Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images
Diabetic retinopathy (DR) is a visual obstacle caused by diabetic disease, which forms because of long-standing diabetes mellitus, which damages the retinal blood vessels. This disease is considered one of the principal causes of sightlessness and accounts for more than 158 million cases all over th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/5/535 |
| _version_ | 1827669947505967104 |
|---|---|
| author | Muhammad Kashif Jabbar Jianzhuo Yan Hongxia Xu Zaka Ur Rehman Ayesha Jabbar |
| author_facet | Muhammad Kashif Jabbar Jianzhuo Yan Hongxia Xu Zaka Ur Rehman Ayesha Jabbar |
| author_sort | Muhammad Kashif Jabbar |
| collection | DOAJ |
| description | Diabetic retinopathy (DR) is a visual obstacle caused by diabetic disease, which forms because of long-standing diabetes mellitus, which damages the retinal blood vessels. This disease is considered one of the principal causes of sightlessness and accounts for more than 158 million cases all over the world. Since early detection and classification could diminish the visual impairment, it is significant to develop an automated DR diagnosis method. Although deep learning models provide automatic feature extraction and classification, training such models from scratch requires a larger annotated dataset. The availability of annotated training datasets is considered a core issue for implementing deep learning in the classification of medical images. The models based on transfer learning are widely adopted by the researchers to overcome annotated data insufficiency problems and computational overhead. In the proposed study, features are extracted from fundus images using the pre-trained network VGGNet and combined with the concept of transfer learning to improve classification performance. To deal with data insufficiency and unbalancing problems, we employed various data augmentation operations differently on each grade of DR. The results of the experiment indicate that the proposed framework (which is evaluated on the benchmark dataset) outperformed advanced methods in terms of accurateness. Our technique, in combination with handcrafted features, could be used to improve classification accuracy. |
| first_indexed | 2024-03-10T03:14:13Z |
| format | Article |
| id | doaj.art-0cd4da2f88184ded8d5f2d77e88b761b |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-10T03:14:13Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-0cd4da2f88184ded8d5f2d77e88b761b2023-11-23T10:16:44ZengMDPI AGBrain Sciences2076-34252022-04-0112553510.3390/brainsci12050535Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal ImagesMuhammad Kashif Jabbar0Jianzhuo Yan1Hongxia Xu2Zaka Ur Rehman3Ayesha Jabbar4Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaDepartment of Computer Science and IT, Gujrat Campus, The University of Lahore, Gujrat 50700, PakistanDepartment of Science & Technology, University of Education, Lahore 54770, PakistanDiabetic retinopathy (DR) is a visual obstacle caused by diabetic disease, which forms because of long-standing diabetes mellitus, which damages the retinal blood vessels. This disease is considered one of the principal causes of sightlessness and accounts for more than 158 million cases all over the world. Since early detection and classification could diminish the visual impairment, it is significant to develop an automated DR diagnosis method. Although deep learning models provide automatic feature extraction and classification, training such models from scratch requires a larger annotated dataset. The availability of annotated training datasets is considered a core issue for implementing deep learning in the classification of medical images. The models based on transfer learning are widely adopted by the researchers to overcome annotated data insufficiency problems and computational overhead. In the proposed study, features are extracted from fundus images using the pre-trained network VGGNet and combined with the concept of transfer learning to improve classification performance. To deal with data insufficiency and unbalancing problems, we employed various data augmentation operations differently on each grade of DR. The results of the experiment indicate that the proposed framework (which is evaluated on the benchmark dataset) outperformed advanced methods in terms of accurateness. Our technique, in combination with handcrafted features, could be used to improve classification accuracy.https://www.mdpi.com/2076-3425/12/5/535diabetic retinopathyannotated data insufficiencytransfer learningfundus imagescomputer-aided diagnosisconvolutional neural network |
| spellingShingle | Muhammad Kashif Jabbar Jianzhuo Yan Hongxia Xu Zaka Ur Rehman Ayesha Jabbar Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images Brain Sciences diabetic retinopathy annotated data insufficiency transfer learning fundus images computer-aided diagnosis convolutional neural network |
| title | Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images |
| title_full | Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images |
| title_fullStr | Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images |
| title_full_unstemmed | Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images |
| title_short | Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images |
| title_sort | transfer learning based model for diabetic retinopathy diagnosis using retinal images |
| topic | diabetic retinopathy annotated data insufficiency transfer learning fundus images computer-aided diagnosis convolutional neural network |
| url | https://www.mdpi.com/2076-3425/12/5/535 |
| work_keys_str_mv | AT muhammadkashifjabbar transferlearningbasedmodelfordiabeticretinopathydiagnosisusingretinalimages AT jianzhuoyan transferlearningbasedmodelfordiabeticretinopathydiagnosisusingretinalimages AT hongxiaxu transferlearningbasedmodelfordiabeticretinopathydiagnosisusingretinalimages AT zakaurrehman transferlearningbasedmodelfordiabeticretinopathydiagnosisusingretinalimages AT ayeshajabbar transferlearningbasedmodelfordiabeticretinopathydiagnosisusingretinalimages |