Abstract
In this paper, we propose a parallel source separation system designed to extract heart and lung sounds from single-channel mixtures. The proposed system is based on a non-negative matrix factorization (NMF) approach and a clustering strategy together with a soft-masking filtering. Furthermore, we propose an offline and online implementation of the framework which can be applied in many real-time scenarios, such as the extraction of clinical parameters, remote auscultation and breath sound analysis. Experimental results show that it is possible to achieve fast execution times, which enable a real-time behavior, combining parallel and high-performance techniques.
Similar content being viewed by others
References
Alonso P, Cortina R, Rodríguez-Serrano FJ, Vera-Candeas P, Alonso-González M, Ranilla J (2017) Parallel online time warping for real-time audio-to-score alignment in multi-core systems. J Supercomput 73(1):126–138. https://doi.org/10.1007/s11227-016-1647-5
Alonso P, Vera-Candeas P, Cortina R, Ranilla J (2016) An efficient musical accompaniment parallel system for mobile devices. J Supercomput 73(1):1–11. https://doi.org/10.1007/s11227-016-1865-x
Ayari F, Ksouri M, Alouani AT (2012) Lung sound extraction from mixed lung and heart sounds FASTICA algorithm. In: 2012 16th IEEE Mediterranean Electrotechnical Conference, pp 339–342. IEEE. https://doi.org/10.1109/MELCON.2012.6196444
Barabasa C, Jafari M, Plumbley MD (2012) A robust method for S1, S2 heart sounds detection without ECG reference based on music beat tracking. In: 2012 10th International Symposium on Electronics and Telecommunications, pp 307–310. IEEE. https://doi.org/10.1109/ISETC.2012.6408110
Blackford LS, Demmel J, Dongarra J, Duff I, Hammarling S, Henry G, Heroux M, Kaufman L, Lumsdaine A, Petitet A, Pozo R, Remington K, Whaley RC (2001) An updated set of basic linear algebra subprograms (BLAS). ACM Trans Math Softw 28:135–151
Canadas-Quesada F, Ruiz-Reyes N, Carabias-Orti J, Vera-Candeas P, Fuertes-Garcia J (2017) A non-negative matrix factorization approach based on spectro-temporal clustering to extract heart sounds. Appl Acoust 125:7–19. https://doi.org/10.1016/j.apacoust.2017.04.005. https://linkinghub.elsevier.com/retrieve/pii/S0003682X16304923
Charbonneau G, Racineux JL, Sudraud M, Tuchais E (1983) An accurate recording system and its use in breath sounds spectral analysis. J Appl Physiol 55(4):1120–1127. https://doi.org/10.1152/jappl.1983.55.4.1120
Charleston-Villalobos S, Dominguez-Robert LF, Gonzalez-Camarena R, Aljama-Corrales AT (2006) Heart sounds interference cancellation in lung sounds. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, pp 1694–1697. IEEE. https://doi.org/10.1109/IEMBS.2006.259357
Chien JC, Huang MC, Lin YD, Chong FC (2006) A study of heart sound and lung sound separation by independent component analysis technique. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, pp 5708–5711. IEEE. https://doi.org/10.1109/IEMBS.2006.260223. http://ieeexplore.ieee.org/document/4463102/
Dagum L, Menon R (1998) OpenMp: an industry standard API for shared-memory programming. IEEE Comput Sci Eng 5(1):46–55
Févotte C, Bertin N, Durrieu JL (2009) Nonnegative matrix factorization with the Itakura–Saito divergence: with application to music analysis. Neural Comput 21(3):793–830. https://doi.org/10.1162/neco.2008.04-08-771
Frigo M, Johnson SG (2005) The design and implementation of fftw3. Proc IEEE 93(2):216–231
Gavriely N, Palti Y, Alroy G (1981) Spectral characteristics of normal breath sounds. J Appl Physiol 50(2):307–314. https://doi.org/10.1152/jappl.1981.50.2.307
