Skip to main content

Advertisement

SpringerLink
Log in

Second mesiobuccal canal segmentation with YOLOv5 architecture using cone beam computed tomography images

  • Original Article
  • Published:
Odontology Aims and scope Submit manuscript

Abstract

The objective of this study is to use a deep-learning model based on CNN architecture to detect the second mesiobuccal (MB2) canals, which are seen as a variation in maxillary molars root canals. In the current study, 922 axial sections from 153 patients’ cone beam computed tomography (CBCT) images were used. The segmentation method was employed to identify the MB2 canals in maxillary molars that had not previously had endodontic treatment. Labeled images were divided into training (80%), validation (10%) and testing (10%) groups. The artificial intelligence (AI) model was trained using the You Only Look Once v5 (YOLOv5x) architecture with 500 epochs and a learning rate of 0.01. Confusion matrix and receiver-operating characteristic (ROC) analysis were used in the statistical evaluation of the results. The sensitivity of the MB2 canal segmentation model was 0.92, the precision was 0.83, and the F1 score value was 0.87. The area under the curve (AUC) in the ROC graph of the model was 0.84. The mAP value at 0.5 inter-over union (IoU) was found as 0.88. The deep-learning algorithm used showed a high success in the detection of the MB2 canal. The success of the endodontic treatment can be increased and clinicians’ time can be preserved using the newly created artificial intelligence-based models to identify variations in root canal anatomy before the treatment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability

The analyzed data sets generated during the study are available from the corresponding author on reasonable request.

References

  1. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Health J. 2019;6:94.

    Article  Google Scholar 

  2. Ching T, Himmelstein DS, Beaulieu-Jones BK, et al. Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interface. 2018;15:20170387.

    Article  PubMed  PubMed Central  Google Scholar 

  3. Hung KF, Ai QYH, Wong LM, et al. Current applications of deep learning and radiomics on CT and CBCT for maxillofacial diseases. Diagnostics. 2022;13:110.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Redmon J, Divvala S, Girshick R et al. You only look once: unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 779–788

  5. Bayraktar Y, Ayan E. Diagnosis of interproximal caries lesions with deep convolutional neural network in digital bitewing radiographs. Clin Oral Investig. 2022;26:623–32.

    Article  PubMed  Google Scholar 

  6. Nie Y, Sommella P, O’Nils M, et al. Automatic detection of melanoma with yolo deep convolutional neural networks. 2019 E-Health and Bioengineering Conference (EHB)2019: IEEE.

  7. George J, Skaria S, Varun V. Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans. Medical Imaging 2018: Computer-Aided Diagnosis2018: SPIE.

  8. Widiasri M, Arifin AZ, Suciati N, et al. Alveolar bone detection from dental cone beam computed tomography using YOLOv3-tiny. 2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)2021: IEEE.

  9. Du M, Wu X, Ye Y, F, et al. A combined approach for accurate and accelerated teeth detection on cone beam CT ımages. Diagnostics. 2022;12:1679.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Zheng Q-h, Wang Y, Zhou X-d, et al. A cone-beam computed tomography study of maxillary first permanent molar root and canal morphology in a Chinese population. J Endod. 2010;36:1480–4.

    Article  PubMed  Google Scholar 

  11. Smadi L, Khraisat A. Detection of a second mesiobuccal canal in the mesiobuccal roots of maxillary first molar teeth. Oral Surg Oral Med Oral Path Oral Radiol Endod. 2007;103:77–81.

    Article  Google Scholar 

  12. Zhang R, Yang H, Yu X, et al. Use of CBCT to identify the morphology of maxillary permanent molar teeth in a Chinese subpopulation. Int Endod J. 2011;44:162–9.

    Article  CAS  PubMed  Google Scholar 

  13. Weine F, Hayami S, Hata G, et al. Canal configuration of the mesiobuccal root of the maxillary first molar of a Japanese sub-population. Int Endod J. 1999;32:79–87.

    Article  CAS  PubMed  Google Scholar 

  14. Martins JN, Alkhawas M-BA, Altaki Z, et al. Worldwide analyses of maxillary first molar second mesiobuccal prevalence: a multicenter cone-beam computed tomographic study. J Endod. 2018;44:1641–9.

