Characterization of $S_1$ and $S_2$ Heart Sounds Using Stacked Autoencoder and Convolutional Neural Network

2019 ◽  
Vol 68 (9) ◽  
pp. 3211-3220 ◽  
Author(s):  
Madhusudhan Mishra ◽  
Hrishikesh Menon ◽  
Anirban Mukherjee
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Heart Sounds ◽  
Stacked Autoencoder

scholarly journals A novel 1-D densely connected feature selection convolutional neural network for heart sounds classification

2021 ◽  
Vol 9 (24) ◽  
pp. 1752-1752
Author(s):  
Xin Zhou ◽  
Xuying Wang ◽  
Xianhong Li ◽  
Yao Zhang ◽  
Ying Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Convolutional Neural Network ◽  
Heart Sounds

scholarly journals A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound

2017 ◽  
Vol 21 (1) ◽  
pp. 48-55 ◽  
Author(s):  
Karim Lekadir ◽  
Alfiia Galimzianova ◽  
Angels Betriu ◽  
Maria del Mar Vila ◽  
Laura Igual ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Carotid Ultrasound ◽  
Plaque Composition

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 A measurement of epidermal thickness of fingertip skin from OCT images using convolutional neural network

2020 ◽  
pp. 2140005
Author(s):  
Yongping Lin ◽  
Dezi Li ◽  
Wang Liu ◽  
Zhaowei Zhong ◽  
Zhifang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Coherence Tomography ◽  
Convolutional Neural Network ◽  
Cross Section ◽  
Skin Diseases ◽  
Skin Surface ◽  
Epidermal Thickness ◽  
Quantitative Characterization ◽  
Local Maxima

In this study, we proposed a method to measure the epidermal thickness (ET) of skin based on deep convolutional neural network, which was used to determine the boundaries of skin surface and the ridge portion in dermal–epidermis junction (DEJ) in cross-section optical coherence tomography (OCT) images of fingertip skin. The ET was calculated based on the row difference between the surface and the ridge top, which is determined by search the local maxima of boundary of the ridge portion. The results demonstrated that the region of ridge portion in DEJ was well determined and the ET measurement in this work can reduce the effect of the papillae valley in DEJ by 9.85%. It can be used for quantitative characterization of skin to differentiate the skin diseases.

Sign in / Sign up

Export Citation Format

Share Document