Logo image
Curvature correction of retinal OCTs using graph-based geometry detection
Journal article   Open access   Peer reviewed

Curvature correction of retinal OCTs using graph-based geometry detection

Raheleh Kafieh, Hossein Rabbani, Michael D Abramoff and Milan Sonka
Physics in medicine and biology, Vol.58(9), pp.2925-2938
05/07/2013
DOI: 10.1088/0031-9155/58/9/2925
PMCID: PMC3794717
PMID: 23574790
url
https://durham-repository.worktribe.com/output/1197946View
Open Access

Abstract

In this paper, we present a new algorithm as an enhancement and preprocessing step for acquired optical coherence tomography (OCT) images of the retina. The proposed method is composed of two steps, first of which is a denoising algorithm with wavelet diffusion based on a circular symmetric Laplacian model, and the second part can be described in terms of graph-based geometry detection and curvature correction according to the hyper-reflective complex layer in the retina. The proposed denoising algorithm showed an improvement of contrast-to-noise ratio from 0.89 to 1.49 and an increase of signal-to-noise ratio (OCT image SNR) from 18.27 to 30.43 dB. By applying the proposed method for estimation of the interpolated curve using a full automatic method, the mean ± SD unsigned border positioning error was calculated for normal and abnormal cases. The error values of 2.19 ± 1.25 and 8.53 ± 3.76 µm were detected for 200 randomly selected slices without pathological curvature and 50 randomly selected slices with pathological curvature, respectively. The important aspect of this algorithm is its ability in detection of curvature in strongly pathological images that surpasses previously introduced methods; the method is also fast, compared to the relatively low speed of similar methods.
Computer Graphics Retina - cytology Humans Signal-To-Noise Ratio Retinal Diseases - pathology Image Processing, Computer-Assisted - methods Tomography, Optical Coherence - methods Retina - pathology

Details

Metrics

Logo image