    Article  PubMed  Google Scholar 

  15. Sempira H, Hartwell G. Frequency of second mesiobuccal canals in maxillary molars as determined by use of an operating microscope: a clinical study. J Endod. 2000;26:673–4.

    Article  CAS  PubMed  Google Scholar 

  16. Barrington C, Balandrano F. Diaphanization techniques in the study of root canal anatomy. In: The root canal anatomy in permanent dentition. Cham: Springer; 2019. p. 57–88.

    Chapter  Google Scholar 

  17. Schwarze T, Baethge C, Stecher T, et al. Identification of second canals in the mesiobuccal root of maxillary first and second molars using magnifying loupes or an operating microscope. Aust Endod J. 2002;28:57–60.

    Article  CAS  PubMed  Google Scholar 

  18. Verma P, Love R. A micro CT study of the mesiobuccal root canal morphology of the maxillary first molar tooth. Int Endod J. 2011;44:210–7.

    Article  CAS  PubMed  Google Scholar 

  19. Blattner TC, George N, Lee CC, et al. Efficacy of cone-beam computed tomography as a modality to accurately identify the presence of second mesiobuccal canals in maxillary first and second molars: a pilot study. J Endod. 2010;36:867–70.

    Article  PubMed  Google Scholar 

  20. Cotton TP, Geisler TM, Holden DT, et al. Endodontic applications of cone-beam volumetric tomography. J Endod. 2007;33:1121–32.

    Article  PubMed  Google Scholar 

  21. Nepal U, Eslamiat H. Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs. Sensors. 2022;22:464.

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  22. Wang K, Liew JH, Zou Y et al. Panet: Few-shot image semantic segmentation with prototype alignment. Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.

  23. Martins JN, Marques D, Silva EJNL, et al. Second mesiobuccal root canal in maxillary molars—a systematic review and meta-analysis of prevalence studies using cone beam computed tomography. Arch Oral Biol. 2020;113:104589.

    Article  PubMed  Google Scholar 

  24. Betancourt P, Navarro P, Muñoz G, et al. Prevalence and location of the secondary mesiobuccal canal in 1,100 maxillary molars using cone beam computed tomography. BMC Med Imaging. 2016;16:1–8.

    Article  Google Scholar 

  25. Albitar L, Mahdian M. The long journey to set up artificial intelligence (AI) data for automatic detection and localization of missed mesial-buccal (MB2) canals in endodontically-treated maxillary molars with cone beam computed tomography. Oral Surg Oral Med Oral Path Oral Radiol. 2022;134:80.

    Article  Google Scholar 

  26. Normando PHC, Dos Santos JCM, Akisue E, et al. Location of the second mesiobuccal canal of maxillary molars in a Brazilian subpopulation: analyzing using cone-beam computed tomography. J Contemp Dent Pract. 2023;23:979–83.

    Article  Google Scholar 

  27. Betancourt P, Navarro P, Cantín M, Fuentes R. Cone-beam computed tomography study of prevalence and location of MB2 canal in the mesiobuccal root of the maxillary second molar. Int J Clin Exp Med. 2015;8:9128.

    PubMed  PubMed Central  Google Scholar 

  28. Kewalramani R, Murthy CS, Gupta R. The second mesiobuccal canal in three-rooted maxillary first molar of Karnataka Indian sub-populations: a cone-beam computed tomography study. J Oral Biol Craniofac Res. 2019;9:347–51.

    Article  PubMed  PubMed Central  Google Scholar 

  29. Bauman R, Scarfe W, Clark S, et al. Ex vivo detection of mesiobuccal canals in maxillary molars using CBCT at four different isotropic voxel dimensions. Int Endod J. 2011;44:752–8.

    Article  CAS  PubMed  Google Scholar 

  30. Setzer FC, Shi KJ, Zhang Z, et al. Artificial intelligence for the computer-aided detection of periapical lesions in cone-beam computed tomographic images. J Endod. 2020;46:987–93.

    Article  PubMed  Google Scholar 

  31. Orhan K, Bayrakdar I, Ezhov M, et al. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int Endod J. 2020;53:680–9.

