DETEKSI DIABETIC RETINOPATHY MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS EFFICIENTNET DAN GRAD-CAM PADA CITRA FUNDUS RETINA
DOI:
https://doi.org/10.70248/jrsit.v3i1.2896Abstract
Retinopati diabetik merupakan salah satu komplikasi utama diabetes yang dapat menyebabkan kebutaan permanen jika tidak dideteksi secara dini. Penelitian ini bertujuan untuk mengembangkan sistem deteksi otomatis retinopati diabetik menggunakan algoritma Convolutional Neural Network (CNN) berbasis arsitektur EfficientNet dan visual Grad-CAM pada citra fundus retina. Dataset yang digunakan adalah APTOS 2019 Blindness Detection dengan lima klasifikasi tingkat keparahan retinopati. Proses meliputi preprocessing data, augmentasi citra, pelatihan model dengan transfer learning pada EfficientNetB3, evaluasi model melalui confusion matrix dan classification report, serta deployment menggunakan aplikasi Streamlit. Hasil evaluasi menunjukkan bahwa model mencapai akurasi validasi sebesar 75,70%, dengan performa terbaik pada kelas normal (kelas 0) dan akurasi yang masih dapat ditingkatkan pada kelas parah (kelas 3 dan 4). Integrasi Grad-CAM memberikan visualisasi yang membantu dalam interpretasi hasil prediksi. Sistem ini diharapkan dapat menjadi alat bantu diagnosis awal retinopati diabetik secara cepat dan akurat dalam praktik medis.
References
Abdullah, S. H., Magdalena, R., & Fu’adah, R. Y. N. (2022). Klasifikasi Diabetic Retinopathy Berbasis Pengolahan Citra Fundus Dan Deep Learning. Journal of Electrical and System Control Engineering, 5(2), 84–90. https://doi.org/10.31289/jesce.v5i2.5659
Alqahtani, A. S., Alshareef, W. M., Aljadani, H. T., Hawsawi, W. O., & Shaheen, M. H. (2025). The efficacy of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis. International Journal of Retina and Vitreous, 11(1). https://doi.org/10.1186/s40942-025-00670-9
Arora, L., Singh, S. K., Kumar, S., Gupta, H., Alhalabi, W., Arya, V., Bansal, S., Chui, K. T., & Gupta, B. B. (2024). Ensemble deep learning and EfficientNet for accurate diagnosis of diabetic retinopathy. Scientific Reports, 14(1), 1–16. https://doi.org/10.1038/s41598-024-81132-4
Daanouni, O., Cherradi, B., & Tmiri, A. (2021). Automatic Detection of Diabetic Retinopathy Using Custom CNN and Grad-CAM. Advances in Intelligent Systems and Computing, 1188(January), 15–26. https://doi.org/10.1007/978-981-15-6048-4_2
Dai, L., Sheng, B., Chen, T., Wu, Q., Liu, R., Cai, C., Wu, L., Yang, D., Hamzah, H., Liu, Y., Wang, X., Guan, Z., Yu, S., Li, T., Tang, Z., Ran, A., Che, H., Chen, H., Zheng, Y., … Jia, W. (2024). A deep learning system for predicting time to progression of diabetic retinopathy. Nature Medicine, 30(2), 584–594. https://doi.org/10.1038/s41591-023-02702-z
Haq, N. U., Waheed, T., Ishaq, K., Hassan, M. A., Safie, N., Elias, N. F., & Shoaib, M. (2024). Computationally efficient deep learning models for diabetic retinopathy detection: a systematic literature review. Artificial Intelligence Review, 57(11). https://doi.org/10.1007/s10462-024-10942-9
Hidayah, A. N., Adiputra, F., & Koeshardianto, M. (2025). Klasifikasi Citra Diabetic Retinopathy Menggunakan CNN ( Convolutional Neural Network ) Dengan Arsitektur VGG-16. 9(2), 2451–2458.
Long, X., Gan, F., Fan, H., Qin, W., Li, X., Ma, R., Wang, L., Hu, R., Xie, Y., Chen, L., Cao, J., Shao, Y., Liu, K., & You, Z. (2025). EfficientNetB0-Based End-to-End Diagnostic System for Diabetic Retinopathy Grading and Macular Edema Detection. Diabetes, Metabolic Syndrome and Obesity , 18(April), 1311–1321. https://doi.org/10.2147/DMSO.S506494
Navaneethan, S., Pardhiv, A., & Teja, K. (2024). Automated Diabetic Retinopathy Detection and Multi-Stage Classification Using Convolutional Neural Networks. Proceedings of the 2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024, 6(5), 1–24. https://doi.org/10.1109/ICSES63760.2024.10910687
Nayak, D. R., Padhy, N., Mallick, P. K., Zymbler, M., & Kumar, S. (2022). Brain Tumor Classification Using Dense Efficient-Net. Axioms, 11(1). https://doi.org/10.3390/axioms11010034
Rautaray, J., Ali, A. B. M., Kandpal, M., Mishra, P., Rashid, R. F., Alimova, F., Kallel, M., & Batool, N. (2025). Leveraging FastViT based knowledge distillation with EfficientNet-B0 for diabetic retinopathy severity classification. SLAS Technology, 33. https://doi.org/10.1016/j.slast.2025.100325
Refat, S. R., Raha, Z. S., Sarker, S., Preotee, F. F., Rahman, MD. M., Muhammad, T., & Alam, M. S. (2025). VR-FuseNet: A Fusion of Heterogeneous Fundus Data and Explainable Deep Network for Diabetic Retinopathy Classification. http://arxiv.org/abs/2504.21464
Romario, M. H., Ihsanto, E., & Kadarina, T. M. (2020). Sistem Hitung dan Klasifikasi Objek dengan Metode Convolutional Neural Network. Jurnal Teknologi Elektro, 11(2), 108. https://doi.org/10.22441/jte.2020.v11i2.007
Satrio, B., Poetro, W., Mulyono, S., & Pramesti, V. A. (2024). Prediksi Penyakit Batu Ginjal dengan Menerapkan Convolutional Neural Network. 153–162.
Schielein, M. C., Christl, J., Sitaru, S., Pilz, A. C., Kaczmarczyk, R., Biedermann, T., Lasser, T., & Zink, A. (2023). Outlier detection in dermatology: Performance of different convolutional neural networks for binary classification of inflammatory skin diseases. Journal of the European Academy of Dermatology and Venereology, 37(5), 1071–1079. https://doi.org/10.1111/jdv.18853
Sharma, N., & Lalwani, P. (2025). A multi model deep net with an explainable AI based framework for diabetic retinopathy segmentation and classification. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-93376-9
Swaminathan, R. (2025). An Attention Infused Deep Learning System with Grad-CAM Visualization for Early Screening of Glaucoma. http://arxiv.org/abs/2505.17808
Tewari, Y., Singh Parihar, N., Rautela, K., Kaundal, N., Diwakar, M., & Pandey, N. K. (2025). Diabetic Retinopathy Detection and Analysis with Convolutional Neural Networks and Vision Transformer. 1(1). https://doi.org/10.62762/BISH.2025.724307
Yang, Z., Tan, T. E., Shao, Y., Wong, T. Y., & Li, X. (2022). Classification of diabetic retinopathy: Past, present and future. Frontiers in Endocrinology, 13(December), 1–18. https://doi.org/10.3389/fendo.2022.1079217
Zahir, M., & Adi Saputra, R. (2024). Deteksi Penyakit Retinopati Diabetes Menggunakan Citra Mata Dengan Implementasi Deep Learning Cnn. Jurnal Teknoinfo, 18(1), 121–132. https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification
