Fundus image based diabetic retinopathy detection using EfficientNetB3 with squeeze and excitation block

Diabetic retinopathy (DR) is a retinal affliction in patients suffering from diabetes. If DR is unidentified at an earlier stage, it may lead to blindness. Manual screening of DR using fundus images is a complex and time-consuming task. In the past, many automated techniques have been developed for DR detection and classification. In the case of multiclass fundus images, producing reliable classification performance is a challenge for researchers. Hence, this paper presents a novel transfer learning-based approach to classify DR using fundus images. The proposed technique is based on EfficientNetB3 with squeeze and excitation block. EfficientNetB3 performs classification tasks very well using an effective architecture with fewer parameters while the squeeze and excitation block improves the model's ability by focusing on crucial features. For experimentation of the proposed technique, fundus images of the APTOS-2019 dataset are utilized. The proposed technique achieves overall 88.44% accuracy, 98.00% specificity, 84.00% precision, 83.00% sensitivity, 83.00% F1-score, and 0.88 kappa score for all five classes of fundus images of the APTOS-2019 dataset. In addition to this, the proposed technique is also experimented using fundus images of the IDRiD and Messidor-2 datasets. The performance of the proposed technique is better than many existing DR detection techniques.