A computer-aided diagnosis system for detecting various diabetic retinopathy grades based on a hybrid deep learning technique

Abstract

Diabetic retinopathy (DR) is a serious disease that may cause vision loss unawares without any alarm. Therefore, it is essential to scan and audit the DR progress continuously. In this respect, deep learning techniques achieved great success in medical image analysis. Deep convolution neural network (CNN) architectures are widely used in multi-label (ML) classification. It helps in diagnosing normal and various DR grades: mild, moderate, and severe non-proliferative DR (NPDR) and proliferative DR (PDR). DR grades are formulated by appearing multiple DR lesions simultaneously on the color retinal fundus images. Many lesion types have various features that are difficult to segment and distinguished by utilizing conventional and hand-crafted methods. Therefore, the practical solution is to utilize an effective CNN model. In this paper, we present a novel hybrid, deep learning technique, which is called E-DenseNet. We integrated EyeNet and DenseNet models based on transfer learning. We customized the traditional EyeNet by inserting the dense blocks and optimized the resulting hybrid E-DensNet model’s hyperparameters. The proposed system based on the E-DenseNet model can accurately diagnose healthy and different DR grades from various small and large ML color fundus images. We trained and tested our model on four different datasets that were published from 2006 to 2019. The proposed system achieved an average accuracy (ACC), sensitivity (SEN), specificity (SPE), Dice similarity coefficient (DSC), the quadratic Kappa score (QKS), and the calculation time (T) in minutes (m) equal $$91.2\%$$ 91.2 % , $$96\%$$ 96 % , $$69\%$$ 69 % , $$92.45\%$$ 92.45 % , 0.883, and 3.5m respectively. The experiments show promising results as compared with other systems. Graphical abstract

Smart grading of diabetic retinopathy: an intelligent recommendation-based fine-tuned EfficientNetB0 framework

“…The authors worked using Kaggle APTOS 2019 and ISBI IDRiD datasets and obtained the accuracy values of 85.54 and 66.41%, respectively. AbdelMaksoud et al ( 2022 ) combined the EyeNet and DenseNet models for the diagnosis of DR and used four datasets, namely, EyePACS, Indian diabetic retinopathy image dataset, MESSIDOR, and Asia Pacific Tele-Ophthalmology Society (APTOS 2019), and resized the images to 256 * 256. The proposed model achieved an Acc of 0.912, a Se of 0.96, and a Sp of 0.69.…”

LuNet-LightGBM: An Effective Hybrid Approach for Lesion Segmentation and DR Grading

“…When employing different methods for DR classification, this feature set is supplied to several classifiers, and the results are compared. E-DenseNet-based hybrid deep learning method was presented by AbdelMaksoud et al [27] for DR classification. They combined transfer learning-based DenseNet and EyeNet models for classification.…”

The Present and Future of Artificial Intelligence-Based Medical Image in Diabetes Mellitus: Focus on Analytical Methods and Limitations of Clinical Use

“…Moreover, the existence of variations in the model performance depending on the dataset will be an important issue in the future. 53 It should be considered separately and verified whether this could be used clinically. 54 55 …”