Klasifikasi Citra Fundus untuk Identifikasi Diabetic Retinopathy, Glaucoma, Cataract Menggunakan ResNet-50 dan Transfer Learning: Fundus-Based Classification and Identification of Diabetic Retinopathy, Glaucoma, and Cataracts Using ResNet-50 Transfer Learning

Karina Karina; Novan Wijaya

doi:10.57152/malcom.v6i4.3306

Authors

Karina Karina Universitas Multi Data Palembang
Novan Wijaya Universitas Multi Data Palembang

DOI:

https://doi.org/10.57152/malcom.v6i4.3306

Keywords:

Glaukoma, Katarak, Klasifikasi, ResNet-50, Retinopati Diabetik

Abstract

Klasifikasi penyakit mata berdasarkan citra fundus retina merupakan tantangan besar dalam bidang analisis citra medis karena kemiripan karakteristik visual antar berbagai penyakit dapat memengaruhi akurasi diagnosis. Penelitian ini bertujuan untuk menganalisis kinerja arsitektur ResNet-50 berbasis transfer learning dalam melakukan klasifikasi multi-kelas pada citra fundus yang dibagi menjadi tiga kategori, yaitu diabetic retinopathy, glaucoma, dan katarak. Dataset yang digunakan terdiri dari total 3.143 gambar setelah penyaringan pada kelas normal. Tahap preprocessing meliputi resize menggunakan metode interpolasi bicubic, normalisasi, dan augmentasi data. Penelitian ini menerapkan strategi fine-tuning parsial; selain itu, penelitian ini juga membandingkan optimasi antara penggunaan optimizer Adam dan Stochastic Gradient Descent (SGD) terhadap kinerja model. Hasil menunjukkan bahwa model mencapai kinerja terbaik dengan akurasi 95.13% menggunakan optimizer Adam, sementara model dengan optimizer SGD hanya mencapai akurasi 61.23%. Hasil ini menunjukkan bahwa pada learning rate yang sama, optimizer Adam memberikan konvergensi yang lebih cepat dan akurasi yang lebih tinggi dibandingkan dengan SGD dalam klasifikasi multi-class pada citra fundus.

Downloads

Download data is not yet available.

References

P. P. Raharjo, A. T. Poli, P. Syawal, dan S. Syamsuddin, “The Relationship Between Visual Impairment and Depression in Low Vision Patients: A Systematic Review,” Acta Biomedica Atenei Parmensis, vol. 96, no. 4, Agu 2025, doi: 10.23750/abm.v96i4.16504.

H. Yadav dan S. Mallick, “Early Detection Of Cataract, Diabetic Retinopathy, and Glaucoma Using Deep Learning,” International Journal of Creative Research Thoughts (IJCRT), vol. 12, no. 12, hal. b736–b747, Des 2024. [Daring]. Tersedia pada: https://www.ijcrt.org/papers/IJCRT2412184.pdf

U. ?evik dan O. Mutlu, “Automated Multi-Class Classification of Retinal Pathologies: A Deep Learning Approach to Unified Ophthalmic Screening,” Diagnostics, vol. 15, no. 21, Art. no. 2745, Okt 2025, doi: 10.3390/diagnostics15212745.

A. Agarwal dkk., “Retinal Disease Detection and Classification Using Convolution Neural Networks and Transfer Learning,” dalam Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025), Atlantis Press, Jun 2025, hal. 702–714, doi: 10.2991/978-94-6463-754-0_61.

A. Sebastian, O. Elharrouss, S. Al-Maadeed, dan N. Almaadeed, “A Survey on Deep-Learning-Based Diabetic Retinopathy Classification,” Diagnostics, vol. 13, no. 3, Art. no. 345, Jan 2023, doi: 10.3390/diagnostics13030345.

Y. Pan dkk., “Fundus Image Classification Using Inception V3 and ResNet-50 for the Early Diagnostics of Fundus Diseases,” Frontiers in Physiology, vol. 14, Art. no. 1126780, Feb 2023, doi: 10.3389/fphys.2023.1126780.

V. K. Madduri dan B. S. Rao, “Detection and Diagnosis of Diabetic eye diseases using two phase transfer learning approach,” PeerJ Computer Science, vol. 10, Art. no. e2135, Sep 2024, doi: 10.7717/peerj-cs.2135.

A. M. S. Choo, S. Chua, L. T. Lim, D. N. A. Iskandar, M. H. A. Hijazi, dan P. N. E. Nohuddin, “Multiclass Eye Disease Classification Using Transfer Learning Approach,” International Journal of Computer Theory and Engineering, vol. 17, no. 4, hal. 170–178, 2025, doi: 10.7763/IJCTE.2025.V17.1379.

N. A. Melyani dkk., “Analysis Comparison Classification Image Disease Eye Using the CNN Algorithm, Inception V3, DenseNet 121 and MobileNet V2 Architecture Models,” Public Research Journal of Engineering, Data Technology and Computer Science, vol. 3, no. 1, hal. 42–58, Jul 2025, doi: 10.57152/predatecs.v3i1.1559.

G. V. Doddi, “Eye_diseases_classification,” Kaggle, 2022. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification

K. He, X. Zhang, S. Ren, dan J. Sun, “Deep Residual Learning for Image Recognition,” dalam 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, hal. 770–778, doi: 10.1109/CVPR.2016.90.

M. H. Ashraf dkk., “HIRD-Net: An Explainable CNN-Based Framework with Attention Mechanism for Diabetic Retinopathy Diagnosis Using CLAHE-D-DoG Enhanced Fundus Images,” Life, vol. 15, no. 9, Art. no. 1411, Sep 2025, doi: 10.3390/life15091411.

