Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients
-
Fethi Cheikh
and
Salim Sbaa
Abstract
Although fetal phonocardiogram (fPCG) signals have become a good indicator for discovered heart disease, they may be contaminated by various noises that reduce the signals quality and the final diagnosis decision. Moreover, the noise may cause the risk of the data to misunderstand the heart signal and to misinterpret it. The main objective of this paper is to effectively remove noise from the fPCG signal to make it clinically feasible. So, we proposed a novel noise reduction method based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), wavelet threshold and Crow Search Algorithm (CSA). This noise reduction method, named ICEEMDAN-DWT-CSA, has three major advantages. They were, (i) A better suppress of mode mixing and a minimized number of IMFs, (ii) A choice of wavelet corresponding to the study signal proven by the literature and (iii) Selection of the optimal threshold value. Firstly, the noisy fPCG signal is decomposed into Intrinsic Mode Functions (IMFs) by the (ICEEMDAN). Each noisy IMFs were decomposed by the Discrete Wavelet Transform (DWT). Then, the optimal threshold value using the (CSA) technique is selected and the thresholding function is carried out in the detail’s coefficients. Secondly, each denoised (IMFs) is reconstructed by applying the Inverse Discrete Wavelet Transform (IDWT). Finally, all these denoised (IMFs) are combined to get the denoised fPCG signal. The performance of the proposed method has been evaluated by Signal to Noise Ratio (SNR), Mean Square Error (MSE) and the Correlation Coefficient (COR). The experiment gave a better result than some standard methods.
-
Research funding: No funding.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: Authors state no conflict of interest.
-
Conflict of interest: The authors have no competing interests to declare.
-
Informed consent: Not applicable.
-
Ethical approval: Not applicable.
References
1. Chetlur, AP, Hart, S, Moreno, WA, Moreno, VA, Sankar, R. Trends in fetal monitoring through phonocardiography: challenges and future directions. Biomed Signal Process Control 2017;33:289–305. https://doi.org/10.1016/j.bspc.2016.11.007.Search in Google Scholar
2. Kovacs, F, Torok, M, Habermajer, I. A rule-based phonocardiographic method for long-term foetal heart rate monitoring. IEEE Trans Biomed Eng 2000;47:124–30. https://doi.org/10.1109/10.817627.Search in Google Scholar PubMed
3. Sbrollini, A, Strazza, A, Caragiuli, M, Mozzoni, C, Tomassini, S. Fetal phonocardiogram denoising by wavelet transformation: robustness to noise. Comput in Cardio (CinC) 2017;44:1–4. https://doi.org/10.22489/cinc.2017.331-075.Search in Google Scholar
4. Fuadina, I, Hendry, J, Zulherman, D. Performance analysis of fetal-phonocardiogram signal denoising using the discrete wavelet transform. J Infotel 2019;11:99–107. https://doi.org/10.20895/infotel.v11i4.458.Search in Google Scholar
5. Kyzdarbekova, AS, Dutbaeva, DM, Kasymbekova, KB, Kyzdarbek, US. Adaptive noise reduction phonocardiograms based on wavelet transformation. In: Proc quality management, transport and information security, information technologies (IT&QM&IS). St. Petersburg, Russia: IEEE; 2017: 391–4. pp.10.1109/ITMQIS.2017.8085841Search in Google Scholar
6. Donoho, DL. Denoising by soft thresholding. IEEE Trans Inf Theor 1993;43:933–6.Search in Google Scholar
7. Donoho, DL, Johnstone, IM. Ideal adaptation by wavelet shrinkage. Biometrika 1994;81:425–55. https://doi.org/10.1093/biomet/81.3.425.Search in Google Scholar
8. Huang, NE, Shen, Z, Lng, SR, Wu, MC, Shih, HH, Zheng, Q, et al.. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A: Math, Phys Eng 1998;454:903–95. https://doi.org/10.1098/rspa.1998.0193.Search in Google Scholar
