Display options
Share it on

J Med Imaging (Bellingham). 2017 Apr;4(2):024005. doi: 10.1117/1.JMI.4.2.024005. Epub 2017 May 24.

Semiautomated biventricular segmentation in three-dimensional echocardiography by coupled deformable surfaces.

Journal of medical imaging (Bellingham, Wash.)

Jørn Bersvendsen, Fredrik Orderud, Øyvind Lie, Richard John Massey, Kristian Fosså, Raúl San José Estépar, Stig Urheim, Eigil Samset

Affiliations

  1. GE Vingmed Ultrasound AS, Horten, Norway.
  2. University of Oslo, Department of Informatics, Oslo, Norway.
  3. Center for Cardiological Innovation, Oslo, Norway.
  4. Oslo University Hospital, Department of Cardiology, Oslo, Norway.
  5. Oslo University Hospital, Department of Radiology and Nuclear Medicine, Oslo, Norway.
  6. Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, United States.
  7. Oslo University Hospital, Institute for Surgical Research, Oslo, Norway.

PMID: 28560243 PMCID: PMC5443355 DOI: 10.1117/1.JMI.4.2.024005

Abstract

With the advancement of three-dimensional (3-D) real-time echocardiography in recent years, automatic creation of patient specific geometric models is becoming feasible and important in clinical decision making. However, the vast majority of echocardiographic segmentation methods presented in the literature focus on the left ventricle (LV) endocardial border, leaving segmentation of the right ventricle (RV) a largely unexplored problem, despite the increasing recognition of the RV's role in cardiovascular disease. We present a method for coupled segmentation of the endo- and epicardial borders of both the LV and RV in 3-D ultrasound images. To solve the segmentation problem, we propose an extension of a successful state-estimation segmentation framework with a geometrical representation of coupled surfaces, as well as the introduction of myocardial incompressibility to regularize the segmentation. The method was validated against manual measurements and segmentations in images of 16 patients. Mean absolute distances of [Formula: see text], [Formula: see text], and [Formula: see text] between the proposed and reference segmentations were observed for the LV endocardium, RV endocardium, and LV epicardium surfaces, respectively. The method was computationally efficient, with a computation time of [Formula: see text].

Keywords: image segmentation; medical imaging; surface representation; three-dimensional echocardiography

References

  1. BMC Med Imaging. 2014 Sep 08;14 :31 - PubMed
  2. IEEE Trans Med Imaging. 2016 Jan;35(1):42-51 - PubMed
  3. Med Image Anal. 2015 Apr;21(1):29-39 - PubMed
  4. J Am Coll Cardiol. 2012 May 15;59(20):1799-808 - PubMed
  5. J Am Soc Echocardiogr. 2012 Jan;25(1):3-46 - PubMed
  6. IEEE Trans Med Imaging. 2007 Sep;26(9):1136-53 - PubMed
  7. Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9790: - PubMed
  8. J Am Soc Echocardiogr. 2010 Sep;23(9):943-53 - PubMed
  9. IEEE Trans Med Imaging. 2007 Sep;26(9):1154-65 - PubMed
  10. J Am Soc Echocardiogr. 2010 Feb;23 (2):116-26 - PubMed
  11. Med Image Comput Comput Assist Interv. 2007;10 (Pt 2):428-35 - PubMed
  12. J Am Coll Cardiol. 2004 Jun 16;43(12 ):2207-15 - PubMed
  13. Ultrasound Med Biol. 2005 Sep;31(9):1143-58 - PubMed
  14. Cardiovasc Ultrasound. 2012 Jan 06;10 :1 - PubMed
  15. Med Image Anal. 2010 Jun;14(3):429-48 - PubMed

Publication Types