 Transfer learning is a machine learning technique which uses a pre-trained model as a starting point for a new task. In this paper, it was applied to diabetic retinopathy classification with promising results. Retinal image processing was done using three phases including pre-processing, segmentation and feature extraction. The pre-processing phase included noise reduction, A-clay, DNCNN and Wiener filtering. Blood vessel segmentation was done using OTSU thresholding and mathematical morphology. Finally, feature extraction and classification were performed using modified ResNet 101 architecture. The network was trained on more than 6,000 images from Mesidor and ODAR datasets and achieved a classification accuracy of 98.72%. This article was authored by Dimple Nagpal, Nudja Alsebe, Ben Othman Safin and others.