Accurate Detection of Non-Proliferative Diabetic Retinopathy in Optical Coherence Tomography Images Using Convolutional Neural Networks

Abstract

Diabetic retinopathy (DR) is a disease that forms as a complication of diabetes. It is particularly dangerous since it often goes unnoticed and can lead to blindness if not detected early. Despite the clear importance and urgency of such an illness, there is no precise system for the early detection of DR so far. Fortunately, such system could be achieved using deep learning including convolutional neural networks (CNNs), which gained momentum in the field of medical imaging due to its capability of being effectively integrated into various systems in a manner that significantly improves the performance. This paper proposes a computer aided diagnostic (CAD) system for the early detection of non-proliferative DR (NPDR) using CNNs. The proposed system is developed for the optical coherence tomography (OCT) imaging modality. Throughout this paper, all aspects of deployment of the proposed system are studied starting from the preprocessing stage required to extract input retina patches to train the CNN without resizing the image, to the use of transfer learning principals and how to effectively combine features in order to optimize performance. This is done through investigating several scenarios for the system setup and then selecting the best one, which from the results revealed to be a two pre-trained CNNs based system, in which one of these CNNs is independently fed by nasal retina patches and the other one by temporal retina patches. The proposed transfer learning based CAD system achieves a promising accuracy of 94%. INDEX TERMS Convolutional neural network (CNN), diabetic retinopathy (DR), optical coherence tomography (OCT).

RETRACTED ARTICLE: Threshold segmentation based multi-layer analysis for detecting diabetic retinopathy using convolution neural network

“…It is done by trained experts where the images are used to diagnose the fatal diseases, and it is named deep CNN models. Ghazal et al (2019) observed a non-proliferative diabetic retinopathy using CNN. The author addresses the computeraided diagnostic (CAD) system to detect non-proliferative DR (NPDR) usingCNN.…”

Comparative Analysis of the Effects of the Anti-VEGF Drug and Glucocorticoid by Injection before the End of Vitrectomy for Proliferative Diabetic Retinopathy

“…The clinical hazards of PDR mainly to lead to blindness and increase the risk of poor prognosis [ 1 ]. At present, vitrectomy combined with panretinal laser photocoagulation is commonly used in practice, but patients are prone to bleeding and iatrogenic retinal breaks during surgery, and postsurgical complications such as vitreous rehemorrhage and retinal detachment seriously affect the surgical effect, which may result in patients' irreversible loss of vision [ 2 ]. According to its pathological characteristics, perioperative application of anti-VEGF drugs or anti-inflammatory drugs can reduce intraoperative blood loss and the probability of postsurgical complications.…”

The Role of Medical Image Modalities and AI in the Early Detection, Diagnosis and Grading of Retinal Diseases: A Survey

“…Li et al [ 183 ] applied a deep network, called OCTD_Net, for early detection of DR using OCT images. Ghazal et al [ 184 ] developed early detection of NPDR using OCT images based on an AlexNet followed by an SVM for classification.…”