Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network
Diabetic retinopathy (DR) is an eye disease associated with diabetes that can lead to blindness. Early diagnosis is critical to ensure that patients with diabetes are not affected by blindness. Deep learning plays an important role in diagnosing diabetes, reducing the human effort to diagnose and cl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/15/2606 |
| _version_ | 1797586893304496128 |
|---|---|
| author | Usharani Bhimavarapu Nalini Chintalapudi Gopi Battineni |
| author_facet | Usharani Bhimavarapu Nalini Chintalapudi Gopi Battineni |
| author_sort | Usharani Bhimavarapu |
| collection | DOAJ |
| description | Diabetic retinopathy (DR) is an eye disease associated with diabetes that can lead to blindness. Early diagnosis is critical to ensure that patients with diabetes are not affected by blindness. Deep learning plays an important role in diagnosing diabetes, reducing the human effort to diagnose and classify diabetic and non-diabetic patients. The main objective of this study was to provide an improved convolution neural network (CNN) model for automatic DR diagnosis from fundus images. The pooling function increases the receptive field of convolution kernels over layers. It reduces computational complexity and memory requirements because it reduces the resolution of feature maps while preserving the essential characteristics required for subsequent layer processing. In this study, an improved pooling function combined with an activation function in the ResNet-50 model was applied to the retina images in autonomous lesion detection with reduced loss and processing time. The improved ResNet-50 model was trained and tested over the two datasets (i.e., APTOS and Kaggle). The proposed model achieved an accuracy of 98.32% for APTOS and 98.71% for Kaggle datasets. It is proven that the proposed model has produced greater accuracy when compared to their state-of-the-art work in diagnosing DR with retinal fundus images. |
| first_indexed | 2024-03-11T00:29:37Z |
| format | Article |
| id | doaj.art-a1bcba42a9924d91b5a9c526023eb683 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T00:29:37Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-a1bcba42a9924d91b5a9c526023eb6832023-11-18T22:47:45ZengMDPI AGDiagnostics2075-44182023-08-011315260610.3390/diagnostics13152606Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural NetworkUsharani Bhimavarapu0Nalini Chintalapudi1Gopi Battineni2Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram 522302, IndiaClinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyClinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyDiabetic retinopathy (DR) is an eye disease associated with diabetes that can lead to blindness. Early diagnosis is critical to ensure that patients with diabetes are not affected by blindness. Deep learning plays an important role in diagnosing diabetes, reducing the human effort to diagnose and classify diabetic and non-diabetic patients. The main objective of this study was to provide an improved convolution neural network (CNN) model for automatic DR diagnosis from fundus images. The pooling function increases the receptive field of convolution kernels over layers. It reduces computational complexity and memory requirements because it reduces the resolution of feature maps while preserving the essential characteristics required for subsequent layer processing. In this study, an improved pooling function combined with an activation function in the ResNet-50 model was applied to the retina images in autonomous lesion detection with reduced loss and processing time. The improved ResNet-50 model was trained and tested over the two datasets (i.e., APTOS and Kaggle). The proposed model achieved an accuracy of 98.32% for APTOS and 98.71% for Kaggle datasets. It is proven that the proposed model has produced greater accuracy when compared to their state-of-the-art work in diagnosing DR with retinal fundus images.https://www.mdpi.com/2075-4418/13/15/2606CNNdiabetic retinopathyfundus imagepooling function |
| spellingShingle | Usharani Bhimavarapu Nalini Chintalapudi Gopi Battineni Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network Diagnostics CNN diabetic retinopathy fundus image pooling function |
| title | Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network |
| title_full | Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network |
| title_fullStr | Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network |
| title_full_unstemmed | Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network |
| title_short | Automatic Detection and Classification of Diabetic Retinopathy Using the Improved Pooling Function in the Convolution Neural Network |
| title_sort | automatic detection and classification of diabetic retinopathy using the improved pooling function in the convolution neural network |
| topic | CNN diabetic retinopathy fundus image pooling function |
| url | https://www.mdpi.com/2075-4418/13/15/2606 |
| work_keys_str_mv | AT usharanibhimavarapu automaticdetectionandclassificationofdiabeticretinopathyusingtheimprovedpoolingfunctionintheconvolutionneuralnetwork AT nalinichintalapudi automaticdetectionandclassificationofdiabeticretinopathyusingtheimprovedpoolingfunctionintheconvolutionneuralnetwork AT gopibattineni automaticdetectionandclassificationofdiabeticretinopathyusingtheimprovedpoolingfunctionintheconvolutionneuralnetwork |