Phonocardiogram Research Articles

CNN-based classification of phonocardiograms using fractal techniques

Deep Learning based heart sound classification is of significant interest in reducing the burden of manual auscultation through the automated detection of signals, including abnormal heartbeats. This work presents a method for classifying phonocardiogram (PCG) signals as normal or abnormal by applying a deep Convolutional Neural Network (CNN) after transforming the signals into 2D color images. In particular, a new methodology based on fractal theory, which exploits Partitioned Iterated Function Systems (PIFS) to generate 2D color images from 1D signals is presented. PIFS have been extensively investigated in the context of image coding and indexing on account of their ability to interpolate and identify self-similar features in an image. Our classification approach has shown a high potential in terms of noise robustness and does not require any pre-processing steps or an initial segmentation of the signal, as instead happens in most of the approaches proposed in the literature. In this preliminary work, we have carried out several experiments on the database released for the 2016 Physionet Challenge, both in terms of different classification networks and different inputs to the networks, thus also evaluating the data quality. Among all experiments, we have obtained the best result of 0.85 in terms of modified Accuracy (MAcc).

Accurate Segmentation of Phonocardiogram Signals using Fractal Decomposition with WB-MFA in MATLAB 2022

This work describes a unique method for segmenting phonocardiogram (PCG) signals inMATLAB 2022 utilizing fractal decomposition. Fractal decomposition is an effective technique forbreaking down a PCG signal into simpler components based on their fractal features. The suggested methodfor fractal decomposition employs the wavelet-based multifractal analysis (WB-MFA) method, which hasalready been proved to be successful for PCG segmentation. The proposed method was tested on a datasetof PCG signals and found to be highly accurate in segmenting the signals into separate heart sounds.

Heart Sound Classification using the Nonlinear Dynamic Feature Approach along with Conventional Classifiers

Heart sounds show chaotic and complex behavior when murmurs are present, containing nonlinear and non-Gaussian information. This paper studies ways to extract features from nonlinear dynamic models. The features frequently used to describe the underlying dynamics of the heart are derived from nonlinear dynamical modeling of heart sound signals. This study incorporates nonlinear dynamic features alongside conventional classifiers in the analysis of phonocardiograms (PCGs), achieving a significant improvement in the classification performance with 0.90 sensitivity and 0.92 specificity.

A robust sliding window adaptive filtering technique for phonocardiogram signal denoising

AbstractObjectiveThe digital sound recording of several heart sounds (HSs) is named phonocardiogram (PCG) signal. Analysing these PCG signals is essential for diagnosing diverse sorts of heart disorders. Nevertheless, owing to troubling surrounding noise signals, PCG signal recording is challenging. So, before utilising PCG for advanced processing, de‐noising the PCG signal is executed. A new sliding window adaptive noise cancellers (SWANC)‐centred filter technique is proposed in this paper for de‐noising along with recovering the PCG signal effectively.MethodUtilising the least mean square (LMS), an SW optimum adaptive filter (AF) structure is introduced in this work for estimating a De‐noised signal (DS) with better accuracy. Here, via the SWAF stage, a noisy signal is processed. An SW of fixed duration slides over the signal; also, the signal is filtered utilising the AF in each window. Utilising this SWAF architecture, this method approximates the PCG signal's clean version with better accuracy.ResultsThe proposed robust SWAF is analogized to experimental PCG signals that were corrupted by Gaussian noise (GN) together with pink noise (PN) with distinct noise levels (NLs). From the physionet database, the experiential data are acquired. The outcomes exhibited that a remarkable performance was attained by the robust SWAF model.DiscussionA 2–10 times decrease in MSE values was attained by the proposed filter structure when analogized with conventional LMS filter configuration. Further, the SNR is improved by 3 times and comparatively, the PSNR enhancement was 4%–25%. The association betwixt the clean signal along with its estimate is greater than 0.92.ConclusionA cost‐efficient hardware installation of ANC with higher accuracy was offered by the SW LMS AF model. For obtaining desired convergence speed and accuracy, such models are tested for real‐time performances in the future.

Heartbeat Cardiac Sounds Analysis

Phonocardiography provides the clinician with a complementary tool to record the heart sounds heard during auscultation. This paper presents an algorithm for the detection of heart sounds (the first and second sounds, S1 and S2) and heart murmurs. Secondly the heartbeat cardiac sounds represented by the phonocardiogram (PCG) signal once segmented is one of the useful approaches to explore cardiac activity and extract many features to help researchers develop techniques that can be used for the medical treatment of several heart diseases. For people affected by a heart activity problem, it is a serious health problem that requires special care. In this paper, importance is given to heart murmurs and their severity to show their impact on heart rate. Heart murmurs are very widespread pathologies in the world and depending on their severity they could constitute. This paper is concerned to the segmentation of heart sounds by using state of art Hidden Markov Models technology which used to extract a smooth envelogram which enable us to apply the tests necessary for temporal localization of heart sounds and heart murmurs.

AmtNet: Attentional multi-scale temporal network for phonocardiogram signal classification

Phonocardiogram (PCG) signals reflect the mechanical activity of the heart. With the automatic diagnosis of PCG signals, cardiovascular diseases can be effectively detected. This paper presents an effective PCG signal classification model, called the attentional multi-scale temporal network (AmtNet), which is constructed by one-dimensional convolution and pooling as the basic components. AmtNet can directly classify raw PCG signals without complicated feature engineering processes. Specifically, we design a multi-scale feature extraction architecture using dense connections and three different dilated convolutional paths. We adopt a one-dimensional convolutional block attention module (CBAM) to adaptively refine the intermediate feature map and design a temporal pyramid pooling layer to incorporate the multi-scale temporal information. Moreover, we further study the effectiveness of several time series data augmentation and transfer learning techniques for improving the performance of AmtNet. Extensive experiments on four public PCG datasets indicate that the proposed AmtNet can achieve competitive results for PCG signal classification.

A Hardware-Software System for Accurate Segmentation of Phonocardiogram Signal.

Phonocardiogram (PCG) signal provides valuable information for diagnosing heart diseases. However, its applications in quantitative analyses of heart function are limited because the interpretation of this signal is difficult. A key step in quantitative PCG is the identification of the first and second sounds (S1 and S2) in this signal. This study aims to develop a hardware-software system for synchronized acquisition of two signals electrocardiogram (ECG) and PCG and to segment the recorded PCG signal via the information provided in the acquired ECG signal. In this analytical study, we developed a hardware-software system for real-time identification of the first and second heart sounds in the PCG signal. A portable device to capture synchronized ECG and PCG signals was developed. Wavelet de-noising technique was used to remove noise from the signal. Finally, by fusing the information provided by the ECG signal (R-peaks and T-end) into a hidden Markov model (HMM), the first and second heart sounds were identified in the PCG signal. ECG and PCG signals from 15 healthy adults were acquired and analyzed using the developed system. The average accuracy of the system in correctly detecting the heart sounds was 95.6% for S1 and 93.4% for S2. The presented system is cost-effective, user-friendly, and accurate in identifying S1 and S2 in PCG signals. Therefore, it might be effective in quantitative PCG and diagnosing heart diseases.

Chest-Worn Self-Injection-Locked Oscillator Tag for Monitoring Heart Sounds

This letter presents a heart sound monitoring system with a chest-worn sensor without contact with the skin. A self-injection-locked oscillator (SILO) and tag antenna are the essential components of the sensor, which operates at 5.8 GHz. The sensor uses the tag antenna to transmit the SILO output signal whose frequency is modulated by the Doppler effect that is caused by the chest movement, to a remote frequency modulation (FM) receiver for extracting the heart sounds. The tag antenna comprises a loop antenna and a concentric loop (CL) in a stack to improve the directivity toward the chest. Experiments were conducted at several auscultation sites to identify the four major heart sounds—the first heart sound (S1), the second heart sound (S2), systole, and diastole—based on a hidden semi-Markov model (HSMM). The results thus obtained correlate well with phonocardiogram (PCG) measurements.

Transfer learning based heart valve disease classification from Phonocardiogram signal

Physiological conditions that prevent heart valves from functioning precisely to ensure proper blood circulation are known as heart valve disorder (HVD). Detection of HVD is critical as untreated heart valve disease often develops life-threatening cardiac diseases. Typical HVD detection methods, like echocardiography, MRI, and cardiac CT, are costly, complex, and require robust healthcare infrastructure. Although, by simple non-invasive listening to heart sound irregularities, an expert physician can anticipate the signs of HVD from ancient times. Contemporary development suggests that with machine learning-based algorithms, a graphical representation of heart sound, known as the phonocardiogram (PCG), can effectively predict the anomaly in the valvular activity. In recent studies, deep learning-based strategies showed promising results in the PCG classification task but demand extensive resources and training data. This work investigates the merits of transfer learning (TL) using pre-trained convolution neural networks for the automatic PCG classification when data is scarce. With standard time–frequency representations (i.e., spectrogram, log-Mel spectrogram, and scalogram) as input features, audio and image-based pre-trained lightweight models are fine-tuned to categorize the PCG. The proposed YAMNet-based TL method classifies four types of HVD data collected from public heart sound databases and achieves overall accuracy, sensitivity, and specificity of 99.83%, 99.59%, and 99.90%, respectively. Alongside, it classifies the PhysioNet/CinC Challenge 2016 dataset into binary classes with 92.23% accuracy. The study achieves high classification metrics despite data scarcity. It also investigates the proposed method’s computational efficiency and robustness against practical noise contamination for performance evaluation in a possible real-life scenario.

