Two-Path Neutrosophic Fully Convolutional Networks for Fluid Segmentation in Retina Images

Optical coherence tomography (OCT) images are used to reveal retinal diseases and abnormalities such as diabetic macular edema (DME) and age-related macular degeneration (AMD). Fluid regions are the main sign of AMD and DME and automatic fluid segmentation models are very helpful for diagnosis, treatment and follow-up. This paper presents a two-path Neutrosophic (NS) fully convolutional networks; referred as TPNFCN; as a fully-automated model for fluid segmentation. For this task, OCT images are first transferred to NS domain and then inner limiting membrane (ILM) and retinal pigmentation epithelium (RPE) layers as first and last layers of retina, respectively, are segmented by graph shortest path algorithms in NS domain. Then, a basic block of FCN is presented for fluid segmentation and this block is used in the architecture of the proposed TPNFCN. Both the basic block and TPNFCN are evaluated on 600 OCT scans of 24 AMD subjects containing different fluid types. Results reveals that the proposed basic block and TPNFCN outperforms 5 competitive models by improvement of 6.28%, 4.44% and 2.54% with respect to sensitivity, dice coefficients and precision, respectively. It is also demonstrated that the proposed TPNFCN is robust against low number of training samples in comparison with current models.