Signals Research Articles

A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection

This study concerns the task of automatic structural heart abnormality risk detection from digital phonocardiogram (PCG) signals aiming at pediatric heart disease screening applications. Recently, various systems based on convolutional neural networks trained on time-frequency representations of segmental PCG frames have been presented that outperform systems using hand-crafted features. This study focuses on the segmentation and time-frequency representation components of the CNN-based designs. We consider the most commonly used features (MFCC and Mel-Spectrogram) used in state-of-the-art systems and a time-frequency representation influenced by domain-knowledge, namely sub-band envelopes as an alternative feature. Via tests carried on two high quality databases with a large set of possible settings, we show that sub-band envelopes are preferable to the most commonly used features and period synchronous windowing is preferable over asynchronous windowing.

Automated Heart Sound Classification from Unsegmented Phonocardiogram Signals Using Time Frequency Features

Automated Heart Sound Classification from Unsegmented Phonocardiogram Signals Using Time Frequency Features

Optimal level and order detection in wavelet decomposition for PCG signal denoising.

The recorded phonocardiogram (PCG) signal is often contaminated by different types of noises that can be seen in the frequency band of the PCG signal, which may change the characteristics of this signal. Discrete wavelet transform (DWT) has become one of the most important and powerful tools of signal representation, but its effectiveness is influenced by the issue of the selected mother wavelet and decomposition level (DL). The selection of the DL and the mother wavelet are the main challenges. This work proposes a new approach for finding an optimal DL and optimal mother wavelet for PCG signal denoising. Our approach consists of two algorithms designed to tackle the problems of noise and variability caused by PCG acquisition in a real clinical environment for different categories of patients. The results obtained are evaluated by examining the coherence analysie (Coh) correlation coefficient (Corr) and the mean square error (MSE) and signal-to-noise ratio (SNR) in simulated noisy PCG signals. The experimental results show that the proposed method can effectively reduce noise.

Wavelet‐based fundamental heart sound recognition method using morphological and interval features

Accurate and reliable recognition of fundamental heart sounds (FHSs) plays a significant role in automated analysis of heart sound (HS) patterns. This Letter presents an automated wavelet-based FHS recognition (WFHSR) method using morphological and interval features. The proposed method first performs the decomposition of phonocardiogram (PCG) signal using a synchrosqueezing wavelet transform to extract the HSs and suppresses the murmurs, low-frequency and high-frequency noises. The HS delineation (HSD) is presented using Shannnon energy envelope and amplitude-dependent thresholding rule. The FHS recognition (FHSR) is presented using interval, HS duration and envelope area features with a decision-rule algorithm. The performance of the method is evaluated on PASCAL HSs Challenge, PhysioNet/CinC HS Challenge, eGeneralMedical databases and real-time recorded PCG signals. Results show that the HSD approach achieves an average sensitivity (Se) of 98.87%, positive predictivity (Pp) of 97.50% with detection error rate of 3.67% for PCG signals with signal-to-noise ratio of 10 dB, and outperforms the existing HSD methods. The proposed FHSR method achieves a Se of 99.00%, Sp of 99.08% and overall accuracy of 99.04% on both normal and abnormal PCG signals. Evaluation results show that the proposed WFHSR method is able to accurately recognise the S1/S2 HSs in noisy real-world PCG recordings with murmurs and other abnormal sounds.

Heart Sound Extraction From Sternal Seismocardiographic Signal

The phonocardiogram (PCG) signal indicates closing instants of atrio-ventricular and semilunar valves, and this information can also be extracted from two major profiles of a seismocardiographic (SCG) cycle. This letter presents a method to extract fundamental heart sounds (HSs) from a SCG signal. The proposed method employs discrete wavelet transform for signal decomposition, and subsequently, center of gravity (CoG) of power spectrum for each of the subbands is computed. Our method can optimally select wavelet subbands for any combination of sampling frequencies of the signal and number of decomposition levels. Based on proposed CoG criterion, the signal is reconstructed from a number of selected subbands, and instantaneous Hilbert envelope is constructed for localizing peaks of the signal. Finally, a simple decision rule is applied to annotate S1 and S2 sounds of the PCG signal. Experimental results show that the HS waves S1 and S2 can be well localized with the help of one SCG cycle without using a reference ECG cycle.

