Penerapan CNN dengan Arsitektur EfficientNet-B4 untuk Deteksi Penyakit Glaukoma Berbasis Web

Rizal Rachman; Adi Karawinata Sataynegara

doi:10.54914/jtt.v12i1.2623

Penulis

Rizal Rachman Universitas Adhirajasa Reswara Sanjaya
Adi Karawinata Sataynegara Universitas Adhirajasa Reswara Sanjaya

DOI:

https://doi.org/10.54914/jtt.v12i1.2623

Kata Kunci:

Convolutional Neural Network, Deep Learning, Deteksi Glaukoma, EfficientNet-B4, Fundus Retina

Abstrak

Glaukoma menjadi salah satu penyebab kebutaan yang sering tidak terdeteksi pada tahap awal karena gejalanya berkembang perlahan dan tidak menimbulkan rasa nyeri. Banyak kasus baru diketahui setelah kerusakan saraf optik sudah berat. Pemeriksaan rutin masih rendah di masyarakat karena keterbatasan fasilitas, minimnya kesadaran, serta kebutuhan tenaga ahli untuk membaca citra retina. Proses identifikasi juga cukup menantang karena variasi kualitas citra, perbedaan kondisi pencahayaan, dan kemiripan visual antara mata normal dan glaukoma. Penelitian ini mengembangkan sistem deteksi dini glaukoma berbasis web dengan model Convolutional Neural Network EfficientNet-B4. Dataset EyePACS digunakan sebagai sumber citra retina dengan total 9.540 citra, terdiri dari 8.000 data latih, 770 data validasi, dan 770 data uji. Kriteria klasifikasi mencakup dua kategori, yakni mata normal dan glaukoma berdasarkan anotasi ahli pada dataset. Pelatihan dilakukan selama 30 epoch menggunakan strategi transfer learning dan fine-tuning untuk memperoleh stabilitas performa. Hasil evaluasi menunjukkan akurasi validasi berada pada kisaran 90–92% dengan nilai loss yang stabil. Model kemudian diintegrasikan ke sistem web yang memungkinkan pengguna mengunggah citra retina dan memperoleh prediksi awal beserta informasi dasar mengenai glaukoma. Sistem ini berpotensi meningkatkan skrining awal yang mudah dijangkau masyarakat.

Unduhan

Data unduhan belum tersedia.

Referensi

D. M. S. Barros, J. C. C. Moura, C. R. Freire, A. C. Taleb, R. A. M. Valentim, and P. S. G. Morais, “Machine learning applied to retinal image processing for glaucoma detection: review and perspective,” Biomed Eng Online, vol. 19, no. 1, p. 20, 2020.

X. Chen, Y. Xu, D. W. K. Wong, T. Y. Wong, and J. Liu, “Glaucoma detection based on deep convolutional neural network,” in 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC), IEEE, pp. 715–718, 2015.

A. Serener and S. Serte, “Transfer learning for early and advanced glaucoma detection with convolutional neural networks,” in 2019 Medical technologies congress (TIPTEKNO), IEEE, pp. 1–4, 2019.

A. Sarhan, J. Rokne, and R. Alhajj, “Glaucoma detection using image processing techniques: A literature review,” Computerized Medical Imaging and Graphics, vol. 78, p. 101657, 2019.

M. Kim, O. Janssens, H. Park, J. Zuallaert, S. Van Hoecke, and W. De Neve, “Web applicable computer-aided diagnosis of glaucoma using deep learning,” arXiv preprint arXiv:1812.02405, 2018.

D. M. S. Barros, J. C. C. Moura, C. R. Freire, A. C. Taleb, R. A. M. Valentim, and P. S. G. Morais, “Machine learning applied to retinal image processing for glaucoma detection: review and perspective,” Biomed Eng Online, vol. 19, no. 1, p. 20, 2020.

L. Li et al., “A large-scale database and a CNN model for attention-based glaucoma detection,” IEEE Trans Med Imaging, vol. 39, no. 2, pp. 413–424, 2019.

K. Duvvuri, S. Chethana, S. S. Charan, V. Srihitha, T. K. Ramesh, and K. S. Srikanth, “Grad-cam for visualizing diabetic retinopathy,” in 2022 3rd International Conference for Emerging Technology (INCET), IEEE, pp. 1–4, 2022.

T. N. Poly, M. M. Islam, B. A. Walther, M. C. Lin, and Y.-C. J. Li, “Artificial intelligence in diabetic retinopathy: Bibliometric analysis,” Comput Methods Programs Biomed, vol. 231, p. 107358, 2023.

Z. S. Lie et al., “Automatic Cataract and Cholesterol Detection System Based on Recurrent Neural Network (RNN): A Comparison with Convolutional Neural Network (CNN) and Siamese Neural Network (SNN),” in The International Conference on Intelligent Unmanned Systems, Springer, pp. 233–242, 2023.

L. A. Hark et al., “Philadelphia telemedicine glaucoma detection and follow-up study: methods and screening results,” Am J Ophthalmol, vol. 181, pp. 114–124, 2017.

S. Zhu et al., “Screening of common retinal diseases using six-category models based on EfficientNet,” Front Med (Lausanne), vol. 9, p. 808402, 2022.

L. K. Singh, Pooja, H. Garg, and M. Khanna, “Performance evaluation of various deep learning based models for effective glaucoma evaluation using optical coherence tomography images,” Multimed Tools Appl, vol. 81, no. 19, pp. 27737–27781, 2022.

A. Geetha and N. B. Prakash, “Classification of Glaucoma in Retinal Images Using EfficientnetB4 Deep Learning Model.,” Computer Systems Science & Engineering, vol. 43, no. 3, 2022.

S. A. Haja and V. Mahadevappa, “Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology,” Rom J Ophthalmol, vol. 67, no. 3, p. 222, 2023.

M. Ashtari-Majlan, M. M. Dehshibi, and D. Masip, “Deep learning and computer vision for glaucoma detection: A review,” arXiv preprint arXiv:2307.16528, 2023.