Automatic Choroid Layer Segmentation from Optical Coherence Tomography Images Using Deep Learning

Abstract

The choroid layer is a vascular layer in human retina and its main function is to provide oxygen and support to the retina. Various studies have shown that the thickness of the choroid layer is correlated with the diagnosis of several ophthalmic diseases. For example, diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. Despite contemporary advances, automatic segmentation of the choroid layer remains a challenging task due to low contrast, inhomogeneous intensity, inconsistent texture and ambiguous boundaries between the choroid and sclera in Optical Coherence Tomography (OCT) images. The majority of currently implemented methods manually or semi-automatically segment out the region of interest. While many fully automatic methods exist in the context of choroid layer segmentation, more effective and accurate automatic methods are required in order to employ these methods in the clinical sector. This paper proposed and implemented an automatic method for choroid layer segmentation in OCT images using deep learning and a series of morphological operations. The aim of this research was to segment out Bruch’s Membrane (BM) and choroid layer to calculate the thickness map. BM was segmented using a series of morphological operations, whereas the choroid layer was segmented using a deep learning approach as more image statistics were required to segment accurately. Several evaluation metrics were used to test and compare the proposed method against other existing methodologies. Experimental results showed that the proposed method greatly reduced the error rate when compared with the other state-of-the-art methods.

A New Choroidal Layer Segmentation Method Based on Graph Theory and Directional Curvelet Transform in OCT Images

“…Therefore, the results of ten methods presented in Table 1 are generally discussed here. As, shown in this Table, the minimum presented DSC is 78% ± 8% (39) and the maximum presented DSC is 97.35% ± 2.3% (8). The average of DSC for these 10 methods was 90.56% ± 3% while the mean DSC of our proposed method was calculated to be 92.14% ± 3.30%.…”

“…So most of the ophthalmologists segment this layer using manual or semi-automatic techniques. The inhomogeneous intensity of choroidal layer, low contrast of OCT images, and the presence of speckle noise has made the automatic choroidal segmentation to be a challenging task (7,8). In order to reduce speckle noise from OCT images, many traditional methods such as adaptive median and Wiener filtering (9, 10), median and Lee filtering (11)(12)(13)(14) are suggested but these methods are often obscure in details and affect edges in an image.…”

Detection of Diabetic Macular Edema in Optical Coherence Tomography Image Using an Improved Level Set Algorithm

“…It helps to identify, classify, and quantify pathological features in OCT images. However, deep learning is highly dependent on the following factors: (a) advances in high-tech central processing units (CPUs) and graphics processing units (GPUs), (b) the availability of a huge amount of data (i.e., big data), and (c) developments in learning algorithms [35,36]. However, in the hospitals of rural areas, they do not have high configuration computers and sophisticated computer specialists.…”

MultiSDGAN: Translation of OCT Images to Superresolved Segmentation Labels Using Multi-Discriminators in Multi-Stages

“…There were other efforts in the segmentation of OCT images, such as the one described in [19], which employs a layer boundary evolution method as well as in [20], which involves the shortest path using the backtracking method. Some of the other efforts which employ deep learning are [21]- [24].…”