Skip to main content
SpringerLink
Log in

A Deep Learning Approach to Using Wearable Seismocardiography (SCG) for Diagnosing Aortic Valve Stenosis and Predicting Aortic Hemodynamics Obtained by 4D Flow MRI

  • Original Article
  • Published:
Annals of Biomedical Engineering Aims and scope Submit manuscript

Abstract

In this paper, we explored the use of deep learning for the prediction of aortic flow metrics obtained using 4-dimensional (4D) flow magnetic resonance imaging (MRI) using wearable seismocardiography (SCG) devices. 4D flow MRI provides a comprehensive assessment of cardiovascular hemodynamics, but it is costly and time-consuming. We hypothesized that deep learning could be used to identify pathological changes in blood flow, such as elevated peak systolic velocity (\(\text {V}_{\text {max}}\)) in patients with heart valve diseases, from SCG signals. We also investigated the ability of this deep learning technique to differentiate between patients diagnosed with aortic valve stenosis (AS), non-AS patients with a bicuspid aortic valve (BAV), non-AS patients with a mechanical aortic valve (MAV), and healthy subjects with a normal tricuspid aortic valve (TAV). In a study of 77 subjects who underwent same-day 4D flow MRI and SCG, we found that the \(\text {V}_{\text {max}}\) values obtained using deep learning and SCGs were in good agreement with those obtained by 4D flow MRI. Additionally, subjects with non-AS TAV, non-AS BAV, non-AS MAV, and AS could be classified with ROC-AUC (area under the receiver operating characteristic curves) values of 92%, 95%, 81%, and 83%, respectively. This suggests that SCG obtained using low-cost wearable electronics may be used as a supplement to 4D flow MRI exams or as a screening tool for aortic valve disease.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Pelc, N. J., R. J. Herfkens, A. Shimakawa, and D. R. Enzmann. Phase contrast cine magnetic resonance imaging. J. Magn. Reson. 7(4):229–254, 1991.

    CAS  Google Scholar 

  2. Lotz, J., C. Meier, A. Leppert, and M. Galanski. Cardiovascular flow measurement with phase-contrast MR imaging: basic facts and implementation. Radiographics. 22(3):651–671, 2002.

    Article  PubMed  Google Scholar 

  3. Gatehouse, P. D., et al. Applications of phase-contrast flow and velocity imaging in cardiovascular MRI. Eur. Radiol. 15(10):2172–2184, 2005.

    Article  PubMed  Google Scholar 

  4. Srichai, M. B., R. P. Lim, S. Wong, and V. S. Lee. Cardiovascular applications of phase-contrast MRI. AJR Am. J. Roentgenol. 192(3):662–675, 2009.

    Article  PubMed  Google Scholar 

  5. Uribe, S., P. Beerbaum, T. S. Sørensen, A. Rasmusson, R. Razavi, and T. Schaeffter. Four-dimensional (4D) flow of the whole heart and great vessels using real-time respiratory self-gating. Magn. Reson. Med. 62(4):984–992, 2009.

    Article  PubMed  Google Scholar 

  6. Hope, M. D., et al. Bicuspid aortic valve: four-dimensional MR evaluation of ascending aortic systolic flow patterns. Radiology. 255(1):53–61, 2010.

    Article  PubMed  Google Scholar 

  7. Hope, M. D., et al. 4D flow CMR in assessment of valve-related ascending aortic disease. JACC Cardiovasc. Imaging. 4(7):781–787, 2011.

    Article  PubMed  Google Scholar 

  8. Markl, M., P. J. Kilner, and T. Ebbers. Comprehensive 4D velocity mapping of the heart and great vessels by cardiovascular magnetic resonance. J. Cardiovasc. Magn. Reson. 13(1):1–22, 2011.

    Article  Google Scholar 

  9. Clough, R. E., M. Waltham, D. Giese, P. R. Taylor, and T. Schaeffter. A new imaging method for assessment of aortic dissection using four-dimensional phase contrast magnetic resonance imaging. Vasc. Surg. 55(4):914–923, 2012.

    Article  Google Scholar 

  10. Dyverfeldt, P., et al. 4D flow cardiovascular magnetic resonance consensus statement. J. Magn. Reson. 17(1):1–19, 2015.

    Google Scholar 

  11. Azarine, A., et al. Four-dimensional flow MRI: principles and cardiovascular applications. Radiographics. 39(3):632–648, 2019.

    Article  PubMed  Google Scholar 

  12. Wymer, D. T., K. P. Patel, W. F. Burke III., and V. K. Bhatia. Phase-contrast MRI: physics, techniques, and clinical applications. Radiographics. 40(1):122–140, 2020.

    Article  PubMed  Google Scholar 

  13. Rizk, J. 4D flow MRI applications in congenital heart disease. Eur. Radiol. 31(2):1160–1174, 2021.

    Article  PubMed  Google Scholar 

  14. Markl, M., et al. Time-resolved three-dimensional phase-contrast MRI. J. Magn. Reson. Imaging. 17(4):499–506, 2003.

    Article  PubMed  Google Scholar 

  15. Markl, M., A. Frydrychowicz, S. Kozerke, M. Hope, and O. Wieben. 4D flow MRI. J. Magn. Reson. Imaging. 36(5):1015–1036, 2012.

    Article  PubMed  Google Scholar 

  16. Stankovic, Z., B. D. Allen, J. Garcia, K. B. Jarvis, and M. Markl. 4D flow imaging with MRI. Cardiovasc. Diagn. Ther. 4(2):173, 2014.

    PubMed Central  PubMed  Google Scholar 

  17. Soulat, G., P. McCarthy, and M. Markl. 4D Flow with MRI. Annu. Rev. Biomed. Eng. 22:103–126, 2020.

    Article  CAS  PubMed  Google Scholar 

  18. Schnell, S., et al. k-t GRAPPA accelerated four-dimensional flow MRI in the aorta: Effect on scan time, image quality, and quantification of flow and wall shear stress. Magn. Reson. Med. 72(2):522–533, 2014.

    Article  PubMed  Google Scholar 

  19. Barker, A. J., et al. Four-dimensional flow assessment of pulmonary artery flow and wall shear stress in adult pulmonary arterial hypertension: Results from two institutions. Magn. Reson. Med. 73(5):1904–1913, 2015.

    Article  PubMed  Google Scholar 

  20. Gabbour, M., S. Schnell, K. Jarvis, J. D. Robinson, M. Markl, and C. K. Rigsby. 4-D flow magnetic resonance imaging: blood flow quantification compared to 2-D phase-contrast magnetic resonance imaging and Doppler echocardiography. Pediatr. Radiol. 45(6):804–813, 2015.

    Article  PubMed  Google Scholar 

  21. Guzzardi, D. G., et al. Valve-related hemodynamics mediate human bicuspid aortopathy. J. Am. Coll. Cardiol. 66(8):892–900, 2015.

    Article  PubMed Central  PubMed  Google Scholar 

  22. van Ooij, P., et al. Characterization of abnormal wall shear stress using 4D flow MRI in human bicuspid aortopathy. Ann. Biomed. Eng. 43(6):1385–1397, 2015.

    Article  PubMed  Google Scholar 

  23. Van Ooij, P., et al. Reproducibility and interobserver variability of systolic blood flow velocity and 3D wall shear stress derived from 4D flow MRI in the healthy aorta. J. Magn. Reson. Imaging. 43(1):236–248, 2016.

    Article  PubMed  Google Scholar 

  24. Piatti, F., et al. 4D flow analysis of BAV-related fluid-dynamic alterations: evidences of wall shear stress alterations in absence of clinically-relevant aortic anatomical remodeling. Front. Physiol. 8:96, 2017.

