Pemanfaatan Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Penyakit Mata Menggunakan Citra Fundus Dalam Mendukung Diagnosis Medis

Rizki Ikhwan Nur Rahim; Taufik Rendi Anggara

doi:10.23960/jitet.v14i3.9714

Rizki Ikhwan Nur Rahim
Universitas Esa Unggul
Taufik Rendi Anggara
Universitas Esa Unggul

DOI: https://doi.org/10.23960/jitet.v14i3.9714

Keywords Klasifikasi Penyakit Mata, Convolutional Neural Network, Citra Fundus, Transfer Learning, Fine-tuning

Abstract Views (Last 12 Months)

5 Abstract Views

4 Downloads

Abstract

Penyakit mata seperti katarak, retinopati diabetik, dan glaukoma merupakan penyebab utama gangguan penglihatan dan kebutaan yang dapat dicegah, namun proses diagnosisnya masih sangat bergantung pada interpretasi manual tenaga medis yang terbatas ketersediaannya. Penelitian ini bertujuan mengembangkan model klasifikasi otomatis berbasis Convolutional Neural Network untuk membedakan empat kondisi mata, yaitu mata normal, katarak, retinopati diabetik, dan glaukoma, menggunakan citra fundus digital. Tiga arsitektur jaringan saraf konvolusional yang telah dilatih sebelumnya, yakni EfficientNetV2B3, EfficientNetV2S, dan ConvNeXtTiny, diimplementasikan menggunakan pendekatan transfer learning dan fine-tuning. Dataset yang digunakan terdiri dari 4.217 gambar fundus berlabel yang terdistribusi merata pada empat kelas, dengan rasio pembagian data latih dan validasi sebesar 80:20. Proses pengembangan model mencakup augmentasi data, optimasi Bayesian untuk penyetelan hiperparameter, serta mekanisme callback untuk pengendalian pelatihan. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, F1-score, dan matriks kebingungan. Hasil penelitian menunjukkan bahwa model EfficientNetV2B3 mencapai akurasi validasi tertinggi sebesar 93,48% dengan efisiensi waktu pelatihan yang lebih unggul dibandingkan arsitektur lainnya. Temuan ini mengindikasikan bahwa pendekatan berbasis jaringan saraf konvolusional memiliki potensi signifikan sebagai alat bantu skrining penyakit mata yang efisien dan akurat dalam mendukung tenaga medis.

Downloads

Download data is not yet available.

References

World Health Organization, World Report on Vision. Geneva: WHO, 2019.

Rokom, "Katarak Penyebab Terbanyak Gangguan Penglihatan di Indonesia," Sehat Negeriku, Okt. 2021.

T. Li et al., "Applications of deep learning in fundus images: A review," Medical Image Analysis, vol. 69, 2021.

R. Sarki, K. Ahmed, H. Wang, dan Y. Zhang, "Automatic detection of diabetic eye disease through deep learning using fundus images: A survey," IEEE Access, vol. 8, 2020.

M. M. Taye, "Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions," Computation, vol. 11, no. 3, 2023.

I. Kandel dan M. Castelli, "Transfer learning with convolutional neural networks for diabetic retinopathy image classification: A review," Applied Sciences, vol. 10, no. 6, 2020.

S. Das et al., "Deep learning architecture based on segmented fundus image features for classification of diabetic retinopathy," Biomedical Signal Processing and Control, vol. 68, 2021.

Y. N. Fuadah et al., "Glaucoma classification based on fundus images processing with convolutional neural network," Jurnal Teknik Informatika (JUTIF), vol. 3, no. 3, 2022.

G. Arslan dan C. B. Erdas, "Detection of cataract, diabetic retinopathy and glaucoma eye diseases with deep learning approach," Intelligent Methods in Engineering Sciences, 2023.

R. Yasashvini et al., "Diabetic retinopathy classification using CNN and hybrid deep convolutional neural networks," Symmetry, vol. 14, no. 9, 2022.

M. F. Novriandy, B. Rahmat, dan A. Junaidi, "Klasifikasi Citra Penyakit Kanker Mulut Menggunakan Arsitektur Resnet50 Optimasi Adam Dan SGD," Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3, pp. 2284-2294, 2024, doi: 10.23960/jitet.v12i3.4732.

D. Passos dan P. Mishra, "A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classification tasks," Chemometrics and Intelligent Laboratory Systems, vol. 223, 2022.

G. Kalyani et al., "Diabetic retinopathy detection and classification using capsule networks," Complex and Intelligent Systems, vol. 9, no. 3, 2023.

Encord, "Pre Trained Model," encord.com, 2025.

M. Tan dan Q. V. Le, "EfficientNetV2: Smaller models and faster training," arXiv preprint, arXiv:2104.00298, 2021.

A. C. Milano, A. Yasid, dan R. T. Wahyuningrum, "Klasifikasi Penyakit Daun Padi Menggunakan Model Deep Learning EfficientNet-B6," Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 1, 2024, doi: 10.23960/jitet.v12i1.3855.

Z. Liu et al., "A ConvNet for the 2020s," arXiv preprint, arXiv:2201.03545, 2022.

D. Bergmann, "What is fine-tuning?", IBM Think, Mar. 2024.

Keras, "Keras 3 API documentation: Callbacks," keras.io, 2025.

S. Wang et al., "Advances in data preprocessing for bio-medical data fusion," Information Fusion, vol. 76, 2021.

M. Lin, Q. Chen, dan S. Yan, "Network in network," arXiv preprint, arXiv:1312.4400, 2014.

O. Harris dan M. Andrews, "Effects and results of dropout layer in reducing overfitting with convolutional neural networks," World Journal of Advanced Engineering Technology and Sciences, vol. 13, no. 2, 2024.

D. A. N. Wulandari et al., "Prototyping model in information system development of Al-Ruhamaa Bogor Yatim Center Foundation," Jurnal Pilar Nusa Mandiri, vol. 17, no. 2, 2021.

G. V. Doddi, "eye_diseases_classification," Kaggle, 2023. [Online]. Tersedia: https://www.kaggle.com/datasets/gunavenkdoddi/eye-diseases-classification

R. Thanki, "A deep neural network and machine learning approach for retinal fundus image classification," Healthcare Analytics, vol. 3, 2023.