An EMD-Based Algorithm for Emboli Detection in Echo Doppler Audio Signals
Abstract
:1. Introduction
2. Materials and Methods
3. Bubbles Detection Algorithm
- identify all extrema of ;
- interpolate between minima (and maxima) ending up with envelope (and );
- compute the mean r(t) between and ;
- extract the detail signal ;
- iterate on the residual signal .
- the number of IMF extrema (the sum of the maxima and minima) and the number of zero-crossings must either be equal or differ at most by one;
- at any point of an IMF, the mean value of the envelope defined by the local maxima and the envelope defined by the local minima shall be zero.
3.1. Pre-Processing of Input Signal
3.2. EMD Implementation
3.3. Threshold Calculation and IMF Windowing
3.4. Bubble Detection Refining and Determination of Embolism Risk
4. Results
5. Discussion
6. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Abbreviations
DCS | Decompression sickness |
VGE | venous gas emboli |
DU | Doppler ultrasounds |
STFT | short-time Fourier transform |
MRA | Multiresolution analysis |
DWT | Discrete wavelet transform |
EMD | Empirical mode decomposition |
IMF | Intrinsic mode function |
DAN | Divers Alert Network |
TP− | True Positive |
FP− | False Positive |
FN | False Negative |
TN | True Negative |
D+ | Total Frames With Bubbles |
D− | Total Frames Without Bubbles |
T+ | Total Frames With Detected Bubbles |
T− | Total Frames Without Detected Bubbles |
N | Total Frames |
References
- Jamharee, F.; Noh, A.Y.M.; Kamauzaman, T.H.T.; Abdullah, A.A.; Nor, J. A descriptive study of decompression illness among scuba divers treated with hyperbaric oxygen therapy at a military hospital-based recompression facility in peninsular Malaysia. Malays. J. Emerg. Med. 2016, 1, 11–23. [Google Scholar]
- Pond, K. Water Recreation and Disease: Plausibility of Associated Infections: Acute Effects, Sequelae, and Mortality; World Health Organization: Geneva, Switzerland, 2005. [Google Scholar]
- Petri, N.M.; Andri, D. Differential diagnostic problems of decompression sickness—Examples from specialist physicians’ practices in diving medicine. Arch. Med. Res. 2003, 34, 26–30. [Google Scholar] [PubMed]
- Auten, J.D.; Kuhne, M.A.; Walker, H.M.; Porter, H.O. Neurologic decompression sickness following cabin pressure fluctuations at high altitude. Aviat. Space Environ. Med. 2010, 81, 427–430. [Google Scholar] [PubMed]
- Mathieu, D. Handbook on Hyperbaric Medicine; Springer: Berlin, Germany, 2006; Volume 27. [Google Scholar]
- Pierleoni, P.; Pernini, L.; Palma, L.; Belli, A.; Valenti, S.; Maurizi, L.; Sabbatini, L.; Marroni, A. An innovative webRTC solution for e-health services. In Proceedings of the 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), Munich, Germany, 14–16 September 2016; pp. 1–6. [Google Scholar]
- Thalmann, E. Decompression Illness: What Is It and What Is the Treatment? Divers Alert Network (DAN): Durham, NC, USA, 2004. [Google Scholar]
- Pulley, S.A. Decompression Sickness. Available online: https://emedicine.medscape.com/article/769717-overview (accessed on 23 May 2019).
