Detection of Choroidal Neovascularization (CNV) in Retina OCT Images Using VGG16 and DenseNet CNN

In this study, we intend to diagnose Choroidal Neovascularization in retinal Optical Coherence Tomography (OCT) images using Deep Learning Architectures. OCT can be used differentiate between a healthy eye and an with CNV disease. the Retinal Pigment Epithelial layer experiences changes various properties which related assistance of Images. This paper proposes technique for finding OCTA pictures. Among few attributes CNV, bigger turning point veins is moderately clear element, so will utilize property see if there picture. DenseNet Vgg16 Architectures were study hyper parameters both architectures changed disease properly. After detection disease, diseased are segmented from background Region Interest Python OpenCV library that processing images. The results implementation showed better detecting rather than Dense Net Architecture accuracy percentage 97.53% approximately percent greater Net.