Deteksi Kondisi Gigi Anak pada Radiografi Panoramik Menggunakan YOLOv8 dan Teknik Peningkatan Citra: Detection of Children's Dental Conditions in Panoramic Radiography Using YOLOv8 and Image Enhancement Techniques

Khoifah Inda Maula; Chastine Fatichah; Hilya Tsaniya Ismet

doi:10.57152/malcom.v6i1.2438

Authors

Khoifah Inda Maula Institut Teknologi Sepuluh Nopember
Chastine Fatichah Institut Teknologi Sepuluh Nopember
Hilya Tsaniya Ismet Universitas Telkom

DOI:

https://doi.org/10.57152/malcom.v6i1.2438

Keywords:

Deteksi Objek, Gigi Anak, Panoramic Gigi, Peningkatan Citra, YOLO

Abstract

Citra panoramik gigi merupakan teknik radiografi yang memberikan gambaran menyeluruh terhadap struktur gigi, rahang, serta jaringan pendukung lainnya dalam satu citra, sehingga banyak digunakan untuk diagnosis awal dan perencanaan perawatan, khususnya pada pasien anak-anak. Namun, karakteristik gigi anak yang unik seperti keberadaan gigi campuran dan perubahan posisi gigi yang dinamis mengakibatkan interpretasi citra menjadi lebih kompleks. Selain itu, kualitas citra yang kurang optimal seperti kontras rendah dan distribusi sinar-X yang tidak merata dapat menghambat proses deteksi secara akurat. Penelitian ini bertujuan meningkatkan kualitas citra serta melakukan deteksi otomatis citra panoramik gigi anak menggunakan You Only Look Once (YOLO) yang dikenal unggul dalam kecepatan dan akurasi deteksi objek. Proses peningkatan citra dilakukan dengan tiga teknik, yaitu Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), dan gamma correction. Hasil pengujian menunjukkan bahwa penerapan CLAHE memberikan performa deteksi terbaik dibandingkan dengan metode HE maupun gamma correction. Berdasarkan analisis metrik evaluasi, penggunaan CLAHE terbukti paling optimal dalam meratakan kontras lokal dan menekan noise, sehingga YOLOv8 dapat mengekstraksi fitur gigi anak yang kompleks. Sebagai kesimpulan, kombinasi metode prapemrosesan CLAHE dan model deteksi YOLOv8 merupakan pendekatan yang paling efektif untuk mengatasi permasalahan kualitas citra dan direkomendasikan untuk pengembangan sistem diagnosis otomatis citra panoramik gigi anak.

Downloads

Download data is not yet available.

References

A. H. Abdi, S. Kasaei, and M. Mehdizadeh, “Automatic segmentation of mandible in panoramic x-ray,” Journal of Medical Imaging, vol. 2, no. 4, p. 044003, Nov. 2015, doi: 10.1117/1.jmi.2.4.044003.

R. Izzetti, M. Nisi, G. Aringhieri, L. Crocetti, F. Graziani, and C. Nardi, “Basic knowledge and new advances in panoramic radiography imaging techniques: A narrative review on what dentists and radiologists should know,” Applied Sciences (Switzerland), vol. 11, no. 17, Sep. 2021, doi: 10.3390/app11177858.

M. O. Ovi et al., “Enhanced Pediatric Dental Segmentation Using a Custom SegUNet with VGG19 Backbone on Panoramic Radiographs,” Mar. 2025, [Online]. Available: http://arxiv.org/abs/2503.06321

Y. Zhang et al., “Children’s dental panoramic radiographs dataset for caries segmentation and dental disease detection,” Sci Data, vol. 10, no. 1, Dec. 2023, doi: 10.1038/s41597-023-02237-5.

T. Kabir, C. T. Lee, L. Chen, X. Jiang, and S. Shams, “A comprehensive artificial intelligence framework for dental diagnosis and charting,” BMC Oral Health, vol. 22, no. 1, Dec. 2022, doi: 10.1186/s12903-022-02514-6.

G. Siracusano, A. La Corte, M. Gaeta, G. Cicero, M. Chiappini, and G. Finocchio, “Pipeline for advanced contrast enhancement (Pace) of chest x-ray in evaluating covid-19 patients by combining bidimensional empirical mode decomposition and contrast limited adaptive histogram equalization (clahe),” Sustainability (Switzerland), vol. 12, no. 20, pp. 1–18, Oct. 2020, doi: 10.3390/su12208573.

R. B. Rahman, S. A. Tanim, N. Alfaz, T. E. Shrestha, M. S. U. Miah, and M. F. Mridha, “A comprehensive dental dataset of six classes for deep learning based object detection study,” Data Brief, 2024, doi: 10.1016/j.dib.2024.110970.

H. Tsaniya, C. Fatichah, and N. Suciati, “Automatic Radiology Report Generator Using Transformer With Contrast-Based Image Enhancement,” IEEE Access, vol. 12, pp. 25429–25442, 2024, doi: 10.1109/ACCESS.2024.3364373.

A. Juyal, H. Tiwari, U. K. Singh, N. Kumar, and S. Kumar, “Dental Caries Detection Using Faster R-CNN and YOLO V3,” ITM Web of Conferences, vol. 53, p. 02005, 2023, doi: 10.1051/itmconf/20235302005.

B. Beser et al., “YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition,” BMC Med Imaging, vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12880-024-01338-w.

U. Sevik and O. Mutlu, “Detection of Dental Anomalies in Digital Panoramic Images Using YOLO: A Next Generation Approach Based on Single Stage Detection Models.” [Online]. Available: https://ssrn.com/abstract=5181597

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” 2016. [Online]. Available: http://pjreddie.com/yolo/

E. N. Olam, A. R. Himamunanto, and H. Budiati, “Analisis Komparasi Performa Metode Deteksi Tepi Sebagai Predektor Diabetes Berbasis Citra Lidah,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 4, pp. 1218–1223, Jul. 2024, doi: 10.57152/malcom.v4i4.1393.

Ö. Aldanma, H. B. Atarda?, E. Y. Özdemir, and F. Özyurt, “AI-Driven Dental Radiography Analysis: Enhancing Diagnosis and Education Through YOLOv8 and Eigen-CAM,” Traitement du Signal, vol. 41, no. 6, pp. 2875–2882, Dec. 2024, doi: 10.18280/ts.410608.

Y. Hua, R. Chen, and H. Qin, “YOLO-DentSeg: A Lightweight Real-Time Model for Accurate Detection and Segmentation of Oral Diseases in Panoramic Radiographs,” Electronics (Switzerland), vol. 14, no. 4, Feb. 2025, doi: 10.3390/electronics14040805.

J. C. Mello Román et al., “Panoramic dental radiography image enhancement using multiscale mathematical morphology,” Sensors, vol. 21, no. 9, 2021, doi: 10.3390/s21093110.

M. Yaseen, “What is YOLOv8: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector,” Aug. 2024, [Online]. Available: http://arxiv.org/abs/2408.15857