Choroid Segmentation of Retinal OCT Images Based on CNN Classifier and l 2-l q Fitter.

Fang He,Rachel Ka Man Chun,Zicheng Qiu,Yun Shi,Xiaojun Chen,Chi Ho To,Shijie Yu,Dong Song

doi:10.1155/2021/8882801

Abstract

Optical coherence tomography (OCT) is a noninvasive cross-sectional imaging technology used to examine the retinal structure and pathology of the eye. Evaluating the thickness of the choroid using OCT images is of great interests for clinicians and researchers to monitor the choroidal thickness in many ocular diseases for diagnosis and management. However, manual segmentation and thickness profiling of choroid are time-consuming which lead to low efficiency in analyzing a large quantity of OCT images for swift treatment of patients. In this paper, an automatic segmentation approach based on convolutional neural network (CNN) classifier and l2-lq (0 < q < 1) fitter is presented to identify boundaries of the choroid and to generate thickness profile of the choroid from retinal OCT images. The method of detecting inner choroidal surface is motivated by its biological characteristics after light reflection, while the outer chorioscleral interface segmentation is transferred into a classification and fitting problem. The proposed method is tested in a data set of clinically obtained retinal OCT images with ground-truth marked by clinicians. Our numerical results demonstrate the effectiveness of the proposed approach to achieve stable and clinically accurate autosegmentation of the choroid.

Highlights

Choroid is the vascular layer located between retina and sclera
Its inner surface is connected with the retinal pigment epithelium (RPE) through Bruch’s membrane (BM), and the outer surface is connected with the sclera
We propose and implement an automated segmentation method based on convolutional neural network (CNN) classifier and l2-lq fitter to detect the region of the choroid

Summary

Introduction

Choroid is the vascular layer located between retina and sclera. Its inner surface is connected with the retinal pigment epithelium (RPE) through Bruch’s membrane (BM), and the outer surface is connected with the sclera. Optical coherence tomography (OCT) is a technique for obtaining subsurface images of translucent or opaque materials with high resolution [5, 6]. It uses low-coherence interferometry and imaging reflections from interior tissues to generate cross-sectional images. Comparing with traditional imaging methods, OCT has some obvious advantages of being nondestructive, high resolution, and minimally invasive, and it has been widely applied in ocular detections for many years [3, 7, 8]. The major challenges of the choroidal segmentation are from low contrast of the lower boundary and unknown noise in the images, which will make the detection result inaccurate and unreliable

Methods

Results

Conclusion