Display options
Share it on

Proc SPIE Int Soc Opt Eng. 2014 Mar 21;9034:90341G. doi: 10.1117/12.2043715.

Robust Optic Nerve Segmentation on Clinically Acquired CT.

Proceedings of SPIE--the International Society for Optical Engineering

Swetasudha Panda, Andrew J Asman, Michael P Delisi, Louise A Mawn, Robert L Galloway, Bennett A Landman

Affiliations

  1. Electrical Engineering, Vanderbilt University, Nashville, TN, USA 37235.
  2. Biomedical Engineering, Vanderbilt University, Nashville, TN, USA 37235.
  3. Ophthalmology and Neurological Surgery, Vanderbilt University, Nashville, TN, USA 37235.
  4. Electrical Engineering, Vanderbilt University, Nashville, TN, USA 37235 ; Biomedical Engineering, Vanderbilt University, Nashville, TN, USA 37235.

PMID: 24817810 PMCID: PMC4013110 DOI: 10.1117/12.2043715

Abstract

The optic nerve is a sensitive central nervous system structure, which plays a critical role in many devastating pathological conditions. Several methods have been proposed in recent years to segment the optic nerve automatically, but progress toward full automation has been limited. Multi-atlas methods have been successful for brain segmentation, but their application to smaller anatomies remains relatively unexplored. Herein we evaluate a framework for robust and fully automated segmentation of the optic nerves, eye globes and muscles. We employ a robust registration procedure for accurate registrations, variable voxel resolution and image field-of-view. We demonstrate the efficacy of an optimal combination of SyN registration and a recently proposed label fusion algorithm (Non-local Spatial STAPLE) that accounts for small-scale errors in registration correspondence. On a dataset containing 30 highly varying computed tomography (CT) images of the human brain, the optimal registration and label fusion pipeline resulted in a median Dice similarity coefficient of 0.77, symmetric mean surface distance error of 0.55 mm, symmetric Hausdorff distance error of 3.33 mm for the optic nerves. Simultaneously, we demonstrate the robustness of the optimal algorithm by segmenting the optic nerve structure in 316 CT scans obtained from 182 subjects from a thyroid eye disease (TED) patient population.

Keywords: Computed Tomography; Multi-Atlas; Optic Nerve; Segmentation; Statistical Label Fusion

References

  1. J Comput Assist Tomogr. 1995 Jul-Aug;19(4):615-23 - PubMed
  2. IEEE Trans Med Imaging. 1999 Aug;18(8):712-21 - PubMed
  3. Neuroimage. 2011 Apr 1;55(3):968-85 - PubMed
  4. IEEE Trans Med Imaging. 2012 Jun;31(6):1326-36 - PubMed
  5. Med Image Anal. 2013 Feb;17(2):194-208 - PubMed
  6. IEEE Trans Med Imaging. 2009 Aug;28(8):1266-77 - PubMed
  7. Med Image Anal. 2008 Feb;12(1):26-41 - PubMed
  8. Radiother Oncol. 2008 Apr;87(1):93-9 - PubMed
  9. IEEE Trans Med Imaging. 2010 Oct;29(10):1714-29 - PubMed
  10. Neuroimage. 2010 Feb 1;49(3):2352-65 - PubMed
  11. IEEE Trans Med Imaging. 2004 Jul;23(7):903-21 - PubMed
  12. IEEE Trans Med Imaging. 2004 Aug;23(8):983-94 - PubMed
  13. Neuroimage. 2009 Jul 1;46(3):726-38 - PubMed
  14. Neuroimage. 2006 Oct 15;33(1):115-26 - PubMed
  15. IEEE Trans Med Imaging. 2009 Jul;28(7):1000-10 - PubMed
  16. Med Phys. 2008 Feb;35(2):735-43 - PubMed
  17. Neuroimage. 2011 Jun 1;56(3):1386-97 - PubMed
  18. J Cogn Neurosci. 1991 Winter;3(1):71-86 - PubMed

Publication Types

Grant support