Diabetic Retinopathy Grading by Deep Graph Correlation Network on Retinal Images Without Manual Annotations

Abstract

BackgroundDiabetic retinopathy, as a severe public health problem associated with vision loss, should be diagnosed early using an accurate screening tool. While many previous deep learning models have been proposed for this disease, they need sufficient professional annotation data to train the model, requiring more expensive and time-consuming screening skills.MethodThis study aims to economize manual power and proposes a deep graph correlation network (DGCN) to develop automated diabetic retinopathy grading without any professional annotations. DGCN involves the novel deep learning algorithm of a graph convolutional network to exploit inherent correlations from independent retinal image features learned by a convolutional neural network. Three designed loss functions of graph-center, pseudo-contrastive, and transformation-invariant constrain the optimisation and application of the DGCN model in an automated diabetic retinopathy grading task.ResultsTo evaluate the DGCN model, this study employed EyePACS-1 and Messidor-2 sets to perform grading results. It achieved an accuracy of 89.9% (91.8%), sensitivity of 88.2% (90.2%), and specificity of 91.3% (93.0%) on EyePACS-1 (Messidor-2) data set with a confidence index of 95% and commendable effectiveness on receiver operating characteristic (ROC) curve and t-SNE plots.ConclusionThe grading capability of this study is close to that of retina specialists, but superior to that of trained graders, which demonstrates that the proposed DGCN provides an innovative route for automated diabetic retinopathy grading and other computer-aided diagnostic systems.

A multidomain bio-inspired feature extraction and selection model for diabetic retinopathy severity classification: an ensemble learning approach

“…The proposed framework is implemented on the Windows 11 operating system with an i7 processor, 16 GB of RAM, 1 TB of SSD memory, and 4 GB of NVIDIA GPU resources using NumPy and TensorFlow libraries in a Python environment. The proposed framework has yielded superior results when compared to the existing models, namely, the Mixed Model-DR Ensemble model 17 , the Deep U-Net architecture 18 , the DGCN model 20 , and the Hybrid Retinal-DL model 24 . The performance metrics that are used to calculate the performance of the training and testing data are Accuracy, Precision, Recall and F1-Score based on the true positive ( T p ) rate, true negative ( T n ) rate, false positive ( F p ) rate, and false negative ( F n ) rates of the classes.…”

“…However, this task was quite tedious because considering the complexity of the disease, the existence of a large amount of variability in the degree of detail of the eye retinal images, and the requirement for accurate and reliable classification performance levels via the use of UNet and Multiple Scale Attention Network (MSA-Net) 18 , 19 . The authors in 20 proposed a deep graph correlation network (DGCN) that provides an innovative path for automated DR classification and other computer-assisted medical diagnosis systems. Similarly, the proposed technique utilized DenseNet169’s encoder and Convolutional Block Attention Module (CBAM) 21 to construct a visual embedding for automated DR diagnostics.…”

Is it time to consider teleophthalmology as a game-changer in the management of diabetic retinopathy?

“…(81,82) The development of innovative approaches continues. (83)(84)(85)(86)(87)(88)(89)(90)(91)(92)(93) The recent one presented by Zhang et al (83) is based on Deep Graph Correlation Network for grading. Researchers postulated that it has an accuracy near to retinal specialists and more than trained graders.…”

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

“…The final results showed that the AUC, sensitivity, and specificity of the model were 0.992, 0.925, and 0.961, respectively, which were better than those of ophthalmologists. To better assist the diagnosis of severe DR, Zhang et al (2022a) developed an AI model that can diagnose DR automatically on the basis of Inception V3 and applied The In this study, EyePACS-1 and Messidor-2 datasets were used to train and test the model. Finally, the results showed that the accuracy, sensitivity, and specificity of the model on the EyePACS-1 dataset were 0.899, 0.882, and 0.913, respectively, and the accuracy, sensitivity and specificity of the model on the Messidor-2 dataset Frontiers in Cell and Developmental Biology frontiersin.org were 0.918, 0.902, and 0.930, respectively.…”

“…The final results showed that the AUC, sensitivity, and specificity of the model were 0.992, 0.925, and 0.961, respectively, which were better than those of ophthalmologists. To better assist the diagnosis of severe DR, Zhang et al (2022a) developed an AI model that can diagnose DR automatically on the basis of Inception V3 and applied The Kaggle public dataset to the development and validation of the AI model. After validation, the sensitivity, specificity, and AUC of the model for diagnosing severe DR were 0.925, 0.907, and 0.968, respectively.…”