Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation

Anday Duru; Fatih Karayürek

doi:10.29130/dubited.1906306

TR EN

Abstract

Panoramik radyografilerde apikal periodontitis lezyonlarının saptanması zordur; çünkü bulgular ince olabilir ve çoğu zaman anatomik süperpozisyon, değişken kontrast ve restoratif artefaktlar nedeniyle değerlendirme güçleşir. Bu çalışma, panoramik radyografilerde apikal lezyon lokalizasyonu için yeni nesil nesne tespit modellerini karşılaştırmış ve herkese açık bir veri kümesi kullanarak, eşleştirilmiş deneysel koşullar altında eğitim verisi artırmanın katkısını nicel olarak değerlendirmiştir. YOLOv8 (s/l), YOLOv11 (s/l) ve RT-DETR-l modelleri, veri artırmalı ve veri artırmasız olmak üzere iki farklı düzende eğitilmiştir. Tüm modeller, 392 görüntü ve 639 anotasyonlu lezyondan oluşan sabit bir test ayrımı üzerinde değerlendirilmiştir. Veri artırma, tüm modellerde tespit performansını tutarlı biçimde iyileştirmiştir. En iyi genel test performansı, veri artırmalı YOLOv8-l modeli ile elde edilmiştir (F1 = 0.975; AP@0.50 = 0.994), buna karşılık RT-DETR-l modeli veri artırmasız senaryoda en güçlü başlangıç performansını göstermiştir (F1 = 0.689; AP@0.50 = 0.720). Bu bulgular, eşleştirilmiş koşullar altında veri artırmanın panoramik radyografi tabanlı apikal lezyon tespitini belirgin biçimde güçlendirdiğini ve modern nesne tespit modellerinin yüksek hacimli diş hekimliği iş akışlarında tarama amacıyla güvenilir yardımcı destek sağlayabildiğini, ancak nihai klinik kararın diş hekimine ait olduğunu göstermektedir.

Keywords

Apikal periodontitis, Panoramik radyografi, Nesne tespiti, YOLO, Veri artırma, Klinik karar destek sistemi.

Ethical Statement

Bu çalışmada, insan katılımcılara ait herkese açık bir veri kümesi kullanılmıştır. Yeni katılımcı dâhil edilmemiş ve yazarlar tarafından herhangi bir doğrudan etkileşim ya da müdahale gerçekleştirilmemiştir. Veri kümesi, özgün sağlayıcıları tarafından daha önce toplanmış ve kamuya açık olarak paylaşılmıştır. Bu nedenle, bu çalışma için ek etik kurul onayı ve bilgilendirilmiş onam gerekmemiştir.

Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation

Abstract

Detecting apical periodontitis lesions on panoramic radiographs (PR) is challenging because lesions may be subtle and affected by anatomic superimposition, variable contrast, and restorative artifacts. This study compared five modern object detectors from the YOLOv8, YOLOv11, and RT-DETR families and quantified the effect of training data augmentation using a publicly available dataset. All final comparisons used a standardized input size of 1024×1024 pixels and batch size of 16. Each model–regime combination was evaluated over three independent random seeds, and performance was assessed on a fixed held-out test split comprising 393 images with 693 annotated lesions. Augmentation improved F1-score and AP-based detection performance across all architectures. Among augmented models, RT-DETR-l achieved the highest mean F1-score (0.685 ± 0.011; 95% CI: 0.657–0.714), while YOLOv11-l achieved the highest mean AP@0.50 (0.738 ± 0.018; 95% CI: 0.694–0.782) and AP@0.50:0.95 (0.352 ± 0.012; 95% CI: 0.323–0.380). The largest absolute F1 improvement was observed for YOLOv11-s (ΔF1 = +0.141). Two-sided paired comparisons with Holm correction showed significant augmentation-related F1 improvements for all five detectors. Region-wise failure analysis of augmented YOLOv11-l showed a higher false-negative rate in the maxilla (57.6%) than in the mandible (30.0%). These findings demonstrate that augmentation consistently improves PR-based apical lesion detection under repeated-seed evaluation and support the use of modern detectors as assistive second-reader tools, while final clinical decisions remain with the dentist.

Keywords

Apical periodontitis, Panoramic radiography, Object detection, Data augmentation, Clinical decision support

Supporting Institution

This research received no external funding.