An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

Background and objectives:Valvular heart diseases (VHDs) are one of the dominant causes of cardiovascular abnormalities that have been associated with high mortality rates globally. Rapid and accurate diagnosis of the early stage of VHD based on cardiac phonocardiogram (PCG) signal is critical that allows for optimum medication and reduction of mortality rate. Methods:To this end, the current study proposes novel deep learning (DL)-based high-performance VHD detection frameworks that are relatively simpler in terms of network structures, yet effective for accurately detecting multiple VHDs. We present three different frameworks considering both 1D and 2D PCG raw signals. For 1D PCG, Mel frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) features, whereas, for 2D PCG, various deep convolutional neural networks (D-CNNs) features are extracted. Additionally, nature/bio-inspired algorithms (NIA/BIA) including particle swarm optimization (PSO) and genetic algorithm (GA) have been utilized for automatic and efficient feature selection directly from the raw PCG signal. To further improve the performance of the classifier, vision transformer (ViT) has been implemented levering the self-attention mechanism on the time frequency representation (TFR) of 2D PCG signal. Our extensive study presents a comparative performance analysis and the scope of enhancement for the combination of different descriptors, classifiers, and feature selection algorithms. Main Results:Among all classifiers, ViT provides the best performance by achieving mean average accuracy Acc of 99.90 % and F1-score of 99.95 % outperforming current state-of-the-art VHD classification models. Conclusions:The present research provides a robust and efficient DL-based end-to-end PCG signal classification framework for designing a automated high-performance VHD diagnosis system.

Phonocardiogram signal classification for the detection of heart valve diseases using robust conglomerated models

The diagnosis of cardiovascular diseases is quite important in the field of medical community. An important physiological signal of human body is heart sound and it arises due to the blood turbulence and pulsing of cardiac structures. For the early diagnosis of heart diseases, the analysis of heart sounds play an important role as they contain a huge quantity of pathological information associated with heart. To detect heart sounds, Phonocardiogram (PCG) is used as it is a highly useful and non-invasive technique and can be easily analyzed well. In this paper, some efficient models are proposed for the classification of PCG signals. Two important and robust conglomerated models are proposed initially, wherein the first strategy utilizes the concept of semi-supervised Non-negative Matrix Factorization (NMF) along with Brain Storming (BS) optimization algorithm and an advanced version of BS termed as Advanced BS (ABS) is proposed and then it is merged with Genetic Programming (GP) so that new algorithms such as BS-GP and ABS-GP are formed and finally the features selected through it are fed to classification through machine learning. The second strategy utilizes the concept of using three dimensionality reduction techniques along with Fuzzy C-means (FCM) clustering and then an Advanced Sine-Cosine (ASC) optimization algorithm with three different modifications is proposed for the purpose of feature selection and finally it is classified. Deep learning techniques were also employed in the study such as the usage of an Attention based Bidirectional Long Short-Term Memory (A-BLSTM), Ordinal Variational Autoencoder (O-VAE), Conditional Variational Autoencoders (CVAE), Hyperspherical CVAE (H-CVAE) and the Restricted Boltzmann Machine based Deep Belief Network (RBM-DBN) for the classification of PCG signals. The experiment is conducted on a publicly available dataset and results show that a high classification accuracy of 95.39% is obtained for the semi-supervised NMF concept with ABS-GP technique and Support Vector Machine (SVM) classifier.

