Share Email Print
cover

Proceedings Paper

Automated choroidal segmentation method in human eye with 1050nm optical coherence tomography
Author(s): Cindy Liu; Ruikang K. Wang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 26 February 2014
PDF: 10 pages
Proc. SPIE 8942, Dynamics and Fluctuations in Biomedical Photonics XI, 89420O (26 February 2014); doi: 10.1117/12.2038679
Show Author Affiliations
Cindy Liu, The Harker School (United States)
Ruikang K. Wang, Univ. of Washington (United States)


Published in SPIE Proceedings Vol. 8942:
Dynamics and Fluctuations in Biomedical Photonics XI
Valery V. Tuchin; Donald D. Duncan; Kirill V. Larin; Martin J. Leahy; Ruikang K. Wang, Editor(s)

© SPIE. Terms of Use
Back to Top