Abstract:
The prevalence of vision impairment is rising at an alarming rate. The goal of the study is to create an
automated method that uses Optical Coherence Tomography (OCT) to classify retinal disorders into four
categories, namely, Choroidal Neovascularization, Diabetic Macular Edema, Drusen, and normal cases.
The study proposed a new framework that combines machine learning and deep learning-based
techniques. The utilized classifi ers were Support Vector Machine (SVM), K-Nearest Neighbor (K-NN),
Decision Tree (DT), and Ensemble Model (EM). A feature extractor was also employed, which was the
InceptionV3 convolutional neural network. The performance of the models has been measured over nine
criteria using a dataset of 18000 OCT images. For the SVM, K-NN, DT, and EM, the analysis exhibited
state-of-the-art performance with classifi cation accuracies of 99.43%, 99.54%, 97.98%, and 99.31%,
respectively. A promising methodology has been introduced for the automatic identifi cation and
classifi cation of retinal disorders leading to reducing human error and saving time alike.