Skip to main content

Advertisement

SpringerLink
Log in

Automated multi-beat tissue Doppler echocardiography analysis using deep neural networks

  • Review Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Tissue Doppler imaging is an essential echocardiographic technique for the non-invasive assessment of myocardial blood velocity. Image acquisition and interpretation are performed by trained operators who visually localise landmarks representing Doppler peak velocities. Current clinical guidelines recommend averaging measurements over several heartbeats. However, this manual process is both time-consuming and disruptive to workflow. An automated system for accurate beat isolation and landmark identification would be highly desirable. A dataset of tissue Doppler images was annotated by three cardiologist experts, providing a gold standard and allowing for observer variability comparisons. Deep neural networks were trained for fully automated predictions on multiple heartbeats and tested on tissue Doppler strips of arbitrary length. Automated measurements of peak Doppler velocities show good Bland–Altman agreement (average standard deviation of 0.40 cm/s) with consensus expert values; less than the inter-observer variability (0.65 cm/s). Performance is akin to individual experts (standard deviation of 0.40 to 0.75 cm/s). Our approach allows for > 26 times as many heartbeats to be analysed, compared to a manual approach. The proposed automated models can accurately and reliably make measurements on tissue Doppler images spanning several heartbeats, with performance indistinguishable from that of human experts, but with significantly shorter processing time.

Highlights

• Novel approach successfully identifies heartbeats from Tissue Doppler Images

• Accurately measures peak velocities on several heartbeats

• Framework is fast and can make predictions on arbitrary length images

• Patient dataset and models made public for future benchmark studies

Graphical Abstract

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Quiñones M, Otto C, Stoddard M, Waggoner A, Zoghbi W (2002) Recommendations for quantification of Doppler echocardiography: a report from the Doppler quantification task force of the nomenclature and standards committee of the American Society of Echocardiography. J Am Soc Echocardiogr 15(2):167–184

    Article  PubMed  Google Scholar 

  2. Nagueh S, Smiseth O, Appleton C, Byrd B, Dokainish H, Edvardsen T, Flachskampf F, Gillebert T, Klein A, Lancellotti P, Marino P, Oh J, Popescu B, Waggoner A (2016) Recommendations for the evaluation of left ventricular diastolic function by echocardiography: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr 29(4):277–314

    Article  PubMed  Google Scholar 

  3. Ho CY, Solomon SD (2006) A clinician's guide to tissue Doppler imaging. Circulation 113(10):e396–e398

  4. Cikes M, Solomon S (2015) Beyond ejection fraction: an integrative approach for assessment of cardiac structure and function in heart failure. Eur Heart J 37(21):1642–1650

    Article  PubMed  Google Scholar 

  5. Kadappu KK, Thomas L (2015) Tissue Doppler imaging in echocardiography: value and limitations. Heart Lung Circ 24(3):224–233

  6. Nikitin N (2005) Prognostic value of systolic mitral annular velocity measured with Doppler tissue imaging in patients with chronic heart failure caused by left ventricular systolic dysfunction. Heart 92(6):775–779

    Article  PubMed  PubMed Central  Google Scholar 

  7. Nagueh S, Appleton C, Gillebert T, Marino P, Oh J, Smiseth O, Waggoner A, Flachskampf F, Pellikka P, Evangelisa A (2008) Recommendations for the evaluation of left ventricular diastolic function by echocardiography. Eur J Echocardiogr 10(2):165–1938

    Article  Google Scholar 

  8. Meluzín J (2001) Pulsed Doppler tissue imaging of the velocity of tricuspid annular systolic motion. A new, rapid, and non-invasive method of evaluating right ventricular systolic function. Eur Heart J 22(4):340–348

    Article  PubMed  Google Scholar 

  9. Yamamoto T, Oki T, Yamada H, Tanaka H, Ishimoto T, Wakatsuki T, Tabata T, Ito S (2003) Prognostic value of the atrial systolic mitral annular motion velocity in patients with left ventricular systolic dysfunction. J Am Soc Echocardiogr 16(4):333–339

    Article  PubMed  Google Scholar 

  10. Flachskampf F, Martensson M (2014) How should tissue Doppler tracings be measured? Eur Heart J - Cardiovasc Imaging 15(7):828–829

    Article  PubMed  Google Scholar 

  11. Dhutia N, Zolgharni M, Willson K, Cole G, Nowbar A, Dawson D, Zielke S, Whelan C, Newton J, Mayet J, Manisty C, Francis D (2014) Guidance for accurate and consistent tissue Doppler velocity measurement: comparison of echocardiographic methods using a simple vendor-independent method for local validation. Eur Heart Jo - Cardiovasc Imaging 15(7):817–827

    Article  Google Scholar 

  12. Lui E, Steinman A, Cobbold R, Johnston K (2005) Human factors as a source of error in peak Doppler velocity measurement. J Vasc Surg 42(5):972.e1-972.e10

