Eye Disease Classification Using Convolutional Neural Network (CNN) with Web-based MobileNetV2 Architecture
Abstract
The high prevalence of preventable eye diseases, such as cataracts, glaucoma, and diabetic retinopathy, emphasizes the importance of accessible and efficient diagnostic solutions. This research aims to develop a web-based eye disease classification system using a lightweight Convolutional Neural Network (CNN) architecture, MobileNetV2, to overcome computational limitations in real-time applications. CRISP-DM methodology is applied, including dataset preparation, transfer learning with MobileNetV2 and VGG16, model evaluation, and implementation using Flask. The dataset from Kaggle consisting of 4,217 eye fundus images with four classes (cataract, glaucoma, diabetic retinopathy, and normal) was divided into 80% training, 10% validation, and 10% testing. Data augmentation and normalization were performed to improve model generalization. The results showed MobileNetV2 achieved the highest accuracy (90.14%) with low computational requirements, outperforming VGG16 (89.66%) and CNN (86.78%). MobileNetV2 displays balanced precision (89-99%), recall (74-96%), and F1-score (81-99%) across all classes, especially excelling in diabetic retinopathy detection. Its efficiency on resource-constrained environments makes it ideal for web integration. The developed Flask-based application allows users to upload images for instant classification, bridging the healthcare access gap. This research proves the effectiveness of MobileNetV2 in combining high accuracy and computational efficiency, offering a scalable solution for early screening of eye diseases, especially in remote areas.
Downloads
References
H. Pratiwi, Buku Ajar Kecerdasan Buatan: Disertai Praktik Baik Pemanfaatannya. Asadel Liamsindo Teknologi, 2024.
A. Refani, H. Pratiwi, dan Azahari, "Penerapan Metode K-Nearest Neighbor dalam Klasifikasi Penerima Bantuan Dana Desa pada Kecamatan Muara Ancalong," Skripsi, STMIK Widya Cipta Dharma, 2024.
A. A. Khair, H. Pratiwi, dan N. J. Saputra, "Penerapan Algoritma K-Nearest Neighbor untuk Klasifikasi Penerima Beasiswa pada STMIK Widya Cipta Dharma," 2024.
B. Harpad, S. Salmon, dan R. M. Saputra, "Sistem Monitoring Kualitas Udara di Kawasan Industri dengan NodeMCU ESP32 Berbasis IoT," Jurnal Informatika Wicida, vol. 12, no. 2, hal. 39-47, 2022.
B. Harpad, A. Yusnita, dan H. Priscila, "Sistem Pendukung Keputusan Penentuan Ketua Koperasi pada Koperasi Leka Mandiri Menggunakan Metode Smarter Berbasis Web," Jurnal Informatika Wicida, vol. 13, no. 1, hal. 1-7, 2023.
World Health Organization, "World report on vision," 2020. [Online]. Available: https://www.who.int/publications/i/item/9789241516570. [Accessed: Apr. 2, 2025].
Kementerian Kesehatan Republik Indonesia, "Katarak Penyebab Terbanyak Gangguan Penglihatan di Indonesia," 2021. [Online]. Available: https://sehatnegeriku.kemkes.go.id/baca/umum/20211012/5738714/katarak-penyebab-terbanyak-gangguan-penglihatan-di-indonesia/. [Accessed: Apr. 2, 2025].
M. A. Agmalaro et al., "Implementasi Pendekatan Algoritma Deep Learning CNN untuk Identifikasi Citra Pasien Keratitis," Jurnal Ilmu Komputer dan Agri-Informatika, vol. 10, no. 2, hal. 164–175, 2023.
F. V. Austrin, J. Danil, R. I. Iman, M. R. Putri, dan P. Rosyani, "Klasifikasi Penyakit Mata Pada Data OCT Menggunakan Convolutional Neural Network (CNN)," OKTAL: Jurnal Ilmu Komputer dan Sains, vol. 1, no. 1, hal. 1–7, 2024.
A. A. Pratama dan F. Utaminingrum, "Sistem Pendeteksi Tingkat Keparahan Katarak Berdasarkan Citra Digital Menggunakan Metode U-Net dan CNN," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, 2024.
R. Firdaus, J. Satria, dan Baidarus, "Klasifikasi Jenis Kelamin Berdasarkan Gambar Mata Menggunakan Algoritma Convolutional Neural Network (CNN)," Jurnal CoSciTech (Computer Science and Information Technology), vol. 3, no. 3, hal. 267–273, 2022.
Y. Rong et al., "Surrogate-assisted retinal OCT image classification based on convolutional neural networks," Biomedical Signal Processing and Control, vol. 71, hal. 103107, 2022.
T. Babaqi, M. Jaradat, A. E. Yildirim, S. H. Al-Nimer, dan D. Won, "Eye Disease Classification Using Deep Learning Techniques," arXiv preprint arXiv:2307.10501, 2023.
D. Hananta Firdaus, B. Imran, L. Darmawan Bakti, dan E. Suryadi, "Klasifikasi Penyakit Katarak pada Mata menggunakan Metode Convolutional Neural Network (CNN) berbasis Web," Jurnal Kecerdasan Buatan Dan Teknologi Informasi (JKBTI), vol. 1, no. 3, hal. 18–26, 2022.
A. R. Prasetyo, Sussi, dan B. Aditya, "Analisis Perbandingan Algoritma Support Vector Machine (SVM) dan Convolutional Neural Network (CNN) untuk Sistem Deteksi Katarak," Jurnal Ilmiah Teknik Mesin, Elektro Dan Komputer, vol. 3, no. 1, hal. 1–10, 2023.
F. S. Putra, Kusrini, dan M. P. Kurniawan, "Deteksi Otomatis Jerawat Wajah Menggunakan Metode Convolutional Neural Network (CNN)," JIFoTech (Journal of Information Technology), vol. 1, no. 2, 2021.
B. D. Satoto, M. I. Utoyo, R. Rulaningtyas, dan E. B. Koendhori, "Custom Convolutional Neural Network untuk Deteksi Penyakit Mata pada Citra Fundus Retina," Jurnal Teknologi dan Sistem Komputer, vol. 8, no. 2, hal. 93–100, 2020.
A. I. Pradana, R. W. Abdullah, dan Harsanto, "Deteksi Ketepatan Penggunaan Masker Wajah Dengan Algoritma CNN Dan Haar Cascade," Jurnal Teknik Informatika Dan Sistem Informasi, vol. 3, 2022.
F. N. Cahya, N. Hardi, D. Riana, dan S. Hadianti, "Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network (CNN)," SISTEMASI: Jurnal Sistem Informasi, vol. 10, no. 3, hal. 618–626, 2021.
D. Marcella, Y. Yohannes, dan S. Devella, "Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network Dengan Arsitektur VGG-19," Jurnal Algoritme, vol. 3, no. 1, hal. 60–70, 2022.
Kaggle, "Eye Diseases Classification Dataset," [Online]. Available: https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification/data. [Accessed: Apr. 2, 2025].
