Automated retinal pigment epithelium identification from optical coherence tomography images

Tapio Fabritius; Shuichi Makita; Risto Myllylä; Yoshiaki Yasuno

doi:10.1117/12.808543

20 February 2009 Automated retinal pigment epithelium identification from optical coherence tomography images

Tapio Fabritius, Shuichi Makita, Risto Myllylä, Yoshiaki Yasuno

Proceedings Volume 7168, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XIII; 716827 (2009) https://doi.org/10.1117/12.808543
Event: SPIE BiOS, 2009, San Jose, California, United States

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.

Citation Download Citation

Tapio Fabritius, Shuichi Makita, Risto Myllylä, and Yoshiaki Yasuno "Automated retinal pigment epithelium identification from optical coherence tomography images", Proc. SPIE 7168, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XIII, 716827 (20 February 2009); https://doi.org/10.1117/12.808543

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available