Paper Key : IRJ************281
Author: Avadhanula Pranathi,Dr.a.lakshman,Avadhanula Narsimha Rohit,Anandula Chandana
Date Published: 04 Apr 2024
Abstract
Diabetic Retinopathy is becoming a prevalent disease in diabetic patients nowadays. The surprising fact about it is it leaves no symptoms at the beginning stage and the patient can realize the disease only when his vision starts to fall. If the disease is not found at the earliest, it leads to a stage where the probability of curing the disease is less. But if we find the disease at that stage, the patient might be in a situation of losing vision completely. Hence, this project aims at finding the disease at the earliest possible stage with the help of Deep Learning (DL) algorithms. Deep neural networks, on the other hand, have brought many breakthroughs in various tasks in the recent years. To automate the diagnosis of DR and provide appropriate suggestions to DR patients, we have built a dataset of DR fundus images that have been labeled by the proper treatment method that is required. Using this dataset, we trained deep convolutional neural network models to grade the severities of DR fundus images. This system not only focuses on diabetic retinopathy detection but also on the analysis of different DR stages, which is performed with the help of Deep Learning (DL) and hybrid Deep Convolutional Neural Network algorithm. CNN and hybrid CNN with LSTM, are used on a huge dataset with around 1500 train images to automatically detect which stage DR has progressed. Five DR stages, which are 0 (No DR), 1 (Mild DR), 2 (Moderate), 3 (Severe) and 4 (Proliferative DR) are processed in the proposed work.