A Newly Developed Deep Learning-Based Xception Model for Classification and Detection of Eye Disease Using Fundus Images
Keywords:
Diabetic Retinopathy, Fundus images, DDR Dataset, Deep Learning, Xception, CNN, Cross-Validation.Abstract
A condition affecting the retina, Diabetic Retinopathy (DR) develops in patients with long-term diabetes mellitus (>20 years). In many parts of the globe, DR is a leading cause of avoidable blindness. People with diabetes are at increased risk for developing diabetic retinopathy (DR), a serious eye disease. Treatment of eye diseases and prevention of irreversible vision loss depends on early diagnosis and prompt treatment. Fundus photos aid medical professionals in identifying disorders affecting patients' eyes. A fundus picture could show several eye diseases. One frequent method for identifying eye diseases is screening retinal fundus images, although manual identification is labor-intensive and takes a lot of time. Many scholars have thus resorted to deep learning (DL) methods in an effort to automate the diagnosis of retinal eye disorders. To classify and detect eye diseases using fundus images from the DDR Dataset, images are preprocessed, resized, and filtered before being labelled into three classes. The dataset undergoes 5-fold cross-validation. A fine-tuned Xception model with additional fully connected layers is trained using the Adam optimiser. The experimental findings show that the suggested system achieves 92.78% and 98.98% train and validation accuracy with Xception architecture and surpasses existing approaches for categorising eye diseases. The model's robustness is shown by its accuracy, recall, and F1-score metrics, which demonstrate its ability to produce correct predictions for each class. The model's training and validation accuracy, as well as loss curves, show that it avoids overfitting and has high generalisation capabilities. The suggested model has great potential as a helpful resource for doctors to use in the early and accurate identification of eye disorders, which would lead to better care for patients and better ocular health management overall.
Downloads
References
T. Nazir, A. Irtaza, A. Javed, H. Malik, D. Hussain, and R. A. Naqvi, “Retinal image analysis for diabetes-based eye disease detection using deep learning,” Appl. Sci., 2020, doi: 10.3390/APP10186185.
P. Saeedi et al., “Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition,” Diabetes Res. Clin. Pract., 2019, doi: 10.1016/j.diabres.2019.107843.
“Retinal Image Analysis for Diabetes-Based Eye Disease Detection Using Deep Learning,” Int. J. Progress. Res. Eng. Manag. Sci., 2023, doi: 10.58257/ijprems31685.
H. Mustafa, S. F. Ali, M. Bilal, and M. S. Hanif, “Multi-Stream Deep Neural Network for Diabetic Retinopathy Severity Classification under a Boosting Framework,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3217216.
P. Porwal et al., “Indian diabetic retinopathy image dataset (IDRiD): A database for diabetic retinopathy screening research,” Data, 2018, doi: 10.3390/data3030025.
S. Patil et al., “Artificial Intelligence in the Diagnosis of Oral Diseases: Applications and Pitfalls,” Diagnostics. 2022. doi: 10.3390/diagnostics12051029.
S. Sengupta, A. Singh, H. A. Leopold, T. Gulati, and V. Lakshminarayanan, “Ophthalmic diagnosis using deep learning with fundus images – A critical review,” Artificial Intelligence in Medicine. 2020. doi: 10.1016/j.artmed.2019.101758.
J. H. Tan, U. R. Acharya, S. V. Bhandary, K. C. Chua, and S. Sivaprasad, “Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network,” J. Comput. Sci., 2017, doi: 10.1016/j.jocs.2017.02.006.
R. Chavan and D. Pete, “Automatic multi-disease classification on retinal images using multilevel glowworm swarm convolutional neural network,” J. Eng. Appl. Sci., 2024, doi: 10.1186/s44147-023-00335-0.
R. H. Paradisa, A. Bustamam, W. Mangunwardoyo, A. A. Victor, A. R. Yudantha, and P. Anki, “Deep feature vectors concatenation for eye disease detection using fundus image,” Electron., 2022, doi: 10.3390/electronics11010023.
J. Colcombe, R. Mundae, A. Kaiser, J. Bijon, and Y. Modi, “Retinal Findings and Cardiovascular Risk: Prognostic Conditions, Novel Biomarkers, and Emerging Image Analysis Techniques,” Journal of Personalized Medicine. 2023. doi: 10.3390/jpm13111564.