    Article  CAS  PubMed  Google Scholar 

  32. Zheng Z, Yan H, Setzer FC, et al. Anatomically constrained deep learning for automating dental CBCT segmentation and lesion detection. IEEE Trans Autom Sci Eng. 2020;18:603–14.

    Article  Google Scholar 

  33. Saghiri MA, Asgar K, Boukani K, et al. A new approach for locating the minor apical foramen using an artificial neural network. Int Endod J. 2012;45:257–65.

    Article  CAS  PubMed  Google Scholar 

  34. Fukuda M, Inamoto K, Shibata N, et al. Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography. Oral Radiol. 2020;36:337–43.

    Article  PubMed  Google Scholar 

  35. Johari M, Esmaeili F, Andalib A, et al. Detection of vertical root fractures in intact and endodontically treated premolar teeth by designing a probabilistic neural network: an ex vivo study. Dentomaxillofac Radiol. 2017;46:20160107.

    Article  PubMed  PubMed Central  Google Scholar 

  36. Jeon S-J, Yun J-P, Yeom H-G, et al. Deep-learning for predicting C-shaped canals in mandibular second molars on panoramic radiographs. Dentomaxillofac Radiol. 2021;50:20200513.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Sherwood AA, Sherwood AI, Setzer FC, et al. A deep learning approach to segment and classify C-shaped canal morphologies in mandibular second molars using cone-beam computed tomography. J Endod. 2021;47:1907–16.

    Article  PubMed  Google Scholar 

  38. Hiraiwa T, Ariji Y, Fukuda M, et al. A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography. Dentomaxillofac Radiol. 2019;48:20180218.

    Article  PubMed  Google Scholar 

Download references

Funding

This work has been supported by Eskisehir Osmangazi University Scientific Research Projects Coordination Unit under grant number 202045E06.

Author information

Authors and Affiliations

  1. Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Inonu University Malatya, Malatya, Turkey

    Şuayip Burak Duman & Duygu Çelik Özen

  2. Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskişehir Osmangazi University, Eskişehir, Turkey

    Ibrahim Şevki Bayrakdar

  3. Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ege University İzmir, İzmir, Turkey

    Oğuzhan Baydar

  4. College of Dental Medicine, QU Health, Qatar University, Doha, Qatar

    Elham S. Abu Alhaija & Dilek Helvacioğlu Yiğit

  5. Department of Mathematics-Computer, Faculty of Science, Eskişehir Osmangazi University, Eskişehir, Turkey

    Özer Çelik

  6. Division of Oral and Maxillofacial Radiology, Department of Care Planning and Restorative Sciences, Medical Center School of Dentistry, University of Mississippi, Jackson, MS, USA

    Rohan Jagtap

  7. Department of Endodontics, College of Dentistry, University of Florida, Florida, USA

    Roberta Pileggi

  8. Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara, Turkey

    Kaan Orhan

Authors
  1. Şuayip Burak Duman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Duygu Çelik Özen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ibrahim Şevki Bayrakdar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Oğuzhan Baydar
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Elham S. Abu Alhaija
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Dilek Helvacioğlu Yiğit
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Özer Çelik
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Rohan Jagtap
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Roberta Pileggi
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Kaan Orhan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All the authors have read and approved the manuscript. Conceptualization: DSB, BIS. Data curation: ODC, BO. Formal analysis: CO Investigation: DSB, ODC Methodology: AESA, YDH. Project administration: OK, JR. Resources: BIS. Supervision: AESA, OK. Validation: JR. Visualization: DSB. Writing—original draft: DSB, ODC, BIS. Writing—review and editing: AESA, OK, PR.

Corresponding author

Correspondence to Şuayip Burak Duman.

Ethics declarations

Conflict of interest

The authors declare that he has no conflict of interest.

Ethical approval

This research was approved by Inonu University Scientific Research and publication ethics committee numbered: 2022/3031.

Informed consent

For this type of study, formal consent is not required.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duman, Ş.B., Çelik Özen, D., Bayrakdar, I.Ş. et al. Second mesiobuccal canal segmentation with YOLOv5 architecture using cone beam computed tomography images. Odontology 112, 552–561 (2024). https://doi.org/10.1007/s10266-023-00864-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10266-023-00864-3

Keywords

Search

Navigation