- Gempp, E.; Blatteau, J.E. Preconditioning methods and mechanisms for preventing the risk of decompression sickness in scuba divers: A review. Res. Sports Med. 2010, 18, 205–218. [Google Scholar] [PubMed]
- Eftedal, O.S.; Lydersen, S.; Brubakk, A.O. The relationship between venous gas bubbles and adverse effects of decompression after air dives. Undersea Hyperb. Med. 2007, 34, 99. [Google Scholar] [PubMed]
- Doolette, D.J. Venous gas emboli detected by two-dimensional echocardiography are an imperfect surrogate endpoint for decompression sickness. Diving Hyperb. Med. 2016, 46, 4–10. [Google Scholar] [PubMed]
- Park, J.H.; Jeong, Y.J.; Lee, G.E.; Oh, J.T.; Yang, J.R. 915-MHz continuous-wave doppler radar sensor for detection of vital signs. Electronics 2019, 8, 561. [Google Scholar]
- Ricci, S.; Meacci, V. Data-adaptive coherent demodulator for high dynamics pulse-wave ultrasound applications. Electronics 2018, 7, 434. [Google Scholar]
- Ricci, S. Switching power suppliers noise reduction in ultrasound doppler fluid measurements. Electronics 2019, 8, 421. [Google Scholar]
- Chappell, M.; Payne, S. A method for the automated detection of venous gas bubbles in humans using empirical mode decomposition. Ann. Biomed. Eng. 2005, 33, 1411–1421. [Google Scholar]
- Nishi, R.; Brubakk, A.; Eftedal, O. Bubble detection. Bennett and Elliott’s Physiology and Medicine of Diving, 5th ed.; W.B. Saunders Ltd.: London, UK, 2003; pp. 501–529. [Google Scholar]
- Shaikh, N.; Ummunisa, F. Acute management of vascular air embolism. J. Emerg. Trauma Shock 2009, 2, 180–185. [Google Scholar] [PubMed]
- Blogg, L.S.; Gennser, M.; Møllerløkken, A.; Brubakk, A.O. Ultrasound Detection of Vascular Decompression Bubbles: The Influence of New Technology and Considerations on Bubble Load. Diving Hyperb. Med. 2014, 44, 35–44. [Google Scholar] [PubMed]
- Smart, D.R.; Van den Broek, C.; Nishi, R.; Cooper, P.D.; Eastman, D. Field validation of Tasmania’s aquaculture industry bounce-diving schedules using Doppler analysis of decompression stress. Diving Hyperb. Med. 2014, 44, 124–136. [Google Scholar] [PubMed]
- Pierleoni, P.; Maurizi, L.; Palma, L.; Belli, A.; Valenti, S.; Marroni, A. A software for the annotation of embolic events in echo Doppler audio signals. Biomed. Inf. Insights 2017, 9, 1178222617745557. [Google Scholar]
- Kisman, K. Spectral analysis of Doppler ultrasonic decompression data. Ultrasonics 1977, 15, 105–110. [Google Scholar] [PubMed]
- Aydin, N. Dwt based adaptive threshold determination in embolic signal detection. In Proceedings of the Second NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2007), Edinburgh, UK, 5–8 August 2007; pp. 214–219. [Google Scholar]
- Northrop, R.B. Signals and Systems Analysis in Biomedical Engineering; CRC Press: Boca Raton, FL, USA, 2016. [Google Scholar]
- Gençer, M.; Bilgin, G.; Aydin, N. Embolic Doppler ultrasound signal detection via fractional Fourier transform. In Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, 3–7 July 2013; pp. 3050–3053. [Google Scholar]
- Tufan, K.; Ademoglu, A.; Kurtaran, E.; Yildiz, G.; Aydin, S.; Egi, S.M. Automatic detection of bubbles in the subclavian vein using doppler ultrasound signals. Aviat. Space Environ. Med. 2006, 77, 957–962. [Google Scholar]
- Kaur, A. Comparative analysis of wavelet transform and fourier transform. Glob. J. Res. Anal. 2016, 5, 105–110. [Google Scholar]
- Pellegrini, M.; Sini, F.; Taramasso, A. Wavelet-based automated localization and classification of peaks in streamflow data series. Comput. Geosci. 2012, 40, 200–204. [Google Scholar]
- Popov, D.; Gapochkin, A.; Nekrasov, A. An algorithm of daubechies wavelet transform in the final field when processing speech signals. Electronics 2018, 7, 120. [Google Scholar]
- Chan, B.C.; Chan, F.H.; Lam, F.; Lui, P.W.; Poon, P.W. Fast detection of venous air embolism in Doppler heart sound using the wavelet transform. IEEE Trans. Biomed. Eng. 1997, 44, 237–246. [Google Scholar]
- Marvasti, S.; Gillies, D.; Marvasti, F.; Markus, H.S. Online automated detection of cerebral embolic signals using a wavelet-based system. Ultrasound Med. Biol. 2004, 30, 647–653. [Google Scholar] [PubMed]
- Aydin, N.; Marvasti, F.; Markus, H.S. Embolic doppler ultrasound signal detection using discrete wavelet transform. IEEE Trans. Inf. Technol. Biomed. 2004, 8, 182–190. [Google Scholar] [PubMed]
- Huang, N.E.; Shen, Z.; Long, S.R.; Wu, M.C.; Shih, H.H.; Zheng, Q.; Yen, N.C.; Tung, C.C.; Liu, H.H. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences; The Royal Society: London, UK, 1998; Volume 454, pp. 903–995. [Google Scholar]
- Kopsinis, Y.; McLaughlin, S. Development of EMD-based denoising methods inspired by wavelet thresholding. IEEE Trans. Signal Process. 2009, 57, 1351–1362. [Google Scholar]
- Marroni, A.; Cali-Corleo, R.; Denoble, P. Understanding the safety of recreational diving. In DAN Europe’s Project SAFE DIVE Phase I: Fine Tuning of the Field Research Engine and Methods Proceedings of the International Joint Meeting on Hyperbaric and Underwater Medicine, EUBS, ECHM, ICHM, DAN; 1996; pp. 279–284. Available online: https://www.daneurope.org/c/document_library/get_file?folderId=13501&name=DLFE-113.pdf (accessed on 23 May 2019).