B. Goutam, M. F. Hashmi, Z. W. Geem, and N. D. Bokde, “A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images,” IEEE Access. 2022. doi: 10.1109/ACCESS.2022.3178372.
S. Dubey and M. Dixit, “Recent developments on computer aided systems for diagnosis of diabetic retinopathy: a review,” Multimed. Tools Appl., 2023, doi: 10.1007/s11042-022-13841-9.
M. Vadduri and P. Kuppusamy, “Enhancing Ocular Healthcare: Deep Learning-Based Multi-Class Diabetic Eye Disease Segmentation and Classification,” IEEE Access, 2023, doi: 10.1109/ACCESS.2023.3339574.
R. Sarki, K. Ahmed, H. Wang, Y. Zhang, J. Ma, and K. Wang, “Image Preprocessing in Classification and Identification of Diabetic Eye Diseases,” Data Sci. Eng., 2021, doi: 10.1007/s41019-021-00167-z.
N. Chea and Y. Nam, “Classification of Fundus Images Based on Deep Learning for Detecting Eye Diseases,” Comput. Mater. Contin., 2021, doi: 10.32604/cmc.2021.013390.
S. Ortiz and M. A. Goenaga Jimenez, “Deep Learning-Based Ocular Disease Classification in Fundus Images,” in 1st IEEE Colombian Caribbean Conference, C3 2023, 2023. doi: 10.1109/C358072.2023.10436234.
M. A. Abini and S. S. S. Priya, “A Deep Learning Framework for Detection and Classification of Diabetic Retinopathy in Fundus Images Using Residual Neural Networks,” in 9th International Conference on Smart Computing and Communications: Intelligent Technologies and Applications, ICSCC 2023, 2023. doi: 10.1109/ICSCC59169.2023.10335079.
R. Chavan and D. Pete, “Classification of Retinal Fundus Images using VGG16 and Inception V3,” in 2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023, 2023. doi: 10.1109/ICCCNT56998.2023.10306593.
G. R. S. N. Kumar, R. S. Sankuri, and S. P. K. Karri, “Multi Scale aided Deep Learning model for High F1-score classification of fundus images based Diabetic Retinopathy and Glaucoma,” in 2023 International Conference on Computer, Electronics and Electrical Engineering and their Applications, IC2E3 2023, 2023. doi: 10.1109/IC2E357697.2023.10262434.
H. Y. Sam, S. A. Zikri B Sayed Aluwee, N. S. Bt Che Lah, C. M. Goh, C. M. Tyng, and H. Ikhwan B Murat, “Preliminary Study of Diabetic Retinopathy Classification from Fundus Images Using Deep Learning Model,” in 2022 3rd International Conference on Artificial Intelligence and Data Sciences: Championing Innovations in Artificial Intelligence and Data Sciences for Sustainable Future, AiDAS 2022 - Proceedings, 2022. doi: 10.1109/AiDAS56890.2022.9918681.
K. Chauhan, Kashish, K. Dagar, and R. K. Yadav, “Cataract detection from eye fundus image using an ensemble of transfer learning models,” in 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2022, 2022. doi: 10.1109/ICACITE53722.2022.9823638.
A. A. Mukhlif, B. Al-Khateeb, and M. A. Mohammed, “Breast cancer images Classification using a new transfer learning technique,” Iraqi J. Comput. Sci. Math., 2023, doi: 10.52866/ijcsm.2023.01.01.0014.
M. M. A. Shibly, T. A. Tisha, T. A. Tani, and S. Ripon, “Convolutional neural network-based ensemble methods to recognize Bangla handwritten character,” PeerJ Comput. Sci., 2021, doi: 10.7717/peerj-cs.565.
R. E. Mandiya, H. M. Kongo, S. K. Kasereka, K. Kyandoghere, P. M. Tshakwanda, and N. M. Kasoro, “Enhancing COVID-19 Detection: An Xception-Based Model with Advanced Transfer Learning from X-ray Thorax Images,” J. Imaging, vol. 10, no. 3, 2024, doi: 10.3390/jimaging10030063.
C. Szegedy et al., “Going deeper with convolutions,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015. doi: 10.1109/CVPR.2015.7298594.
S. Ioffe and C. Szegedy, “Batch normalisation: Accelerating deep network training by reducing internal covariate shift,” in 32nd International Conference on Machine Learning, ICML 2015, 2015.
A. Tharwat, “Classification assessment methods,” Appl. Comput. Informatics, 2018, doi: 10.1016/j.aci.2018.08.003.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
