Display options
Cite
Herz C, Pace DF, Nam HH, et al. Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning. Front Cardiovasc Med. 2021;8:735587doi: 10.3389/fcvm.2021.735587.
Herz, C., Pace, D. F., Nam, H. H., Lasso, A., Dinh, P., Flynn, M., Cianciulli, A., Golland, P., & Jolley, M. A. (2021). Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning. Frontiers in cardiovascular medicine, 8735587. https://doi.org/10.3389/fcvm.2021.735587
Herz, Christian, et al. "Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning." Frontiers in cardiovascular medicine vol. 8 (2021): 735587. doi: https://doi.org/10.3389/fcvm.2021.735587
Herz C, Pace DF, Nam HH, Lasso A, Dinh P, Flynn M, Cianciulli A, Golland P, Jolley MA. Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning. Front Cardiovasc Med. 2021 Dec 09;8:735587. doi: 10.3389/fcvm.2021.735587. eCollection 2021. PMID: 34957233; PMCID: PMC8696083.
Copy Download .nbib Format: NLM
Share it on

Front Cardiovasc Med. 2021 Dec 09;8:735587. doi: 10.3389/fcvm.2021.735587. eCollection 2021.

Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning.

Frontiers in cardiovascular medicine

Christian Herz, Danielle F Pace, Hannah H Nam, Andras Lasso, Patrick Dinh, Maura Flynn, Alana Cianciulli, Polina Golland, Matthew A Jolley

Affiliations

  1. Children's Hospital of Philadelphia, Department of Anesthesia and Critical Care Medicine, Philadelphia, PA, United States.
  2. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, United States.
  3. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States.
  4. Laboratory for Percutaneous Surgery, Queen's University, Kingston, ON, Canada.
  5. Division of Pediatric Cardiology, Children's Hospital of Philadelphia, Philadelphia, PA, United States.

PMID: 34957233 PMCID: PMC8696083 DOI: 10.3389/fcvm.2021.735587

Abstract

Hypoplastic left heart syndrome (HLHS) is a severe congenital heart defect in which the right ventricle and associated tricuspid valve (TV) alone support the circulation. TV failure is thus associated with heart failure, and the outcome of TV valve repair are currently poor. 3D echocardiography (3DE) can generate high-quality images of the valve, but segmentation is necessary for precise modeling and quantification. There is currently no robust methodology for rapid TV segmentation, limiting the clinical application of these technologies to this challenging population. We utilized a Fully Convolutional Network (FCN) to segment tricuspid valves from transthoracic 3DE. We trained on 133 3DE image-segmentation pairs and validated on 28 images. We then assessed the effect of varying inputs to the FCN using Mean Boundary Distance (MBD) and Dice Similarity Coefficient (DSC). The FCN with the input of an annular curve achieved a median DSC of 0.86 [IQR: 0.81-0.88] and MBD of 0.35 [0.23-0.4] mm for the merged segmentation and an average DSC of 0.77 [0.73-0.81] and MBD of 0.6 [0.44-0.74] mm for individual TV leaflet segmentation. The addition of commissural landmarks improved individual leaflet segmentation accuracy to an MBD of 0.38 [0.3-0.46] mm. FCN-based segmentation of the tricuspid valve from transthoracic 3DE is feasible and accurate. The addition of an annular curve and commissural landmarks improved the quality of the segmentations with MBD and DSC within the range of human inter-user variability. Fast and accurate FCN-based segmentation of the tricuspid valve in HLHS may enable rapid modeling and quantification, which in the future may inform surgical planning. We are now working to deploy this network for public use.

Copyright © 2021 Herz, Pace, Nam, Lasso, Dinh, Flynn, Cianciulli, Golland and Jolley.

Keywords: congenital heart disease; deep learning; echocardiography; image segmentation; machine learning; tricuspid valve

Conflict of interest statement

PG and DP received funding from Philips Research. The funder was not involved in the study design, collection, analysis, interpretation of data, the writing of this article, or the decision to submit

References

  1. Front Cardiovasc Med. 2020 Mar 05;7:25 - PubMed
  2. J Thorac Cardiovasc Surg. 2016 Sep;152(3):847-59 - PubMed
  3. Magn Reson Imaging. 2012 Nov;30(9):1323-41 - PubMed
  4. Med Image Anal. 2017 Jan;35:599-609 - PubMed
  5. J Biomech. 2012 Mar 15;45(5):903-7 - PubMed
  6. Med Image Anal. 2014 Jan;18(1):118-29 - PubMed
  7. IEEE Trans Med Imaging. 2019 Sep;38(9):2198-2210 - PubMed
  8. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:334-342 - PubMed
  9. Med Phys. 2012 Feb;39(2):933-50 - PubMed
  10. Circulation. 2002 Aug 6;106(6):711-7 - PubMed
  11. J Biomech Eng. 2019 Apr 20;: - PubMed
  12. Interact Cardiovasc Thorac Surg. 2015 Feb;20(2):200-8 - PubMed
  13. Int J Comput Assist Radiol Surg. 2019 Jul;14(7):1227-1235 - PubMed
  14. Circulation. 2009 Sep 22;120(12):1091-8 - PubMed
  15. IEEE Trans Image Process. 2019 Oct 28;: - PubMed
  16. Circulation. 2013 Feb 19;127(7):832-41 - PubMed
  17. Semin Thorac Cardiovasc Surg. 2017 Spring;29(1):64-69 - PubMed
  18. J Am Soc Echocardiogr. 2013 Aug;26(8):828-34 - PubMed
  19. Circulation. 2012 Sep 11;126(11 Suppl 1):S183-8 - PubMed
  20. Med Image Comput Comput Assist Interv. 2011;14(Pt 3):520-7 - PubMed
  21. J Med Imaging (Bellingham). 2018 Apr;5(2):021214 - PubMed
  22. Eur Heart J Cardiovasc Imaging. 2013 Feb;14(2):135-41 - PubMed
  23. IEEE J Biomed Health Inform. 2020 Apr;24(4):994-1003 - PubMed
  24. J Am Coll Cardiol. 2019 Feb 26;73(7):810-822 - PubMed
  25. J Am Soc Echocardiogr. 2019 May;32(5):655-666.e13 - PubMed
  26. IEEE Trans Med Imaging. 2018 Feb;37(2):384-395 - PubMed
  27. Nature. 2020 Apr;580(7802):252-256 - PubMed
  28. Ultrasound Med Biol. 2015 Jan;41(1):251-67 - PubMed
  29. Funct Imaging Model Heart. 2017;10263:95-105 - PubMed
  30. Pediatr Cardiol. 2018 Mar;39(3):538-547 - PubMed
  31. Circulation. 2010 Mar 30;121(12):1423-31 - PubMed
  32. Circ Cardiovasc Imaging. 2014 Sep;7(5):765-72 - PubMed
  33. J Am Soc Echocardiogr. 2018 May;31(5):624-633 - PubMed

Publication Types