Ethical Statement

This study used secondary analysis of a publicly available dataset and did not involve new participant recruitment, data collection, or intervention. Ethical approval for the original data collection was obtained by the dataset providers from the Institutional Review Board of Hanoi Medical University (HMUIRB463; August 3, 2021).

Thanks

The authors do not wish to acknowledge any individual or institution.

References

Abbott, P. V. (2004). Classification, diagnosis and clinical manifestations of apical periodontitis. Endodontic Topics, 8(1), 36–54. https://doi.org/10.1111/j.1601-1546.2004.00098.x
Ali, M. L., & Zhang, Z. (2024). The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection. Computers, 13(12), Article 336. https://doi.org/10.3390/computers13120336
Arbildo-Vega, H. I., Cruzado-Oliva, F. H., Coronel-Zubiate, F. T., Meza-Málaga, J. M., Luján-Valencia, S. A., Luján-Urviola, E., Echevarria-Goche, A., Farje-Gallardo, C. A., Castillo-Cornock, T. B., Serquen-Olano, K., Padilla-Cáceres, T., Caballero-Apaza, L., & Aguirre-Ipenza, R. (2024). Periodontal disease and cardiovascular disease: Umbrella review. BMC Oral Health, 24(1), Article 1308. https://doi.org/10.1186/s12903-024-04907-1
Ba-Hattab, R., Barhom, N., Osman, S. A. A., Naceur, I., Odeh, A., Asad, A., Al-Najdi, S. A. R. N., Ameri, E., Daer, A., Da Silva, R. L. B., Costa, C., Cortes, A. R. G., & Tamimi, F. (2023). Detection of periapical lesions on panoramic radiographs using deep learning. Applied Sciences, 13(3), Article 1516. https://doi.org/10.3390/app13031516
Basso, Á., Salas, F., Hernández, M., Fernández, A., Sierra, A., & Jiménez, C. (2024). Machine learning and deep learning models for the diagnosis of apical periodontitis: A scoping review. Clinical Oral Investigations, 28(11), Article 600. https://doi.org/10.1007/s00784-024-05989-5
Boztuna, M., Firincioglulari, M., Akkaya, N., & Orhan, K. (2024). Segmentation of periapical lesions with automatic deep learning on panoramic radiographs: an artificial intelligence study. BMC Oral Health, 24(1), Article 1332. https://doi.org/10.1186/s12903-024-05126-4
Butera, A., Maiorani, C., Morandini, A., Trombini, J., Simonini, M., Ogliari, C., & Scribante, A. (2023). Periodontitis in pregnant women: A possible link to adverse pregnancy outcomes. Healthcare, 11(10), Article 1372. https://doi.org/10.3390/healthcare11101372
Çelik, B., Savaştaer, E. F., Kaya, H. I., & Çelik, M. E. (2023). The role of deep learning for periapical lesion detection on panoramic radiographs. Dentomaxillofacial Radiology, 52(8), Article 20230118. https://doi.org/10.1259/dmfr.20230118
Do, H. V., Vo, T. N. N., Nguyen, P. T., Luong, T. H. L., Cu, N. G., & Le, H. S. (2024). A dataset of apical periodontitis lesions in panoramic radiographs for deep-learning-based classification and detection. Data in Brief, 54, Article 110486. https://doi.org/10.1016/j.dib.2024.110486
Do, V. (2024). Panoramic radiographs with periapical lesions dataset (Version 3) [Data set]. Mendeley Data. https://doi.org/10.17632/kx52tk2ddj.3

