Diabetic Retinopathy Detection with Deep Transfer Learning Methods

Abstract

Diabetic retinopathy is an eye disease that occurs with damage to the retina and has many different complications, ranging from permanent blindness. The aim of this study is to develop a (convolutional neural network) CNN model that determines with high accuracy whether fundus images are diabetic retinopathy. The performance of the model has been verified in Kaggle APTOS 2019 dataset with AlexNET and VggNET-16 deep transfer learning algorithms. Various image processing techniques have been used as well as deep learning methods to further improve the classification performance. Images in the data set were rescaled to 224 × 224 × 3 and converted to Grayscale color space. Besides Gauss filter applied to eliminate the noise in the images. The area under the curve (AUC), precision, recall, and accuracy metrics of the deep transfer learning models used in this study were compared. The AlexNet model achieved a 98.6% AUC score, 95.2% accuracy, and the VggNET-16 model achieved a 99.6% AUC score and 98.1% accuracy. VggNET-16 was found to have higher confidence. Our results show that with the correct optimization of the CNN model applied in diabetic retinopathy classification, deep transfer learning models can achieve high performance and can be used in the detection of diabetic retinopathy patients.