Phonocardiogram and Electrocardiogram Signals Processing using Wavelet Transform and Multilayer Perceptron Neural Network

This article deals with an original approach of acquiring and processing electrocardiogram (ECG) and phonocardiogram (PCG) signals for the diagnosis of cardiac arrhythmias in order to remedy the difficulties encountered with the ECG. Indeed, it integrates an analysis tool based on wavelet transforms for the characterization of ECG signals and a classification system from multilayer perceptron neural network of five categories of cardiac arrhythmias: normal (N), left bundle branch block (LBBB), right bundle branch block (RBBB), premature atrial contraction (PAC) and premature ventricular contraction (PVC). The digitization of the signals is made from an Arduino Mega 2560 board. The realized system has been tested on 6 patients and the results are visualized on a smart phone turning under android operating system. These results are in agreement with medical previsions. Recognition rates are as follows: 100% for class N, 100% for class LBBB, 75% for class RBBB, 90.9% for class PVC and 100% for class PAC. We obtain a generalization rate of 92.9%.

Phonocardiogram signals processing approach for PASCAL Classifying Heart Sounds Challenge

This paper describes a new approach of the first and the second challenge presented by Pattern Analysis, Statistical Modeling and Computational Learning (PASCAL) Classifying Heart Sounds Challenge. The segmentation of phonocardiogram signals into the first heart sound S1 and the second heart sound S2 consists in heart sounds preprocessing, heart sounds peaks detection, extra peaks rejection and S1 and S2 peaks identification. Regarding heart sounds classification into few classes, relevant descriptors have been extracted from phonocardiogram signals, some of which have relied on segmentation results, and used as parameters for an appropriate classifier. The results of this methodology are compared with those of other approaches obtained at PASCAL Classifying Heart Sounds Challenge by means of the segmentation total error value and the precision of each category.

Cardiorespiratory system monitoring using a developed acoustic sensor

This Letter proposes a wireless acoustic sensor for monitoring heartbeat and respiration rate based on phonocardiogram (PCG). The developed sensor comprises a processor, a transceiver which operates at industrial, scientific and medical band and the frequency of 2.54 GHz as well as two capacitor microphones which one for recording the heartbeat and another one for respiration rate. To evaluate the precision of the presented sensor in estimating heartbeat and respiration rate, the sensor is tested on the different volunteers and the obtained results are compared with a gold standard as a reference. The results reveal that root-mean-square error are determined <2.27 beats/min and 0.92 breaths/min for the heartbeat and respiration rate in turn. While the standard deviation of the error is obtained <1.26 and 0.63 for heartbeat and respiration rate, respectively. Also, the sensor estimate sounds of n}{}S_1 to n}{}S_4 obtained PCG signal with sensitivity and specificity 98.1% and 98.3% in turn that make 3% improvement than previous works. The results prove that the sensor can be appropriate candidate for recognising abnormal condition in the cardiorespiratory system.

The packet wavelet transform in the analysis of phonocardiogram's signals (aortic stenosis and mitral stenosis)

Heart murmurs are the first signs of cardiac valve disorders. Indeed, heart auscultation through a stethoscope has been recognised for a long time as an important tool for the diagnosis of heart disease. But, it remains insufficient for an efficient treatment of cardiovascular pathologies. The efficiency and accuracy of diagnosis can be improved considerably by using digital signal processing techniques to analyse the phonocardiographic (PCG) signals. The wavelet packet transforms (WPT) was successfully used as a feature to distinguish different heart sounds. It is introduced to analyse and identify the phonocardiogram's signals. The importance of application of the wavelet packet transform (WPT) to analyse the pathological severity of the aortic stenosis 'AS' and mitral stenosis 'MS' was presented. Then, the calculation of various parameters was performed for each patient.

The packet wavelet transform in the analysis of phonocardiogram's signals (aortic stenosis and mitral stenosis)

Heart murmurs are the first signs of cardiac valve disorders. Indeed, heart auscultation through a stethoscope has been recognised for a long time as an important tool for the diagnosis of heart disease. But, it remains insufficient for an efficient treatment of cardiovascular pathologies. The efficiency and accuracy of diagnosis can be improved considerably by using digital signal processing techniques to analyse the phonocardiographic (PCG) signals. The wavelet packet transforms (WPT) was successfully used as a feature to distinguish different heart sounds. It is introduced to analyse and identify the phonocardiogram's signals. The importance of application of the wavelet packet transform (WPT) to analyse the pathological severity of the aortic stenosis 'AS' and mitral stenosis 'MS' was presented. Then, the calculation of various parameters was performed for each patient.

