Automated choroid segmentation in three-dimensional 1 - μ m wide-view OCT images with gradient and regional costs

Abstract

Choroid thickness and volume estimated from optical coherence tomography (OCT) images have emerged as important metrics in disease management. This paper presents an automated three-dimensional (3-D) method for segmenting the choroid from 1 - ? m wide-view swept source OCT image volumes, including the Bruch’s membrane (BM) and the choroidal–scleral interface (CSI) segmentation. Two auxiliary boundaries are first detected by modified Canny operators and then the optical nerve head is detected and removed. The BM and the initial CSI segmentation are achieved by 3-D multiresolution graph search with gradient-based cost. The CSI is further refined by adding a regional cost, calculated from the wavelet-based gradual intensity distance. The segmentation accuracy is quantitatively evaluated on 32 normal eyes by comparing with manual segmentation and by reproducibility test. The mean choroid thickness difference from the manual segmentation is 19.16 ± 4.32 ?? ? m , the mean Dice similarity coefficient is 93.17 ± 1.30 % , and the correlation coefficients between fovea-centered volumes obtained on repeated scans are larger than 0.97.

An Update on Choroidal Layer Segmentation Methods in Optical Coherence Tomography Images: a Review

“…In addition, the volume quantification reproducibility was high statistically and the segmentation error was remarkably smaller than the interobserver variability. As shown in Figure 6, both qualitative and quantitative analyses demonstrated that this segmentation method had a good performance [60].…”

“…According to the results, it seems that methods based on graph theory have better and more acceptable results than other methods since using the graph theory and dynamic programming can provide accurate, repeatable and rapid quantitative measurements of choroidal thickness [61]. The techniques based on graph searching are widely used for segmentation of choroidal boundaries [6, 8, 9, 12, 13, 54-57, 60-63, 67] and the comparison of maintained results such as DSC in Table 1 generally shows great superiority of this method [6,12,13,54,60] over other proposed methods [59,64,65,68]. A graph searching algorithm was performed accurately if appropriate graph-edge weights is assigned and in comparison with dynamic programming method and traditional methods of boundary detection, the graph search method contains two advantages, as follows: (1) dynamic programming method and the traditional boundary detection methods are mainly dependent on gradient of image.…”

OIPAV: an Integrated Software System for Ophthalmic Image Processing, Analysis, and Visualization

“…Computer-aided detection (CADe) is one of the research that focuses in the medical applications and effective CADe systems speed up the medical diagnostic process, reduce diagnostic errors and improve quantitative evaluations [46]. Combining with our laboratory research experience of many years on ophthalmic diseases detection and analysis [11][12][13][14][15][16][17][18][19][20][21][22], we implement automatic detection algorithms for multiple ophthalmic diseases in the system including branch retinal artery occlusion (BRAO), symptomatic exudate-associated derangements (SEAD), pigment epithelial detachment (PED), micro aneurysm, and exudation. All algorithms are pre-trained and without parameter optimization to provide the "one button" solutions.…”

“…(2) In image processing, in addition to extensive commonly employed operations, OIPAV provides targeted functionalities to recognize and segment eye structures automatically. Combining with our laboratory research experience of many years on ophthalmic diseases detection and analysis [11][12][13][14][15][16][17][18][19][20][21][22], the system integrates our algorithms to provide the "one button" solutions for various ophthalmic diseases' detection. (3) The analysis module in OIPAV includes automatic important parameters measuring, lesion areas assessing, recovery tracking, and diagnostic report generating.…”

Automated framework for intraretinal cystoid macular edema segmentation in three-dimensional optical coherence tomography images with macular hole

“…The OCT volume is first segmented into 10 layers by 11 surfaces using the multiscale 3-D graph-search approach. [22][23][24][25] To remove the image deformation caused by eye movement, the 3-D OCT volume is flattened based on the retinal pigment epithelium (surface 11). [26][27][28] The inner retina is defined as the region between surfaces 1 and 6, and the outer retina refers to the region between surfaces 7 and 11.…”