Classification of Diabetic Retinopathy Using ResNet50
DOI:
https://doi.org/10.12962/jaree.v9i2.436Abstrak
Deep learning has been proposed as an automated solution for classifying the severity levels of Diabetic Retinopathy (DR). In this study, we utilized ResNet50 architecture to classify DR using the APTOS2019 dataset. As an initial step, we initialized the model with pre-trained weights from ResNet50 on ImageNet and implemented augmentation and resampling during training. We adopted an ensemble approach combined with classifiers such as SVM, Random Forest, and Logistic Regression, resulting in a ResNet50-Ensemble (SVM+RF+LR), with outputs obtained using a Soft Voting Classifier. The model achieved an accuracy of 85%, with a precision of 0.72, recall of 0.71, and F1-score of 0.71. The AUC values for the normal, mild, moderate, severe, and proliferative classes were 1.00, 0.96, 0.95, 0.95, and 0.91, respectively, with a Macro-average AUC of 0.96. These findings indicate that the appropriate use of ensemble methods can significantly enhance DR classification performance with suitable optimization strategies.Referensi
R. Yasashvini, V. Raja Sarobin M, R. Panjanathan, S. Graceline Jasmine, dan L. Jani Anbarasi, “Diabetic Retinopathy Classification Using CNN and Hybrid Deep Convolutional Neural Networks,” Symmetry (Basel)., vol. 14, no. 9, 2022, doi: 10.3390/sym14091932.
M. Saini dan S. Susan, “Diabetic retinopathy screening using deep learning for multi-class imbalanced datasets,” Comput. Biol. Med., vol. 149, no. August, hal. 105989, 2022, doi: 10.1016/j.compbiomed.2022.105989.
A. Mustapha, L. Mohamed, H. Hamid, dan K. Ali, “Diabetic Retinopathy Classification Using ResNet50 and VGG-16 Pretrained Networks,” Int. J. Comput. Eng. Data Sci., vol. 1, no. 1, hal. 2737–8543, 2021, [Daring]. Tersedia pada: www.ijceds.com.
N. M. A. Tajudin et al., “Deep learning in the grading of diabetic retinopathy: A review,” IET Comput. Vis., vol. 16, no. 8, hal. 667–682, 2022, doi: 10.1049/cvi2.12116.
M. Y. T. Yip et al., “Technical and imaging factors influencing performance of deep learning systems for diabetic retinopathy,” npj Digit. Med., vol. 3, no. 1, hal. 31–34, 2020, doi: 10.1038/s41746-020-0247-1.
M. Z. Atwany, A. H. Sahyoun, dan M. Yaqub, “Deep Learning Techniques for Diabetic Retinopathy Classification: A Survey,” IEEE Access, vol. 10, hal. 28642–28655, 2022, doi: 10.1109/ACCESS.2022.3157632.
S. Taufiqurrahman, A. Handayani, B. R. Hermanto, dan T. L. E. R. Mengko, “Diabetic Retinopathy Classification Using A Hybrid and Efficient MobileNetV2-SVM Model,” IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, vol. 2020-Novem, hal. 235–240, 2020, doi: 10.1109/TENCON50793.2020.9293739.
R. Patel dan A. Chaware, “Transfer learning with fine-tuned MobileNetV2 for diabetic retinopathy,” 2020 Int. Conf. Emerg. Technol. INCET 2020, hal. 6–9, 2020, doi: 10.1109/INCET49848.2020.9154014.
Z. Mungloo-Dilmohamud, M. H. M. Khan, K. Jhumka, B. N. Beedassy, N. Z. Mungloo, dan C. Peña-Reyes, “Balancing Data through Data Augmentation Improves the Generality of Transfer Learning for Diabetic Retinopathy Classification,” Appl. Sci., vol. 12, no. 11, 2022, doi: 10.3390/app12115363.
B. Graham, “Kaggle Diabetic Retinopathy Detection competition report,” Kaggle, hal. 1–9, 2015.
J. Zhang, B. Xie, X. Wu, R. Ram, dan D. Liang, “Classification of Diabetic Retinopathy Severity in Fundus Images with DenseNet121 and ResNet50,” hal. 1–15, 2021, [Daring]. Tersedia pada: http://arxiv.org/abs/2108.08473.
R. N. Lazuardi, N. Abiwinanda, T. H. Suryawan, M. Hanif, dan A. Handayani, “Automatic diabetic retinopathy classification with efficientnet,” IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, vol. 2020-Novem, hal. 756–760, 2020, doi: 10.1109/TENCON50793.2020.9293941.
K. He, X. Zhang, S. Ren, dan J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, vol. 7, no. 1, hal. 770–778, doi: 10.1109/CVPR.2016.90.
S. S. Mondal, N. Mandal, K. K. Singh, A. Singh, dan I. Izonin, “EDLDR: An Ensemble Deep Learning Technique for Detection and Classification of Diabetic Retinopathy,” Diagnostics, vol. 13, no. 1, hal. 124, Des 2022, doi: 10.3390/diagnostics13010124.
H. Narasimhan, W. Pan, P. Kar, P. Protopapas, dan H. G. Ramaswamy, “Optimizing the Multiclass F-Measure via Biconcave Programming,” 2016 IEEE 16th Int. Conf. Data Min., hal. 1101–1106, 2017, doi: 10.1109/icdm.2016.0143.
S. Qummar et al., “A Deep Learning Ensemble Approach for Diabetic Retinopathy Detection,” IEEE Access, vol. 7, hal. 150530–150539, 2019, doi: 10.1109/ACCESS.2019.2947484.
K. Liu, T. Si, C. Huang, Y. Wang, H. Feng, dan J. Si, “Diagnosis and detection of diabetic retinopathy based on transfer learning,” Multimed. Tools Appl., vol. 83, no. 35, hal. 82945–82961, 2024, doi: 10.1007/s11042-024-18792-x.
A. Eko, M. Hazmi, C. Mandiri, Y. Azhar, dan F. Bimantoro, “Classification of Diabetic Retinopathy Disease Using Convolutional Neural Network,” vol. 6, no. March, hal. 12–18, 2022.
M. K. Yaqoob, S. F. Ali, M. Bilal, M. S. Hanif, dan U. M. Al-Saggaf, “Resnet based deep features and random forest classifier for diabetic retinopathy detection†,” Sensors, vol. 21, no. 11, hal. 1–14, 2021, doi: 10.3390/s21113883.
C. Mohanty et al., “Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy,” Sensors, vol. 23, no. 12, hal. 5726, Jun 2023, doi: 10.3390/s23125726.
##submission.downloads##
Diterbitkan
Terbitan
Bagian
Lisensi
Copyright
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis or report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. Authors or others are allowed to multiply article as long as not for commercial purposes. For the new invention, authors are suggested to manage its patent before published. The license type is CC-BY-NC 4.0.
Disclaimer
No responsibility is assumed by publisher and co-publishers, nor by the editors for any injury and/or damage to persons or property as a result of any actual or alleged libelous statements, infringement of intellectual property or privacy rights, or products liability, whether resulting from negligence or otherwise, or from any use or operation of any ideas, instructions, procedures, products or methods contained in the material therein.
