Machine Vision and Applications

, Volume 23, Issue 6, pp 1129–1139

Layer extraction in rodent retinal images acquired by optical coherence tomography

Authors

  • József Molnár
    • MTA SZTAKI and Eötvös Loránd University
    • MTA SZTAKI and Eötvös Loránd University
  • Delia Cabrera DeBuc
    • Bascom Palmer Eye Institute, Miller School of MedicineUniversity of Miami
  • Wei Gao
    • Bascom Palmer Eye Institute, Miller School of MedicineUniversity of Miami
  • Gábor Márk Somfai
    • Department of OphthalmologySemmelweis University
Original Paper

DOI: 10.1007/s00138-011-0343-y

Cite this article as:
Molnár, J., Chetverikov, D., Cabrera DeBuc, D. et al. Machine Vision and Applications (2012) 23: 1129. doi:10.1007/s00138-011-0343-y

Abstract

Optical coherence tomography (OCT) is a modern technique that allows for in vivo, fast, high-resolution 3D imaging. OCT can be efficiently used in eye research and diagnostics, when retinal images are processed to extract borders of retinal layers. In this paper, we present two novel algorithms for delineation of three main borders in rodent retinal images. The first, fast algorithm is based on row projections in a sliding window. It provides initial borders for a slower but more precise variational algorithm that iteratively refines the borders. The results obtained by the two algorithms are quantitatively evaluated by comparison to the borders manually extracted in a set of retinal images.

Keywords

Optical coherence tomographyRetinal imagesRetinal layersSegmentationVariational methods

Copyright information

© Springer-Verlag 2011