Klasifikasi Penyakit Mata Pada Data OCT Menggunakan Convolutional Neural Network (CNN)

Fausta Vita Austrin; Jefri Danil; Rahmat Ibnu Iman; Meidina Rahmawati Putri; Perani Rosyani

Authors

Fausta Vita Austrin Universitas Pamulang
Jefri Danil Universitas Pamulang
Rahmat Ibnu Iman Universitas Pamulang
Meidina Rahmawati Putri Universitas Pamulang
Perani Rosyani Universitas Pamulang

Keywords:

Optical Coherence Tomography (OCT), Eye Disease Classification, Convolutional Neural Network (CNN), Machine Learning, Computer-Aided Diagnosis

Abstract

Optical Coherence Tomography (OCT) is a non-invasive medical imaging technique used to diagnose various eye diseases, such as age-related macular degeneration, glaucoma, and diabetic retinopathy. In this study, we developed a Convolutional Neural Network (CNN) model to classify eye diseases on OCT data. Our CNN model consists of several convolution, pooling, and fully connected layers trained on an OCT dataset comprising 7 common classes of eye diseases. Further analysis reveals that the features learned by the CNN model effectively capture the visual characteristics that distinguish between different eye disease classes. We believe that the proposed CNN-based approach can be a useful tool for ophthalmologists to assist in the early and accurate diagnosis of eye diseases using OCT data.

References

Kermany, D. S., et al. (2018). "Identifying Medical Diagnoses and Treatable Diseases by Image Based Deep Learning." Cell, 172(5), 1122-1131.

Rong, Y., et al. (2019). "Surrogate-assisted retinal OCT image classification based on convolutional neural networks." IEEE J Biomed Health Inform, 23(1), 253-263.

Lee, C. S., et al. (2020). "Deep learning is effective for classifying normal versus age-related macular degeneration OCT images." Ophthalmology Retina, 4(4), 322-327.

Zhang, K., et al. (2021). "An interpretable ensemble deep learning model for diabetic retinopathy disease classification." IEEE Access, 9, 23372-23382.

Wang, J., et al. (2022). "Attention-guided CNN for automated diagnosis of retinal diseases using OCT images." Biomedical Signal Processing and Control, 71, 103175.

Russakoff, D. B., et al. (2019). "Deep learning for automated OCT analysis." Biomedical Optics Express, 10(2), 892-901.

Li, F., et al. (2020). "Deep learning-based automated detection of retinal diseases using optical coherence tomography images." Biomed Opt Express, 11(8), 4753-4765.

Waldstein, S. M., et al. (2018). "Comparison of deep learning approaches for multi-class segmentation of optical coherence tomography images." Scientific Reports, 8(1), 1-12.

De Fauw, J., et al. (2018). "Clinically applicable deep learning for diagnosis and referral in retinal disease." Nature Medicine, 24(9), 1342-1350.

Schmidt-Erfurth, U., et al. (2018). "Artificial intelligence in retina." Progress in Retinal and Eye Research, 67, 1-29.

Syahrul Al Fadil Syahputra, Nur Mita Azizah, Jannibatu Aiman, Dinar Ainun Nikmah, Perani Rosyani. (2024). IDENTIFIKASI DAN PREDIKSI UMUR BERDASARKAN CITRA WAJAH MENGGUNAKAN DEEP LEARNINGALGORITMA Convolutional Neural Network (CNN). Volume2, No. 1 Hal 87-95.

Fazha Regina Pramushela, Maulidiya Alifiany, Tiara Octavia, Asninda Sari, Perani Rosyani. (2024). Studi Kasus Penerapan Multi-Task Cascaded Convolutional Neural Network Untuk Deteksi Banyak Wajah. Volume 2, No. 1 Hal 108-111.

Hazmy Auza’i, Mas Bagus Arisila Putra, Muhammad Azril Saputra, Rudi Hartono, Perani Rosyani. (2024). Implementasi Deep Learning untuk Deteksi Wajah dan Ekspresi menggunakan Algoritma Convolutional Neural Network (CNN) dengan OpenCV. Volume 1, No. 4 Hal 261-265.