A new approach for the detection of abnormal heart sound signals using TQWT, VMD and neural networks

Zeng, Wei; Yuan, Jian; Yuan, Chengzhi; Wang, Qinghui; Liu, Fenglin; Wang, Ying

doi:10.1007/s10462-020-09875-w

Cited by 42 publications

(21 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several statistical, time-domain and frequency-domain techniques have been investigated [5,6,7]. Discrete wavelet transform (DWT) [8,9], empirical mode decomposition (EMD) [10], variational mode decomposition (VMD) [6,11], combination of singular value decomposition (SVD) and compressed sensing [12], non-negative matrix factorization (NMF) with adaptive contour representation computation (ACRC) from corresponding spectrogram [7] are some of the best performing approaches reported so far. Nevertheless, these techniques are often computationally intensive, time-consuming, and highly dependent on the data, predefined basis functions, the number of decomposition levels, thresholding parameters, and types [5,9].…”

Section: Introductionmentioning

confidence: 99%

An End-to-end Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise

Ali¹,

Shuvo²,

Hasan³

2023

Preprint

View full text Add to dashboard Cite

<p>The heart sound signal captured via a digital stethoscope is often corrupted with environmental and physiological noise, altering its salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels. In this study, inspired by the heart sound’s quasi-periodic nature, we present a novel deep encoder-decoder based LU-Net architecture to suppress ambient hospital and internal lung sound noises that corrupt the heart sounds. Training is done using a large benchmark PCG dataset mixed with physiological noise, i.e., breathing sounds. Two different noisy datasets were created for experimental evaluation by mixing unseen lung sounds and hospital ambiance noises with the clean heart sound recordings. We also use the inherently noisy portion of the PASCAL heart sound dataset for evaluation. Experimental results show that the proposed framework can effectively suppress background noise in both real-world and synthetically generated noisy heart sound recordings, improving the signal-to-noise ratio (SNR) level by 5.575 dB on an average using only 1.32 M parameters. The study reveals that the proposed model outperforms the current state-of-the-art U-Net model with an average SNR improvement of 5.613 dB and 5.537 dB in the presence of lung sound and hospital noise, respectively. LU-Net also outperformed the state-of-the-art Fully Convolutional Network (FCN) by 1.750 dB and 1.748 dB for lung sound and hospital noise conditions, respectively. In addition, the proposed denoising method model improves classification accuracy by 38.93% in the noisy portion of the PASCAL heart sound dataset. The proposed enhancement scheme can thus play a vital role in deploying automated cardiac screening systems in low-resource and underserved communities. </p>

show abstract

Section: Introductionmentioning

confidence: 99%

An End-to-end Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise

Ali¹,

Shuvo²,

Hasan³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to its inherent characteristics, DL networks address both of these concerns naturally 41,42 . To perform automatic feature extraction, the DL model must be trained on a large data set 43,44 . Ideally, networking settings should be configured on a platform with a small memory size.…”

Section: Introductionmentioning

confidence: 99%

Graph convolutional network‐based deep feature learning for cardiovascular disease recognition from heart sound signals

Rezaee

Khosravi

Jabari

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

The high mortality rate and prevalence of cardiovascular disease (CVD) make early detection of the disease essential. Due to its simplicity and low cost, the phonocardiogram (PCG) system is widely used in healthcare applications for the recognition of CVD in multiclass problems. On the basis of the PCG signal, this paper proposes a hybrid method for classifying cardiac sounds with deep extracted features through two‐step learning. For fine‐grained features in Graph Convolutional Networks (GCNs), sampling and prior layers are employed. A PCG signal is divided into equal parts with overlap using the windowing process. L‐spectrograms extract frequency‐domain information from signals to figure out their power spectrum. Furthermore, the deep GCN tries to determine the association between CVD and spectrogram images to recognize CVD signals better. Combining retrieved features with convolutional neural network (CNN) characteristics reveals an image's intrinsic associations. To generate relational feature representations, correlations between clusters and GCN are visualized using a graph structure. CNN's discriminative ability has been enhanced by incorporating GCN attributes. Using Michigan Heart Sound and Murmur Database and PhysioNet/CinC 2016 Challenge results, we are 99.44% and 96.16% accurate, respectively. Through a combination of GCN architecture, CNN design, and deep features, the hybrid model significantly improves CVD classification accuracy. Measuring metrics demonstrate that the proposed approach detects CVD more effectively than previous approaches.

show abstract

“…The proposed system will be able to categorize heart beat recordings as normal or abnormal. This would be beneficial for the physicians and untrained people to perform an initial screening of a heart disease [5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Heart Sound Analysis for Abnormality Detection

Arshad¹,

Bhatti²,

Tauseef³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

A new approach for the detection of abnormal heart sound signals using TQWT, VMD and neural networks

Cited by 42 publications

References 71 publications

An End-to-end Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise

An End-to-end Deep Learning Framework for Real-Time Denoising of Heart Sounds for Cardiac Disease Detection in Unseen Noise

Graph convolutional network‐based deep feature learning for cardiovascular disease recognition from heart sound signals

Heart Sound Analysis for Abnormality Detection

Contact Info

Product

Resources

About