Share Email Print
cover

Proceedings Paper

Automated retinal pigment epithelium identification from optical coherence tomography images
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Simple and robust method for identifying the retinal pigment epithelium (RPE) from optical coherence tomography images is demonstrated. At first, the maximum intensity value of each A-scans were determined and the depth position of those pixels are identified. The obtained 2D matrix is used as first estimation for the position of RPE. The erroneous pixel from the RPE is masked out and new approximation for them is calculated based on the neighbouring pixels. Finally, the obtained RPE matrix is smoothened. The RPE identification is used for separating the retina and choroid from optical coherence tomography images obtained by 830 nm spectral domain OCT. Both normal and ARMD patient eye were investigated to demonstrate the usability of that method. The calculation time for three dimensional data set (1024x450x137 pixels) was only 16 seconds and it identifies RPE reliably.

Paper Details

Date Published: 20 February 2009
PDF: 6 pages
Proc. SPIE 7168, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XIII, 716827 (20 February 2009); doi: 10.1117/12.808543
Show Author Affiliations
Tapio Fabritius, Univ. of Oulu (Finland)
Computational Optics Group (Japan)
Shuichi Makita, Computational Optics Group (Japan)
Risto Myllylä, Univ. of Oulu (Finland)
Yoshiaki Yasuno, Computational Optics Group (Japan)


Published in SPIE Proceedings Vol. 7168:
Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XIII
James G. Fujimoto; Joseph A. Izatt; Valery V. Tuchin, Editor(s)

© SPIE. Terms of Use
Back to Top