Phonocardiography (PCG)-based early detection of heart anomalies using deep learning

A simple-to-use and cost-effective Phonocardiography (PCG)-based system is proposed for the early detection of cardiovascular anomalies. A summary is provided related to the main results of a comparative study of various signal processing and deep learning techniques applied to PCG signals to automatically differentiate normal heart sounds from five types of common murmurs. Initial results indicate an average of over 92 % and 71 % heart anomaly detection and classification rates, respectively. This is accomplished using a 5-layer-Deep Neural Network (DNN) with 100 neurons per layer using the Hyperbolic Tangent (tanh) as an activation function. The Discrete Wavelet Transform (DWT) and Heart Sound Envelogram (HSE) were found to be best in respectively denoising and segmenting the PCG signal. Mel Frequency Cepstral Coefficients (MFCC) Features were found to outperform their Frequency and Time Domain counterparts and were used to train and run the DNN. The proposed system should be useful in providing early warnings and initial indications to potentially sick people directing them to cardiologists in order to pursue more accurate diagnostics, making it a handy home-care tool in the context of smart and preventive public health systems.

Phonocardiogram transfer learning-based CatBoost model for diastolic dysfunction identification using multiple domain-specific deep feature fusion

Left ventricular diastolic dyfunction detection is particularly important in cardiac function screening. This paper proposed a phonocardiogram (PCG) transfer learning-based CatBoost model to detect diastolic dysfunction noninvasively. The Short-Time Fourier Transform (STFT), Mel Frequency Cepstral Coefficients (MFCCs), S-transform and gammatonegram were utilized to perform four different representations of spectrograms for learning the representative patterns of PCG signals in two-dimensional image modality. Then, four pre-trained convolutional neural networks (CNNs) such as VGG16, Xception, ResNet50 and InceptionResNetv2 were employed to extract multiple domain-specific deep features from PCG spectrograms using transfer learning, respectively. Further, principal component analysis and linear discriminant analysis (LDA) were applied to different feature subsets, respectively, and then these different selected features are fused and fed into CatBoost for classification and performance comparison. Finally, three typical machine learning classifiers such as multilayer perceptron, support vector machine and random forest were employed to compared with CatBoost. The hyperparameter optimization of the investigated models was determined through grid search. The visualized result of the global feature importance showed that deep features extracted from gammatonegram by ResNet50 contributed most to classification. Overall, the proposed multiple domain-specific feature fusion based CatBoost model with LDA achieved the best performance with an area under the curve of 0.911, accuracy of 0.882, sensitivity of 0.821, specificity of 0.927, F1-score of 0.892 on the testing set. The PCG transfer learning-based model developed in this study could aid in diastolic dysfunction detection and could contribute to non-invasive evaluation of diastolic function.

Classifying the heart sound signals using textural‐based features for an efficient decision support system

AbstractCardiovascular diseases have surpassed cancer as the leading cause of death on the planet today. Numerous decision‐making systems with computer‐assisted support have been developed to assist cardiologists to detect heart disease, and thus, lowering the mortality rate. The purpose of this research is to classify audio signals received from the heart as normal or abnormal. The PhysioNet Computing in Cardiology (CinC) 2016 benchmark dataset, popularly known as PhysioNet 2016, has been used to validate the proposed methodology presented here. PhysioNet 2016 contains a total of 3200 phonocardiogram (PCG) recordings divided into sub‐datasets A‐F. The state‐of‐the‐art studies conducted till date have not considered the harmonic details of the beat that can be extracted from its equivalent chromagram image. In this work, textural features such as linear binary pattern (LBP), adaptive‐LBP, and ring‐LBP have been extracted from the existing spectrogram and combined with the features extracted from the chromagram. It has been observed that the combination of features extracted from both the image variants has resulted in a greater accuracy as compared to the scenario where researchers were using only the spectrogram. The experiment yielded the mean accuracy, precision, and F1‐score as 94.87, 93.11, and 95.273, respectively. The heart sound classification models employ spectrogram, scalogram, and mel‐spectrogram images to view and analyse the acoustic properties of a PCG signal. Although these visual tools provide useful information about the signal, yet they are unable to distinguish between pitch and resonance in heart sound generation. However, this paper proposes an alternative approach of heart sound signal representation that allows for a more precise measure of pitch‐related changes in the heart sound. Its results highlight the significance of extracting textural features from time‐chroma representation (i.e., chromagram) of PCG signals that have not been explored yet in the domain related to classification of heart sound signals as normal and abnormal.

Generalized Generative Deep Learning Models for Biosignal Synthesis and Modality Transfer.

