Choroidal Neovascularisation Classification on Fundus Retinal Images Using Local Linear Estimator

Abstract

Choroidal neovascularization describes the abnormal growth of vessels from the choriocapillaris through the Bruch membrane into the space beneath the retinal pigment epithelium or the space beneath the retina. Choroidal neovascularization detection is considered to be the most important feature in the pathogenesis and treatment of a number of chorioretinal disorders, one of which to detection in digital fundus retinal images. In this study, we classify choroidal neovascularization by using statistical modeling approach based on local linear estimator. Based on 40 in samples and 10 out samples data images, we obtain the same accuracy of classification of 90 percent and their sensitivity are 90 percent and 83.33 percent, respectively. So, we conclude that the local linear is a good estimator to classify choroidal neovascularization on fundus retinal image.