Deteksi Dini Karies dan Karang Gigi Berbasis Android Menggunakan CNN MobileNetV2 dan Transfer Learning
Abstract
Karies dan karang gigi merupakan gangguan kesehatan gigi yang umum dan dapat berkembang menjadi infeksi serta kerusakan gigi yang lebih parah apabila terlambat ditangani, sementara akses terhadap pemeriksaan rutin masih terbatas. Penelitian ini bertujuan mengembangkan sistem klasifikasi citra gigi sebagai alat bantu deteksi dini karies, karang gigi, dan gigi normal menggunakan Convolutional Neural Network (CNN) arsitektur MobileNetV2 dengan pendekatan transfer learning yang diimplementasikan pada aplikasi Android. Dataset Kaggle berjumlah 3.539 citra; pemeriksaan hashing MD5 menemukan 467 citra duplikat pada kelas karang gigi sehingga dataset akhir berjumlah 2.829 citra yang dibagi dengan rasio 70:15:15. Citra diubah menjadi 224 × 224 piksel dan data latih diaugmentasi. Pelatihan dilakukan dalam dua tahap, yaitu pelatihan classifier dengan base model dibekukan dan fine-tuning sekitar 30 lapisan terakhir. Evaluasi pada 425 citra uji menghasilkan akurasi 98,59% dengan precision, recall, dan F1-score yang seimbang pada ketiga kelas, dengan enam citra salah diklasifikasikan, sebagian besar antara karies dan karang gigi. Model diintegrasikan melalui FastAPI ke aplikasi Android berbasis Flutter. Pengujian pada citra di luar dataset menunjukkan confidence yang lebih rendah akibat domain shift. Sistem ini berpotensi menjadi alat bantu klasifikasi awal, bukan pengganti diagnosis tenaga medis, dan deduplikasi data perlu dilakukan sebelum pembagian dataset.
References
Carrington, A. M., Manuel, D. G., Fieguth, P. W., Ramsay, T., Osmani, V., Wernly, B., … Holzinger, A. (2023). Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1), 329–341. https://doi.org/10.1109/TPAMI.2022.3145392
Daniel Erku, R. K. A. E. E. W. F. N. A. Z. dan Y. A. (2023). Digital health interventions to improve access to and quality of primary health care services: A scoping review. International Journal of Environmental Research and Public Health, 20(19), 6854. https://doi.org/10.3390/ijerph20196854
GBD 2021 Oral Disorders Collaborators. (2025). Trends in the global, regional, and national burden of oral conditions from 1990 to 2021: A systematic analysis for the Global Burden of Disease Study 2021. The Lancet, 405(10482), 897–910. https://doi.org/10.1016/S0140-6736(24)02811-3
Gonzalez, R. C., & Woods, R. E. (2021). Digital image processing (4th ed.). Pearson.
Hasan, F., Yuliana, L. T., Budi, H. S., Ramasamy, R., Ambiya, Z. I., & Ghaisani, A. M. (2024). Prevalence of dental caries among children in Indonesia: A systematic review and meta-analysis of observational studies. Heliyon, 10(11), e32102. https://doi.org/10.1016/j.heliyon.2024.e32102
Iman, M., Arabnia, H. R., & Rasheed, K. (2023). A review of deep transfer learning and recent advancements. Technologies, 11(2), 40. https://doi.org/10.3390/technologies11020040
Iqbal, F. N. (2023). A brief introduction to application programming interface (API). https://doi.org/10.5281/zenodo.10198423
Kementerian Kesehatan Republik Indonesia. (2022). Profil kesehatan Indonesia 2021. https://kemkes.go.id/app_asset/file_content_download/Profil-KesehatanIndonesia-2021.pdf
Lee, J. H., Kim, D. H., Jeong, S. N., & Choi, S. H. (2018). Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. Journal of Dentistry, 77, 106–111. https://doi.org/10.1016/j.jdent.2018.07.015
Luque, A., Carrasco, A., Martín, A., & de las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 216–231. https://doi.org/10.1016/j.patcog.2019.02.023
Makarim, A., Karlita, T., Sigit, R., Bayu Dewantara, B. S., & Brahmanta, A. (2024). Deep learning models for dental conditions classification using intraoral images. JOIV: International Journal on Informatics Visualization, 8(3), 1099–1108. https://doi.org/10.62527/joiv.8.3.1914
Medavarapu, S. S. (2024). Advancements in deep learning: A review of Keras and TensorFlow frameworks. Journal of Scientific and Engineering Research, 11(5), 282–286. https://jsaer.com/download/vol-11-iss-5-2024/JSAER2024-11-5-282-286.pdf
Nguyen, T. T. T., Tran, V. T., Nguyen, T. T., Le, V. N., & Nguyen, T. T. H. (2022). Deep learning application in dental caries detection using intraoral photos taken by smartphones. Scientific Reports, 12, 19114. https://doi.org/10.1038/s41598-022-23329-7
Park, S., Erkinov, H., Hasan, M. A. M., Nam, S.-H., Kim, Y.-R., Shin, J., & Chang, W.-D. (2023). Periodontal disease classification with color teeth images using convolutional neural networks. Electronics, 12(7), 1518. https://doi.org/10.3390/electronics12071518
Perez-Meana, H., & Nakano-Miyatake, M. (2025). Digital image processing: Technologies and applications. Applied Sciences, 15(23), 12709. https://doi.org/10.3390/app152312709
Putra, F. P. D., & Al-Khowarizmi. (2026). Analisis sentimen efektivitas pembelajaran daring menggunakan hybrid Naive Bayes dan SVM. Indonesian Journal of Multidisciplinary Scientific Studies, 4(6), 467–476. https://doi.org/10.33151/ijomss.v4i6.1120
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
The Dental Association of Thailand. (2023). Guideline on caries risk assessment and management. Journal of the Dental Association of Thailand. https://doi.org/10.14456/jdat.2023.24
Wahyuningsih, W., Nugraha, G. S., & Dwiyansaputra, R. (2024). Classification of dental caries disease in tooth images using a comparison of EfficientNet-B0, MobileNetV2, ResNet-50, InceptionV3 architectures. Jurnal Teknik Informatika (JUTIF), 5(4), 177–185. https://doi.org/10.52436/1.jutif.2024.5.4.2187
Warreth, A. (2023). Dental caries and its management. International Journal of Dentistry, 2023, 1–15. https://doi.org/10.1155/2023/9365845
World Health Organization. (2025). Oral health. Retrieved from https://www.who.int/news-room/fact-sheets/detail/oral-health
Xu, M., Yoon, S., Fuentes, A., & Park, D. S. (2023). A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognition, 137, 109347. https://doi.org/10.1016/j.patcog.2023.109347
Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57, 99. https://doi.org/10.1007/s10462-024-10721-6
Copyright (c) 2026 Dafa Fadhillah Matondang, Mahardika Abdi Prawira Tanjung

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
