Improved recovery of cardiac auscultation sounds using modified cosine transform and LSTM-based masking

Obtaining accurate cardiac auscultation signals, including basic heart sounds (S1 and S2) and subtle signs of disease, is crucial for improving cardiac diagnoses and making the most of telehealth. This research paper introduces an innovative approach that utilizes a modified cosine transform (MCT) and a masking strategy based on long short-term memory (LSTM) to effectively distinguish heart sounds and murmurs from background noise and interfering sounds. The MCT is used to capture the repeated pattern of the heart sounds, while the LSTMs are trained to construct masking based on the repeated MCT spectrum. The proposed strategy's performance in maintaining the clinical relevance of heart sounds continues to demonstrate effectiveness, even in environments marked by increased noise and complex disruptions. The present work highlights the clinical significance and reliability of the suggested methodology through in-depth signal visualization and rigorous statistical performance evaluations. In comparative assessments, the proposed approach has demonstrated superior performance compared to recent algorithms, such as LU-Net and PC-DAE. Furthermore, the system's adaptability to various datasets enhances its reliability and practicality. The suggested method is a potential way to improve the accuracy of cardiovascular diagnostics in an era of rapid advancement in medical signal processing. The proposed approach showed an enhancement in the average signal-to-noise ratio (SNR) by 9.6 dB at an input SNR of - 6 dB and by 3.3 dB at an input SNR of 10 dB. The average signal distortion ratio (SDR) achieved across a variety of input SNR values was 8.56 dB.

Parameter-Efficient Densely Connected Dual Attention Network for Phonocardiogram Classification

Cardiac auscultation, exhibited by phonocardiogram (PCG), is a non-invasive and low-cost diagnostic method for cardiovascular diseases (CVDs). However, deploying it in practice is quite challenging, due to the inherent murmurs and a limited number of supervised samples in heart sound data. To solve these problems, not only heart sound analysis based on handcrafted features, but also computer-aided heart sound analysis based on deep learning have been extensively studied in recent years. Though with elaborate design, most of these methods still use additional pre-processing to improve classification performance, which heavily relies on time-consuming experienced engineering. In this article, we propose a parameter-efficient densely connected dual attention network (DDA) for heart sound classification. It combines two advantages simultaneously of the purely end-to-end architecture and enriched contextual representations of the self-attention mechanism. Specifically, the densely connected structure can automatically extract the information flow of heart sound features hierarchically. Alongside, improving contextual modeling capabilities, the dual attention mechanism adaptively aggregates local features with global dependencies via a self-attention mechanism, which captures the semantic interdependencies across position and channel axes respectively. Extensive experiments across stratified 10-fold cross-validation strongly evidence that our proposed DDA model surpasses current 1D deep models on the challenging Cinc2016 benchmark with significant computational efficiency.

Detection of valvular heart diseases combining orthogonal non-negative matrix factorization and convolutional neural networks in PCG signals

BACKGROUND AND OBJECTIVE

Valvular heart disease (VHD) is associated with elevated mortality rates. Although transthoracic echocardiography (TTE) is the gold standard detection tool, phonocardiography (PCG) could be an alternative as it is a cost-effective and noninvasive method for cardiac auscultation. Many researchers have dedicated their efforts to improving the decision-making process and developing robust and precise approaches to assist physicians in providing reliable diagnoses of VHD.

METHODS

This research proposes a novel approach for the detection of anomalous valvular heart sounds from PCG signals. The proposed approach combines orthogonal non-negative matrix factorization (ONMF) and convolutional neural network (CNN) architectures in a three-stage cascade. The aim of the proposal is to improve the learning process by identifying the optimal ONMF temporal or spectral patterns for accurate detection. In the first stage, the time-frequency representation of the input PCG signal is computed. Next, band-pass filtering is performed to locate the spectral range that is most relevant for the presence of such cardiac abnormalities. In the second stage, the temporal and spectral cardiac structures are extracted using the ONMF approach. These structures are utilized in the third stage and fed into the CNN architecture to detect abnormal heart sounds.

RESULTS

Several state-of-the-art CNN architectures, such as LeNet5, AlexNet, ResNet50, VGG16 and GoogLeNet, have been evaluated to determine the effectiveness of using ONMF temporal features for VHD detection. The results reveal that the integration of ONMF temporal features with a CNN classifier significantly improve VHD detection. Specifically, the proposed approach achieves an accuracy improvement of approximately 45% when ONMF spectral features are used and 35% when time-frequency features from the short-time Fourier transform (STFT) spectrogram are used. Additionally, feeding ONMF temporal features into low-complexity CNN architectures yields competitive results comparable to those obtained with complex architectures.

CONCLUSIONS

The temporal structure factorized by ONMF plays a critical role in distinguishing between normal heart sounds and abnormal heart sounds since the repeatability of normal heart cycles is disrupted by the presence of cardiac abnormalities. Consequently, the results highlight the importance of appropriate input data representation in the learning process of CNN models in the biomedical field of valvular heart sound detection.

A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data

Heart sounds have been extensively studied for heart disease diagnosis for several decades. Traditional machine learning algorithms applied in the literature have typically partitioned heart sounds into small windows and employed feature extraction methods to classify samples. However, as there is no optimal window length that can effectively represent the entire signal, windows may not provide a sufficient representation of the underlying data. To address this issue, this study proposes a novel approach that integrates window-based features with features extracted from the entire signal, thereby improving the overall accuracy of traditional machine learning algorithms. Specifically, feature extraction is carried out using two different time scales. Short-term features are computed from five-second fragments of heart sound instances, whereas long-term features are extracted from the entire signal. The long-term features are combined with the short-term features to create a feature pool known as long short-term features, which is then employed for classification. To evaluate the performance of the proposed method, various traditional machine learning algorithms with various models are applied to the PhysioNet/CinC Challenge 2016 dataset, which is a collection of diverse heart sound data. The experimental results demonstrate that the proposed feature extraction approach increases the accuracy of heart disease diagnosis by nearly 10%.

