A New Eyenet Model for Diagnosis of Diabetic Retinopathy

Abstract

& Diabetic retinopathy (DR) is an eye disease caused by complications of diabetes and it should be detected early for effective treatment. As diabetes progresses, the vision of a patient may start to deteriorate and lead to diabetic retinopathy. Two types were identified: nonproliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). In this study, to diagnose diabetic retinopathy, we have proposed a new EYENET model that was obtained by combining the modified probabilistic neural network (PNN) and a modified radial basis function neural network (RBFNN), and hence, it possesses the advantages of both models. The features such as blood vessels and hemorrhages of the NPDR image and exudates of the PDR image are extracted from the raw images using image-processing techniques and are fed to the classifier for classification. A total of 600 fundus images were used, out of which 400 were used for training, and 200 images were used for testing. Experimental results show that PNN has an accuracy of 96%, modified PNN has an accuracy of 97.5%, RBFNN has an accuracy of 93.5%, modified RBFNN has an accuracy of 95.5%, and the proposed EYENET model has an accuracy of 98.5%. This infers that our proposed model outperforms all other models.

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

“…We resized images to ( 256 × 256 ), cropped, rotated, and made color normalization for all images of the four utilized ML datasets. Then, in the modeling phase, we customized the traditional EyeNet model [16] by optimizing its hyperparameters to diagnose the healthy and various DR grades accurately [16]. We combined the customized EyeNet model and the DenseNet BC-121 architecture [17] to produce the E-DenseNet model.…”

“…In this phase, we give an overall definition for transfer learning and highlight details about EyeNet [16] and the DenseNet-BC architectures [17]. In addition, we provide the pseudo-code of the modeling steps.…”

“…The proposed model diagnoses the normal and various DR grades without the need to use hand-crafted feature extraction/selection and segmentation. We made a hybrid model that integrates the customized EyeNet model [16] and the fine-tuned DenseNet model [17] based on transfer learning. We modified the traditional EyeNet model to diagnose the normal and four various DR grades rather than DR presence/absence.…”

A transfer learning with deep neural network approach for diabetic retinopathy classification

“…Detecting the severity level of diabetic retinopathy eye early is crucial for preventing possible advancement of this disease. Due to the importance of this problem, many researchers have developed various machine learning techniques for detecting diabetic retinopathy including [21][22][23][24][25][26][27][28][29][30][31].…”

“…Our research shares with the previous research effort the idea of detecting diabetic retinopathy but it is significantly different. For example, our dataset contains 3,562 original images whereas many previous work trained their model on a small dataset with less than 500 images such as [21][22][23][24][25][26][27]. Other research work trained their models on a bigger dataset such as [28] and [29] with 1,200 images and [30][31][32] with around 35,000 images.…”