    Article  Google Scholar 

  13. Matthew T, Steeds R, Jones R, Kanagala P, Lloyd G, Knight D, O’Gallagher K, Oxborough D, Rana B, Ring L, Sandoval J, Wharton G, Wheeler R (2013) ECHO - The Journal of the British Society of Echocardiography, pp 1–6

  14. Finegold J, Manisty C, Cecaro F, Sutaria N, Mayet J, Francis D (2013) Choosing between velocity-time-integral ratio and peak velocity ratio for calculation of the dimensionless index (or aortic valve area) in serial follow-up of aortic stenosis. Int J Cardiol 167(4):1524–1531

    Article  PubMed  Google Scholar 

  15. Testuz A, Muller H, Keller P, Meyer P, Stampfli T, Sekoranja L, Vuille C, Burri H (2012) Diagnostic accuracy of pocket-size handheld echocardiographs used by cardiologists in the acute care setting. Eur Heart J - Cardiovasc Imaging 14(1):38–42

    Article  PubMed  Google Scholar 

  16. Zolgharni M, Negoita M, Dhutia N, Mielewczik M, Manoharan K, Sohaib S, Finegold J, Sacchi S, Cole G, Francis D (2017) Automatic detection of end-diastolic and end-systolic frames in 2D echocardiography. Echocardiogr 34(7):956–967

    Article  Google Scholar 

  17. Lane E, Azarmehr N, Jevsikov J, Howard J, Shun-shin M, Cole G, Francis D, Zolgharni M (2021) Multibeat echocardiographic phase detection using deep neural networks. Comput Biol Med 133:104373

    Article  PubMed  Google Scholar 

  18. Zolgharni M et al (2014) Automated aortic Doppler flow tracing for reproducible research and clinical measurements. In: IEEE transactions on medical imaging 33(5):1071–1082

  19. Kiruthika NV, Prabhakar B, Reddy MR (2006) Automated assessment of aortic regurgitation using 2D Doppler echocardiogram. In: Proceedings of the 2006 IEEE international workshop on imagining systems and techniques (IST 2006), pp 95–99

  20. Biradar N, Dewal ML, Rohit MK (2015) Automated delineation of Doppler echocardiographic images using texture filters. 2015 2nd international conference on computing for sustainable global development (INDIACom), pp 1903–1907

  21. Taebi A, Sandler RH, Kakavand B, Mansy HA (2018) Estimating peak velocity profiles from Doppler echocardiography using digital image processing. In: 2018 IEEE signal processing in medicine and biology symposium (SPMB), pp 1–4

  22. Dhutia N, Zolgharni M, Mielewczik M, Negoita M, Sacchi S, Manoharan K, Francis D, Cole G (2017) Open-source, vendor-independent, automated multi-beat tissue Doppler echocardiography analysis. Int J Cardiovasc Imaging 33(8):1135–1148

    Article  PubMed  PubMed Central  Google Scholar 

  23. Kalinić H, Lončarić S, Čikeš M, Miličić D, Bijnens B (2011) Model-based segmentation of aortic ultrasound images. In: 2011 7th international symposium on image and signal processing and analysis (ISPA), pp 739–743

  24. Higa M, Pilon P, Lage S, Gutierrez M (2009) A computational tool for quantitative assessment of peripheral arteries in ultrasound images. In: 2009 36th annual computers in cardiology conference (CinC), pp 41–44

  25. Magagnin V, Caiani EG, Delfino L, Champlon C, Cerutti S, Turiel M (2006) Semi-automated analysis of coronary flow Doppler images: validation with manual tracings. In: 2006 international conference of the IEEE engineering in medicine and biology society, pp 719–722

  26. Greenspan H, Shechner O, Scheinowitz M, Feinberg M (2005) Doppler echocardiography flow-velocity image analysis for patients with atrial fibrillation. Ultrasound Med Biol 31(8):1031–1040

    Article  PubMed  Google Scholar 

  27. Gaillard E, Kadem L, Clavel M, Pibarot P, Durand L (2010) Optimization of Doppler echocardiographic velocity measurements using an automatic contour detection method. Ultrasound Med Biol 36(9):1513–1524

    Article  PubMed  Google Scholar 

  28. Zamzmi G, Hsu L-Y, Li W, Sachdev V, Antani S (2020) Fully automated spectral envelope and peak velocity detection from Doppler echocardiography images. In: Proc. SPIE 11314, Medical imaging 2020: computer-aided diagnosis, p 113144G. https://doi.org/10.1117/12.2551183

  29. Zhu S, Gao R (2016) A novel generalized gradient vector flow snake model using minimal surface and component-normalized method for medical image segmentation. Biomed Signal Process Control 26:1–10

    Article  CAS  Google Scholar 

  30. Kalinić H, Lončarić S, Čikeš M, Miličić D, Bijnens B (2012) Image registration and atlas-based segmentation of cardiac outflow velocity profiles. Comput Methods Programs Biomed 106(3):188–200