Monaural cardiopulmonary sound separation via complex-valued deep autoencoder and cyclostationarity

Objective.Cardiopulmonary auscultation is promising to get smart due to the emerging of electronic stethoscopes. Cardiac and lung sounds often appear mixed at both time and frequency domain, hence deteriorating the auscultation quality and the further diagnosis performance. The conventional cardiopulmonary sound separation methods may be challenged by the diversity in cardiac/lung sounds. In this study, the data-driven feature learning advantage of deep autoencoder and the common quasi-cyclostationarity characteristic are exploited for monaural separation.Approach.Different from most of the existing separation methods that only handle the amplitude of short-time Fourier transform (STFT) spectrum, a complex-valued U-net (CUnet) with deep autoencoder structure, is built to fully exploit both the amplitude and phase information. As a common characteristic of cardiopulmonary sounds, quasi-cyclostationarity of cardiac sound is involved in the loss function for training.Main results. In experiments to separate cardiac/lung sounds for heart valve disorder auscultation, the averaged achieved signal distortion ratio (SDR), signal interference ratio (SIR), and signal artifact ratio (SAR) in cardiac sounds are 7.84 dB, 21.72 dB, and 8.06 dB, respectively. The detection accuracy of aortic stenosis can be raised from 92.21% to 97.90%.Significance. The proposed method can promote the cardiopulmonary sound separation performance, and may improve the detection accuracy for cardiopulmonary diseases.

A novel heart sound segmentation algorithm via multi-feature input and neural network with attention mechanism

Objective. Heart sound segmentation (HSS), which aims to identify the exact positions of the first heart sound(S1), second heart sound(S2), the duration of S1, systole, S2, and diastole within a cardiac cycle of phonocardiogram (PCG), is an indispensable step to find out heart health. Recently, some neural network-based methods for heart sound segmentation have shown good performance.Approach. In this paper, a novel method was proposed for HSS exactly using One-Dimensional Convolution and Bidirectional Long-Short Term Memory neural network with Attention mechanism (C-LSTM-A) by incorporating the 0.5-order smooth Shannon entropy envelope and its instantaneous phase waveform (IPW), and third intrinsic mode function (IMF-3) of PCG signal to reduce the difficulty of neural network learning features.Main results. An average F1-score of 96.85 was achieved in the clinical research dataset (Fuwai Yunnan Cardiovascular Hospital heart sound dataset) and an average F1-score of 95.68 was achieved in 2016 PhysioNet/CinC Challenge dataset using the novel method.Significance. The experimental results show that this method has advantages for normal PCG signals and common pathological PCG signals, and the segmented fundamental heart sound(S1, S2), systole, and diastole signal components are beneficial to the study of subsequent heart sound classification.

Research on Monocular-Vision-Based Finger-Joint-Angle-Measurement System

The quantitative measurement of finger-joint range of motion plays an important role in assessing the level of hand disability and intervening in the treatment of patients. An industrial monocular-vision-based knuckle-joint-activity-measurement system is proposed with short measurement time and the simultaneous measurement of multiple joints. In terms of hardware, the system can adjust the light-irradiation angle and the light-irradiation intensity of the marker by actively adjusting the height of the light source to enhance the difference between the marker and the background and reduce the difficulty of segmenting the target marker and the background. In terms of algorithms, a combination of multiple-vision algorithms is used to compare the image-threshold segmentation and Hough outer- and inner linear detection as the knuckle-activity-range detection method of the system. To verify the accuracy of the visual-detection method, nine healthy volunteers were recruited for experimental validation, and the experimental results showed that the average angular deviation in the flexion/extension of the knuckle was 0.43° at the minimum and 0.59° at the maximum, and the average angular deviation in the adduction/abduction of the knuckle was 0.30° at the minimum and 0.81° at the maximum, which were all less than 1°. In the multi-angle velocimetry experiment, the time taken by the system was much less than that taken by the conventional method.

A comparative study of single-channel signal processing methods in fetal phonocardiography

Fetal phonocardiography is a non-invasive, completely passive and low-cost method based on sensing acoustic signals from the maternal abdomen. However, different types of interference are sensed along with the desired fetal phonocardiography. This study focuses on the comparison of fetal phonocardiography filtering using eight algorithms: Savitzky-Golay filter, finite impulse response filter, adaptive wavelet transform, maximal overlap discrete wavelet transform, variational mode decomposition, empirical mode decomposition, ensemble empirical mode decomposition, and complete ensemble empirical mode decomposition with adaptive noise. The effectiveness of those methods was tested on four types of interference (maternal sounds, movement artifacts, Gaussian noise, and ambient noise) and eleven combinations of these disturbances. The dataset was created using two synthetic records r01 and r02, where the record r02 was loaded with higher levels of interference than the record r01. The evaluation was performed using the objective parameters such as accuracy of the detection of S1 and S2 sounds, signal-to-noise ratio improvement, and mean error of heart interval measurement. According to all parameters, the best results were achieved using the complete ensemble empirical mode decomposition with adaptive noise method with average values of accuracy = 91.53% in the detection of S1 and accuracy = 68.89% in the detection of S2. The average value of signal-to-noise ratio improvement achieved by complete ensemble empirical mode decomposition with adaptive noise method was 9.75 dB and the average value of the mean error of heart interval measurement was 3.27 ms.

