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

2020 ◽  
Vol 10 (20) ◽  
pp. 7049
Author(s):  
Yibo Yin ◽  
Kainan Ma ◽  
Ming Liu
Keyword(s):  
Markov Model ◽  
Viterbi Algorithm ◽  
Heart Sound ◽  
Time Algorithm ◽  
Heart Sounds ◽  
Disease Classification ◽  
Convolutional Network ◽  
Data Set ◽  
State Duration ◽  
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.

scholarly journals Heart Sound Segmentation Based on Personalized Gaussian Mixture Model and Convolutional Neural Network

2020 ◽  
Author(s):  
Chun Dong Xu ◽  
Jing Zhou ◽  
Dong Wen Ying ◽  
Lei Jing Hou ◽  
Qing Hua Long
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Heart Sound ◽  
Gaussian Mixture ◽  
Heart Sounds ◽  
Spectral Amplitude ◽  
Heart Sound Segmentation ◽  
F Measure

Abstract Background: Heart sound segmentation is a long-standing problem in heart analysis, and it is mainly caused by noise interference and diversification of heart sounds. Faced with the challenging of heart sound segmentation, a more applicable segmentation model was studied. Methods: In this process, the optimal modified Log-spectral amplitude and wavelet were used to suppress the noise in the heart sound, and used the duration-dependent hidden Markov model based on personalized Gaussian mixture model (PGMM-DHMM) to segment the fundamental heart sound (FHS) and the non-fundamental heart sound (non-FHS). Then used the optimized Mel frequency cepstral coefficient (MFCC) to realize the classification of S1 and S2 heart sound frames through the Convolutional neural network (CNN) classifier, which can avoid the errors caused by the ambiguity of the time domain features. Results: PGMM-DHMM can segment FHS more effectively, and the accuracy is 94.3%. The CNN classifier obtained the best results in the S1 and S2 classifications, the accuracy is 90.92%, the precision of S1 is 90.76%, the recall is 91.05%, the F-measure is 90.9%, and the precision of S2 is 91.07%, the recall is 90.79%, the F-measure is 90.93%. The final segmentation accuracy is 92.92%. In addition, the experimental results further indicate that CNN has more robust performance when classifying abnormal S1 and abnormal S2. Conclusions: The PGMM-DHMM model can better segment FHS and Non-FHS. The optimization of MFCC improves the classification effect of S1 and S2, and the improvement effect by the CNN classifier is significant, especially for abnormal heart sounds. The proposed algorithm is better than other algorithms at this stage.

scholarly journals Heart Sound Segmentation Based on Personalized Gaussian Mixture Model and Convolutional Neural Network

2020 ◽  
Author(s):  
Chun Dong Xu ◽  
Jing Zhou ◽  
Dong Wen Ying ◽  
Lei Jing Hou ◽  
Qing Hua Long
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Heart Sound ◽  
Gaussian Mixture ◽  
Heart Sounds ◽  
Spectral Amplitude ◽  
Heart Sound Segmentation ◽  
F Measure

Abstract Background: Heart sound segmentation is a long-standing problem in heart analysis, and it is mainly caused by noise interference and diversification of heart sounds. Faced with the challenging of heart sound segmentation, a more applicable segmentation model was studied. Methods: In this process, the optimal modified Log-spectral amplitude and wavelet were used to suppress the noise in the heart sound, and used the duration-dependent hidden Markov model based on personalized Gaussian mixture model (PGMM-DHMM) to segment the fundamental heart sound (FHS) and the non-fundamental heart sound (non-FHS). Then used the optimized Mel frequency cepstral coefficient (MFCC) to realize the classification of S1 and S2 heart sound frames through the Convolutional neural network (CNN) classifier, which can avoid the errors caused by the ambiguity of the time domain features. Results: PGMM-DHMM can segment FHS more effectively, and the accuracy is 94.3%. The CNN classifier obtained the best results in the S1 and S2 classifications, the accuracy is 90.92%, the precision of S1 is 90.76%, the recall is 91.05%, the F-measure is 90.9%, and the precision of S2 is 91.07%, the recall is 90.79%, the F-measure is 90.93%. The final segmentation accuracy is 92.92%. In addition, the experimental results further indicate that CNN has more robust performance when classifying abnormal S1 and abnormal S2. Conclusions: The PGMM-DHMM model can better segment FHS and Non-FHS. The optimization of MFCC improves the classification effect of S1 and S2, and the improvement effect by the CNN classifier is significant, especially for abnormal heart sounds. The proposed algorithm is better than other algorithms at this stage.

scholarly journals Robust Heart Sound Segmentation and Detection using biased Cramer-Rao Lower Bound Estimation and Variance Algorithm

2019 ◽  
Vol 9 (2S3) ◽  
pp. 14-22
Keyword(s):  
Lower Bound ◽  
Heart Sound ◽  
Principal Component ◽  
Minimum Variance ◽  
Heart Sounds ◽  
Second Order Statistics ◽  
Frequency Components ◽  
Cardiac Disorders ◽  
Cramer Rao Lower Bound ◽  
Heart Sound Segmentation