9. Salman, AH, Ahmadi, N, Mengko, R, Langi, AZR, Mengko, TLR. Empirical Mode Decomposition (EMD) based denoising method for heart sound signal and its performance analysis. IJ Elec & Comput Eng (IJECE) 2016;6:1–8. https://doi.org/10.11591/ijece.v6i5.11344.Search in Google Scholar
10. Wu, Z, Huang, NE. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 2009;1:1–41. https://doi.org/10.1142/s1793536909000047.Search in Google Scholar
11. Yeh, JR, Shieh, JS, Huang, NE. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method. Adv Adapt Data Anal 2010;2:135–56. https://doi.org/10.1142/s1793536910000422.Search in Google Scholar
12. Torres, ME, Colominas, MA, Schlotthauer, G, Flandrin, P. A complete ensemble empirical mode decomposition with adaptive noise. In: Proc IEEE acou spee signal process (ICASSP). Prague, Czech Republic: Prague Congress Center; 2011:4144–7 pp.10.1109/ICASSP.2011.5947265Search in Google Scholar
13. Colominas, MA, Schlotthauer, G, Torres, ME. Improved complete ensemble EMD: a suitable tool for biomedical signal processing. Biomed. Signal Process 2014;14:19–29. https://doi.org/10.1016/j.bspc.2014.06.009.Search in Google Scholar
14. Flandrin, P, Goncalves, P, Rilling, G. Detrending and denoising with empirical mode decomposition. In: Proc 12th europ signal process conf, vol 2. Vienna, Austria: EUSIPCO; 2004: 1581–4. pp.10.1109/LSP.2003.821662Search in Google Scholar
15. Kopsinis, Y, McLaughlin, S. Development of EMD-based denoising methods inspired by wavelet thresholding. IEEE Trans Signal Process 2009;57:1351–62. https://doi.org/10.1109/tsp.2009.2013885.Search in Google Scholar
16. Ashfanoor, KM, Shahnaz, C. Denoising of ECG signals based on noise reduction algorithms in EMD and wavelet domains. Biomed Signal Process Control 2012;7:481–9. https://doi.org/10.1016/j.bspc.2011.11.003.Search in Google Scholar
17. Taebi, A, Mansg, HA. Noise Cancellation from Vibrocardiographic signals based on the ensemble empirical mode decomposition. J Appl Biotechnol Bioeng 2017;2:00024. https://doi.org/10.15406/jabb.2017.02.00024.Search in Google Scholar
18. Ladrova, M, Sidikova, M, Martinek, R, Jaros, R, Bilik, P. Elimination of interference phonocardiogram signal based on wavelet transform and empirical decomposition. IFAC-PO 2019;52:440–5. https://doi.org/10.1016/j.ifacol.2019.12.703.Search in Google Scholar
19. Chen, W, Wang, SX, Chuai, XY, Zhang, Z. Random noise reduction based on ensemble empirical mode decomposition and wavelet threshold filtering. Adv Mater Res 2012;518–523:3887–90. https://doi.org/10.4028/www.scientific.net/amr.518-523.3887.Search in Google Scholar
20. Li, YX, Wang, L. A novel noise reduction technique for underwater acoustic signals based on complete ensemble empirical mode decomposition with adaptive noise, minimum mean square variance criterion and least mean square adaptive filter. J Def Techno 2020;16:543–54. https://doi.org/10.1016/j.dt.2019.07.020.Search in Google Scholar
21. Dong, LC, Guo, XM, Zheng, YN. Wavelet packet de-noising algorithm for heart sound signals based on CEEMD. J Vib Shock 2019;38:192–8.Search in Google Scholar
22. Xu, Y, Luo, M, Li, T, Song, G. ECG signal de-noising and baseline wander correction based on CEEMDAN and wavelet threshold. J Sens 2017;17:2754–70. https://doi.org/10.3390/s17122754.Search in Google Scholar PubMed PubMed Central
23. Zhang, JX, Guo, Y, Shen, Y, Zhao, DF, Li, M. Improved CEEMDAN–wavelet transform de-noising method and its application in well logging noise reduction. J Geophys Eng 2018;15:775–87. https://doi.org/10.1088/1742-2140/aaa076.Search in Google Scholar
24. Sameera, VMS, Sudhish, NG. A review on medical image denoising algorithms. Biomed Signal Process Control 2020;61:102036. https://doi.org/10.1016/j.bspc.2020.102036.Search in Google Scholar