    Article  PubMed  Google Scholar 

  31. Baličević V, Kalinić H, Lončarić S, Čikeš M, Bijnens B (2018) A computational model-based approach for atlas construction of aortic Doppler velocity profiles for segmentation purposes. Biomed Signal Process Control 40:23–32

    Article  Google Scholar 

  32. Park J, Zhou SK, Jackson J, Comaniciu D (2008) Automatic mitral valve inflow measurements from Doppler echocardiography. In: Metaxas D, Axel L, Fichtinger G, Székely G (eds) Medical image computing and computer-assisted intervention – MICCAI 2008 (MICCAI). Lecture notes in computer science, vol 5241. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85988-8_117

  33. Zhou SK et al (2007) A probabilistic, hierarchical, and discriminant framework for rapid and accurate detection of deformable anatomic structure. In: 2007 IEEE 11th international conference on computer vision, pp 1–8. https://doi.org/10.1109/ICCV.2007.4409045

  34. Zamzmi G, Hsu L, Li W, Sachdev V, Antani S (2021) Harnessing machine intelligence in automatic echocardiogram analysis: current status, limitations, and future directions. IEEE Rev Biomed Eng 14:181–203

    Article  PubMed  PubMed Central  Google Scholar 

  35. Zolgharni M, Francis D, Dhutia N, Cole G, Bahmanyar M, Jones S, Sohaib S, Tai S, Willson K, Finegold J (2014) Automated aortic Doppler flow tracing for reproducible research and clinical measurements. IEEE Trans Med Imaging 33(5):1071–1082

    Article  PubMed  Google Scholar 

  36. He K, Gkioxari G, Dollár P, Girshick RB (2017) Mask R-CNN. In: 2017 IEEE international conference on computer vision (ICCV), pp 2980–2988

  37. Abdulla W (2017) Matterport/MASK_RCNN: mask R-CNN for object detection and instance segmentation on Keras and tensorflow, GitHub repository. Available at: https://github.com/matterport/Mask_RCNN. Accessed 3 Jan 2023

  38. Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149

    Article  PubMed  Google Scholar 

  39. Lin T-Y et al (2014) Microsoft COCO: common objects in context. CoRR, abs/1405.0312. Available at: http://arxiv.org/abs/1405.0312

  40. Belagiannis V, Zisserman A (2017) Recurrent human pose estimation. In: 2017 12th IEEE international conference on automatic face & gesture recognition (FG 2017), pp 468–475. https://doi.org/10.1109/FG.2017.64

  41. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro , Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jozefowicz R, Jia Y, Kaiser L, Kudlur M, Levenberg J, Mané D, Schuster M, Monga R, Moore S, Murray D, Olah C, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software available from http://tensorflow.org

  42. Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  43. Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations (ICLR 2015)

  44. Sacchi S, Dhutia N, Shun-Shin M, Zolgharni M, Sutaria N, Francis D, Cole G (2018) Doppler assessment of aortic stenosis: a 25-operator study demonstrating why reading the peak velocity is superior to velocity time integral. Eur Heart J - Cardiovasc Imaging 19(12):1380–1389

    Article  PubMed  PubMed Central  Google Scholar 

  45. Vinereanu D, Khokhar A, Fraser A (1999) Reproducibility of pulsed wave tissue Doppler echocardiography. J Am Soc Echocardiogr 12(6):492–499

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

This research and open-access release of the has been conducted under: The Imperial College London and University of West London, United Kingdom [IRAS: 279328, REC:20/SC/0386].

Funding

This work was supported in part by the British Heart Foundation, UK (Grant no. PG/19/78/34733). E. Lane is supported by the Vice Chancellor’s Scholarship at the University of West London.

Author information

Authors and Affiliations

  1. School of Computing and Engineering, University of West London, St Mary’s Rd, Ealing, London, W5 5RF, UK

    Elisabeth S. Lane, Jevgeni Jevsikov, Nasser Matoorian & Massoud Zolgharni

  2. National Heart and Lung Institute, Imperial College, London, UK

    Matthew J. Shun-shin, Graham D. Cole, Darrel P. Francis & Massoud Zolgharni

  3. New York University Abu Dhabi, Saadiyat Island, Abu Dhabi, United Arab Emirates

    Niti Dhutia

Authors
  1. Elisabeth S. Lane
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jevgeni Jevsikov
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Matthew J. Shun-shin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Niti Dhutia
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nasser Matoorian
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Graham D. Cole
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Darrel P. Francis
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Massoud Zolgharni
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Elisabeth S. Lane.

Additional information

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

Lane, E.S., Jevsikov, J., Shun-shin, M.J. et al. Automated multi-beat tissue Doppler echocardiography analysis using deep neural networks. Med Biol Eng Comput 61, 911–926 (2023). https://doi.org/10.1007/s11517-022-02753-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-022-02753-3

Keywords

Search

Navigation