Automatic choroid layer segmentation in OCT images via context efficient adaptive network

Optical Coherence Tomography (OCT) is a non-invasive and newly-developing technique to image human retina and choroid. Many ocular diseases such as pathological myopia and Age-related Macular Degeneration (AMD) are related to the morphological changes of the choroid. Consequently, the automatic choroid segmentation becomes an important step to the examination and diagnosis of those choroid-related diseases. However, there are still challenges such as the inseparability of the histogram between the choroid and sclera boundaries and the inconsistency of the choroid layer texture and intensity. To solve those challenges, we propose a Context Efficient Adaptive network (CEA-Net) that includes a module of Efficient Channel Attention (ECA), a novel block called adaptive morphological refinement (AMR) and a new loss function called Choroidal Convex Boundary (CCB) regularization. The Adaptive Morphological Refinement (AMR) block is designed to avoid the segmentation of discrete subtle objects in choroid. The new Choroidal Convex Boundary (CCB) loss is proposed to refine the segmented choroidal boundaries. The proposed method is applied to two OCT datasets acquired from two different manufacturers respectively in order to evaluate its effectiveness. The results show that the AMR block and CCB loss function enable the deep network to obtain more accurate choroid segmentations. In addition, for the first time in the field of medical image analysis, we construct a dedicated OCT choroid layer segmentation dataset (OCHID), which consists of 640 OCT images with choroidal boundaries annotations. This dataset is available for public use to assist community researchers in their research on related topics.

Automated summary

Optical Coherence Tomography (OCT) is a non-invasive technique used to image the human retina and choroid. Researchers propose a Context Efficient Adaptive network (CEA-Net) to address challenges in choroid segmentation, including histogram inseparability and inconsistency of texture and intensity. The method incorporates an Efficient Channel Attention module, an Adaptive Morphological Refinement block, and a Choroidal Convex Boundary regularization loss. Evaluation on two OCT datasets demonstrates the effectiveness of the proposed method, and a dedicated dataset (OCHID) is created to assist research in this field.