- Rilling, G.; Flandrin, P.; Goncalves, P. On empirical mode decomposition and its algorithms. In Proceedings of the IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing NSIP-03, Grado, Italy, 8–11 June 2003. [Google Scholar]
- Huang, N.E.; Wu, M.L.C.; Long, S.R.; Shen, S.S.; Qu, W.; Gloersen, P.; Fan, K.L. A confidence limit for the empirical mode decomposition and Hilbert spectral analysis. In Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences; The Royal Society: London, UK, 2003; Volume 459, pp. 2317–2345. [Google Scholar]
- Hou, T.Y.; Shi, Z. Sparse time-frequency representation of nonlinear and nonstationary data. Sci. China Math. 2013, 56, 2489–2506. [Google Scholar]
- Sharma, P.; Abrol, V.; Sao, A.K. Learned dictionaries for sparse representation based unit selection speech synthesis. In Proceedings of the 2016 Twenty Second National Conference on Communication (NCC), Guwahati, India, 4–6 March 2016; pp. 1–5. [Google Scholar]
- Sprent, P. Introduction to nonparametric estimation. J. R. Stat. Soc. Ser. A (Stat. Soc.) 2009, 172, 944–945. [Google Scholar]
- Germonpré, P.; Papadopoulou, V.; Hemelryck, W.; Obeid, G.; Lafère, P.; Eckersley, R.J.; Tang, M.X.; Balestra, C. The use of portable 2D echocardiography and ‘frame-based’bubble counting as a tool to evaluate diving decompression stress. Diving Hyperb. Med. 2014, 44, 5–13. [Google Scholar] [PubMed]
- Marroni, A.; Bennett, P.; Cronje, F.; Cali-Corleo, R.; Germonpre, P.; Pieri, M.; Bonuccelli, C.; Balestra, C. A deep stop during decompression from 82 fsw (25 m) significantly reduces bubbles and fast tissue gas tensions. Undersea Hyperb. Med. 2004, 31, 233–243. [Google Scholar] [PubMed]
- Donoho, D.L.; Johnstone, I.M. Ideal spatial adaptation by wavelet shrinkage. Biometrika 1994, 81, 425–455. [Google Scholar]
- Johnstone, I.M.; Silverman, B.W. Wavelet threshold estimators for data with correlated noise. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 1997, 59, 319–351. [Google Scholar]
- Donoho, D.L. De-noising by soft-thresholding. IEEE Trans. Inf. Theory 1995, 41, 613–627. [Google Scholar]
Spencer Level | Number of File | Matching (%) | Matching with Threshold (%) | Not Matching (%) |
---|---|---|---|---|
0 | 12 | 91.67 | 0 | 8.33 |
0.5 | 5 | 100 | 0 | 0 |
1 | 11 | 81.82 | 18.18 | 0 |
1.5 | 3 | 66.67 | 33.33 | 0 |
2 | 1 | 0 | 100 | 0 |
2.5 | 2 | 100 | 0 | 0 |
3 | 1 | 100 | 0 | 0 |
3.5 | 1 | 100 | 0 | 0 |
4 | 1 | 100 | 0 | 0 |
Algorithm Output | DAN Annotations | Total | |
---|---|---|---|
Bubble | Not Bubble | ||
Bubble | TP | FP | T+ |
Not Bubble | FN | TN | T− |
D+ | D− | N |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pierleoni, P.; Palma, L.; Belli, A.; Pieri, M.; Maurizi, L.; Pellegrini, M.; Marroni, A. An EMD-Based Algorithm for Emboli Detection in Echo Doppler Audio Signals. Electronics 2019, 8, 824. https://doi.org/10.3390/electronics8080824
Pierleoni P, Palma L, Belli A, Pieri M, Maurizi L, Pellegrini M, Marroni A. An EMD-Based Algorithm for Emboli Detection in Echo Doppler Audio Signals. Electronics. 2019; 8(8):824. https://doi.org/10.3390/electronics8080824
Chicago/Turabian StylePierleoni, Paola, Lorenzo Palma, Alberto Belli, Massimo Pieri, Lorenzo Maurizi, Marco Pellegrini, and Alessandro Marroni. 2019. "An EMD-Based Algorithm for Emboli Detection in Echo Doppler Audio Signals" Electronics 8, no. 8: 824. https://doi.org/10.3390/electronics8080824