Development of an Electronic Stethoscope and a Classification Algorithm for Cardiopulmonary Sounds

With conventional stethoscopes, the auscultation results may vary from one doctor to another due to a decline in his/her hearing ability with age or his/her different professional training, and the problematic cardiopulmonary sound cannot be recorded for analysis. In this paper, to resolve the above-mentioned issues, an electronic stethoscope was developed consisting of a traditional stethoscope with a condenser microphone embedded in the head to collect cardiopulmonary sounds and an AI-based classifier for cardiopulmonary sounds was proposed. Different deployments of the microphone in the stethoscope head with amplification and filter circuits were explored and analyzed using fast Fourier transform (FFT) to evaluate the effects of noise reduction. After testing, the microphone placed in the stethoscope head surrounded by cork is found to have better noise reduction. For classifying normal (healthy) and abnormal (pathological) cardiopulmonary sounds, each sample of cardiopulmonary sound is first segmented into several small frames and then a principal component analysis is performed on each small frame. The difference signal is obtained by subtracting PCA from the original signal. MFCC (Mel-frequency cepstral coefficients) and statistics are used for feature extraction based on the difference signal, and ensemble learning is used as the classifier. The final results are determined by voting based on the classification results of each small frame. After the testing, two distinct classifiers, one for heart sounds and one for lung sounds, are proposed. The best voting for heart sounds falls at 5-45% and the best voting for lung sounds falls at 5-65%. The best accuracy of 86.9%, sensitivity of 81.9%, specificity of 91.8%, and F1 score of 86.1% are obtained for heart sounds using 2 s frame segmentation with a 20% overlap, whereas the best accuracy of 73.3%, sensitivity of 66.7%, specificity of 80%, and F1 score of 71.5% are yielded for lung sounds using 5 s frame segmentation with a 50% overlap.

Unsupervised detection and classification of heartbeats using the dissimilarity matrix in PCG signals

BACKGROUND AND OBJECTIVE

Auscultation is the first technique applied to the early diagnose of any cardiovascular disease (CVD) in rural areas and poor-resources countries because of its low cost and non-invasiveness. However, it highly depends on the physician's expertise to recognize specific heart sounds heard through the stethoscope. The analysis of phonocardiogram (PCG) signals attempts to segment each cardiac cycle into the four cardiac states (S1, systole, S2 and diastole) in order to develop automatic systems applied to an efficient and reliable detection and classification of heartbeats. In this work, we propose an unsupervised approach, based on time-frequency characteristics shown by cardiac sounds, to detect and classify heartbeats S1 and S2.

METHODS

The proposed system consists of a two-stage cascade. The first stage performs a rough heartbeat detection while the second stage refines the previous one, improving the temporal localization and also classifying the heartbeats into types S1 and S2. The first contribution is a novel approach that combines the dissimilarity matrix with the frame-level spectral divergence to locate heartbeats using the repetitiveness shown by the heart sounds and the temporal relationships between the intervals defined by the events S1/S2 and non-S1/S2 (systole and diastole). The second contribution is a verification-correction-classification process based on a sliding window that allows the preservation of the temporal structure of the cardiac cycle in order to be applied in the heart sound classification. The proposed method has been assessed using the open access databases PASCAL, CirCor DigiScope Phonocardiogram and an additional sound mixing procedure considering both Additive White Gaussian Noise (AWGN) and different kinds of clinical ambient noises from a commercial database.

RESULTS

The proposed method outperforms the detection and classification performance of other recent state-of-the-art methods. Although our proposal achieves the best average accuracy for PCG signals without cardiac abnormalities, 99.4% in heartbeat detection and 97.2% in heartbeat classification, its worst average accuracy is always above 92% for PCG signals with cardiac abnormalities, signifying an improvement in heartbeat detection/classification above 10% compared to the other state-of-the-art methods evaluated.

CONCLUSIONS

The proposed method provides the best detection/classification performance in realistic scenarios where the presence of cardiac anomalies as well as different types of clinical environmental noises are active in the PCG signal. Of note, the promising modelling of the temporal structures of the heart provided by the dissimilarity matrix together with the frame-level spectral divergence, as well as the removal of a significant number of spurious heart events and recovery of missing heart events, both corrected by the proposed verification-correction-classification algorithm, suggest that our proposal is a successful tool to be applied in heart segmentation.

A strong anti-noise segmentation algorithm based on variational mode decomposition and multi-wavelet for wearable heart sound acquisition system

Wearable devices have now been widely used in the acquisition and measurement of heart sound signals with good effect. However, the wearable heart sound acquisition system (WHSAS) will face more noise compared with the traditional system, such as Gaussian white noise, powerline interference, colored noise, motion artifact noise, and lung sound noise, because users often wear these devices for running, walking, jumping or various strong noise occasions. In a strong noisy environment, WHSAS needs a high-precision segmentation algorithm. This paper proposes a segmentation algorithm based on Variational Mode Decomposition (VMD) and multi-wavelet. In the algorithm, various noises are layered and filtered out using VMD. The cleaner signal is fed into multi-wavelet to construct a time-frequency matrix. Then, the principal component analysis method is applied to reduce the dimension of the matrix. After extracting the high order Shannon envelope and Teager energy envelope of the heart sound, we accurately segment the signals. In this paper, the algorithm is verified through our developing WHSAS. The results demonstrate that the proposed algorithm can achieve high-precision segmentation of the heart sound under a mixed noise condition.

