Diabetic Neovascularization Identification from Fundus Images Retinopathy

¹ Assistant Professor, Department of Information Technology, GRIET, India
^2,3,4,5,6 Student, Department of Information Technology, GRIET, India

^* Corresponding author: sandeepreddy283@gmail.com

Abstract

Proliferative Diabetic Retinopathy (PDR) is a retinal disease that can affect people with diabetes and cause visual loss if left untreated. Detecting neovascularization, an abnormal growth of veins in the retina, can be difficult due to its irregular pattern and small size. To improve detection, deep learning algorithms, such as MobileNet, are being used to automate complex object recognition. In a neovascularization affirmation technique based on transfer learning, multiple pre-trained models were built during the training phase, including MobileNet, CNN with SVM, AlexNet, GoogleNet, ResNet, ResNet18, and ResNet and GoogleNet models. Machine learning models for HOG feature extraction were also implemented, such as Random Forest, Decision Tree, Gradient Boosting, Support Vector Classifier, and Voting Classifier. MobileNet performed the best and was used to build the model for predicting results from user-uploaded images.