Automatic Segmentation of Swelling Optic Disc using Factorized Gradient Vector Flow

Optic disc edema (ODE) is an essential ocular manifestation in neuro-ophthalmic diseases. The presence of ODE is recommended to detect at an early stage to avoid blindness and visual impairment. The ODE area was suggested as a reliable index to evaluate the severity of ODE. Retinal images with ODE have different textures from a typical optic disc (OD) and abnormal characteristics such as dimmer color than usual, blurring and enlargement of OD, and obscuring veins. These unique characteristics make existing OD segmentation methods fail to work. This work presents an ODE segmentation method using a factorized gradient vector flow model. The proposed method obtains a localization success rate of 97.14% and an F-measure of 84.24% for ODE segmentation performance.