Embedded platform based heart murmur classification using deep learning approach

Ubiquitous Perturbations in cardiac auscultation properties, cardiovascular diseases (CVDs) are widely recognized. In the auscultation procedure, the appearance of pathological cardiac murmurs is linked to heart disorders. A noble automated detection system using 1-D Convolutional Neural Network (CNN) for the detection of pathological heart murmurs is proposed in this study, which removes the difficult task of extracting and selecting features. It directly acts on the phonocardiogram (PCG) signals. The fundamental purpose of this research is to develop a classification model for consistent recognition of cardiac murmurs when the data-set is imbalanced. In view of this, the proposed study for the imbalanced data-set incorporates the Adaptive Synthetic (ADASYN) approach to generate synthetic data for the minority class. The outcome analysis illustrates the positive result in the identification of heart murmurs on both balanced and imbalanced data-sets. Therefore, the developed deep learning model will learn better from the minority class and classify heart murmurs accurately.

Automatic segmentation for neonatal phonocardiogram

This work addresses the automatic segmentation of neonatal phonocardiogram (PCG) to be used in the artificial intelligence-assisted diagnosis of abnormal heart sounds. The proposed novel algorithm has a single free parameter - the maximum heart rate. The algorithm is compared with the baseline algorithm, which was developed for adult PCG segmentation. When evaluated on a large clinical dataset of neonatal PCG with a total duration of over 7h, an F1 score of 0.94 is achieved. The main features relevant for the segmentation of neonatal PCG are identified and discussed. The algorithm is able to increase the number of cardiac cycles by a factor of 5 compared to manual segmentation, potentially allowing to improve the performance of heart abnormality detection algorithms.

Unsupervised Heart Sound Decomposition and State Estimation with Generative Oscillation Models

This paper proposes a new generative probabilistic model for phonocardiograms (PCGs) that can simultaneously capture oscillatory factors and state transitions in cardiac cycles. Conventionally, PCGs have been modeled in two main aspects. One is a state space model that represents recurrent and frequently appearing state transitions. Another is a factor model that expresses the PCG as a non-stationary signal consisting of multiple oscillations. To model these perspectives in a unified framework, we combine an oscillation decomposition with a state space model. The proposed model can decompose the PCG into cardiac state dependent oscillations by reflecting the mechanism of cardiac sounds generation in an unsupervised manner. In the experiments, our model achieved better accuracy in the state estimation task compared to the empirical mode decomposition method. In addition, our model detected S2 onsets more accurately than the supervised segmentation method when distributions among PCG signals were different.

Cardiovascular Disease Recognition Based on Heartbeat Segmentation and Selection Process

Assessment of heart sounds which are generated by the beating heart and the resultant blood flow through it provides a valuable tool for cardiovascular disease (CVD) diagnostics. The cardiac auscultation using the classical stethoscope phonological cardiogram is known as the most famous exam method to detect heart anomalies. This exam requires a qualified cardiologist, who relies on the cardiac cycle vibration sound (heart muscle contractions and valves closure) to detect abnormalities in the heart during the pumping action. Phonocardiogram (PCG) signal represents the recording of sounds and murmurs resulting from the heart auscultation, typically with a stethoscope, as a part of medical diagnosis. For the sake of helping physicians in a clinical environment, a range of artificial intelligence methods was proposed to automatically analyze PCG signal to help in the preliminary diagnosis of different heart diseases. The aim of this research paper is providing an accurate CVD recognition model based on unsupervised and supervised machine learning methods relayed on convolutional neural network (CNN). The proposed approach is evaluated on heart sound signals from the well-known, publicly available PASCAL and PhysioNet datasets. Experimental results show that the heart cycle segmentation and segment selection processes have a direct impact on the validation accuracy, sensitivity (TPR), precision (PPV), and specificity (TNR). Based on PASCAL dataset, we obtained encouraging classification results with overall accuracy 0.87, overall precision 0.81, and overall sensitivity 0.83. Concerning Micro classification results, we obtained Micro accuracy 0.91, Micro sensitivity 0.83, Micro precision 0.84, and Micro specificity 0.92. Using PhysioNet dataset, we achieved very good results: 0.97 accuracy, 0.946 sensitivity, 0.944 precision, and 0.946 specificity.

Can empirical mode decomposition improve heartbeat detection in fetal phonocardiography signals?

BACKGROUND AND OBJECTIVE

A fetal phonocardiography signal can be hard to interpret and classify due to various sources of additive noise in the womb, spanning from fetal movement to maternal heart sounds. Nevertheless, the non-invasive nature of the method makes it potentially suitable for long-term monitoring of fetal health, especially since it can be implemented on ubiquitous devices such as smartphones. We have employed empirical mode decomposition for the extraction of intrinsic mode functions that would enable the utilization of additional characteristics from the signal.

METHODS

Fetal heart recordings from 7 pregnant women in the 3rd trimester or pregnancy were taken in parallel with a measurement microphone and a portable Doppler device. Signal peaks positions from the Doppler were taken as the locations of S1 heart sounds and subsequently used as classification labels for the microphone signal. After employing a moving window approach for segmentation, more than 7600 observations were stored in the final dataset. The 135 extracted features consisted of typical audio temporal and spectral characteristics, each taken from separate sets of audio signals and intrinsic mode functions. We have used a number of metrics and methods to validate the usability of features, including univariate analysis of feature ranking and importance. Furthermore, we have used machine learning to train a number of classifiers to validate the usability of features based on intrinsic mode functions, taking prediction accuracy as the comparison metric.

RESULTS

Features extracted from intrinsic mode functions combined with audio features significantly improve accuracy in comparison to using only audio features. The improvements of detection accuracy obtained with a selected set of combined features spanned from 3.8% to even 10.3% based on the employed classifier.

CONCLUSIONS

We have utilized empirical mode decomposition as a method of extracting features relevant for fetal heartbeat classification. The results show consistent improvements in detection accuracy when these characteristics are added to a set of conventional audio features. This implies substantial benefits of applying empirical mode decomposition and lays the groundwork for future research on fetal heartbeat detection.