Spectral Fault Recovery Analysis Revisited With Normal and Abnormal Heart Sound Signals

The computation of fast Fourier transform (FFT) plays a vital role in all fields of science and engineering, especially in the medical domain. Spectral results of the data convey more information to the clinicians to take handy decisions during the diagnosis. If a problem happens during the computation of FFT, the incorrect results misinterpret the information and hence the suggestions and decisions by practitioners would be the useless one moreover, it may yield harmful result to the patients. This paper deals with how to recover the spectrum from the faulty one with the heart sound case reports. The heart sound recording is the phonocardiogram (PCG) signal. Stethoscopes are commonly used to hear the heart sound for diagnosis. The two PCG signals of normal and abnormal subjects in each were analyzed in this paper. The normal subject produce clear lub and dub sounds, where the abnormal subject produce a kind of whistling or swishing sound in middle which may be due to the problem of septal defect in a heart. This paper analyzes four PCG signals spectrally with fault and the recovered ones along with the execution time results in each using Matlab R2016b tool.

Improved computerized cardiac auscultation by discarding artifact contaminated PCG signal sub-sequence

Abstract Hearts sound signal recording through electronic stethoscope, also termed as phonocardiogram (PCG), is very sensitive to different kind of interferences. These interferences come as extra sounds which can appear at any instance of a heart sound cycle. A novice user may interpret these short duration interferences as a diseased marker. Also, for automated analysis of heart sound signal it is important to discard the artifact-affected signal sub-sequences. In this work, a novel method of detection of artifact in heart sound is presented. It uses a fusion of tunable Q-wavelet transform and signal second difference with median filter to detect the artifact-infected sub-sequences. The proposed method is compared with the discrete wavelet packet transform based method and quasi-periodicity based method used before. Performance of this technique is evaluated by considering most common occurring artifact types and at −5 dB, −3 dB and 0 dB SNRs. Four common types of pathological murmur sounds are considered in this experiment. An average accuracy of 96.13% is achieved for the proposed method which is superior to earlier published techniques.

Cyclic Analysis of Phonocardiogram Signals

Cyclic Analysis of Phonocardiogram Signals

HEART MURMURS DETECTION AND CHARACTERIZATION USING WAVELET ANALYSIS WITH RENYI ENTROPY

Phonocardiogram signals (PCGs) represent a nonstationary signal due to their complicated production. Also, during the registration they may be added with different noise and pathological murmurs. Indeed, in real situation, the heart sound signal (HSs) may present some abnormal murmur characterizing a variety of heart diseases. This work deals with the segmentation of pathological PCGs based on the Discrete Wavelet Transform (DWT) which permits signal decomposition in different frequency bands. After the decomposition step, we estimate the Renyi Entropy (RE) of the detail coefficients. Then, we apply a threshold allowing detecting the murmur of the PCGs. After the detection, we characterize the results in time–frequency domain in order to extract some features such as frequency band, peak frequency and time duration of the abnormal murmur. The validation of the method is evaluated and proved using some pathological PCGs such as: Early Aortic Stenosis (EAS), Late Aortic Stenosis (LAS), Mitral Regurgitation (MR), Aortic Regurgitation (AR), Opening Snap (OS) and Pulmonary Stenosis (PS). The method presents good results in terms of the detection and the characterization of the main components and the abnormal murmurs associated with some valves disease.

Automatic heart activity diagnosis based on Gram polynomials and probabilistic neural networks.

The paper proposes a new approach to heart activity diagnosis based on Gram polynomials and probabilistic neural networks (PNN). Heart disease recognition is based on the analysis of phonocardiogram (PCG) digital sequences. The PNN provides a powerful tool for proper classification of the input data set. The novelty of the proposed approach lies in a powerful feature extraction based on Gram polynomials and the Fourier transform. The proposed system presents good performance obtaining overall sensitivity of 93%, specificity of 91% and accuracy of 94%, using a public database of over 3000 heart beat sound recordings, classified as normal and abnormal heart sounds. Thus, it can be concluded that Gram polynomials and PNN prove to be a very efficient technique using the PCG signal for characterizing heart diseases.

Design and evaluation of a parametric model for cardiac sounds

Heart sound analysis plays an important role in the auscultative diagnosis process to detect the presence of cardiovascular diseases. In this paper we propose a novel parametric heart sound model that accurately represents normal and pathological cardiac audio signals, also known as phonocardiograms (PCG). The proposed model considers that the PCG signal is formed by the sum of two parts: one of them is deterministic and the other one is stochastic. The first part contains most of the acoustic energy. This part is modeled by the Matching Pursuit (MP) algorithm, which performs an analysis-synthesis procedure to represent the PCG signal as a linear combination of elementary waveforms. The second part, also called residual, is obtained after subtracting the deterministic signal from the original heart sound recording and can be accurately represented as an autoregressive process using the Linear Predictive Coding (LPC) technique. We evaluate the proposed heart sound model by performing subjective and objective tests using signals corresponding to different pathological cardiac sounds. The results of the objective evaluation show an average Percentage of Root-Mean-Square Difference of approximately 5% between the original heart sound and the reconstructed signal. For the subjective test we conducted a formal methodology for perceptual evaluation of audio quality with the assistance of medical experts. Statistical results of the subjective evaluation show that our model provides a highly accurate approximation of real heart sound signals. We are not aware of any previous heart sound model rigorously evaluated as our proposal.

