Noisy Neonatal Chest Sound Separation for High-Quality Heart and Lung Sounds

Stethoscope-recorded chest sounds provide the opportunity for remote cardio-respiratory health monitoring of neonates. However, reliable monitoring requires high-quality heart and lung sounds. This paper presents novel Non-negative Matrix Factorisation (NMF) and Non-negative Matrix CoFactorisation (NMCF) methods for neonatal chest sound separation. To assess these methods and compare with existing singlesource separation methods, an artificial mixture dataset was generated comprising of heart and lung and noise sounds. Signalto-noise ratios were then calculated for these artificial mixtures. These methods were also tested on real-world noisy neonatal chest sounds and assessed based on vital sign estimation error and a signal quality score of 1-5 developed in our previous works. Additionally, the computational cost of all methods was assessed to determine the applicability for real-time processing. Overall, both the proposed NMF and NMCF methods outperform the next best existing method by 2.7 dB to 11.6 dB for the artificial dataset and 0.40 to 1.12 signal quality improvement for the real-world dataset. The median processing time for the sound separation of a 10 s recording was found to be 28.3 s for NMCF and 342 ms for NMF. Because of stable and robust performance, we believe that our proposed methods are useful to denoise neonatal heart and lung sound in a real-world environment. Codes for proposed and existing methods can be found at: https://github. com/egrooby-monash/Heart-and-Lung-Sound-Separation.

[1]  Rémi Gribonval,et al.  Performance measurement in blind audio source separation , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[2]  P. Alam.  ‘G’ , 2021, Composites Engineering: An A–Z Guide.

[3]  Constantinos B. Papadias,et al.  On the Blind Recovery of Cardiac and Respiratory Sounds , 2015, IEEE Journal of Biomedical and Health Informatics.

[4]  Ashok Mondal,et al.  A Noise Reduction Technique Based on Nonlinear Kernel Function for Heart Sound Analysis , 2018, IEEE Journal of Biomedical and Health Informatics.

[5]  Faezeh Marzbanrad,et al.  Digital stethoscopes in paediatric medicine , 2019, Acta paediatrica.

[6]  A. Malhotra,et al.  Acoustic analysis of neonatal breath sounds using digital stethoscope technology , 2020, Pediatric pulmonology.

[7]  Yu Tsao,et al.  Blind Monaural Source Separation on Heart and Lung Sounds Based on Periodic-Coded Deep Autoencoder , 2020, IEEE Journal of Biomedical and Health Informatics.

[8]  Tzu-Hao Lin,et al.  Improving biodiversity assessment via unsupervised separation of biological sounds from long-duration recordings , 2017, Scientific Reports.

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

[10]  W. Marsden.  I and J , 2012 .

[11]  Jonathan Le Roux,et al.  SDR – Half-baked or Well Done? , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  R. Sarpong,et al.  Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c9sc02572c , 2019, Chemical science.

[13]  Nicolás Ruiz-Reyes,et al.  A non-negative matrix factorization approach based on spectro-temporal clustering to extract heart sounds , 2017 .

[14]  E. Bancalari,et al.  Neonatal monitoring during delivery room emergencies. , 2019, Seminars in fetal & neonatal medicine.

[15]  Saeid Sanei,et al.  Separation of heart sound signal from lung sound signal by adaptive line enhancement , 2007, 2007 15th European Signal Processing Conference.

[16]  Feng Wan,et al.  Adaptive Fourier decomposition approach for lung-heart sound separation , 2015, 2015 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA).

[17]  Tiago H. Falk,et al.  Modulation filtering for heart and lung sound separation from breath sound recordings , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  W. Hager,et al.  and s , 2019, Shallow Water Hydraulics.

[19]  Rémi Gribonval,et al.  BSS_EVAL Toolbox User Guide -- Revision 2.0 , 2005 .

[20]  A. G. Rudnitskii.  Using nonlocal means to separate cardiac and respiration sounds , 2014 .

[21]  Ruban Nersisson,et al.  Heart sound and lung sound separation algorithms: a review , 2017, Journal of medical engineering & technology.

[22]  January Gnitecki,et al.  Recursive least squares adaptive noise cancellation filtering for heart sound reduction in lung sounds recordings , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[23]  Hamid Reza Mohseni,et al.  Localizing Heart Sounds in Respiratory Signals Using Singular Spectrum Analysis , 2011, IEEE Transactions on Biomedical Engineering.

[24]  Zahra Moussavi,et al.  An overview of heart-noise reduction of lung sound using wavelet transform based filter , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[25]  A. Malhotra,et al.  Assessment of breath sounds at birth using digital stethoscope technology , 2019, European Journal of Pediatrics.

[26]  Amir Lahav,et al.  Questionable sound exposure outside of the womb: frequency analysis of environmental noise in the neonatal intensive care unit , 2015, Acta paediatrica.

[27]  Guy A. Dumont,et al.  A New Non-Negative Matrix Co-Factorisation Approach for Noisy Neonatal Chest Sound Separation , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[28]  A. Malhotra,et al.  Tools to assess lung aeration in neonates with respiratory distress syndrome , 2020, Acta paediatrica.

[29]  Guy A. Dumont,et al.  Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications , 2021, IEEE Access.

[30]  Stavros M. Panas,et al.  A wavelet-based reduction of heart sound noise from lung sounds , 1998, Int. J. Medical Informatics.

[31]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[32]  Z. Moussavi,et al.  Heart sound cancellation from lung sound recordings using time-frequency filtering , 2006, Medical and Biological Engineering and Computing.

[33]  Guy A. Dumont,et al.  Neonatal Heart and Lung Sound Quality Assessment for Robust Heart and Breathing Rate Estimation for Telehealth Applications , 2020, IEEE Journal of Biomedical and Health Informatics.

[34]  Le Roux.  Sparse NMF – half-baked or well done? , 2015 .

[35]  Wai Lok Woo,et al.  Unsupervised Single-Channel Separation of Nonstationary Signals Using Gammatone Filterbank and Itakura–Saito Nonnegative Matrix Two-Dimensional Factorizations , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[36]  Goutam Saha,et al.  Reduction of heart sound interference from lung sound signals using empirical mode decomposition technique , 2011, Journal of medical engineering & technology.