A Two-Stage Deep Learning Approach Using YOLO11 and U-Net for Detection and Segmentation of Caries Under Crowns in Panoramic Radiographs
DOI:
https://doi.org/10.58600/eurjther2981Keywords:
artificial intelligence, deep learning, dental caries, panoramic radiographyAbstract
Objective: This study aimed to develop and evaluate deep learning models for the automatic detection and segmentation of caries under crowns on panoramic radiographs.
Methods: A retrospective study was conducted. From 1742 panoramic radiographs initially screened, 257 high-quality regions of interest (ROIs) containing crowns with radiographically detectable caries were extracted. Multiple ROIs could be obtained from a single panoramic radiograph when more than one qualifying crown was present. A two-stage coarse-to-fine strategy was implemented. In the first stage, the YOLO11l (Large) model was used for automatic detection and localization of crowns, achieving 0.977 mAP@50 and 0.857 mAP@50-95 on the validation set. In the second stage, three deep learning architectures were compared for caries segmentation: YOLO11-seg variants, U-Net with ResNet34 backbone, and U-Net++ with ResNet34 backbone. Expert annotations were created by three dentists with over 10 years of experience, showing near-perfect interobserver agreement.
Results: In ROI detection, the YOLO11l model achieved a 97.7% mAP@50 value. In the segmentation phase, YOLO11s-seg showed the highest object detection success with a 74.3% instance F1 score, while in pixel-based evaluation, U-Net++ (71.2% Dice) performed 9.8 points higher than YOLO11s-seg (61.4% pixel F1) (p<0.01). Dice coefficient and F1 score are mathematically equivalent metrics when calculated at the pixel level. The final U-Net++ model achieved a 68.6% Dice score in the independent test set.
Conclusion: U-Net++ (ResNet34 backbone) achieved significantly superior pixel-based segmentation performance compared to standard U-Net and YOLO11-seg, demonstrating the effectiveness of nested skip connections for caries detection. An inverse relationship between model size and performance was observed in YOLO11 variants, emphasizing the critical importance of matching model capacity to dataset size. While these deep learning architectures demonstrate considerable potential for enhancing diagnostic accuracy, they should be implemented as adjunctive decision-support tools integrated with clinical expertise rather than standalone diagnostic systems.
References
[1] Bischof FM, Mathey AA, Stähli A, Salvi GE, Brägger U (2024) Survival and complication rates of tooth- and implant-supported restorations after an observation period up to 36 years. Clin Oral Implants Res. 35(12):1640-1654. https://doi.org/10.1111/clr.14351
[2] Pjetursson BE, Brägger U, Lang NP, Zwahlen M (2007) Comparison of survival and complication rates of tooth-supported fixed dental prostheses (FDPs) and implant-supported FDPs and single crowns (SCs). Clin Oral Implants Res. 18(Suppl 3):97-113. https://doi.org/10.1111/j.1600-0501.2007.01439.x
[3] Kamburoglu K, Kolsuz E, Murat S, Yüksel S, Özen T (2012) Proximal caries detection accuracy using intraoral bitewing radiography, extraoral bitewing radiography and panoramic radiography. Dentomaxillofac Radiol. 41(7):585-591. https://doi.org/10.1259/dmfr/3052617
[4] Choi JW (2011) Assessment of panoramic radiography as a national oral examination tool: review of the literature. Imaging Sci Dent. 41(1):1-6. https://doi.org/10.5624/isd.2011.41.1.1
[5] Moran M, Faria M, Giraldi G, Bastos L, Oliveira L, Conci A (2021) Classification of approximal caries in bitewing radiographs using convolutional neural networks. Sensors (Basel). 21. https://doi.org/10.3390/s21155192
[6] Mao YC, Chen TY, Chou HS, Lin SY, Liu SY, Chen YA, Liu YL, Chen CA, Huang YC, Chen SL, Li CW, Abu PAR, Chiang WY (2021) Caries and restoration detection using bitewing film based on transfer learning with CNNs. Sensors (Basel). 21. https://doi.org/10.3390/s21134613
[7] Lee S, Oh SI, Jo J, Kang S, Shin Y, Park JW (2021) Deep learning for early dental caries detection in bitewing radiographs. Sci Rep. 11:16807. https://doi.org/10.1038/s41598-021-96368-7
[8] Schwendicke F, Tzschoppe M, Paris S (2015) Radiographic caries detection: A systematic review and meta-analysis. J Dent. 43:924–933. https://doi.org/10.1016/j.jdent.2015.02.009
[9] Fourcade A, Khonsari RH (2019) Deep learning in medical image analysis: A third eye for doctors. J Stomatol Oral Maxillofac Surg. 120:279–288. https://doi.org/10.1016/j.jormas.2019.06.002
[10] Nguyen TT, Larrivée N, Lee A, Bilaniuk O, Durand R (2021) Use of artificial intelligence in dentistry: Current clinical trends and research advances. J Can Dent Assoc. 87:l7.
