Retinal vascular segmentation can provide support for the diagnosis and treatment of ocular diseases such as hypertension,diabe-tes and glaucoma.Compared with manual diagnosis,computer-aided retinal vascular segmentation is easier to reduce the chance of missed diagnosis and misdiagnosis.In order to improve the accuracy of retinal vascular segmentation,a method based on PCNN and GAN is proposed.It combines PCNN with GAN,and embedding the discriminant in the GAN into the loop structure with PCNN as the main body.The game competition mechanism against the network gives the discriminant the power and vitali-ty of continuous self-upgrading,and the constantly improved discriminant provides the segmentation standard for PCNN.Finally,the experimental results show that the proposed method has a good performance in the segmentation of retinal vessels.
万方数据