Cross-Domain Transfer Learning for PCG Diagnosis Algorithm

Cardiechema is a way to reflect cardiovascular disease where the doctor uses a stethoscope to help determine the heart condition with a sound map. In this paper, phonocardiogram (PCG) is used as a diagnostic signal, and a deep learning diagnostic framework is proposed. By improving the architecture and modules, a new transfer learning and boosting architecture is mainly employed. In addition, a segmentation method is designed to improve on the existing signal segmentation methods, such as R wave to R wave interval segmentation and fixed segmentation. For the evaluation, the final diagnostic architecture achieved a sustainable performance with a public PCG database.

End-to-end heart sound segmentation using deep convolutional recurrent network

Heart sound segmentation (HSS) aims to detect the four stages (first sound, systole, second heart sound and diastole) from a heart cycle in a phonocardiogram (PCG), which is an essential step in automatic auscultation analysis. Traditional HSS methods need to manually extract the features before dealing with HSS tasks. These artificial features highly rely on extraction algorithms, which often result in poor performance due to the different operating environments. In addition, the high-dimension and frequency characteristics of audio also challenge the traditional methods in effectively addressing HSS tasks. This paper presents a novel end-to-end method based on convolutional long short-term memory (CLSTM), which directly uses audio recording as input to address HSS tasks. Particularly, the convolutional layers are designed to extract the meaningful features and perform the downsampling, and the LSTM layers are developed to conduct the sequence recognition. Both components collectively improve the robustness and adaptability in processing the HSS tasks. Furthermore, the proposed CLSTM algorithm is easily extended to other complex heart sound annotation tasks, as it does not need to extract the characteristics of corresponding tasks in advance. In addition, the proposed algorithm can also be regarded as a powerful feature extraction tool, which can be integrated into the existing models for HSS. Experimental results on real-world PCG datasets, through comparisons to peer competitors, demonstrate the outstanding performance of the proposed algorithm.

Research on Segmentation and Classification of Heart Sound Signals Based on Deep Learning

The heart sound signal is one of the signals that reflect the health of the heart. Research on the heart sound signal contributes to the early diagnosis and prevention of cardiovascular diseases. As a commonly used deep learning network, convolutional neural network (CNN) has been widely used in images. In this paper, the method of analyzing heart sound through using CNN has been studied. Firstly, the original data set was preprocessed, and then the heart sounds were segmented on U-net, based on the deep CNN. Finally, the classification of heart sounds was completed through CNN. The data from 2016 PhysioNet/CinC Challenge was utilized for algorithm validation, and the following results were obtained. When the heart sound segmented, the overall accuracy rate was 0.991, the accuracy of the first heart sound was 0.991, the accuracy of the systolic period was 0.996, the accuracy of the second heart sound was 0.996, and the accuracy of the diastolic period was 0.997, and the average accuracy rate was 0.995; While in classification, the accuracy was 0.964, the sensitivity was 0.781, and the specificity was 0.873. These results show that deep learning based on CNN shows good performance in the segmentation and classification of the heart sound signal.

Deep Layer Kernel Sparse Representation Network for the Detection of Heart Valve Ailments from the Time-Frequency Representation of PCG Recordings

The heart valve ailments (HVAs) are due to the defects in the valves of the heart and if untreated may cause heart failure, clots, and even sudden cardiac death. Automated early detection of HVAs is necessary in the hospitals for proper diagnosis of pathological cases, to provide timely treatment, and to reduce the mortality rate. The heart valve abnormalities will alter the heart sound and murmurs which can be faithfully captured by phonocardiogram (PCG) recordings. In this paper, a time-frequency based deep layer kernel sparse representation network (DLKSRN) is proposed for the detection of various HVAs using PCG signals. Spline kernel-based Chirplet transform (SCT) is used to evaluate the time-frequency representation of PCG recording, and the features like L1-norm (LN), sample entropy (SEN), and permutation entropy (PEN) are extracted from the different frequency components of the time-frequency representation of PCG recording. The DLKSRN formulated using the hidden layers of extreme learning machine- (ELM-) autoencoders and kernel sparse representation (KSR) is used for the classification of PCG recordings as normal, and pathology cases such as mitral valve prolapse (MVP), mitral regurgitation (MR), aortic stenosis (AS), and mitral stenosis (MS). The proposed approach has been evaluated using PCG recordings from both public and private databases, and the results demonstrated that an average sensitivity of 100%, 97.51%, 99.00%, 98.72%, and 99.13% are obtained for normal, MVP, MR, AS, and MS cases using the hold-out cross-validation (CV) method. The proposed approach is applicable for the Internet of Things- (IoT-) driven smart healthcare system for the accurate detection of HVAs.

Heart Disease Prediction System Using Decision Tree and Naive Bayes Algorithm

The huge information of healthcare data is collected from the healthcare industry which is not "mined" unfortunately to make effective decision making for the identification of hidden information. The end user support system is used as the prediction application for the heart disease and this paper proposes windows through the intelligent prediction system the instance guidance for the heart disease is given to the user. Various symptoms of the heart diseases are fed into the application. The user precedes the processes by checking the specific detail and symptoms of the heart disease. The decision tree (ID3) and navie Bayes techniques in data mining are used to retrieve the details associated with each patient. Based on the accurate result prediction, the performance of the system is analyzed.

