ABSTRACT
Seismocardiography is a method commonly used to monitor and prevent cardiovascular diseases. However, noise and artifacts in the signals often interfere with the assessment of cardiac health and the analysis of the signal morphology. Therefore, this work presents a new approach to denoise seismocardiography signals by applying fully convolutional denoising autoencoders. In order to investigate the suitability and robustness of this approach, a series of experiments have been carried out with respect to the optimal configuration for the denoising task and a comparison with wavelet denoising as a traditional approach. Furthermore, the practical applicability of the method is tested with the use case of transforming noisy seismocardiography signals into electrocardiography signals. Our approach using autoencoders outperforms the commonly used wavelet denoising. Additionally, we demonstrate that the widespread usage of Butterworth filters may not only be unnecessary but even detrimental. Finally, the generalizability of the method is verified on unseen data. With those combined improvements in noise reduction, the assessment of cardiac health using seismocardiography in the presence of noise may be facilitated in the future.
- Aditya Sundar and Vivek Pahwa. 2017. Evaluating the Performance of State of the Art Algorithms for Enhancement of Seismocardiogram Signals. In Proceedings of the First International Conference on Intelligent Computing and Communication(Advances in Intelligent Systems and Computing), Jyotsna Kumar Mandal, Suresh Chandra Satapathy, Manas Kumar Sanyal, and Vikrant Bhateja (Eds.). Springer, Singapore, 37–45. https://doi.org/10.1007/978-981-10-2035-3_5Google ScholarCross Ref
- Manjula B M and Chirag Sharma. 2018. Ballistocardiogram Signal Denoising Using Independent Component Analysis. 259–267. https://doi.org/10.1007/978-981-10-4762-6_24Google ScholarCross Ref
- Hsin-Tien Chiang, Yi-Yen Hsieh, Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao, and Shao-Yi Chien. 2019. Noise Reduction in ECG Signals Using Fully Convolutional Denoising Autoencoders. IEEE Access 7 (2019), 60806–60813. https://doi.org/10.1109/ACCESS.2019.2912036Google ScholarCross Ref
- Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2016. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arxiv:1511.07289 [cs]Google Scholar
- M. Di Rienzo, E. Vaini, P. Castiglioni, G. Merati, P. Meriggi, G. Parati, A. Faini, and F. Rizzo. 2013. Wearable Seismocardiography: Towards a Beat-by-Beat Assessment of Cardiac Mechanics in Ambulant Subjects. Autonomic Neuroscience 178, 1 (Nov. 2013), 50–59. https://doi.org/10.1016/j.autneu.2013.04.005Google ScholarCross Ref
- Miguel A García-González, Ariadna Argelagós-Palau, Mireya Fernández-Chimeno, and Juan Ramos-Castro. 2013. A Comparison of Heartbeat Detectors for the Seismocardiogram. In Computing in Cardiology 2013. 461–464.Google Scholar
- Ary L. Goldberger, Luis A. N. Amaral, Leon Glass, Jeffrey M. Hausdorff, Plamen Ch. Ivanov, Roger G. Mark, Joseph E. Mietus, George B. Moody, Chung-Kang Peng, and H. Eugene Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101, 23 (June 2000). https://doi.org/10.1161/01.CIR.101.23.e215Google ScholarCross Ref
- Marian Haescher, Florian Höpfner, Wencke Chodan, Dimitri Kraft, Mario Aehnelt, and Bodo Urban. 2020. Transforming Seismocardiograms Into Electrocardiograms by Applying Convolutional Autoencoders. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4122–4126. https://doi.org/10.1109/ICASSP40776.2020.9053130Google ScholarCross Ref
- Abdul Q. Javaid, Hazar Ashouri, Alexis Dorier, Mozziyar Etemadi, J. Alex Heller, Shuvo Roy, and Omer T. Inan. 2017. Quantifying and Reducing Motion Artifacts in Wearable Seismocardiogram Measurements During Walking to Assess Left Ventricular Health. IEEE Transactions on Biomedical Engineering 64, 6 (June 2017), 1277–1286. https://doi.org/10.1109/TBME.2016.2600945Google ScholarCross Ref
- Matti Kaisti, Mojtaba Jafari Tadi, Olli Lahdenoja, Tero Hurnanen, Antti Saraste, Mikko Pänkäälä, and Tero Koivisto. 2019. Stand-Alone Heartbeat Detection in Multidimensional Mechanocardiograms. IEEE Sensors Journal 19, 1 (Jan. 2019), 234–242. https://doi.org/10.1109/JSEN.2018.2874706Google ScholarCross Ref
- Puneet Kumar Jain and Anil Kumar Tiwari. 2016. A Novel Method for Suppression of Motion Artifacts from the Seismocardiogram Signal. In 2016 IEEE International Conference on Digital Signal Processing (DSP). 6–10. https://doi.org/10.1109/ICDSP.2016.7868504Google ScholarCross Ref
- David J. Lin, Jacob P. Kimball, Jonathan Zia, Venu G. Ganti, and Omer T. Inan. 2022. Reducing the Impact of External Vibrations on Fiducial Point Detection in Seismocardiogram Signals. IEEE Transactions on Biomedical Engineering 69, 1 (2022), 176–185. https://doi.org/10.1109/TBME.2021.3090376Google ScholarCross Ref
- Loc Luu and Anh Dinh. 2018. Artifact Noise Removal Techniques on Seismocardiogram Using Two Tri-Axial Accelerometers. Sensors (Basel, Switzerland) 18 (04 2018). https://doi.org/10.3390/s18041067Google ScholarCross Ref
- Lis Neubeck, Genevieve Coorey, David Peiris, John Mulley, Emma Heeley, Fred Hersch, and Julie Redfern. 2016. Development of an Integrated E-Health Tool for People with, or at High Risk of, Cardiovascular Disease: The Consumer Navigation of Electronic Cardiovascular Tools (CONNECT) Web Application. International Journal of Medical Informatics 96 (Dec. 2016), 24–37. https://doi.org/10.1016/j.ijmedinf.2016.01.009Google ScholarCross Ref
- World Health Organization. 2023. World Health Statistics 2023: Monitoring Health for the SDGs, Sustainable Development Goals. World Health Organization.Google Scholar
- Keya Pandia, Sourabh Ravindran, Randy Cole, Gregory Kovacs, and Laurent Giovangrandi. 2010. Motion artifact cancellation to obtain heart sounds from a single chest-worn accelerometer. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 590–593. https://doi.org/10.1109/ICASSP.2010.5495553Google ScholarCross Ref
- Deepak Rai, Hiren Kumar Thakkar, Shyam Singh Rajput, Jose Santamaria, Chintan Bhatt, and Francisco Roca. 2021. A Comprehensive Review on Seismocardiogram: Current Advancements on Acquisition, Annotation, and Applications. Mathematics 9, 18 (Jan. 2021), 2243. https://doi.org/10.3390/math9182243Google ScholarCross Ref
- D.M. Salerno and J.M. Zanetti. 1990. Seismocardiography : A New Technique for Recording Cardiac Vibrations. Concept, Method, and Initial Observations. Seismocardiography : a new technique for recording cardiac vibrations. Concept, method, and initial observations 9, 2 (1990), 111–118.Google Scholar
- Amirtahà Taebi, Brian E. Solar, Andrew J. Bomar, Richard H. Sandler, and Hansen A. Mansy. 2019. Recent Advances in Seismocardiography. Vibration 2, 1 (March 2019), 64–86. https://doi.org/10.3390/vibration2010005Google ScholarCross Ref
- Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. 2008. Extracting and Composing Robust Features with Denoising Autoencoders. In Proceedings of the 25th International Conference on Machine Learning(ICML ’08). Association for Computing Machinery, New York, NY, USA, 1096–1103. https://doi.org/10.1145/1390156.1390294Google ScholarDigital Library
- Chenxi Yang, Foli Fan, Nicole Aranoff, Philip Green, Yuwen Li, Chengyu Liu, and Negar Tavassolian. 2021. An Open-Access Database for the Evaluation of Cardio-Mechanical Signals From Patients With Valvular Heart Diseases. Frontiers in Physiology 12 (Sept. 2021), 750221. https://doi.org/10.3389/fphys.2021.750221Google ScholarCross Ref
- Chenxi Yang and Negar Tavassolian. 2016. Motion Noise Cancellation in Seismocardiogram of Ambulant Subjects with Dual Sensors. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 5881–5884. https://doi.org/10.1109/EMBC.2016.7592066Google ScholarCross Ref
- J.M. Zanetti and D.M. Salerno. 1991. Seismocardiography: A Technique for Recording Precordial Acceleration. In [1991]Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium. 4–9. https://doi.org/10.1109/CBMS.1991.128936Google ScholarCross Ref
Index Terms
- Making Noise - Improving Seismocardiography Based Heart Analysis With Denoising Autoencoders
Recommendations
Denoising of Heart Sound Signals Using Discrete Wavelet Transform
Signal denoising remains to be one of the main problems in the field of signal processing. Various signal denoising algorithms using wavelet transforms have been introduced. Wavelets show superior signal denoising performance due to their properties ...
Myopotential denoising of ECG signals using wavelet thresholding methods
We present empirical comparisons of several wavelet-denoising methods applied to the problem of removing (denoising) myopotential noise from the observed noisy ECG signal. Namely, we compare the denoising accuracy and robustness of several wavelet ...
Signal Denoising Based on the Adaptive Shrinkage Function and Neighborhood characteristics
In order to provide more accurate and better denoising results, a novel denoising method based on an adaptive shrinkage function and neighborhood characteristics is proposed in this paper for one-dimensional signal. According to the number of large ...
Comments