Generative Adversarial Networks (GANs) are a revolutionary innovation in machine learning that enables the generation of artificial data. Artificial data synthesis is valuable especially in the medical field where it is difficult to collect and annotate real data due to privacy issues, limited access to experts, and cost. While adversarial training has led to significant breakthroughs in the computer vision field, biomedical research has not yet fully exploited the capabilities of generative models for data generation, and for more complex tasks such as biosignal modality transfer. We present a broad analysis on adversarial learning on biosignal data. Our study is the first in the machine learning community to focus on synthesizing 1D biosignal data using adversarial models. We consider three types of deep generative adversarial networks: a classical GAN, an adversarial AE, and a modality transfer GAN; individually designed for biosignal synthesis and modality transfer purposes. We evaluate these methods on multiple datasets for different biosignal modalites, including phonocardiogram (PCG), electrocardiogram (ECG), vectorcardiogram and 12-lead electrocardiogram. We follow subject-independent evaluation protocols, by evaluating the proposed models' performance on completely unseen data to demonstrate generalizability. We achieve superior results in generating biosignals, specifically in conditional generation, by synthesizing realistic samples while preserving domain-relevant characteristics. We also demonstrate insightful results in biosignal modality transfer that can generate expanded representations from fewer input-leads, ultimately making the clinical monitoring setting more convenient for the patient. Furthermore our longer duration ECGs generated, maintain clear ECG rhythmic regions, which has been proven using ad-hoc segmentation models.

Detection of Phonocardiogram Event Patterns in Mitral Valve Prolapse: An Automated Clinically Relevant Explainable Diagnostic Framework

The objective of this study is to develop an automated clinically relevant diagnostic framework for a group of cardiovascular diseases, namely, valvular heart diseases (VHDs). Though for clinical screening, manual auscultation using a stethoscope is the current standard, it is losing its significance due to the demand for years of skill and experience from the clinician. While the physiological location for capturing heart sound signal, called phonocardiogram (PCG), is standardized, the measurement and classification of PCG into different VHDs need automation to redeem its importance. Recent research on the applicability of machine learning (ML) and deep learning (DL) in PCG-based classification of VHDs produced high accuracy, but often loses the clinical explanation behind them, and hence, often not endorsed by the healthcare fraternity. The proposed study attempts to bridge this gap with two types of clinically explainable automated frameworks: 1) one utilizes clinically relevant PCG features in statistical rule-based models (RBM) as well as ML-based decision-tree (DT) frameworks; 2) the other uses time-frequency representation (TFR) with 2-D convolution neural network (CNN) and signal of PCG cycle with 1-D CNN, reveals similar clinically explainable intelligence. As a case study, mitral valve prolapse (MVP) − a specific VHD categorized into three severity subclasses of early systolic click (ESC), ESC with murmur (ESCM), and mid-SC with murmur (MSCM). The signature events (S1, S2, SC, and murmur) in PCG are segmented using a novel Teager–Kaiser energy operator and continuous wavelet transform (TKEO-CWT) algorithm. Clinically relevant intra- and inter-event features like duration, intensity, and pitch (dominant frequency) in RBM and DT produced 100% and 98.6% accuracies, respectively. Interestingly, gradient class activation (Grad-CAM) of 1-D and 2-D CNN with PCG signal and scalogram as input also converges to the same clinical explanations. Thus, the proposed clinically explainable frameworks demonstrate excellent potential in measurements and classifications in future clinical diagnostic products.

Explainable Deep Convolutional Neural Network for Valvular Heart Diseases Classification Using PCG Signals

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective</i> : The heart sounds, recorded through a phonocardiogram (PCG) can assist in the early detection of valvular heart diseases (VHD), which is important for minimizing the chances of cardiac complications like heart failure and sudden cardiac death. Despite a large number of previous studies with highly accurate classifications, PCG-based deep learning (DL) methods for VHD detection are not suitable for clinical practice as they lack transparency and interpretability. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> The proposed work utilizes analytic continuous wavelet transform (CWT) scalograms as the time-frequency representations (TFR) of the PCG signals. A 2D convolutional neural network (CNN) is designed for the multiclass classification (Aortic stenosis, Mitral regurgitation, Mitral stenosis, Mitral valve prolapse, Normal) of PCG signal’s TFR. Besides introducing a VHD classification method in this paper, we also carry out the interpretation of the proposed CNN architecture by using occlusion maps and deep dream images for local and global explanations respectively. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> The highest accuracy achieved during fivefold cross validation is 99.6% and the overall accuracy is 98.32% for a publicly available PCG database. The accuracy of the proposed method for binary classification (Abnormal, Normal), tested on the PhysioNet database is 93.07%. DL visualization methods assisted in determining what features or regions of TFR of PCGs the proposed network was “looking at” for making a class-specific correct prediction. Class-specific morphological and timefrequency features were observed. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusion:</i> DL visualization makes the network decision more reliable. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Significance:</i> The novel classification framework along with its interpretations would enable successful clinical translation of PCG-based VHD detection.

