Segmentation of Common Lesions in Age-related Macular Degeneration Based on Boundary Attention Mechanism

Age-related macular degeneration (AMD) is a common ophthalmic disease, mainly occurring in the elderly. After the occurrence of pigment epithelial detachment (PED), neuroepithelial detachment and subretinal fluid (SRF) are further caused, and patients need follow-up treatment. Quantitative analysis of these two symptoms is very important for clinical diagnosis. Therefore, we propose a new joint segmentation network to accurately segment PED and SRF in this paper. Our main contributions are: (1) a new multi-scale information selection module is proposed. (2) based on the U-shape network, a novel decoder branch is proposed to obtain boundary information, which is critical to segmentation. The experimental results show that our method achieves 72.97% for the average dice (DSC), 79.92% for the average recall, and 67.11% for the average intersection over union (IOU).