Convolutional Neural Network based Retinal Vessel Segmentation

In human eye, the state of blood vessel is a crucial diagnostic factor. The segmentation from fundus image difficult due to spatial complexity, adjacency, overlapping and variability vessel. detection ophthalmic pathologies like hypertensive disorders, diabetic retinopathy cardiovascular diseases are remain challenging task wide-ranging distribution vessels. this paper, Stacked Autoencoder CNN (Convolutional Neural Network) technique proposed extract image. Based on experiments conducted using Convolutional Network gives 90% & 95% accuracy for segmentation.