Improved OCT Human Corneal segmentation Using Bayesian Residual Transform

  • Ahmed Gawish
  • L. Haines
  • S. Marschall
  • Alexander Wong
  • L. Sorbara
  • Kostadinka Bizheva
  • Paul Fieguth

Abstract

The inherent poor signal to noise ratio of Optical Coherent Tomography
(OCT) is considered as a main limitation of OCT segmentation,
particularly because images are sampled quickly, at high resolutions,
and in-vivo. Furthermore, speckle noise is generated by
the reflections of the OCT LASER limits the ability of automatically
segmenting OCT images. This paper presents a novel method to
automatically segment human corneal OCT images. The proposed
method uses Bayesian Residual Transform (BRT) to build a noise
robust external force map, that guides active contours model to the
corneal data in OCT images. Experimental results show that the
proposed method outperforms the classical as well as the state-ofthe-
art methods.

Published
2016-10-03
How to Cite
Gawish, A., Haines, L., Marschall, S., Wong, A., Sorbara, L., Bizheva, K., & Fieguth, P. (2016). Improved OCT Human Corneal segmentation Using Bayesian Residual Transform. Journal of Computational Vision and Imaging Systems, 2(1). https://doi.org/10.15353/vsnl.v2i1.117
Section
Articles