An adaptive thresholding method for the wavelet based denoising of phonocardiogram signal

Abstract Segmentation of the phonocardiography (PCG) signal into cardiac cycles is a primary task for the diagnosis of cardiovascular diseases. However, PCG is highly susceptible to noise, and extra sound called murmur may also be present in the PCG signal due to pathology. These components cause difficulties in the segmentation and therefore, segmentation is often preceded by the denoising of the PCG signal to emphasize the fundamental heart sounds S1 and S2, by removing these unwanted components. For the denoising of the PCG signal, discrete wavelet transform (DWT) based algorithms have shown good performance because such algorithms suppress in-band noise besides the out-of-band noise. Selection of threshold value and threshold function significantly affects the performance of these algorithms. In this paper, for threshold value estimation, an adaptive method based on statistical parameters of the given PCG signal is proposed. The statistical parameters are found to be highly effective for this purpose. We also propose a new threshold function, non-linear mid function, to address the issues of SNR and transients in the existing threshold functions, soft and hard. The proposed method is applied on a large number of PCG signals with additive white Gaussian noise, red noise, and pink noise. The Performance of the proposed method is also evaluated on the PCG signals recorded in real-life noisy scenarios and signals with murmur sound. The obtained results show that the proposed method is significantly superior to the competitive algorithms.

Detection of pathological heart murmurs by feature extraction of phonocardiogram signals

Cardiac auscultation can be perceived as method of determining the human heart condition by listening to the heart sounds. These heart sounds contain vital information related to a person’s heart condition. Any departure from the normal cardiac auscultation readings in terms of presence of additional heart sounds is indicative of an unhealthy heart. The use of Phonocardiogram (PCG)signals (i.e. the electronic recording of heart sounds) completely dismisses the limitation of relying solely on the physician’s hearing ability. At the same time, they provide with a high-fidelity representation of the heart sounds in the most cost-effective way as compared to the methods like Electrocardiogram (ECG). In this paper, a method of detection of heart ailments by extracting the features of PCG signals is proposed. The normal heart sounds, gallop rhythms and the most common pathological murmurs have been used for analysis. By analyzing these signals, early detection and diagnosis of heart diseases can be done reliably. This will not only confirm health and longevity by early diagnosis and pin-pointed prognosis, but will also be economically suitable for those who can hardly afford tests like ECG. It can also be practicable in the case of infants wherein the other non-invasive diagnosis techniques like ECG fail.

Analysis of phonocardiogram signals through proactive denoising using novel self-discriminant learner.

Phonocardiogram (PCG) records heart sound and murmurs, which contains significant information of cardiac health. Analysis of PCG signal has the potential to detect abnormal cardiac condition. However, the presence of noise and motion artifacts in PCG hinders the accuracy of clinical event detection. Thus, noise detection and elimination are crucial to ensure accurate clinical analysis. In this paper, we present a robust denoising technique, Proclean that precisely detects the noisy PCG signal through pattern recognition, and statistical learning. We propose a novel self-discriminant learner that ensures to obtain distinct feature set to distinguish clean and noisy PCG signals without human-in-loop. We demonstrate that our proposed denoising leads to higher accuracy in subsequent clinical analytics for medical investigation. Our extensive experimentations with publicly available MIT-Physionet datasets show that we achieve more than 85% accuracy for noisy PCG signal detection. Further, we establish that physiological abnormality detection improves by more than 20%, when our proposed denoising mechanism is applied.

Pattern discovery and similarity assessment for robust Heart Sound Segmentation.

Heart Sound Segmentation plays a fundamental role in pathology detection in Phonocardiogram (PCG) signals. This matter of study has been widely studied in the past decades, however the majority of algorithms' results correspond only to small databases, composed by only quality signals or signals specific to one acquisition system. In this work we proposed a robust segmentation algorithm integrated with clinical information, based on a pattern recognition approach for segmentation of the fundamental heart sounds, which is validated in several databases from different countries and with different acquisition instrumentations. The database comprises a total of 3153 recordings from 764 patients with a variety of pathological conditions. The general results were 95% and 96% of sensitivity and positive predictivity, respectively. Based on the results the algorithm is able to perform with accuracy maintaining generalization capabilities.