TY - JOUR
T1 - Pathological-corneas layer segmentation and thickness measurement in OCT images
AU - Elsawy, Amr
AU - Gregori, Giovanni
AU - Eleiwa, Taher
AU - Abdel-Mottaleb, Mohamed
AU - Abou Shousha, Mohamed
N1 - Funding Information:
Supported by a NEI K23 award (K23EY026118), NEI core center grant to the University of Miami (P30 EY014801), and Research to Prevent Blindness (RPB).
PY - 2020/10
Y1 - 2020/10
N2 - Purpose: The purpose of this study was to propose a new algorithm for the segmentation and thickness measurement of pathological corneas with irregular layers using a two-stage graph search and ray tracing. Methods: In the first stage, a graph, with only gradient edge-cost, is used to segment the air-epithelium and endothelium-aqueous boundaries. In the second stage, a graph, with gradient, directional, and multiplier edge-cost, is used to correct segmentation. The optical coherence tomography (OCT) image is flattened using the air-epithelium boundary and a graph search is used to segment the epithelium-Bowman’s and Bowman’sstroma boundaries. Then, the OCT image is flattened using the endothelium-aqueous boundary and a graph search is used to segment the Descemet’s membrane. Ray tracing is used to correct the inter-boundary distances, then the thickness is measured using the shortest distance. The proposed algorithm was trained and evaluated using 190 OCT images manually segmented by trained operators. Results: The mean and standard deviation of the unsigned errors of the algorithmoperator and inter-operator were 0.89 ± 1.03 and 0.77 ± 0.68 pixels in segmentation and 3.62 ± 3.98 and 2.95 ± 2.52 μm in thickness measurement. Conclusions: Our proposed algorithm can produce accurate segmentation and thickness measurements compared with the manual operators. Translational Relevance: Our algorithm could be potentially useful in the clinical practice.
AB - Purpose: The purpose of this study was to propose a new algorithm for the segmentation and thickness measurement of pathological corneas with irregular layers using a two-stage graph search and ray tracing. Methods: In the first stage, a graph, with only gradient edge-cost, is used to segment the air-epithelium and endothelium-aqueous boundaries. In the second stage, a graph, with gradient, directional, and multiplier edge-cost, is used to correct segmentation. The optical coherence tomography (OCT) image is flattened using the air-epithelium boundary and a graph search is used to segment the epithelium-Bowman’s and Bowman’sstroma boundaries. Then, the OCT image is flattened using the endothelium-aqueous boundary and a graph search is used to segment the Descemet’s membrane. Ray tracing is used to correct the inter-boundary distances, then the thickness is measured using the shortest distance. The proposed algorithm was trained and evaluated using 190 OCT images manually segmented by trained operators. Results: The mean and standard deviation of the unsigned errors of the algorithmoperator and inter-operator were 0.89 ± 1.03 and 0.77 ± 0.68 pixels in segmentation and 3.62 ± 3.98 and 2.95 ± 2.52 μm in thickness measurement. Conclusions: Our proposed algorithm can produce accurate segmentation and thickness measurements compared with the manual operators. Translational Relevance: Our algorithm could be potentially useful in the clinical practice.
KW - Cornea
KW - Optical coherence tomography (OCT) imaging
KW - Ray tracing
KW - Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85097332333&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097332333&partnerID=8YFLogxK
U2 - 10.1167/tvst.9.11.24
DO - 10.1167/tvst.9.11.24
M3 - Article
AN - SCOPUS:85097332333
VL - 9
SP - 1
EP - 17
JO - Translational Vision Science and Technology
JF - Translational Vision Science and Technology
SN - 2164-2591
IS - 11
M1 - 24
ER -