An Explainable Fully Dense Fusion Neural Network with Deep Support Vector Machine for Retinal Disease Determination

Abstract

AbstractRetinal issues are crucial because they result in visual loss. Early diagnosis can aid physicians in initiating treatment and preventing visual loss. Optical coherence tomography (OCT), which portrays retinal morphology cross-sectionally and noninvasively, is used to identify retinal abnormalities. The process of analyzing OCT images, on the other hand, takes time. This study has proposed a hybrid approach based on a fully dense fusion neural network (FD-CNN) and dual preprocessing to identify retinal diseases, such as choroidal neovascularization, diabetic macular edema, drusen from OCT images. A dual preprocessing methodology, in other words, a hybrid speckle reduction filter was initially used to diminish speckle noise present in OCT images. Secondly, the FD-CNN architecture was trained, and the features obtained from this architecture were extracted. Then Deep Support Vector Machine (D-SVM) and Deep K-Nearest Neighbor (D-KNN) classifiers were proposed to reclassify those features and tested on University of California San Diego (UCSD) and Duke OCT datasets. D-SVM demonstrated the best performance in both datasets. D-SVM achieved 99.60% accuracy, 99.60% sensitivity, 99.87% specificity, 99.60% precision and 99.60% F1 score in the UCSD dataset. It achieved 97.50% accuracy, 97.64% sensitivity, 98.91% specificity, 96.61% precision, and 97.03% F1 score in Duke dataset. Additionally, the results were compared to state-of-the-art works on the both datasets. The D-SVM was demonstrated to be an efficient and productive strategy for improving the robustness of automatic retinal disease classification. Also, in this study, it is shown that the unboxing of how AI systems' black-box choices is made by generating heat maps using the local interpretable model-agnostic explanation method, which is an explainable artificial intelligence (XAI) technique. Heat maps, in particular, may contribute to the development of more stable deep learning-based systems, as well as enhancing the confidence in the diagnosis of retinal disease in the analysis of OCT image for ophthalmologists.