Duru, A., Karaş, İ. R., Karayürek, F., & Gülses, A. (2022). A deep learning approach for classification of dentinal tubule occlusions. Applied Artificial Intelligence, 36(1), Article 2094446. https://doi.org/10.1080/08839514.2022.2094446
Endres, M. G., Hillen, F., Salloumis, M., Sedaghat, A. R., Niehues, S. M., Quatela, O., Hanken, H., Smeets, R., Beck-Broichsitter, B., Rendenbach, C., Lakhani, K., Heiland, M., & Gaudin, R. A. (2020). Development of a deep learning algorithm for periapical disease detection in dental radiographs. Diagnostics, 10(6), Article 430. https://doi.org/10.3390/diagnostics10060430
Graber, T. M. (1967). Panoramic radiography in orthodontic diagnosis. American Journal of Orthodontics, 53(11), 799–821. https://doi.org/10.1016/0002-9416(67)90088-7
Hung, K., Montalvao, C., Tanaka, R., Kawai, T., & Bornstein, M. M. (2020). The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review. Dentomaxillofacial Radiology, 49(1), Article 20190107. https://doi.org/10.1259/dmfr.20190107
İçöz, D., Terzioğlu, H., Özel, M., & Karakurt, R. (2023). Evaluation of an artificial intelligence system for the diagnosis of apical periodontitis on digital panoramic images. Nigerian Journal of Clinical Practice, 26(8), 1085–1090. https://doi.org/10.4103/njcp.njcp_624_22
Issa, J., Jaber, M., Rifai, I., Mozdziak, P., Kempisty, B., & Dyszkiewicz-Konwińska, M. (2023). Diagnostic test accuracy of artificial intelligence in detecting periapical periodontitis on two-dimensional radiographs: A retrospective study and literature review. Medicina, 59(4), Article 768. https://doi.org/10.3390/medicina59040768
Kahraman, İ., Karaş, İ. R., & Turan, M. K. (2024). Real-time protozoa detection from microscopic imaging using YOLOv4 algorithm. Applied Sciences, 14(2), Article 607. https://doi.org/10.3390/app14020607
Kölüş, T., Akbulut, M. B., & Güleç, M. (2025). Detection of periapical lesions on panoramic radiographs using artificial Intelligence. Cumhuriyet Dental Journal, 28(4), 520–525. https://doi.org/10.7126/cumudj.1708342
Krois, J., Garcia Cantu, A., Chaurasia, A., Patil, R., Chaudhari, P. K., Gaudin, R., Gehrung, S., & Schwendicke, F. (2021). Generalizability of deep learning models for dental image analysis. Scientific Reports, 11(1), Article 6102. https://doi.org/10.1038/s41598-021-85454-5
Li, S., Liu, J., Zhou, Z., Zhou, Z., Wu, X., Li, Y., Wang, S., Liao, W., Ying, S., & Zhao, Z. (2022). Artificial intelligence for caries and periapical periodontitis detection. Journal of Dentistry, 122, Article 104107. https://doi.org/10.1016/j.jdent.2022.104107
Liu, J., Hong, Y., Shao, Y., Gao, Y., Pan, K., Jin, C., Du, Y., & Yu, X. (2024). Deep learning–based detection of periapical lesions in periapical radiographs. Journal of Medical and Biological Engineering, 44(5), 676–684. https://doi.org/10.1007/s40846-024-00903-6
Liu, J., Jin, C., Wang, X., Pan, K., Li, Z., Yi, X., Shao, Y., Sun, X., & Yu, X. (2025). A comparative analysis of deep learning models for assisting in the diagnosis of periapical lesions in periapical radiographs. BMC Oral Health, 25(1), Article 801. https://doi.org/10.1186/s12903-025-06104-0
Pekiner, M. Y., Yulek, H., Talmac, A. G. O., Keser, G., Pekiner, F. N., & Bayrakdar, I. S. (2025). A deep learning approach for detecting periapical lesions on panoramic radiographic images. Journal of the College of Physicians and Surgeons Pakistan, 35(11), 1461–1465. https://doi.org/10.29271/jcpsp.2025.11.1461
Rushton, V. E., Horner, K., & Worthington, H. V. (1999). Factors influencing the selection of panoramic radiography in general dental practice. Journal of Dentistry, 27(8), 565–571. https://doi.org/10.1016/S0300-5712(99)00031-7
Said, E. H., Nassar, D. E. M., Fahmy, G., & Ammar, H. H. (2006). Teeth segmentation in digitized dental X-Ray films using mathematical morphology. IEEE Transactions on Information Forensics and Security, 1(2), 178–189. https://doi.org/10.1109/TIFS.2006.873606
Sivari, E., Senirkentli, G. B., Bostanci, E., Guzel, M. S., Acici, K., & Asuroglu, T. (2023). Deep learning in diagnosis of dental anomalies and diseases: A systematic review. Diagnostics, 13(15), Article 2512. https://doi.org/10.3390/diagnostics13152512
Song, I.-S., Shin, H.-K., Kang, J.-H., Kim, J.-E., Huh, K.-H., Yi, W.-J., Lee, S.-S., & Heo, M.-S. (2022). Deep learning-based apical lesion segmentation from panoramic radiographs. Imaging Science in Dentistry, 52(4), 351–357. https://doi.org/10.5624/isd.20220078
Suzuki, K. (2017). Overview of deep learning in medical imaging. Radiological Physics and Technology, 10(3), 257–273. https://doi.org/10.1007/s12194-017-0406-5
Szabó, V., Orhan, K., Dobó-Nagy, C., Veres, D. S., Manulis, D., Ezhov, M., Sanders, A., & Szabó, B. T. (2025). Deep learning-based periapical lesion detection on panoramic radiographs. Diagnostics, 15(4), Article 510. https://doi.org/10.3390/diagnostics15040510
Tattar, R., da Costa, B. D. C., & Neves, V. C. M. (2025). The interrelationship between periodontal disease and systemic health. British Dental Journal, 239(2), 103–108. https://doi.org/10.1038/s41415-025-8642-2
Taylor, G., & Borgnakke, W. (2008). Periodontal disease: Associations with diabetes, glycemic control and complications. Oral Diseases, 14(3), 191–203. https://doi.org/10.1111/j.1601-0825.2008.01442.x
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023). A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. https://doi.org/10.3390/make5040083
Varghese, R., & Sambath, M. (2024). YOLOv8: A novel object detection algorithm with enhanced performance and robustness. In 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) (pp. 1–6). IEEE. https://doi.org/10.1109/ADICS58448.2024.10533619
Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., & Chen, J. (2024). DETRs beat YOLOs on real-time object detection. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 16965–16974). IEEE. https://doi.org/10.1109/CVPR52733.2024.01605