    Article  Google Scholar 

  25. Feneis, J. F., et al. 4D flow MRI quantification of mitral and tricuspid regurgitation: Reproducibility and consistency relative to conventional MRI. J. Magn. Reson. Imaging. 48(4):1147–1158, 2018.

    Article  PubMed Central  PubMed  Google Scholar 

  26. Rodríguez-Palomares, J. F., et al. Aortic flow patterns and wall shear stress maps by 4D-flow cardiovascular magnetic resonance in the assessment of aortic dilatation in bicuspid aortic valve disease. J. Cardiovasc. Magn. Reson. 20(1):1–15, 2018.

    Article  Google Scholar 

  27. Fidock, B., et al. A systematic review of 4D-flow MRI derived mitral regurgitation quantification methods. Front. Cardiovasc. Med. 6:2, 2019.

    Article  Google Scholar 

  28. Garcia, J., A. J. Barker, and M. Markl. The role of imaging of flow patterns by 4D flow MRI in aortic stenosis. JACC Cardiovasc. Imaging. 12(2):252–266, 2019.

    Article  PubMed  Google Scholar 

  29. Garg, P., et al. Assessment of mitral valve regurgitation by cardiovascular magnetic resonance imaging. Nat. Rev. Cardiol. 17(5):298–312, 2020.

    Article  PubMed  Google Scholar 

  30. Jung, B., M. Honal, P. Ullmann, J. Hennig, and M. Markl. Highly k-t-space-accelerated phase-contrast MRI. Magn. Reson. Med. 60(5):1169–1177, 2008.

    Article  PubMed  Google Scholar 

  31. Stadlbauer, A., W. van der Riet, G. Crelier, and E. Salomonowitz. Accelerated time-resolved three-dimensional MR velocity mapping of blood flow patterns in the aorta using SENSE and k-t BLAST. Eur. J. Radiol. 75(1):e15–e21, 2010.

    Article  PubMed  Google Scholar 

  32. Tariq, U., A. Hsiao, M. Alley, T. Zhang, M. Lustig, and S. S. Vasanawala. Venous and arterial flow quantification are equally accurate and precise with parallel imaging compressed sensing 4D phase contrast MRI. J. Magn. Reson. Imaging. 37(6):1419–1426, 2013.

    Article  PubMed  Google Scholar 

  33. Dyvorne, H., et al. Abdominal 4D flow MR imaging in a breath hold: combination of spiral sampling and dynamic compressed sensing for highly accelerated acquisition. Radiology. 275(1):245–254, 2015.

    Article  PubMed  Google Scholar 

  34. Feng, L., T. Benkert, K. T. Block, D. K. Sodickson, R. Otazo, and H. Chandarana. Compressed sensing for body MRI. J. Magn. Reson. Imaging. 45(4):966–987, 2017.

    Article  PubMed  Google Scholar 

  35. Schnell, S., et al. Accelerated dual-venc 4D flow MRI for neurovascular applications. J. Magn. Reson. Imaging. 46(1):102–114, 2017.

    Article  PubMed Central  PubMed  Google Scholar 

  36. Ma, L. E., et al. Aortic 4D flow MRI in 2 minutes using compressed sensing, respiratory controlled adaptive k-space reordering, and inline reconstruction. Magn. Reson. Med. 81(6):3675–3690, 2019.

    Article  PubMed Central  PubMed  Google Scholar 

  37. Neuhaus, E., K. Weiss, R. Bastkowski, J. Koopmann, D. Maintz, and D. Giese. Accelerated aortic 4D flow cardiovascular magnetic resonance using compressed sensing: applicability, validation and clinical integration. J. Cardiovasc. Magn. Reson. 21(1):65, 2019.

    Article  PubMed Central  PubMed  Google Scholar 

  38. Salerno, D. M., and J. Zanetti. Seismocardiography for monitoring changes in left ventricular function during ischemia. Chest. 100(4):991–993, 1991.

    Article  CAS  PubMed  Google Scholar 

  39. Korzeniowska-Kubacka, I., M. Bilińska, and R. Piotrowicz. Usefulness of seismocardiography for the diagnosis of ischemia in patients with coronary artery disease. Ann. Noninvasive Electrocardiol. 10(3):281–287, 2005.

    Article  PubMed Central  PubMed  Google Scholar 

  40. Castiglioni, P., A. Faini, G. Parati, and M. D. Rienzo, Wearable Seismocardiography. In: 2007 29th Annual EMBS, 2007, pp. 3954–3957.

  41. Wick, C. A., et al. A system for seismocardiography-based identification of quiescent heart phases: implications for cardiac imaging. IEEE Trans. Inf. Technol. Biomed. 16(5):869–877, 2012.

    Article  PubMed Central  PubMed  Google Scholar 

  42. Di Rienzo, M., et al. Wearable seismocardiography: towards a beat-by-beat assessment of cardiac mechanics in ambulant subjects. Auton. Neurosci. 178(1):50–59, 2013.

    Article  PubMed  Google Scholar 

  43. Zanetti, J. M. and K. Tavakolian, Seismocardiography: Past, present and future. In: 2013 35th Annual EMBC, 2013, pp. 7004–7007.

  44. Becker, M., et al. Simplified detection of myocardial ischemia by seismocardiography. Herz. 39(5):586–592, 2014.

    CAS  PubMed  Google Scholar 

  45. Inan, O. T., et al. Ballistocardiography and seismocardiography: a review of recent advances. IEEE J. Biomed. Health Inform. 19(4):1414–1427, 2015.

    Article  PubMed  Google Scholar 

  46. Wahlström, J., et al. A hidden Markov model for seismocardiography. IEEE Trans. Biomed. Eng. 64(10):2361–2372, 2017.

    Article  PubMed  Google Scholar 

  47. Inan, O. T., et al. Novel wearable seismocardiography and machine learning algorithms can assess clinical status of heart failure patients. Circulation. 11(1):e004313, 2018.

    PubMed  Google Scholar 

  48. Choudhary, T., L. N. Sharma, and M. K. Bhuyan. Automatic detection of aortic valve opening using seismocardiography in healthy individuals. IEEE J. Biomed. Health. Inform. 23(3):1032–1040, 2019.

    Article  PubMed  Google Scholar 

  49. Taebi, A., B. E. Solar, A. J. Bomar, R. H. Sandler, and H. A. Mansy. Recent advances in seismocardiography. Vibration. 2(1):64–86, 2019.

    Article  PubMed Central  PubMed  Google Scholar 

  50. Johnson, E. M. I., et al. Detecting aortic valve-induced abnormal flow with seismocardiography and cardiac MRI. Ann. Biomed. Eng. 48(6):1779–1792, 2020.

    Article  PubMed Central  PubMed  Google Scholar 

  51. Hersek, S., B. Semiz, M. M. H. Shandhi, L. Orlandic, and O. T. Inan. A globalized model for mapping wearable seismocardiogram signals to whole-body ballistocardiogram signals based on deep learning. IEEE J. Biomed. Health Inform. 24(5):1296–1309, 2020.

    Article  PubMed  Google Scholar 

  52. Rai, D., H. K. Thakkar, S. S. Rajput, J. Santamaria, C. Bhatt, and F. Roca. A comprehensive review on seismocardiogram: current advancements on acquisition, annotation, and applications. Mathematics. 9(18):2243, 2021.

    Article  Google Scholar 

  53. Jafari Tadi, M., et al. A real-time approach for heart rate monitoring using a Hilbert transform in seismocardiograms. Physiol. Meas. 37(11):1885, 2016.

    Article  PubMed  Google Scholar 

  54. Berhane, H., et al. Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning. Magn. Reson. Med. 84(4):2204–2218, 2020.

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  55. Rose, M. J., et al. Efficient method for volumetric assessment of peak blood flow velocity using 4D flow MRI. J. Magn. Reson. Imaging. 44(6):1673–1682, 2016.

    Article  PubMed Central  PubMed  Google Scholar 

  56. Zia, J., J. Kimball, C. Rozell, and O. T. Inan. Harnessing the manifold structure of cardiomechanical signals for physiological monitoring during hemorrhage. IEEE Trans. Biomed. Eng. 68(6):1759–1767, 2021.

    Article  PubMed  Google Scholar 

  57. Friedrich, F. M., J. Schulz-Menger, T. Poetsch, B. Pilz, F. Uhlich, and R. Dietz. Quantification of valvular aortic stenosis by magnetic resonance imaging. Am. Heart J. 144(2):329–334, 2002.

    Article  PubMed  Google Scholar 

  58. Kupfahl, C., M. Honold, G. Meinhardt, H. Vogelsberg, A. Wagner, H. Mahrholdt, and U. Sechtem. Evaluation of aortic stenosis by cardiovascular magnetic resonance imaging: comparison with established routine clinical techniques. Heart. 90(8):893–901, 2004.

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  59. Suresh, P., N. Narayanan, C. V. Pranav, and V. Vijayaraghavan, End-to-end deep learning for reliable cardiac activity monitoring using seismocardiograms. 2020 19th IEEE ICMLA, pp. 1369–1375, 2020.

  60. Chan, M., V. G. Ganti, and O. T. Inan. Respiratory rate estimation using U-net-based cascaded framework from electrocardiogram and seismocardiogram signals. IEEE J. Biomed. Health Inform. 26(6):2481–2492, 2022.

    Article  PubMed Central  PubMed  Google Scholar 

  61. Thakkar, H. K., and P. K. Sahoo. Towards automatic and fast annotation of seismocardiogram signals using machine learning. IEEE Sens. J. 20(5):2578–2589, 2020.

    Article  Google Scholar 

  62. Haescher, M., F. Höpfner, W. Chodan, D. Kraft, M. Aehnelt, and B. Urban. Transforming seismocardiograms into electrocardiograms by applying convolutional autoencoders. In: IEEE ICASSP. pp. 4122–4126, 2020.

  63. Stalder, A. F., M. F. Russe, A. Frydrychowicz, J. Bock, J. Hennig, and M. Markl. Quantitative 2D and 3D phase contrast MRI: optimized analysis of blood flow and vessel wall parameters. Magn. Reson. Med. 60(5):1218–1231, 2008.

    Article  CAS  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL, 60611, USA

    Mahmoud Ebrahimkhani, Ethan M. I. Johnson, Joshua D. Robinson, Cynthia K. Rigsby, Bradly D. Allen & Michael Markl

  2. Ann & Robert H. Lurie Children’s Hospital, Chicago, IL, 60611, USA

    Aparna Sodhi, Joshua D. Robinson & Cynthia K. Rigsby

  3. Department of Pediatrics, Feinberg School of Medicine, Northwestern University, Chicago, IL, 60611, USA

    Joshua D. Robinson & Cynthia K. Rigsby

  4. Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, IL, 60208, USA

    Michael Markl

Authors
  1. Mahmoud Ebrahimkhani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ethan M. I. Johnson
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aparna Sodhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joshua D. Robinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Cynthia K. Rigsby
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bradly D. Allen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Michael Markl
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Michael Markl.

Ethics declarations

Conflict of interest

No benefits in any form have been or will be received from a commercial party related directly or indirectly to the subject of this manuscript.

Additional information

Associate Editor Umberto Morbiducci oversaw the review of this article.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ebrahimkhani, M., Johnson, E.M.I., Sodhi, A. et al. A Deep Learning Approach to Using Wearable Seismocardiography (SCG) for Diagnosing Aortic Valve Stenosis and Predicting Aortic Hemodynamics Obtained by 4D Flow MRI. Ann Biomed Eng 51, 2802–2811 (2023). https://doi.org/10.1007/s10439-023-03342-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10439-023-03342-7

Keywords

Search

Navigation