Q. Yang, Y. Wei, F. Liu, dan Z. Wu, “An Accurate and Efficient Diabetic Retinopathy Diagnosis Method via Depthwise Separable Convolution and Multi-View Attention Mechanism,” Applied Sciences, vol. 15, no. 17, Art. no. 9298, Agu 2025, doi: 10.3390/app15179298.

Q. Abbas, M. Albathan, A. Altameem, R. S. Almakki, dan A. Hussain, “Deep-Ocular: Improved Transfer Learning Architecture Using Self-Attention and Dense Layers for Recognition of Ocular Diseases,” Diagnostics, vol. 13, no. 20, Art. no. 3165, Okt 2023, doi: 10.3390/diagnostics13203165.

H. Imaduddin dan A. R. Sakina, “Eye Disease Detection Using Transfer Learning Based on Retinal Fundus Image Data,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 36, no. 1, hal. 509–516, Okt 2024, doi: 10.11591/ijeecs.v36.i1.pp509-516.

E. S. Cutur dan N. G. Inan, “Multi-class Classification of Retinal Eye Diseases from Ophthalmoscopy Images Using Transfer Learning-Based Vision Transformers,” Journal of Imaging Informatics in Medicine, vol. 38, no. 5, hal. 3110–3124, Okt 2025, doi: 10.1007/s10278-025-01416-7.

R. Alsohemi dan S. Dardouri, “Fundus Image-Based Eye Disease Detection Using EfficientNetB3 Architecture,” Journal of Imaging, vol. 11, no. 8, Art. no. 279, Agu 2025, doi: 10.3390/jimaging11080279.

S. Vidivelli, P. Padmakumari, C. Parthiban, A. DharunBalaji, R. Manikandan, dan A. H. Gandomi, “Optimising deep learning models for ophthalmological disorder classification,” Scientific Reports, vol. 15, Art. no. 3115, Jan 2025, doi: 10.1038/s41598-024-75867-3.

A. Albelaihi dan D. M. Ibrahim, “DeepDiabetic: An Identification System of Diabetic Eye Diseases Using Deep Neural Networks,” IEEE Access, vol. 12, hal. 10769–10789, 2024, doi: 10.1109/ACCESS.2024.3354854.

S. J. Pan dan Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, hal. 1345–1359, Okt 2010, doi: 10.1109/TKDE.2009.191.

J. Yosinski, J. Clune, Y. Bengio, dan H. Lipson, “How transferable are features in deep neural networks?,” dalam Advances in Neural Information Processing Systems 27, Montreal, QC, Canada, 2014, hal. 3320–3328.

N. Tajbakhsh dkk., “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, hal. 1299–1312, Mei 2016, doi: 10.1109/TMI.2016.2535302.

M. Raghu, C. Zhang, J. Kleinberg, dan S. Bengio, “Transfusion: Understanding Transfer Learning for Medical Imaging,” dalam Advances in Neural Information Processing Systems 32, Vancouver, BC, Canada, 2019, hal. 3347–3357.

S. Ioffe dan C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” dalam Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015, hal. 448–456.

PyTorch Contributors, “resnet50 - Torchvision main documentation,” PyTorch. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://docs.pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html

I. Goodfellow, Y. Bengio, dan A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.

H. Robbins dan S. Monro, “A Stochastic Approximation Method,” The Annals of Mathematical Statistics, vol. 22, no. 3, hal. 400–407, Sep 1951, doi: 10.1214/aoms/1177729586.

I. Sutskever, J. Martens, G. Dahl, dan G. Hinton, “On the importance of initialization and momentum in deep learning,” dalam Proceedings of the 30th International Conference on Machine Learning (ICML), 2013, hal. 1139–1147.

D. P. Kingma dan J. Ba, “Adam: A Method for Stochastic Optimization,” dalam Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA, 2015.

A. C. Wilson, R. Roelofs, M. Stern, N. Srebro, dan B. Recht, “The Marginal Value of Adaptive Gradient Methods in Machine Learning,” dalam Advances in Neural Information Processing Systems 30, Long Beach, CA, USA, 2017, hal. 4151–4161.

PyTorch Contributors, “SGD - PyTorch 2.14 documentation,” PyTorch. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://docs.pytorch.org/docs/2.14/generated/torch.optim.SGD.html

PyTorch Contributors, “Adam - PyTorch 2.14 documentation,” PyTorch. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://docs.pytorch.org/docs/2.14/generated/torch.optim.Adam.html

PyTorch Contributors, “CrossEntropyLoss - PyTorch 2.14 documentation,” PyTorch. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://docs.pytorch.org/docs/2.14/generated/torch.nn.CrossEntropyLoss.html

C. Shorten dan T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” Journal of Big Data, vol. 6, Art. no. 60, Jul 2019, doi: 10.1186/s40537-019-0197-0.

R. Keys, “Cubic convolution interpolation for digital image processing,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, no. 6, hal. 1153–1160, Des 1981, doi: 10.1109/TASSP.1981.1163711.

N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, dan R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, hal. 1929–1958, 2014.

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, hal. 861–874, Jun 2006, doi: 10.1016/j.patrec.2005.10.010.

F. Pedregosa dkk., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, hal. 2825–2830, 2011.

scikit-learn developers, “recall_score - scikit-learn documentation,” scikit-learn. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.recall_score.html

PyTorch Contributors, “BatchNorm2d - PyTorch 2.14 documentation,” PyTorch. Diakses: 5 Oktober 2026. [Daring]. Tersedia pada: https://docs.pytorch.org/docs/2.14/generated/torch.nn.BatchNorm2d.html