Temporal Convolutional Network Connected with an Anti-Arrhythmia Hidden Semi-Markov Model for Heart Sound Segmentation

Heart sound segmentation (HSS) is a critical step in heart sound processing, where it improves the interpretability of heart sound disease classification algorithms. In this study, we aimed to develop a real-time algorithm for HSS by combining the temporal convolutional network (TCN) and the hidden semi-Markov model (HSMM), and improve the performance of HSMM for heart sounds with arrhythmias. We experimented with TCN and determined the best parameters based on spectral features, envelopes, and one-dimensional CNN. However, the TCN results could contradict the natural fixed order of S1-systolic-S2-diastolic of heart sound, and thereby the Viterbi algorithm based on HSMM was connected to correct the order errors. On this basis, we improved the performance of the Viterbi algorithm when detecting heart sounds with cardiac arrhythmias by changing the distribution and weights of the state duration probabilities. The public PhysioNet Computing in Cardiology Challenge 2016 data set was employed to evaluate the performance of the proposed algorithm. The proposed algorithm achieved an F1 score of 97.02%, and this result was comparable with the current state-of-the-art segmentation algorithms. In addition, the proposed enhanced Viterbi algorithm for HSMM corrected 30 out of 30 arrhythmia errors after checking one by one in the dataset.

Comparison of Frontal-Temporal Channels in Epilepsy Seizure Prediction Based on EEMD-ReliefF and DNN

Epilepsy patients who do not have their seizures controlled with medication or surgery live in constant fear. The psychological burden of uncertainty surrounding the occurrence of random seizures is one of the most stressful and debilitating aspects of the disease. Despite the research progress in this field, there is a need for a non-invasive prediction system that helps disrupt the seizure epileptiform. Electroencephalogram (EEG) signals are non-stationary, nonlinear and vary with each patient and every recording. Full use of the non-invasive electrode channels is impractical for real-time use. We propose two frontal-temporal electrode channels based on ensemble empirical mode decomposition (EEMD) and Relief methods to address these challenges. The EEMD decomposes the segmented data frame in the ictal state into its intrinsic mode functions, and then we apply Relief to select the most relevant oscillatory components. A deep neural network (DNN) model learns these features to perform seizure prediction and early detection of patient-specific EEG recordings. The model yields an average sensitivity and specificity of 86.7% and 89.5%, respectively. The two-channel model shows the ability to capture patterns from brain locations for non-fontal-temporal seizures.

CLASSIFICATION OF PHONOCARDIOGRAM SIGNALS BASED ON ENVELOPE OPTIMIZATION MODEL AND SUPPORT VECTOR MACHINE

The prevention and diagnosis of cardiovascular diseases have become one of the primary problems in the medical community since the mortality of this kind of diseases accounts for 31% of global deaths in 2016. Heart sound, which is an important physiological signal of human body, mainly comes from the pulsing of cardiac structures and blood turbulence. The analysis of heart sounds plays an irreplaceable role in early diagnosis of heart disease since they contain a large amount of pathological information about each part of human heart. Heart sounds can be detected and recorded by Phonocardiogram (PCG). As a noninvasive method to detect and diagnose heart disease, PCG signals have been paid more and more attention by researchers. In this paper, a novel envelope extraction model is proposed and used to estimate the cardiac cycle of each PCG signal. We present a strategy combining empirical mode decomposition (EMD) technique and the proposed envelope model to extract the time-domain features. After applying EMD process to each PCG signal, the second intrinsic mode function is chosen for further analysis. Based on the proposed envelope model, the cardiac cycles of PCG signals can be estimated and then the time-domain features can be extracted. Combining with the frequency-domain features and wavelet-domain features, the feature vectors are obtained. Finally, the support vector machine (SVM) classifier is used to detect the normal and abnormal PCG signals. Two public datasets are used to test our framework in this paper. And classification accuracies of more than [Formula: see text] on both datasets show the effectiveness of the proposed model.

Segmentation of Radar-Recorded Heart Sound Signals Using Bidirectional LSTM Networks

Sounds caused by the action of the heart reflect both its health as well as deficiencies and are examined by physicians since antiquity. Pathologies of the valves, e.g. insufficiencies and stenosis, cardiac effusion, arrhythmia, inflammation of the surrounding tissue and other diagnosis can be reached by experienced physicians. However, practice is needed to assess the findings correctly. Furthermore, stethoscopes do not allow for long-term monitoring of a patient. Recently, radar technology has shown the ability to perform continuous touchless and thereby burden-free heart sound measurements. In order to perform automated classification of the signals, the first and most important step is to segment the heart sounds into their physiological phases. This paper examines the use of different Long Short-Term Memory (LSTM) architectures for this purpose based on a large dataset of radar-recorded heart sounds gathered from 30 different test persons in a clinical study. The best-performing network, a bidirectional LSTM, achieves a sample-wise accuracy of 93.4 % and a F1 score for the first heart sound of 95.8 %.

Machine Listening for Heart Status Monitoring: Introducing and Benchmarking HSS - the Heart Sounds Shenzhen Corpus

Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).

A Markov-Switching Model Approach to Heart Sound Segmentation and Classification

OBJECTIVE

We consider challenges in accurate segmentation of heart sound signals recorded under noisy clinical environments for subsequent classification of pathological events. Existing state-of-the-art solutions to heart sound segmentation use probabilistic models such as hidden Markov models (HMMs), which, however, are limited by its observation independence assumption and rely on pre-extraction of noise-robust features.

METHODS

We propose a Markov-switching autoregressive (MSAR) process to model the raw heart sound signals directly, which allows efficient segmentation of the cyclical heart sound states according to the distinct dependence structure in each state. To enhance robustness, we extend the MSAR model to a switching linear dynamic system (SLDS) that jointly model both the switching AR dynamics of underlying heart sound signals and the noise effects. We introduce a novel algorithm via fusion of switching Kalman filter and the duration-dependent Viterbi algorithm, which incorporates the duration of heart sound states to improve state decoding.

RESULTS

Evaluated on Physionet/CinC Challenge 2016 dataset, the proposed MSAR-SLDS approach significantly outperforms the hidden semi-Markov model (HSMM) in heart sound segmentation based on raw signals and comparable to a feature-based HSMM. The segmented labels were then used to train Gaussian-mixture HMM classifier for identification of abnormal beats, achieving high average precision of 86.1% on the same dataset including very noisy recordings.

