Automated Diabetic Retinopathy Prediction System Using Inception V3

This paper proposes the use of the InceptionV3 model, a powerful convolutional neural network (CNN), for the detection of diabetic retinopathy (DR) from retinal fundus images. The InceptionV3 model has been widely utilized in various computer vision tasks because it captures intricate features and patterns within images. To implement the diabetic retinopathy detection system, a dataset consisting of retinal fundus images is collected and preprocessed to ensure consistency and remove noise. The trained model is evaluated on a separate test set, and performance metrics such as accuracy, sensitivity, and specificity are calculated to assess its effectiveness. The results obtained from the experiments demonstrate the high accuracy and reliability of the InceptionV3 model in detecting DR. This study sheds light on the potential of deep learning techniques, notably Inception V3, in the early identification and diagnosis of DR, allowing for earlier management and lowering the risk of vision loss in diabetic patients.