The classification of eye diseases from fundus images based on CNN and pretrained models
Visual impairment affects more than a billion people worldwide due to insufficient care or inadequate vision screening. Computer-aided diagnosis using deep neural networks is a promising approach, it can analyse and process retinal fundus images, providing valuable reference data for doctors in cli...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
CTU Central Library
2024-03-01
|
| Series: | Acta Polytechnica |
| Subjects: | |
| Online Access: | https://ojs.cvut.cz/ojs/index.php/ap/article/view/8679 |
| _version_ | 1827318376163180544 |
|---|---|
| author | Samir Benbakreti Soumia Benbakreti Umut Ozkaya |
| author_facet | Samir Benbakreti Soumia Benbakreti Umut Ozkaya |
| author_sort | Samir Benbakreti |
| collection | DOAJ |
| description |
Visual impairment affects more than a billion people worldwide due to insufficient care or inadequate vision screening. Computer-aided diagnosis using deep neural networks is a promising approach, it can analyse and process retinal fundus images, providing valuable reference data for doctors in clinical diagnosis or screening. This study aims to achieve an accurate classification of fundus images, including images of healthy patients as well as those with diabetic retinopathy, cataracts, and glaucoma, using a convolutional neural network (CNN) architecture and several pretrained models (AlexNet, GoogleNet, ResNet18, ResNet50, YOLOv3, and VGG 19). To enhance the training process, a mirror effect technique was applied to augment the volume of data. The experimental study resulted in very satisfactory outcomes, with the GoogleNet model paired with the SGDM optimiser achieving the highest accuracy (92.7 %).
|
| first_indexed | 2024-04-24T23:56:53Z |
| format | Article |
| id | doaj.art-1980bd44ca6a496d87146a9a980b0bec |
| institution | Directory Open Access Journal |
| issn | 1805-2363 |
| language | English |
| last_indexed | 2024-04-24T23:56:53Z |
| publishDate | 2024-03-01 |
| publisher | CTU Central Library |
| record_format | Article |
| series | Acta Polytechnica |
| spelling | doaj.art-1980bd44ca6a496d87146a9a980b0bec2024-03-14T11:26:14ZengCTU Central LibraryActa Polytechnica1805-23632024-03-0164110.14311/AP.2024.64.0001The classification of eye diseases from fundus images based on CNN and pretrained modelsSamir Benbakreti0Soumia Benbakreti1Umut Ozkaya2National High School of Telecommunications and ICT (ENSTTIC), Department of specialty, Oran 31 000, AlgeriaUniversity of Djillali Liabes, Laboratory of Mathematic, BP 89, Sidi Bel Abbes 22000, AlgeriaKonya Technical University, Engineering and Natural Science Faculty, Electrical and Electronics Engineering, Konya, Turkey Visual impairment affects more than a billion people worldwide due to insufficient care or inadequate vision screening. Computer-aided diagnosis using deep neural networks is a promising approach, it can analyse and process retinal fundus images, providing valuable reference data for doctors in clinical diagnosis or screening. This study aims to achieve an accurate classification of fundus images, including images of healthy patients as well as those with diabetic retinopathy, cataracts, and glaucoma, using a convolutional neural network (CNN) architecture and several pretrained models (AlexNet, GoogleNet, ResNet18, ResNet50, YOLOv3, and VGG 19). To enhance the training process, a mirror effect technique was applied to augment the volume of data. The experimental study resulted in very satisfactory outcomes, with the GoogleNet model paired with the SGDM optimiser achieving the highest accuracy (92.7 %). https://ojs.cvut.cz/ojs/index.php/ap/article/view/8679eye diseases classificationretinal fundus imagesdeep learningpretrained modelsSGDM |
| spellingShingle | Samir Benbakreti Soumia Benbakreti Umut Ozkaya The classification of eye diseases from fundus images based on CNN and pretrained models Acta Polytechnica eye diseases classification retinal fundus images deep learning pretrained models SGDM |
| title | The classification of eye diseases from fundus images based on CNN and pretrained models |
| title_full | The classification of eye diseases from fundus images based on CNN and pretrained models |
| title_fullStr | The classification of eye diseases from fundus images based on CNN and pretrained models |
| title_full_unstemmed | The classification of eye diseases from fundus images based on CNN and pretrained models |
| title_short | The classification of eye diseases from fundus images based on CNN and pretrained models |
| title_sort | classification of eye diseases from fundus images based on cnn and pretrained models |
| topic | eye diseases classification retinal fundus images deep learning pretrained models SGDM |
| url | https://ojs.cvut.cz/ojs/index.php/ap/article/view/8679 |
| work_keys_str_mv | AT samirbenbakreti theclassificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels AT soumiabenbakreti theclassificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels AT umutozkaya theclassificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels AT samirbenbakreti classificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels AT soumiabenbakreti classificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels AT umutozkaya classificationofeyediseasesfromfundusimagesbasedoncnnandpretrainedmodels |