Cardiac disorders are the most common infirmity suffered by the human race. Medical research states that worldwide almost 30% of the deaths are caused because of cardiovascular diseases. Even though many procedures such as Echocardiography, Carotid pulse and Electrocardiography are available, the conventional approach followed for detecting abnormalities are carried by hearing to the heart rhythms. This proposed study enables the health care physicians to diagnose pathologies of highly non-stationary heart sounds efficiently by using the second-order statistics of the signal. In this paper, a preprocessing methodology is used for removing noise caused by the lower frequency components and to focus only on the primary components S1 & S2, which are further feature extracted by using principal component analysis (PCA). A proposed variance algorithm (VA) is developed to identify the boundary locations of heart sounds and segment the featured signals into series of cardiac cycles. Further, we developed a modified variance algorithm (MVA) using biased Cramer-Rao lower bound (CRLB) to estimate the heart sound (HS) signals that exhibit minimum variance and extract finer boundary locations of the signal components which helps in identifying S1 & S2 positions. When compared with PCA, VA and Shannon energy (SE) methods for the same dataset, the MVA scheme exhibits very low normalized mean square error (NMSE) in extracting boundary locations by -71.60±0.25 dB and achieves high cardiac cycle segmentation ratio of 97.78±0.98 %. A brief analysis of the results showed that the proposed MVA scheme using biased CRLB exhibits 97.4±1.2% accuracy in identifying S1 and S2 heart sounds.

A Heart Sound Segmentation Method Based on Cyclostationary Envelope

2013 ◽  
Vol 347-350 ◽  
pp. 2280-2283 ◽  
Author(s):  
Ting Li ◽  
Tian Shuang Qiu ◽  
Hong Tang
Keyword(s):  
Heart Sound ◽  
Reference Signal ◽  
Heart Sounds ◽  
Automatic Analysis ◽  
Segmentation Method ◽  
Heart Sound Segmentation ◽  
Robust To Noise ◽  
Clinical Cases

Segmentation is generally an important prior process to automatic analysis of heart sounds. The proposed algorithm achieved this in separated cycles. First, the cyclostationary envelopes of heart sound signals are calculated. Second, a threshold is chosen to separate S1 and S2. The segmentation is automatic, and robust to noise. It can identify S1 and S2 correctly even under the circumstance of noise and interference. No reference signal is needed for this segmentation. It was tested by the heart sounds of 20 subjects including 15 normal and 5 abnormal in various clinical cases (715 cycles in total). The statistics showed over 96 percent correctness for segmentation.

Detection and identification of S1 and S2 heart sounds using wavelet decomposition method

2015 ◽  
Vol 08 (06) ◽  
pp. 1550078 ◽  
Author(s):  
Ali Tavakoli Golpaygani ◽  
Nahid Abolpour ◽  
Kamran Hassani ◽  
Kourosh Bajelani ◽  
D. John Doyle
Keyword(s):  
Wavelet Decomposition ◽  
Heart Sound ◽  
Detection System ◽  
Automatic Segmentation ◽  
Heart Sounds ◽  
Segmentation Algorithm ◽  
Discrete Wavelet ◽  
Detection And Identification ◽  
Heart Disorders ◽  
Heart Sound Segmentation

Phonocardiogram (PCG), the digital recording of heart sounds is becoming increasingly popular as a primary detection system for diagnosing heart disorders and it is relatively inexpensive. Electrocardiogram (ECG) is used during the PCG in order to identify the systolic and diastolic parts manually. In this study a heart sound segmentation algorithm has been developed which separates the heart sound signal into these parts automatically. This study was carried out on 100 patients with normal and abnormal heart sounds. The algorithm uses discrete wavelet decomposition and reconstruction to produce PCG intensity envelopes and separates that into four parts: the first heart sound, the systolic period, the second heart sound and the diastolic period. The performance of the algorithm has been evaluated using 14,000 cardiac periods from 100 digital PCG recordings, including normal and abnormal heart sounds. In tests, the algorithm was over 93% correct in detecting the first and second heart sounds. The presented automatic segmentation algorithm using wavelet decomposition and reconstruction to select suitable frequency band for envelope calculations has been found to be effective to segment PCG signals into four parts without using an ECG.

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

2021 ◽  
Vol 11 (2) ◽  
pp. 651
Author(s):  
Yi He ◽  
Wuyou Li ◽  
Wangqi Zhang ◽  
Sheng Zhang ◽  
Xitian Pi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Heart Sound ◽  
Original Data ◽  
Heart Sounds ◽  
Sound Signal ◽  
Accuracy Rate ◽  
Heart Research ◽  
Data Set ◽  
Heart Sound Signal

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.

Sign in / Sign up

Export Citation Format

Share Document