Automatic Segmentation of Corneal Microlayers on Optical Coherence Tomography Images

被引：15

作者：

Elsawy, Amr ^{[1
,2
]}

Abdel-Mottaleb, Mohamed ^{[2
]}

Sayed, Ibrahim-Osama ^{[1
]}

Wen, Dan ^{[1
]}

Roongpoovapatr, Vatookarn ^{[1
]}

Eleiwa, Taher ^{[1
,3
]}

Sayed, Ahmed M. ^{[1
,4
]}

Raheem, Mariam ^{[1
]}

Gameiro, Gustavo ^{[1
]}

Abou Shousha, Mohamed ^{[1
,2
,5
]}

机构：

[1] Univ Miami, Miller Sch Med, Bascom Palmer Eye Inst, 900 Northwest 17th St, Miami, FL 33136 USA

[2] Univ Miami, Elect & Comp Engn, Coral Gables, FL 33136 USA

[3] Benha Fac Med, Ophthalmol Dept, Banha, Egypt

[4] Helwan Univ, Fac Engn, Biomed Engn Dept, Helwan, Egypt

[5] Univ Miami, Biomed Engn, Coral Gables, FL 33136 USA

来源：

TRANSLATIONAL VISION SCIENCE & TECHNOLOGY | 2019年 / 8卷 / 03期

关键词：

OCT imaging; segmentation; corneal microlayers; IN-VIVO CHARACTERISTICS; TOPOGRAPHIC THICKNESS; DIAGNOSIS; MEMBRANE; LAYER; OCT;

D O I：

10.1167/tvst.8.3.39

中图分类号：

R77 [眼科学];

学科分类号：

100212 ;

摘要：

Purpose: To propose automatic segmentation algorithm (AUS) for corneal microlayers on optical coherence tomography (OCT) images. Methods: Eighty-two corneal OCT scans were obtained from 45 patients with normal and abnormal corneas. Three testing data sets totaling 75 OCT images were randomly selected. Initially, corneal epithelium and endothelium microlayers are estimated using a corneal mask and locally refined to obtain final segmentation. Flat-epithelium and flat-endothelium images are obtained and vertically projected to locate inner corneal microlayers. Inner microlayers are estimated by translating epithelium and endothelium microlayers to detected locations then refined to obtain final segmentation. Images were segmented by trained manual operators (TMOs) and by the algorithm to assess repeatability (i.e., intraoperator error), reproducibility (i.e., interoperator and segmentation errors), and running time. A random masked subjective test was conducted by corneal specialists to subjectively grade the segmentation algorithm. Results: Compared with the TMOs, the AUS had significantly less mean intraoperator error (0.53 +/- 1.80 vs. 2.32 +/- 2.39 pixels; P < 0.0001), it had significantly different mean segmentation error (3.44 +/- 3.46 vs. 2.93 +/- 3.02 pixels; P < 0.0001), and it had significantly less running time per image (0.19 +/- 0.07 vs. 193.95 +/- 194.53 seconds; P < 0.0001). The AUS had insignificant subjective grading for microlayer-segmentation grading (4.94 +/- 032 vs. 4.96 +/- 0.24; P = 0.5081), but it had significant subjective grading for regional-segmentation grading (4.96 +/- 0.26 vs. 4.79 +/- 0.60; P = 0.025). Conclusions: The AUS can reproduce the manual segmentation of corneal microlayers with comparable accuracy in almost real-time and with significantly better repeatability. Translational Relevance: The AUS can be useful in clinical settings and can aid the diagnosis of corneal diseases by measuring thickness of segmented corneal microlayers.

引用

页数：16

共 30 条

[1] In Vivo Characteristics of Corneal Endothelium/Descemet Membrane Complex for the Diagnosis of Corneal Graft Rejection [J].