Grais EM, Erdogan H (2011) Single channel speech music separation using nonnegative matrix factorization and spectral masks. In: 2011 17th International Conference on Digital Signal Processing (DSP), pp 1–6. IEEE. https://doi.org/10.1109/ICDSP.2011.6004924
Hedayioglu FL, Jafari MG, Mattos SS, Plumbley MD, Coimbra MT (2011) Separating sources from sequentially acquired mixtures of heart signals. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 653–656. IEEE. https://doi.org/10.1109/ICASSP.2011.5946488
Hossain I, Moussavi Z (2003) An overview of heart-noise reduction of lung sound using wavelet transform based filter. In: Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439), pp 458–461. IEEE. https://doi.org/10.1109/IEMBS.2003.1279719
Lin C, Hasting E (2013) Blind source separation of heart and lung sounds based on nonnegative matrix factorization. In: 2013 International Symposium on Intelligent Signal Processing and Communication Systems, pp 731–736. IEEE. https://doi.org/10.1109/ISPACS.2013.6704646
Peeters G (2004) A large set of audio features for sound description. Tech. rep. https://doi.org/10.1234/12345678
Pourazad M, Moussavi Z, Farahmand F, Ward R (2005) Heart sounds separation from lung sounds using independent component analysis. In: 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, pp 2736–2739. IEEE. https://doi.org/10.1109/IEMBS.2005.1617037
Rudnitskii AG (2014) Using nonlocal means to separate cardiac and respiration sounds. Acoust Phys 60(6):719–726. https://doi.org/10.1134/S1063771014050121
Salazar AJ, Alvarado C, Lozano FE (2012) System of heart and lung sounds separation for store-and-forward telemedicine applications. Rev Fac Ingen 64:175–181
San Juan P, Vidal A, Garcia-Molla V (2017) Updating/downdating the nonnegative matrix factorization. J Comput Appl Math 318:59–68. https://doi.org/10.1016/j.cam.2016.11.048. https://www.sciencedirect.com/science/article/pii/S0377042716305908
Shah G, Koch P, Papadias CB (2015) On the blind recovery of cardiac and respiratory sounds. IEEE J Biomed Health Inf 19(1):151–157. https://doi.org/10.1109/JBHI.2014.2349156. http://ieeexplore.ieee.org/document/6879427/
Shah G, Papadias C (2013) Separation of cardiorespiratory sounds using time-frequency masking and sparsity. In: 2013 18th International Conference on Digital Signal Processing (DSP), pp 1–6. IEEE. https://doi.org/10.1109/ICDSP.2013.6622792
Sibu T, Nishi S (2012) Detection and elimination of heart sound from lung sound based on wavelet multi resolution analysis technique and linear prediction. Int J Res Publ 1(10):28–33
Tracey BH, Miller EL (2012) Nonlocal means denoising of ECG signals. IEEE Trans Biomed Eng 59(9):2383–2386. https://doi.org/10.1109/TBME.2012.2208964. http://ieeexplore.ieee.org/document/6242391/
Virtanen T (2007) Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans Audio, Speech Lang Process 15(3):1066–1074. https://doi.org/10.1109/TASL.2006.885253. http://ieeexplore.ieee.org/document/4100700/
Acknowledgements
This work was supported by the Regional Ministry of the Principality of Asturias under Grant FC-GRUPIN-IDI/2018/000226, by the Ministry of Economy, Knowledge and University of the Government of the Junta de Andalucía under Project P18-RT-1994 and by the “Programa Operativo FEDER Andalucía 2014-2020” under Project with Reference 1257914.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Muñoz-Montoro, A.J., Suarez-Dou, D., Cortina, R. et al. Parallel source separation system for heart and lung sounds. J Supercomput 77, 8135–8150 (2021). https://doi.org/10.1007/s11227-020-03616-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-020-03616-0