Deep Learning untuk Klasifikasi Glaukoma dengan menggunakan Arsitektur EfficientNet

WAHYUNI RIZKY PERDANI, RITA MAGDALENA, NOR KUMALASARI CAECAR PRATIWI

Sari


ABSTRAK

Glaukoma merupakan kerusakan yang terjadi pada saraf mata yang disebabkan oleh meningkatnya tekanan di bola mata. Glaukoma dapat menyebabkan penderitanya mengalami kebutaan permanen. Data dari WHO, jumlah orang yang diperkirakan menjadi buta akibat glaukoma primer adalah 4,5 juta. Penilaian klasifikasi tingkatan glaukoma oleh ophthalmologist menggunakan nilai CDR (Cup to Disc Ratio). Maka dari itu, dibuat sistem yang dapat digunakan dalam mengklasifikasikan glaukoma melalui citra fundus mata dengan menggunakan metode CNN (Convolutional Neural Network) dengan arsitektur EfficientNet. Klasifikasi glaukoma dibagi menjadi 5 kelas, yaitu deep, early, moderate, OHT dan normal. Citra mata yang digunakan didapatkan dari dataset RimOne r1. Penelitian ini mencari sistem dengan performansi terbaik. Model yang mendapatkan parameter performansi terbaik adalah citra dengan hyperparameter optimizer Adamax, learning rate 0,001, epoch 20, dan batch size 32. Akurasi, presisi, recall, dan F1-Score masing-masing mencapai 1,0000.

Kata kunci: Glaukoma, Convolutional Neural Network (CNN), EfficientNet

 

ABSTRACT

Glaucoma is the optic nerve damage caused by increasing pressure on the eyeball. Glaucoma can cause patients to encounter permanent blindness. According to WHO data, the number of people estimated to be blind from primary glaucoma is 4,5 million. Evaluation of glaucoma grade classification by ophthalmologist uses CDR (Cup to Disc Ratio) value. Therefore, a system has been created that can be used to classify glaucoma through eye fundus images using the CNN (Convolutional Neural Network) method with EfficientNet architecture. Glaucoma is classified into 5 classes, namely deep, early, moderate, OHT and normal. The used eye image is obtained from the RimOne r1 dataset. This research is looking for a system with the best performance. The model that got the best performance parameters with the hyperparameter optimizer Adamax, learning rate 0,001, epoch 20, and batch size 32. Accuracy, precision, recall, and F1-Score each reached 1,0000.

Keywords: Glaucoma, Convolutional Neural Network (CNN), EfficientNet


Kata Kunci


Glaukoma; Deep Learning; Convolutional Neural Network (CNN); EfficientNet

Teks Lengkap:

PDF

Referensi


Alhichri, H., Alswayed, A. S., Bazi, Y., Ammour, N., & Alajlan, N. A. (2021). Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model with Attention. IEEE Access, 9, 14078–14094.

Fumero, F., Alayon, S., Sanchez, J., Sigut, J., & Gonzalez-Hernandez, M. (2011). RIM-ONE: An Open Retinal Image Database for Optic Nerve Evaluation. Computer-Based Medical Systems (CBMS), 1-6.

Ghosh, A., Sufian, A., Sultana, F., Chakrabarti, A., & De, D. (2019). Fundamental concepts of convolutional neural network. In Intelligent Systems Reference Library (Vol. 172, Nomor January).

Hussain, Z., Gimenez, F., Yi, D., & Rubin, D. (2017). Differential Data Augmentation Techniques for Medical Imaging Classification Tasks. AMIA ... Annual Symposium proceedings. AMIA Symposium, 2017, (pp. 979–984).

Kurian, Preethi, dan JeyakumarVijay. (2020). Multimodality Medical Image Retrieval Using Convolutional Neural Network. Academis Press: Elsevier Science.

Kizrak, M. A., Muftuoglu, Z., Yildirim, T. (2020). Limitations and challenges on the diagnosis of COVID-19 using radiology images and deep learning. Human Relations, 3(1), 1–8.

Nugraha, G. S., Riyandari, B. A., & Sutoyo, E. (2020). RGB Channel Analysis for Glaucoma Detection in Retinal Fundus Image. 2020 International Conference on Advancement in Data Science, E-learning and Information Systems (ICADEIS), (pp. 1-5).

Padaria, A., & Limbasiya, B. (2015). Detection of Glaucoma Using Retinal Fundus Images With Gabor Filter. International Journal of Advance Engineering and Research Development, 2(6).

Rayungsista, A. (2018). Characteristics Of Primary Glaucoma In Eye Outpatient Clinic Of RA Basoeni Hospital, Mojokerto, Indonesia. Folia Medica Indonesiana, 172-178.

Saxena, M. A., Vyas, M. A., Parashar, M. L., & Vyas, M. A. (2020). A Glaucoma Detection using Convolutional Neural Network. Proceedings of the International Conference on Electronics and Sustainable Communication Systems, ICESC 2020, (pp. 815–820).

Serener, A., & Serte, S. (2019). Transfer Learning for Early and Advanced Glaucoma Detection with Convolutional Neural Networks. Medical Technologies Congress (TIPTEKNO), Turkey,1–4.

Suryansah, A., Habibi, R., & Awangga, R. M. (2020). Penggunaan Face Recognition untuk Akses Ruangan. Bandung: Redaksi.

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. 36th International Conference on Machine Learning, ICML 2019, 2019-June, (pp. 10691–10700).

Touahri, R., Azizi, N., Benzebouchi, N. E., Hammami, N. E., & Moumene, O. (2018). “A Comparative Study of Convolutional Neural Network and Twin SVM for Automatic Glaucoma Diagnosis.†2018 International Conference on Signal, Image, Vision and their Applications, SIVA 2018, (pp. 1–5).

Yu, M., Huang, Q., Qin, H., Scheele, C., & Yang, C. (2019). Deep Learning for Real-Time Social Media Text Classification for Situation Awareness - using Hurricanes Sandy, Harvey, and Irma as Case Studies. International Journal of Digital Earth, 1-18.




DOI: https://doi.org/10.26760/elkomika.v10i2.322

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (print) : 2338-8323 | ISSN (electronic) : 2459-9638

Publisher:

Department of Electrical Engineering Institut Teknologi Nasional Bandung

Address: 20th Building  Institut Teknologi Nasional Bandung PHH. Mustofa Street No. 23 Bandung 40124

Contact: +627272215 (ext. 206)

Email: jte.itenas@itenas.ac.id________________________________________________________________________________________________________________________


Free counters!

Web Analytics Made Easy - StatCounter

Statistic Journal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License