Automated choroidal segmentation method in human eye with 1050nm optical coherence tomography

Cindy Liu; Ruikang K. Wang

doi:10.1117/12.2038679

26 February 2014 Automated choroidal segmentation method in human eye with 1050nm optical coherence tomography

Cindy Liu, Ruikang K. Wang

Proceedings Volume 8942, Dynamics and Fluctuations in Biomedical Photonics XI; 89420O (2014) https://doi.org/10.1117/12.2038679
Event: SPIE BiOS, 2014, San Francisco, California, United States

Abstract

Choroidal thickness (ChT), defined as the distance between the retinal pigment epithelium (RPE) and the choroid-sclera interface (CSI), is highly correlated with various ocular disorders like high myopia, diabetic retinopathy, and central serous chorioretinopathy. Long wavelength Optical Coherence Tomography (OCT) has the ability to penetrate deep to the CSI, making the measurement of the ChT possible. The ability to accurately segment the CSI and RPE is important in extracting clinical information. However, automated CSI segmentation is challenging due to the weak boundary in the lower choroid and inconsistent texture with varied blood vessels. We propose a K-means clustering based automated algorithm, which is effective in segmenting the CSI and RPE. The performance of the method was evaluated using 531 frames from 4 normal subjects. The RPE and CSI segmentation time was about 0.3 seconds per frame, and the average time was around 0.5 seconds per frame with correction among frames, which is faster than reported algorithms. The results from the proposed method are consistent with the manual segmentation results. Further investigation includes the optimization of the algorithm to cover more OCT images captured from patients and the increase of the processing speed and robustness of the segmentation method.

Citation Download Citation

Cindy Liu and Ruikang K. Wang "Automated choroidal segmentation method in human eye with 1050nm optical coherence tomography", Proc. SPIE 8942, Dynamics and Fluctuations in Biomedical Photonics XI, 89420O (26 February 2014); https://doi.org/10.1117/12.2038679

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