Detection and Diagnosis of Diabetic Retinopathy Using Transfer Learning Approach

Abstract

The human eye's anatomical features and defects can be captured by using the retinal image modality known as fundus imaging. The effective method for observing and detecting a variety of ophthalmological diseases is fundus imaging. Diseases including diabetic retinopathy, diabetic macular edema (DME), glaucoma, and cataracts are indicated by changes in and around the structural abnormalities like macula, optic disc, blood vessels, and fovea. More than one retinal disease may be present in one or both of the patient's eyes. For multi-class fundus image classification, the new deep learning (DL) model is proposed for ophthalmological diseases using a transfer learning (TL) based deep identification network (DeepID3) network. The flower pollination optimization algorithm (FPOA) is used to optimize the hyperparameters of the network. The model is tested using many large public datasets. The best pre-trained convolutional neural network (CNN) models from ImageNet were used in the experiment. Different performance optimization strategies were also used. Multi-class multi-label fundus image classification is more effective while using the DeepID3 net pre-trained architecture with FPOA optimizer. Maximum accuracy of 99.23%, sensitivity of 98%, precision of 98.13%, recall of 98%, F1-score of 98.3%, and specificity of 98.28% were attained by the proposed model for multi-class classification. The implementation is done by using the Python platform. The performance of the proposed approach is demonstrated by extensive experiments and comparison with baseline methods.