[11] Svenson B, Ståhlnacke K, Karlsson R, Fält A (2018) Dentists’ use of digital radiographic techniques: Part I – intraoral X-ray: a questionnaire study of Swedish dentists. Acta Odontol Scand. 76:111–118. https://doi.org/10.1080/00016357.2017.1387930
[12] Chen YW, Stanley K, Att W (2020) Artificial intelligence in dentistry: current applications and future perspectives. Quintessence Int. 51:248–257. https://doi.org/10.3290/j.qi.a43952
[13] Mohammed SY (2025) Architecture review: Two-stage and one-stage object detection. Franklin Open. 100322. https://doi.org/10.1016/j.fraope.2025.100322
[14] Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Springer, Cham, pp 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
[15] Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2018) UNet++: A nested U-Net architecture for medical image segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support. 11045:3-11. https://doi.org/10.1007/978-3-030-00889-5_1
[16] Devito KL, de Souza Barbosa F, Felippe Filho WN (2008) An artificial multilayer perceptron neural network for diagnosis of proximal dental caries. Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 106:879–884. https://doi.org/10.1016/j.tripleo.2008.03.002
[17] Mertens S, Krois J, Cantu AG, Arsiwala LT, Schwendicke F (2021) Artificial intelligence for caries detection: Randomized trial. J Dent. 115:103849. https://doi.org/10.1016/j.jdent.2021.103849
[18] Schwendicke F, Golla T, Dreher M, Krois J (2019) Convolutional neural networks for dental image diagnostics: A scoping review. J Dent. 91:103226. https://doi.org/10.1016/j.jdent.2019.103226
[19] Bayraktar Y, Ayan E (2022) Diagnosis of interproximal caries lesions with deep convolutional neural network in digital bitewing radiographs. Clin Oral Investig. 26:623–632. https://doi.org/10.1007/s00784-021-04040-1
[20] Tuzoff DV, Tuzova LN, Bornstein MM, Krasnov AS, Kharchenko MA, Nikolenko SI, Sveshnikov MM, Bednenko GB (2019) Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofac Radiol. 48:20180051. https://doi.org/10.1259/dmfr.20180051
[21] Başaran M, Çelik Ö, Bayrakdar IS, Bilgir E, Orhan K, Odabaş A, Aslan AF, Jagtap R (2022) Diagnostic charting of panoramic radiography using deep-learning artificial intelligence system. Oral Radiol. 38:363–369. https://doi.org/10.1007/s11282-021-00572-0
[22] Lee JH, Kim DH, Jeong SN, Choi SH (2018) Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. J Dent. 77:106–111. https://doi.org/10.1016/j.jdent.2018.07.015
[23] Ariji Y, Yanashita Y, Kutsuna S, Muramatsu C, Fukuda M, Kise Y, Nozawa M, Kuwada C, Fujita H, Katsumata A, Ariji E (2019) Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique. Oral Surg Oral Med Oral Pathol Oral Radiol. 128:424–430. https://doi.org/10.1016/j.oooo.2019.05.014
[24] Ayhan B, Ayan E, Atsü S (2025) Detection of dental caries under fixed dental prostheses by analyzing digital panoramic radiographs with artificial intelligence algorithms based on deep learning methods. BMC Oral Health. 25:216. https://doi.org/10.1186/s12903-025-05577-3
[25] Fukuda M, Inamoto K, Shibata N, Ariji Y, Yanashita Y, Kutsuna S, Nakata K, Katsumata A, Fujita H, Ariji E (2020) Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography. Oral Radiol. 36:337–343. https://doi.org/10.1007/s11282-019-00409-x
[26] White SC, Pharoah MJ (2012) Oral radiology: principles and interpretation. Elsevier.
