Abstract

Diabetic retinopathy is a fast-spreading eye disease and this may lead to blindness in working-age adults. Between 32 to 40 % of about 347 million people suffer from diabetic retinopathy. It is a silent vision problem and thus, requires regular annual check-ups which will help in controlling the disease at initial stage and effective treatment will provide favorable results. The research utilizes a deep learning approach for diabetic retinopathy classification, which also will aid in addressing real-world issues. The work has already been done to solve this issue with the use of different classification techniques but somehow the efficiency of the training algorithm is dependent on the quality of feature extraction, which necessitates domain expertise. The current work solves the issue by applying a deep learning algorithm that recognizes the pattern and classifies retinal fundus images as normal or infected. In this study on the different categories of diabetic retinopathy 3662 retinal images were analyzed. The categories that are present in the data are No- diabetic retinopathy , mild, moderate, severe, and proliferative diabetic retinopathy . The publicly available retinopathy detection database and a trained model will be used in the experiments to retrieve the features of the ocular images and provide an appropriate output. The goal of this study is to apply and comprehend how the performance of a pretrained model distinguishes between proliferative and nonproliferative diabetic retinopathy.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call