Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks
Diabetic Retinopathy (DR) stays a main source of vision deterioration around world and it is getting exacerbated day by day. Almost no warning signs for detecting DR which will be greater challenge with us today. So, it is extremely preferred that DR has to be discovered on time. Adversely, the ex...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stefan cel Mare University of Suceava
2021-08-01
|
| Series: | Advances in Electrical and Computer Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.4316/AECE.2021.03006 |
| _version_ | 1819147946808049664 |
|---|---|
| author | SOMASUNDARAM, K. SIVAKUMAR, P. SURESH, D. |
| author_facet | SOMASUNDARAM, K. SIVAKUMAR, P. SURESH, D. |
| author_sort | SOMASUNDARAM, K. |
| collection | DOAJ |
| description | Diabetic Retinopathy (DR) stays a main source of vision deterioration around world and it is getting
exacerbated day by day. Almost no warning signs for detecting DR which will be greater challenge with
us today. So, it is extremely preferred that DR has to be discovered on time. Adversely, the existing
result involves an ophthalmologist to manually check and identify DR by positioning the exudates related
with vascular irregularity due to diabetes from fundus image. In this work, we are able to classify
images based on different severity levels through an automatic DR classification system. To extract
specific features of image without any loss in spatial information, a Convolutional Neural Network
(CNN) models which possesses an image with a distinct weight matrix is used. In the beginning, we
estimate various CNN models to conclude the best performing CNN for DR classification with an
objective to obtain much better accuracy. In the classification of DR disease with transfer
learning using deep CNN models, 97.72% of accuracy is provided by the proposed CNN model for
Kaggle dataset. The proposed CNN model provides a classification accuracy of 97.58% for MESSIDOR
dataset. The proposed technique provides better results than other state-of-art methods. |
| first_indexed | 2024-12-22T13:37:54Z |
| format | Article |
| id | doaj.art-f5788d7030264ae99b0f0e31d57250e3 |
| institution | Directory Open Access Journal |
| issn | 1582-7445 1844-7600 |
| language | English |
| last_indexed | 2024-12-22T13:37:54Z |
| publishDate | 2021-08-01 |
| publisher | Stefan cel Mare University of Suceava |
| record_format | Article |
| series | Advances in Electrical and Computer Engineering |
| spelling | doaj.art-f5788d7030264ae99b0f0e31d57250e32022-12-21T18:24:01ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002021-08-01213495610.4316/AECE.2021.03006Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural NetworksSOMASUNDARAM, K.SIVAKUMAR, P.SURESH, D.Diabetic Retinopathy (DR) stays a main source of vision deterioration around world and it is getting exacerbated day by day. Almost no warning signs for detecting DR which will be greater challenge with us today. So, it is extremely preferred that DR has to be discovered on time. Adversely, the existing result involves an ophthalmologist to manually check and identify DR by positioning the exudates related with vascular irregularity due to diabetes from fundus image. In this work, we are able to classify images based on different severity levels through an automatic DR classification system. To extract specific features of image without any loss in spatial information, a Convolutional Neural Network (CNN) models which possesses an image with a distinct weight matrix is used. In the beginning, we estimate various CNN models to conclude the best performing CNN for DR classification with an objective to obtain much better accuracy. In the classification of DR disease with transfer learning using deep CNN models, 97.72% of accuracy is provided by the proposed CNN model for Kaggle dataset. The proposed CNN model provides a classification accuracy of 97.58% for MESSIDOR dataset. The proposed technique provides better results than other state-of-art methods.http://dx.doi.org/10.4316/AECE.2021.03006computer aided diagnosisimage classificationlearningneural networksretinopathy |
| spellingShingle | SOMASUNDARAM, K. SIVAKUMAR, P. SURESH, D. Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks Advances in Electrical and Computer Engineering computer aided diagnosis image classification learning neural networks retinopathy |
| title | Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks |
| title_full | Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks |
| title_fullStr | Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks |
| title_full_unstemmed | Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks |
| title_short | Classification of Diabetic Retinopathy disease with Transfer Learning using Deep Convolutional Neural Networks |
| title_sort | classification of diabetic retinopathy disease with transfer learning using deep convolutional neural networks |
| topic | computer aided diagnosis image classification learning neural networks retinopathy |
| url | http://dx.doi.org/10.4316/AECE.2021.03006 |
| work_keys_str_mv | AT somasundaramk classificationofdiabeticretinopathydiseasewithtransferlearningusingdeepconvolutionalneuralnetworks AT sivakumarp classificationofdiabeticretinopathydiseasewithtransferlearningusingdeepconvolutionalneuralnetworks AT sureshd classificationofdiabeticretinopathydiseasewithtransferlearningusingdeepconvolutionalneuralnetworks |