[27] Perschbacher S (2012) Interpretation of panoramic radiographs. Aust Dent J. 57(Suppl 1):40–45. https://doi.org/10.1111/j.1834-7819.2011.01655.x
[28] Chen IDS, Yang CM, Chen MJ, Chen MC, Weng RM, Yeh CH (2023) Deep learning-based recognition of periodontitis and dental caries in dental X-ray images. Bioengineering (Basel). 10. https://doi.org/10.3390/bioengineering10080911
[29] Zhu J, Chen Z, Zhao J, Yu Y, Li X, Shi K, Zhang F, Yu F, Shi K, Sun Z, Lin N, Zheng Y (2023) Artificial intelligence in the diagnosis of dental diseases on panoramic radiographs: a preliminary study. BMC Oral Health. 23:358. https://doi.org/10.1186/s12903-023-03027-6
[30] Vinayahalingam S, Kempers S, Limon L, Deibel D, Maal T, Hanisch M, Bergé S, Xi T (2021) Classification of caries in third molars on panoramic radiographs using deep learning. Sci Rep. 11:12609. https://doi.org/10.1038/s41598-021-92121-2
[31] Ameli N, Moghaddam MM, Lai H, Pacheco-Pereira C (2025) Automated quality evaluation of dental panoramic radiographs using deep learning. Imaging Sci Dent. 55(2):175. https://doi.org/10.5624/isd.20240232
[32] Moran MBH, Faria MDB, Giraldi GA, Bastos LF, Conci A (2021) Using super-resolution generative adversarial network models and transfer learning to obtain high resolution digital periapical radiographs. Comput Biol Med. 129:104139. https://doi.org/10.1016/j.compbiomed.2020.104139
[33] Srivastava MM, Kumar P, Pradhan L, Varadarajan SJapa (2017) Detection of tooth caries in bitewing radiographs using deep learning. arXiv preprint. arXiv:1711.07312.
[34] Panyarak W, Wantanajittikul K, Charuakkra A, Prapayasatok S, Suttapak W (2023) Enhancing caries detection in bitewing radiographs using YOLOv7. J Digit Imaging. 36:2635–2647. https://doi.org/10.1007/s10278-023-00871-4
[35] Cantu AG, Gehrung S, Krois J, Chaurasia A, Rossi JG, Gaudin R, Elhennawy K, Schwendicke F (2020) Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent. 100:103425. https://doi.org/10.1016/j.jdent.2020.103425
[36] Chen X, Guo J, Ye J, Zhang M, Liang Y (2022) Detection of proximal caries lesions on bitewing radiographs using deep learning method. Caries Res. 56:455–463. https://doi.org/10.1159/000527418
[37] Innes NPT, Schwendicke F (2017) Restorative thresholds for carious lesions: Systematic review and meta-analysis. J Dent Res. 96:501–508. https://doi.org/10.1177/0022034517693605
[38] Khan HA, Haider MA, Ansari HA, Ishaq H, Kiyani A, Sohail K, Muhammad M, Khurram SA (2021) Automated feature detection in dental periapical radiographs by using deep learning. Oral Surg Oral Med Oral Pathol Oral Radiol. 131:711–720. https://doi.org/10.1016/j.oooo.2020.08.024
[39] Vinayahalingam S, Goey RS, Kempers S, Schoep J, Cherici T, Moin DA, Hanisch M (2021) Automated chart filing on panoramic radiographs using deep learning. J Dent. 115:103864. https://doi.org/10.1016/j.jdent.2021.103864
Downloads
Published
How to Cite
License
Copyright (c) 2026 Buse Çebi Gül, Can Çebi, Burçin Altınsoy, Numan Dedeoğlu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The content of this journal is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