25. Rohit, V, Jahid, A. A comparative study of various types of image noise and efficient noise removal techniques. IJ Adv Res in Comput Sc & Sof Eng (IJARCSSE) 2013;3:617–22.Search in Google Scholar
26. Akhilesh, B, Aditya, G, Nidhi, S. Wavelet transform based image denoise using threshold approaches. IJ Eng Adv Tech (IJEAT) 2012;1:218–21.Search in Google Scholar
27. Umbaugh, SE. Computer vision and image processing: a practical approach using CVIPTools, 6st ed. New Jersey: Prentice Hall PTR; 1998.Search in Google Scholar
28. Liu, Y. Image denoising method based on threshold, wavelet transform and genetic algorithm. IJ Signal Process, Image Process & Patt Rec 2015;8:29–40. https://doi.org/10.14257/ijsip.2015.8.2.04.Search in Google Scholar
29. Dass, R. Speckle noise reduction of ultrasound images using BFO cascaded with wiener filter and discrete wavelet transform in homomorphic region. Procedia Comput Sci 2018;132:1543–51. https://doi.org/10.1016/j.procs.2018.05.118.Search in Google Scholar
30. Kennedy, J. Particle swarm optimization. In: Encyclopedia of machine learning. Berlin, Germany: Springer; 2010.10.1109/ICNN.1995.488968Search in Google Scholar
31. Askarzadeh, A. A novel metaheuristic method for solving constrained engineering optimizations problems: crow search algorithm. Comp & Struct 2016;169:1–12.10.1016/j.compstruc.2016.03.001Search in Google Scholar
32. Xu, J, Wang, Z, Tan, C, Si, L, Liu, X. A novel denoising method for an acoustic-based system through empirical mode decomposition and an improved fruit fly optimization algorithm. Appl Sci 2017;7:215–348. https://doi.org/10.3390/app7030215.Search in Google Scholar
33. Gagnon, L. Wavelet filtering of speckle noise- some numerical results. In: Proc vision interface, trois-revieres. Quebec, Canada: Vision Interface; 1999:336–42 pp.Search in Google Scholar
34. Benhassine, NE, Boukaache, A, Boudjehem, D. Medical image denoising using optimal thresholding of wavelet coefficients with selection of the best decomposition level and mother wavelet. IJ Imaging Sys Tech 2021;31:1906–20. https://doi.org/10.1002/ima.22589.Search in Google Scholar
35. Cesarelli, M, Ruffo, M, Romano, M, Bifulco, P. Simulation of foetal phonocardiographic recordings for testing of FHR extraction algorithms. Comput Progr Biomed 2012;107:513–23. https://doi.org/10.1016/j.cmpb.2011.11.008.Search in Google Scholar PubMed
36. Benhassine, NE, Boukaache, A, Boudjehem, D. Classification of mammogram images using the energy probability infrequency domain and most discriminative power coefficients. IJ Imaging Sys Tech 2019;30:45–56. https://doi.org/10.1002/ima.22352.Search in Google Scholar
37. Rouis, M, Sbaa, S, Benhassine, NE. The effectiveness of the choice of criteria on the stationary and non-stationary noise removal in the phonocardiogram (PCG) signal using discrete wavelet transform. Biomed Eng Biomed Tech 2019;65:353–66. https://doi.org/10.1515/bmt-2019-0197.Search in Google Scholar PubMed
38. Graps, A. An introduction to wavelets. IEEE Comput Sci Eng 1995;2:50–61. https://doi.org/10.1109/99.388960.Search in Google Scholar
39. Wang, G, Zesong, W, Jinhai, L. A new image denoising method based on adaptive multiscale morphological edge detection. Math Probl Eng 2017;8:1–11. https://doi.org/10.1155/2017/4065306.Search in Google Scholar
40. Eindhoven University of Technology MRJE. Wavelet theory and applications: a literature study, 53. Netherlands: Cont Sys Tech; 2005.Search in Google Scholar
41. Addison, PS. The illustrated wavelet transforms hand-book: introductory theory and applications in science, engineering, medicine and finance, 2nd ed. CRC Press; 2017: 464. p.10.1201/9781315372556Search in Google Scholar