CONCLUSION

The proposed approach shows noticeable performance in heart sound segmentation and classification on a large noisy dataset.

SIGNIFICANCE

It is potentially useful in developing automated heart monitoring systems for pre-screening of heart pathologies.

Classification of Heart Sounds Based on the Wavelet Fractal and Twin Support Vector Machine

Heart is an important organ of human beings. As more and more heart diseases are caused by people’s living pressure or habits, the diagnosis and treatment of heart diseases also require technical improvement. In order to assist the heart diseases diagnosis, the heart sound signal is used to carry a large amount of cardiac state information, so that the heart sound signal processing can achieve the purpose of heart diseases diagnosis and treatment. In order to quickly and accurately judge the heart sound signal, the classification method based on Wavelet Fractal and twin support vector machine (TWSVM) is proposed in this paper. Firstly, the original heart sound signal is decomposed by wavelet transform, and the wavelet decomposition coefficients of the signal are extracted. Then the two-norm eigenvectors of the heart sound signal are obtained by solving the two-norm values of the decomposition coefficients. In order to express the feature information more abundantly, the energy entropy of the decomposed wavelet coefficients is calculated, and then the energy entropy characteristics of the signal are obtained. In addition, based on the fractal dimension, the complexity of the signal is quantitatively described. The box dimension of the heart sound signal is solved by the binary box dimension method. So its fractal dimension characteristics can be obtained. The above eigenvectors are synthesized as the eigenvectors of the heart sound signal. Finally, the twin support vector machine (TWSVM) is applied to classify the heart sound signals. The proposed algorithm is verified on the PhysioNet/CinC Challenge 2016 heart sound database. The experimental results show that this proposed algorithm based on twin support vector machine (TWSVM) is superior to the algorithm based on support vector machine (SVM) in classification accuracy and speed. The proposed algorithm achieves the best results with classification accuracy 90.4%, sensitivity 94.6%, specificity 85.5% and F1 Score 95.2%.

Analysis of PCG signals using quality assessment and homomorphic filters for localization and classification of heart sounds

BACKGROUND AND OBJECTIVE

Accurate localization of heart beats in phonocardiogram (PCG) signal is very crucial for correct segmentation and classification of heart sounds into S1 and S2. This task becomes challenging due to inclusion of noise in acquisition process owing to number of different factors. In this paper we propose a system for heart sound localization and classification into S1 and S2. The proposed system introduces the concept of quality assessment before localization, feature extraction and classification of heart sounds.

METHODS

The signal quality is assessed by predefined criteria based upon number of peaks and zero crossing of PCG signal. Once quality assessment is performed, then heart beats within PCG signal are localized, which is done by envelope extraction using homomorphic envelogram and finding prominent peaks. In order to classify localized peaks into S1 and S2, temporal and time-frequency based statistical features have been used. Support Vector Machine using radial basis function kernel is used for classification of heart beats into S1 and S2 based upon extracted features. The performance of the proposed system is evaluated using Accuracy, Sensitivity, Specificity, F-measure and Total Error. The dataset provided by PASCAL classifying heart sound challenge is used for testing.

RESULTS

Performance of system is significantly improved by quality assessment. Results shows that proposed Localization algorithm achieves accuracy up to 97% and generates smallest total average error among top 3 challenge participants. The classification algorithm achieves accuracy up to 91%.

CONCLUSION

The system provides firm foundation for the detection of normal and abnormal heart sounds for cardiovascular disease detection.

Radar-Based Heart Sound Detection

This paper introduces heart sound detection by radar systems, which enables touch-free and continuous monitoring of heart sounds. The proposed measurement principle entails two enhancements in modern vital sign monitoring. First, common touch-based auscultation with a phonocardiograph can be simplified by using biomedical radar systems. Second, detecting heart sounds offers a further feasibility in radar-based heartbeat monitoring. To analyse the performance of the proposed measurement principle, 9930 seconds of eleven persons-under-tests’ vital signs were acquired and stored in a database using multiple, synchronised sensors: a continuous wave radar system, a phonocardiograph (PCG), an electrocardiograph (ECG), and a temperature-based respiration sensor. A hidden semi-Markov model is utilised to detect the heart sounds in the phonocardiograph and radar data and additionally, an advanced template matching (ATM) algorithm is used for state-of-the-art radar-based heartbeat detection. The feasibility of the proposed measurement principle is shown by a morphology analysis between the data acquired by radar and PCG for the dominant heart sounds S1 and S2: The correlation is 82.97 ± 11.15% for 5274 used occurrences of S1 and 80.72 ± 12.16% for 5277 used occurrences of S2. The performance of the proposed detection method is evaluated by comparing the F-scores for radar and PCG-based heart sound detection with ECG as reference: Achieving an F1 value of 92.22 ± 2.07%, the radar system approximates the score of 94.15 ± 1.61% for the PCG. The accuracy regarding the detection timing of heartbeat occurrences is analysed by means of the root-mean-square error: In comparison to the ATM algorithm (144.9 ms) and the PCG-based variant (59.4 ms), the proposed method has the lowest error value (44.2 ms). Based on these results, utilising the detected heart sounds considerably improves radar-based heartbeat monitoring, while the achieved performance is also competitive to phonocardiography.

Heart Sound Segmentation-An Event Detection Approach Using Deep Recurrent Neural Networks

OBJECTIVE

In this paper, we accurately detect the state-sequence first heart sound (S1)-systole-second heart sound (S2)-diastole, i.e., the positions of S1 and S2, in heart sound recordings. We propose an event detection approach without explicitly incorporating a priori information of the state duration. This renders it also applicable to recordings with cardiac arrhythmia and extendable to the detection of extra heart sounds (third and fourth heart sound), heart murmurs, as well as other acoustic events.