Robust Denoising of Phonocardiogram Signals using Time-Frequency Analysis and U-Nets

Cardiovascular diseases are the cause of many deaths worldwide every day. Automated cardiac auscultation is a promising diagnosis method; however, one of its main disadvantages is that it is prone to receiving too much noise during sound recording, which hinders diagnosis. In the available literature, most phonocardiogram (PCG) denoising methods have been evaluated using only synthetic sources such as white noise; this work proposes a more realistic approach. In this paper, the denoising process occurs in the time-frequency domain. More specifically, we compute the Short-Time Fourier Transform (STFT) of the contaminated PCG signal and train a U-Net to recognize normal and pathological cardiac sounds from noise. We are unaware of previous attempts to develop a robust PCG-denoising algorithm capable of simultaneously removing noise signals from four different sources: additive white Gaussian noise (AWGN), additive pink Gaussian noise (APGN), speech, and real PCG background noise. Since we are limited by the relatively small number of clean PCG signals available, we also propose a method for high-quality phonocardiogram data augmentation. In our tests, the proposed method exhibits high performance even in unfavorable scenarios since it can denoise a PCG signal contaminated with a signal-to-noise ratio (SNR) of −5 dB with average improvements ranging from 11.85 dB up to 17.60 dB, depending on the noise type used to degrade the cardiac signal. This method could significantly improve the performance of automatic cardiac sound classification algorithms in noisy environments but could also be used in electronic stethoscopes.

1D Convolutional Neural Network for Detecting Heart Diseases using Phonocardiograms

According to estimations made by World Health Organization, heart disease is the largest cause of mortality throughout the globe, and it is safe to assume that diagnosing heart diseases in their earliest stages is very essential. Diagnosis of cardiovascular disease may be carried out by detection of interference in cardiac signals, one of which is called phonocardiography, and it can be accomplished in a number of various ways. Using phonocardiogram (PCG) inputs and deep learning, the researchers aim to develop a classification system for different types of heart illness. The slicing and normalization of the signal served as the first step in the study's signal preprocessing, which was subsequently followed by a wavelet based transformation method that employs mother wavelet analytic morlet. The results of the decomposition are first shown with the use of a scalogram, afterwards, they are utilized as input for the deep CNN. In this investigation, the analyzed PCG signals were separated into categories, denoting normal and pathological heart sounds. The entire utilized data was divided into two categories as training and test data as 80% to 20%. The developed model demonstrates the degree of clinical diagnosis, sensitivity, specificity and AUC-ROC value. As a result, it has been determined that the proposed method was superior to the mother wavelet as well as other classifier approaches. Consequently, we were able to acquire an electronic stethoscope that has a diagnostic accuracy of more than 90% when it comes to identifying cardiac problems. To be more specific, the proposed deep CNN model has an accuracy of 93.25% in identifying aberrant heart sounds and 93.50% in identifying regular heartbeats. In addition, given the fact that an examination may be completed in only 15 seconds, speed is the primary advantage offered by the suggested stethoscope.

PCG signal classification using a hybrid multi round transfer learning classifier

Diagnosis of cardiovascular diseases using Phonocardiography(PCG) is a challenging task as signal itself is cyclo-stationary. It has spectral contents which are overlapped by multiple sources having similar spectral contents but acting as noise. Moreover, length variation in the signals and sampling using different equipment also make analysis of these signal a testing task. In this research, authors have introduced a hybrid technique to counter the variations just mentioned. Our technique is composed of high resolution spectrum generation, conversion of spectral contents to Spectrogram and multi round training. Use of fixed length spectral contents makes system independent of signal length. By using Spectrogram, the deep features can be extracted from spectrum which are used as an input to Pre-trained networks (PTNs). Finally, transfer learning is applied with multiple rounds of training.The introduced methodology is validated using multiple datasets having different PCG signals, sampling frequency, signals length and signal quality. From the reported results, it is evident that Chirplet Z transform (CZT) based Spectrogram can be utilized for mutlticlass classification. If CZT based Spectrograms are passed through multi rounds of training, then accuracy can be further increased. The reported results are accurate to 99% in the case of testing for best case scenarios and even in worst case, the results dont fall below 85%. However, an important observation is that they are consistent across the experimental protocols. The computational cost associated with the introduced technique is low which makes it suitable for hardware implementation.