Research of heart sound classification using two-dimensional features

Xiang, Menghui; Zang, Junbin; Wang, Juliang; Wang, Haoxin; Zhou, Chenzheng; Bi, Ruiyu; Zhang, Zhidong; Xue, Chenyang

doi:10.1016/j.bspc.2022.104190

Cited by 20 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suggested technique achieves an accuracy of 99.67% on the GitHub dataset. In a published study (Xiang et al, 2023), the effect of different two‐dimensional features on heart sound classification models utilizing the 2D CNN architecture was examined. The study evaluated features such as mel log spectrograms and signal waveform maps and concluded that log‐mel and log power features outperformed envelope and waveform features in heart sound classification.…”

Section: Deep Learning For Heart Sound Classificationmentioning

confidence: 99%

Artificial intelligence for heart sound classification: A review

Chen,

Guo,

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Heart sound signal analysis is very important for the early identification and treatment of cardiovascular illness. With rapid advancements in science and technology, artificial intelligence technologies are providing tremendous opportunities to enhance diagnosis and clinical decision‐making. Instruments can now perform clinical diagnoses that previously could only be handled by human experts more conveniently and efficiently. Despite multiple works on automatic heart sound analysis, there are few summarization and review works. This article attempts to give a thorough overview of various heart sound analysis subtasks and examine the improvements made in each subtask by both machine learning techniques and deep learning algorithms. It goals to highlight the potential of AI to revolutionize cardiovascular healthcare by enabling accurate and automated analysis of heart sounds. The findings of this review are beneficial for researchers, clinicians, and engineers in the development and application of AI‐based solutions for improved heart sound classification and diagnosis.

show abstract

Section: Deep Learning For Heart Sound Classificationmentioning

confidence: 99%

Artificial intelligence for heart sound classification: A review

Chen,

Guo,

et al. 2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…However, time-frequency representations may discard critical pathological information that is difficult to quantify in the time domain and that may be crucial for distinguishing between normal and abnormal heart sounds. In contrast, time-frequency domain features are more commonly used in heart sound classification algorithms because they contain more feature information (Xiang et al 2023). STFT (Soeta and Bito 2015), wavelet transform (Deng and Han 2016), Mel spectrograms, and MFCC Han 2016, Nogueira et al 2019) are some common signal transformation methods used to represent time-frequency domain features of heart sound signals.…”

Section: Feature Extraction For Heart Soundsmentioning

confidence: 99%

A learnable front-end based efficient channel attention network for heart sound classification

Liu,

Zhang,

Wang

et al. 2023

Physiol. Meas.

View full text Add to dashboard Cite

Objective: To enhance the accuracy of heart sound classification, this study aims to overcome the limitations of common models which rely on handcrafted feature extraction. These traditional methods may distort or discard crucial pathological information within heart sounds due to their requirement of tedious parameter settings. Approach: We propose a learnable front-end based Efficient Channel Attention Network (ECA-Net) for heart sound classification. This novel approach optimizes the transformation of waveform-to-spectrogram, enabling adaptive feature extraction from heart sound signals without domain knowledge. The features are subsequently fed into an ECA-Net based convolutional recurrent neural network (CRNN), which emphasizes informative features and suppresses irrelevant information. To address data imbalance, Focal loss is employed in our model. Main Results: Using the well-known public PhysioNet challenge 2016 dataset, our method achieved a classification accuracy of 97.77%, outperforming the majority of previous studies and closely rivaling the best model with a difference of just 0.57%. Significance: The learnable front-end facilitates end-to-end training by replacing the conventional heart sound feature extraction module. This provides a novel and efficient approach for heart sound classification research and applications, enhancing the practical utility of end-to-end models in this field.

show abstract

“…In feature engineering, feature fusion refers to the process of combining two distinct categories of features in a manner that enhances their performance capabilities (Xiang et al, 2023). To prevent the generation of excessive redundant information due to fusion, and considering the research objectives and the analysis of pathological features, this study proposes a local overlay fusion strategy.…”

Section: K ( )mentioning

confidence: 99%

Assistive diagnostic technology for congenital heart disease based on fusion features and deep learning

Wang,

Yang,

Qian

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Introduction: Congenital heart disease (CHD) is a cardiovascular disorder caused by structural defects in the heart. Early screening holds significant importance for the effective treatment of this condition. Heart sound analysis is commonly employed to assist in the diagnosis of CHD. However, there is currently a lack of an efficient automated model for heart sound classification, which could potentially replace the manual process of auscultation.Methods: This study introduces an innovative and efficient screening and classification model, combining a locally concatenated fusion approach with a convolutional neural network based on coordinate attention (LCACNN). In this model, Mel-frequency spectral coefficients (MFSC) and envelope features are locally fused and employed as input to the LCACNN network. This model automatically analyzes feature map energy information, eliminating the need for denoising processes.Discussion: The proposed classification model in this study demonstrates a robust capability for identifying congenital heart disease, potentially substituting manual auscultation to facilitate the detection of patients in remote areas.Results: This study introduces an innovative and efficient screening and classification model, combining a locally concatenated fusion approach with a convolutional neural network based on coordinate attention (LCACNN). In this model, Mel-frequency spectral coefficients (MFSC) and envelope features are locally fused and employed as input to the LCACNN network. This model automatically analyzes feature map energy information, eliminating the need for denoising processes. To assess the performance of the classification model, comparative ablation experiments were conducted, achieving classification accuracies of 91.78% and 94.79% on the PhysioNet and HS databases, respectively. These results significantly outperformed alternative classification models.

show abstract

Research of heart sound classification using two-dimensional features

Cited by 20 publications

References 35 publications

Artificial intelligence for heart sound classification: A review

Artificial intelligence for heart sound classification: A review

A learnable front-end based efficient channel attention network for heart sound classification

Assistive diagnostic technology for congenital heart disease based on fusion features and deep learning

Contact Info

Product

Resources

About