METHODS

We use data from the 2016 PhysioNet/CinC Challenge, containing heart sound recordings and annotations of the heart sound states. From the recordings, we extract spectral and envelope features and investigate the performance of different deep recurrent neural network (DRNN) architectures to detect the state sequence. We use virtual adversarial training, dropout, and data augmentation for regularization.

RESULTS

We compare our results with the state-of-the-art method and achieve an average score for the four events of the state sequence of ${\bf F}_{1}\approx 96$% on an independent test set.

CONCLUSION

Our approach shows state-of-the-art performance carefully evaluated on the 2016 PhysioNet/CinC Challenge dataset.

SIGNIFICANCE

In this work, we introduce a new methodology for the segmentation of heart sounds, suggesting an event detection approach with DRNNs using spectral or envelope features.

Empirical Mode Decomposition and Monogenic Signal-Based Approach for Quantification of Myocardial Infarction From MR Images

Quantification of myocardial infarction on late Gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) images into heterogeneous infarct periphery (or gray zone) and infarct core plays an important role in cardiac diagnosis, especially in identifying patients at high risk of cardiovascular mortality. However, quantification task is challenging due to noise corrupted in cardiac MR images, the contrast variation, and limited resolution of images. In this study, we propose a novel approach for automatic myocardial infarction quantification, termed DEMPOT, which consists of three key parts: Decomposition of image into intrinsic modes, monogenic phase performing on combined dominant modes, and multilevel Otsu thresholding on the phase. In particular, inspired by the Hilbert-Huang transform, we perform the multidimensional ensemble empirical mode decomposition and 2-D generalization of the Hilbert transform known as the Riesz transform on the MR image to obtain the monogenic phase that is robust to noise and contrast variation. Then, a two-stage algorithm using multilevel Otsu thresholding is accomplished on the monogenic phase to automatically quantify the myocardium into healthy, gray zone, and infarct core regions. Experiments on LGE-CMR images with myocardial infarction from 82 patients show the superior performance of the proposed approach in terms of reproducibility, robustness, and effectiveness.

Detecting fetal heart sounds by means of Fractal Dimension analysis in the Wavelet domain

Phonocardiography is a low-cost technique for the detection of fetal heart sounds (FHS) that can extend clinical auscultation in mobile and home care setups. The work presented here examines the transferability of a Wavelet Transform (WT)-based method that combines also Fractal Dimension (FD) analysis, previously proposed as WT-FD for the cases of lung and bowel sound analysis [4], to the extraction of FHSs. The WT-FD method has been evaluated with 12 simulated FHS signals and has shown promising results in terms of accuracy and performance (89%) in identifying the location of heartbeat, even in cases of signals with additive noise up to (6dB). This robustness paves the way for WT-FD testing in real FHSs, recorded under clinical setting, clearly contributing to better evaluation of the fetal heart functionality.

Fetal Heart Sounds Detection Using Wavelet Transform and Fractal Dimension

Phonocardiography is a non-invasive technique for the detection of fetal heart sounds (fHSs). In this study, analysis of fetal phonocardiograph (fPCG) signals, in order to achieve fetal heartbeat segmentation, is proposed. The proposed approach (namely WT–FD) is a wavelet transform (WT)-based method that combines fractal dimension (FD) analysis in the WT domain for the extraction of fHSs from the underlying noise. Its adoption in this field stems from its successful use in the fields of lung and bowel sounds de-noising analysis. The efficiency of the WT–FD method in fHS extraction has been evaluated with 19 simulated fHS signals, created for the present study, with additive noise up to (3 dB), along with the simulated fPCGs database available at PhysioBank. Results have shown promising performance in the identification of the correct location and morphology of the fHSs, reaching an overall accuracy of 89% justifying the efficacy of the method. The WT–FD approach effectively extracts the fHS signals from the noisy background, paving the way for testing it in real fHSs and clearly contributing to better evaluation of the fetal heart functionality.

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.

A Hybrid EMD-Kurtosis Method for Estimating Fetal Heart Rate from Continuous Doppler Signals

Monitoring of fetal heart rate (FHR) is an important measure of fetal wellbeing during the months of pregnancy. Previous works on estimating FHR variability from Doppler ultrasound (DUS) signal mainly through autocorrelation analysis showed low accuracy when compared with heart rate variability (HRV) computed from fetal electrocardiography (fECG). In this work, we proposed a method based on empirical mode decomposition (EMD) and the kurtosis statistics to estimate FHR and its variability from DUS. Comparison between estimated beat-to-beat intervals using the proposed method and the autocorrelation function (AF) with respect to RR intervals computed from fECG as the ground truth was done on DUS signals from 44 pregnant mothers in the early (20 cases) and late (24 cases) gestational weeks. The new EMD-kurtosis method showed significant lower error in estimating the number of beats in the early group (EMD-kurtosis: 2.2% vs. AF: 8.5%, p < 0.01, root mean squared error) and the late group (EMD-kurtosis: 2.9% vs. AF: 6.2%). The EMD-kurtosis method was also found to be better in estimating mean beat-to-beat with an average difference of 1.6 ms from true mean RR compared to 19.3 ms by using the AF method. However, the EMD-kurtosis performed worse than AF in estimating SNDD and RMSSD. The proposed EMD-kurtosis method is more robust than AF in low signal-to-noise ratio cases and can be used in a hybrid system to estimate beat-to-beat intervals from DUS. Further analysis to reduce the estimated beat-to-beat variability from the EMD-kurtosis method is needed.