Details

Primary Language

English

Subjects

Bioinformatics

Journal Section

Research Article

Authors

Anday Duru ^*
0009-0007-8314-7268
Türkiye

Fatih Karayürek
0000-0003-0602-7610
Türkiye

Publication Date

October 23, 2026

Submission Date

March 9, 2026

Acceptance Date

August 20, 2026

Published in Issue

Year 2026 Volume: 14 Number: 4

DOI

https://doi.org/10.29130/dubited.1906306

IZ

https://izlik.org/JA96MP35LH

APA

Duru, A., & Karayürek, F. (2026). Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation. Duzce University Journal of Science and Technology, 14(4), 1138-1151. https://doi.org/10.29130/dubited.1906306

AMA

1.Duru A, Karayürek F. Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation. DUBİTED. 2026;14(4):1138-1151. doi:10.29130/dubited.1906306

Chicago

Duru, Anday, and Fatih Karayürek. 2026. “Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation”. Duzce University Journal of Science and Technology 14 (4): 1138-51. https://doi.org/10.29130/dubited.1906306.

EndNote

Duru A, Karayürek F (October 1, 2026) Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation. Duzce University Journal of Science and Technology 14 4 1138–1151.

IEEE

[1]A. Duru and F. Karayürek, “Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation”, DUBİTED, vol. 14, no. 4, pp. 1138–1151, Oct. 2026, doi: 10.29130/dubited.1906306.

ISNAD

Duru, Anday - Karayürek, Fatih. “Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation”. Duzce University Journal of Science and Technology 14/4 (October 1, 2026): 1138-1151. https://doi.org/10.29130/dubited.1906306.

JAMA

1.Duru A, Karayürek F. Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation. DUBİTED. 2026;14:1138–1151.

MLA

Duru, Anday, and Fatih Karayürek. “Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation”. Duzce University Journal of Science and Technology, vol. 14, no. 4, Oct. 2026, pp. 1138-51, doi:10.29130/dubited.1906306.

Vancouver

1.Anday Duru, Fatih Karayürek. Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation. DUBİTED. 2026 Oct. 1;14(4):1138-51. doi:10.29130/dubited.1906306

Abstract

Keywords

Ethical Statement

Automated Apical Periodontitis Detection on Panoramic Radiographs: Comparative Analysis of Modern Object Detectors and the Effect of Data Augmentation

Abstract

Keywords

Supporting Institution

Ethical Statement

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite