Unsupervised Heart Abnormality Detection Based on Phonocardiogram Analysis with Beta Variational Auto-Encoders

Heart Sound (also known as phonocardiogram (PCG)) analysis, is a popular way that detects cardiovascular diseases (CVDs). Most PCG analysis uses supervised way, which demands both normal and abnormal samples. This paper proposes a method of unsupervised PCG analysis that uses beta variational auto-encoder (β – VAE) to model the normal PCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Operating Characteristic) test for PCG signals collected from the same source. Unlike majority of β – VAEs that are used as generative models, the best-performed β – VAE has a β value smaller than 1. This fact demonstrates that the resampling process helps the improvements on anomaly PCG detection through reconstruction loss worth a heavier weight. Further investigations suggest that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples in PCG analysis based on VAE systems.

[1]  Matthew Chin Heng Chua,et al.  Semi-supervised and Unsupervised Methods for Heart Sounds Classification in Restricted Data Environments , 2020, ArXiv.

[2]  Avik Ghose,et al.  A Semi-Supervised Approach For Identifying Abnormal Heart Sounds Using Variational Autoencoder , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Björn W. Schuller,et al.  Audio for Audio is Better? An Investigation on Transfer Learning Models for Heart Sound Classification , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[4]  Björn W. Schuller,et al.  Deep Wavelets for Heart Sound Classification , 2019, 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[5]  Mohammad Adiban,et al.  Statistical feature embedding for heart sound classification , 2019, Journal of Electrical Engineering.

[6]  Peng Peng,et al.  Unsupervised Anomaly Detection Using Variational Auto-Encoder based Feature Extraction , 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM).

[7]  Guillaume Desjardins,et al.  Understanding disentangling in β-VAE , 2018, ArXiv.

[8]  Guillaume Desjardins,et al.  Understanding disentangling in $\beta$-VAE , 2018, 1804.03599.

[9]  Kumar Sricharan,et al.  Recognizing Abnormal Heart Sounds Using Deep Learning , 2017, KHD@IJCAI.

[10]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[11]  M. Picheny,et al.  Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences , 2017 .

[12]  Qiao Li,et al.  An open access database for the evaluation of heart sound algorithms , 2016, Physiological measurement.

[13]  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).

[14]  Jan Gieraltowski,et al.  PCG classification using a neural network approach , 2016, 2016 Computing in Cardiology Conference (CinC).

[15]  Aggelos K. Katsaggelos,et al.  Heart sound anomaly and quality detection using ensemble of neural networks without segmentation , 2016, 2016 Computing in Cardiology Conference (CinC).

[16]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[17]  D. Barschdorff,et al.  Automatic phonocardiogram signal analysis in infants based on wavelet transforms and artificial neural networks , 1995, Computers in Cardiology 1995.