HS-Vectors: Heart Sound Embeddings for Abnormal Heart Sound Detection Based on Time-Compressed and Frequency-Expanded TDNN With Dynamic Mask Encoder

In recent years, auxiliary diagnosis technology for cardiovascular disease based on abnormal heart sound detection has become a research hotspot. Heart sound signals are promising in the preliminary diagnosis of cardiovascular diseases. Previous studies have focused on capturing the local characteristics of heart sounds. In this paper, we investigate a method for mapping heart sound signals with complex patterns to fixed-length feature embedding called HS-Vectors for abnormal heart sound detection. To get the full embedding of the complex heart sound, HS-Vectors are obtained through the Time-Compressed and Frequency-Expanded Time-Delay Neural Network(TCFE-TDNN) and the Dynamic Masked-Attention (DMA) module. HS-Vectors extract and utilize the global and critical heart sound characteristics by masking out irreverent information. Based on the TCFE-TDNN module, the heart sound signal within a certain time is projected into fixed-length embedding. Then, with a learnable mask attention matrix, DMA stats pooling aggregates multi-scale hidden features from different TCFE-TDNN layers and masks out irrelevant frame-level features. Experimental evaluations are performed on a 10-fold cross-validation task using the 2016 PhysioNet/CinC Challenge dataset and the new publicly available pediatric heart sound dataset we collected. Experimental results demonstrate that the proposed method excels the state-of-the-art models in abnormality detection.

[1]  Drishti Ramesh Megalmani,et al.  Unsegmented Heart Sound Classification Using Hybrid CNN-LSTM Neural Networks , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[2]  L. Zhiming,et al.  Multi-label classification of heart sound signals , 2021, 2021 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI).

[3]  Omer Deperlioglu,et al.  Heart sound classification with signal instant energy and stacked autoencoder network , 2021, Biomed. Signal Process. Control..

[4]  Devjyoti Chakraborty,et al.  Feature Extraction and Classification of Phonocardiograms using Convolutional Neural Networks , 2020, 2020 IEEE 1st International Conference for Convergence in Engineering (ICCE).

[5]  Jing Zhang,et al.  Heart sound classification based on improved MFCC features and convolutional recurrent neural networks , 2020, Neural Networks.

[6]  Sumair Aziz,et al.  Classification of Myocardial Infarction using MFCC and Ensemble Subspace KNN , 2020, 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE).

[7]  Sridha Sridharan,et al.  A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation , 2020, IEEE Journal of Biomedical and Health Informatics.

[8]  Kris Demuynck,et al.  ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification , 2020, INTERSPEECH.

[9]  Sridha Sridharan,et al.  Heart Sound Segmentation Using Bidirectional LSTMs With Attention , 2020, IEEE Journal of Biomedical and Health Informatics.

[10]  Xu Ma,et al.  Follow the Sound of Children’s Heart: A Deep-Learning-Based Computer-Aided Pediatric CHDs Diagnosis System , 2020, IEEE Internet of Things Journal.

[11]  Ahmed Imtiaz Humayun,et al.  Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks , 2019, IEEE Journal of Biomedical and Health Informatics.

[12]  Abir Hussain,et al.  The Implementation of Pretrained AlexNet on PCG Classification , 2019, ICIC.

[13]  Miguel Tavares Coimbra,et al.  Deep Convolutional Neural Networks for Heart Sound Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.

[14]  S. Balqis Samdin,et al.  A Markov-Switching Model Approach to Heart Sound Segmentation and Classification , 2018, IEEE Journal of Biomedical and Health Informatics.

[15]  Daniel Povey,et al.  Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification , 2018, INTERSPEECH.

[16]  Andrew Lowe,et al.  Fundamental Heart Sound Classification using the Continuous Wavelet Transform and Convolutional Neural Networks , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[17]  Franz Pernkopf,et al.  Heart Sound Segmentation—An Event Detection Approach Using Deep Recurrent Neural Networks , 2018, IEEE Transactions on Biomedical Engineering.

[18]  Sanjeev Khudanpur,et al.  X-Vectors: Robust DNN Embeddings for Speaker Recognition , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Gabriel Jimenez-Moreno,et al.  Deep Neural Networks for the Recognition and Classification of Heart Murmurs Using Neuromorphic Auditory Sensors , 2017, IEEE Transactions on Biomedical Circuits and Systems.

[20]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[21]  Anurag Agarwal,et al.  DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds , 2017, Physiological measurement.

[22]  Weibin Zhang,et al.  Automatic heart and lung sounds classification using convolutional neural networks , 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

[23]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[24]  Qiao Li,et al.  Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016 , 2016, 2016 Computing in Cardiology Conference (CinC).

[25]  Yan Liu,et al.  Normal / abnormal heart sound recordings classification using convolutional neural network , 2016, 2016 Computing in Cardiology Conference (CinC).

[26]  Andreas Dominik,et al.  Using deep gated RNN with a convolutional front end for end-to-end classification of heart sound , 2016, 2016 Computing in Cardiology Conference (CinC).

[27]  Kumar Sricharan,et al.  Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients , 2016, 2016 Computing in Cardiology Conference (CinC).

[28]  Bryan R. Conroy,et al.  Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds , 2016, 2016 Computing in Cardiology Conference (CinC).

[29]  Hayong Shin,et al.  Classification of heart sound recordings using convolution neural network , 2016, 2016 Computing in Cardiology Conference (CinC).

[30]  Lionel Tarassenko,et al.  Logistic Regression-HSMM-Based Heart Sound Segmentation , 2016, IEEE Transactions on Biomedical Engineering.

[31]  Ram Bilas Pachori,et al.  Automatic diagnosis of septal defects based on tunable-Q wavelet transform of cardiac sound signals , 2015, Expert Syst. Appl..

[32]  Zhongwei Jiang,et al.  Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform , 2014, Comput. Methods Programs Biomed..

[33]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[34]  Shyamala C. Doraisamy,et al.  Multi-level basis selection of wavelet packet decomposition tree for heart sound classification , 2013, Comput. Biol. Medicine.

[35]  Yannis Stylianou,et al.  Automatic classification of systolic heart murmurs , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[36]  Harun Uguz.  Adaptive neuro-fuzzy inference system for diagnosis of the heart valve diseases using wavelet transform with entropy , 2012, Neural Computing and Applications.

[37]  Harun Uguz,et al.  A Biomedical System Based on Artificial Neural Network and Principal Component Analysis for Diagnosis of the Heart Valve Diseases , 2012, Journal of Medical Systems.

[38]  Goutam Saha,et al.  Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier , 2010, Expert Syst. Appl..

[39]  Suyi Li,et al.  Heart Sounds Classification Based on Feature Fusion Using Lightweight Neural Networks , 2021, IEEE Transactions on Instrumentation and Measurement.

[40]  Rayaz A. Malik,et al.  Cardiac auscultation: an essential clinical skill in decline , 2010 .

[41]  Juan Ignacio Godino-Llorente,et al.  Selection of Dynamic Features Based on Time–Frequency Representations for Heart Murmur Detection from Phonocardiographic Signals , 2009, Annals of Biomedical Engineering.