42. Donoho, DL, Johnstone, IM. Adapting to unknown smoothness via wavelet shrinkage. J Am Stat Assoc 1995;90:200–1224. https://doi.org/10.1080/01621459.1995.10476626.Search in Google Scholar
43. Gupta, D, Sundaram, S, khanna, A, Hassanien, AE, Dealbuquerque, VHC. Improved diagnosis of Parkinson’s disease based on optimized crow search algorithm. Comput Elect Eng 2018;68:412–24. https://doi.org/10.1016/j.compeleceng.2018.04.014.Search in Google Scholar
44. Jain, M, Rani, A, Singh, V. An improved crow search algorithm for high-dimensional problems. J Intell Fuz Sys 2017;33:3597–614. https://doi.org/10.3233/jifs-17275.Search in Google Scholar
45. Rouis, M, Ouafi, A, Sbaa, S. Optimal level and order detection in wavelet decomposition. Biomed Eng Biomed Tech 2018;63:1–14.Search in Google Scholar
46. Gradolewski, D, Redlarski, G. Wavelet-based denoising method for real PCG signal recorded by mobile devices in noisy environment. J Comput Biol Med 2014;52:119–29. https://doi.org/10.1016/j.compbiomed.2014.06.011.Search in Google Scholar PubMed
47. Puneet, KJ, Anil, KT. An adaptive thresholding method for the wavelet based denoising of phonocardiogram signal. Biomed Sig Process & Cont 2017;9:388–99. https://doi.org/10.1016/j.bspc.2017.07.002.Search in Google Scholar
48. Tomassini, S, Strazza, A, Sbrollini, A, Marcantoni, I, Morettini, M, Fioretti, S, et al.. Wavelet filtering of fetal phonocardiography: a comparative analysis. Math Biosci Eng 2019;16:6034–46. https://doi.org/10.3934/mbe.2019302.Search in Google Scholar PubMed
49. Ghosh, SK, Tripathy, R, Ponnalagu, RN. Evaluation of performance metrics and denoising of PCG signal using wavelet-based decomposition. In: Proc IEEE 17th India council. New Delhi, India: INDICON; 2020: 1–6. pp.10.1109/INDICON49873.2020.9342464Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients
- Layer recurrent neural network-based diagnosis of Parkinson’s disease using voice features
- Automatic sleep scoring with LSTM networks: impact of time granularity and input signals
- Computer-aided diagnosis system for retinal disorder classification using optical coherence tomography images
- Designing and in vitro testing of a novel patient-specific total knee prosthesis using the probabilistic approach
- Biomechanical comparison of different prosthetic materials and posterior implant angles in all-on-4 treatment concept by three-dimensional finite element analysis
- Non-woven textiles for medical implants: mechanical performances improvement
- Corrigendum
- Corrigendum to: Developing a novel resorptive hydroxyapatite-based bone substitute for over-critical size defect reconstruction: physicochemical and biological characterization and proof of concept in segmental rabbit’s ulna reconstruction
Articles in the same Issue
- Frontmatter
- Research Articles
- Fetal phonocardiogram signals denoising using improved complete ensemble (EMD) with adaptive noise and optimal thresholding of wavelet coefficients
- Layer recurrent neural network-based diagnosis of Parkinson’s disease using voice features
- Automatic sleep scoring with LSTM networks: impact of time granularity and input signals
- Computer-aided diagnosis system for retinal disorder classification using optical coherence tomography images
- Designing and in vitro testing of a novel patient-specific total knee prosthesis using the probabilistic approach
- Biomechanical comparison of different prosthetic materials and posterior implant angles in all-on-4 treatment concept by three-dimensional finite element analysis
- Non-woven textiles for medical implants: mechanical performances improvement
- Corrigendum
- Corrigendum to: Developing a novel resorptive hydroxyapatite-based bone substitute for over-critical size defect reconstruction: physicochemical and biological characterization and proof of concept in segmental rabbit’s ulna reconstruction
