Skip to main content
SpringerLink
Log in

Automated methods for sella turcica segmentation on cephalometric radiographic data using deep learning (CNN) techniques

  • Original Article
  • Published:
Oral Radiology Aims and scope Submit manuscript

Abstract

Objective

The objective of this work is to present a novel technique using convolutional neural network (CNN) architectures for automatic segmentation of sella turcica (ST) on cephalometric radiographic image dataset. The proposed work suggests possible deep learning approaches to distinguish ST on complex cephalometric radiographs using deep learning techniques.

Materials and methods

The dataset of 525 lateral cephalometric images was employed and randomly split into different training and testing subset ratios. The ground truth (annotated images) represents pixel-wise annotation of the ST using an online annotation platform by dental specialists. This study compared convolutional neural network architectures based on fine-tuned versions of the VGG19, ResNet34, InceptionV3, and ResNext50 architectures to select an appropriate model for autonomous segmentation of the nonlinear structure of ST.

Results

The study compared training and prediction results of the selected models: VGG19, ResNet34, InceptionV3, and ResNext50. The mean IoU scores for VGG19, ResNet34, InceptionV3 and ResNext50 are 0.7651, 0.7241, 0.4717, 0.4287, dice coefficients are 0.7794, 0.7487, 0.4714, 0.4363 and loss scores are 0.0973, 0.1299, 0.2049 and 0.2251, respectively.

Conclusion

The obtained findings suggest that the VGG19 and Resnet34 architectures (mean IoU and dice coefficient > 75%) comparatively outperformed the InceptionV3 and ResNext50 architectures (mean IoU and dice coefficients is around 45%) for considered cephalometric radiographic dataset. The study findings can be used as a reference model for future investigation of non-linear ST morphological characteristics and related biological anomalies.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Broadbent BH. A new x-ray technique and its application to orthodontia. Angle Orthod. 1931;1(2):45–66.

    Google Scholar 

  2. Tekiner H, Acer N, Kelestimur F. Sella turcica: an anatomical, endocrinological, and historical perspective. Pituitary. 2015;18(4):575–8.

    Article  PubMed  Google Scholar 

  3. Svystun O, Schropp L, Wenzel A, Spin-Neto R. Sella turcica area and location of point sella in cephalograms acquired with simulated patient head movements. J Contemp Dent Pract. 2021;22(3):207–14.

    Article  PubMed  Google Scholar 

  4. Kantor ML, Norton LA. Normal radiographic anatomy and common anomalies seen in cephalometric films. Am J Orthod Dentofacial Orthop. 1987;91(5):414–26.

    Article  PubMed  Google Scholar 

  5. Subhadra Devi V, Baburao S. Age and sex related morphology and morphometry of sellar region of sphenoid in prenatal and postnatal human cadavers. Int J Res Dev Health. 2013;1(3):141–8.

    Google Scholar 

  6. Costea C, Turliuc S, Cucu A, Dumitrescu G, Carauleanu A, Buzduga C, et al. The “polymorphous” history of a polymorphous skull bone: the sphenoid. Anat Sci Int. 2018;93(1):14–22.

    Article  PubMed  Google Scholar 

  7. Jones R, Faqir A, Millett D, Moos K, McHugh S. Bridging and dimensions of sella turcica in subjects treated by surgical-orthodontic means or orthodontics only. Angle Orthod. 2005;75(5):714–8.

    PubMed  Google Scholar 

  8. Muhammed FK, Abdullah AO, Liu Y. Morphology, incidence of bridging, dimensions of sella turcica, and cephalometric standards in three different racial groups. J Craniofac Surg. 2019;30(7):2076–81.

    Article  PubMed  Google Scholar 

  9. Axelsson S, Storhaug K, Kjær I. Post-natal size and morphology of the sella turcica. Longitudinal cephalometric standards for Norwegians between 6 and 21 years of age. Eur J Orthod. 2004;26(6):597–604.

    Article  PubMed  Google Scholar 

  10. Alkofide EA. The shape and size of the sella turcica in skeletal Class I, Class II, and Class III Saudi subjects. Eur J Orthod. 2007;29(5):457–63.

    Article  PubMed  Google Scholar 

  11. Sathyanarayana HP, Kailasam V, Chitharanjan AB. The size and morphology of sella turcica in different skeletal patterns among South Indian population: a lateral cephalometric study. J Indian Orthod Soc. 2013;47(4):266–71.

    Article  Google Scholar 

  12. Shrestha GK, Pokharel PR, Gyawali R, Bhattarai B, Giri J. The morphology and bridging of the sella turcica in adult orthodontic patients. BMC Oral Health. 2018;18(1):1–8.

    Article  Google Scholar 

  13. Zagga A, Ahmed H. Plain radiographic cephalometry of the sella turcica: an overview. Niger J Med. 2008;17(3):333–6.

    Article  PubMed  Google Scholar 

  14. Björk A, Solow B. Measurement on radiographs. J Dent Res. 1962;41(3):672–83.

    Article  PubMed  Google Scholar 

  15. Pancherz H. A cephalometric analysis of skeletal and dental changes contributing to Class II correction in activator treatment. Am J Orthod. 1984;85(2):125–34.

    Article  PubMed  Google Scholar 

  16. Khanagar SB, Al-Ehaideb A, Vishwanathaiah S, Maganur PC, Patil S, Naik S, et al. Scope and performance of artificial intelligence technology in orthodontic diagnosis, treatment planning, and clinical decision-making—a systematic review. J Dent Sci. 2021;16(1):482–92.

    Article  PubMed  Google Scholar 

  17. Xia J, Qi F, Yuan W, Wang D, Qiu W, Sun Y, et al., editors. Computer aided simulation system for orthognathic surgery. In: Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems; 1995. https://doi.org/10.1109/ICSIGP.1996.567341.

  18. Mosleh MAA, Baba MS, Malek S, Almaktari RA. Ceph-X: development and evaluation of 2D cephalometric system. BMC Bioinform. 2016;17(19):193–201.

    Google Scholar 

  19. Frosio I, Borghese NA, editors. Real time enhancement of cephalometric radiographies. In: 3rd Proc IEEE Int Symp Biomed Imaging: Nano to Macro; 2006. https://doi.org/10.1109/ISBI.2006.1625082.

  20. Mosleh MA, Baba MS, Himazian N, AL-Makramani BM, editors. An image processing system for cephalometric analysis and measurements. In: 2008 International Symposium on Information Technology; 2008. https://doi.org/10.1109/ITSIM.2008.4631953.

  21. Yue W, Yin D, Li C, Wang G, Xu T, editors. Locating large-scale craniofacial feature points on X-ray images for automated cephalometric analysis. In: IEEE International Conference on Image Processing; 2005. https://doi.org/10.1109/ICIP.2005.1530288.

  22. Cardillo J, Sid-Ahmed MA. An image processing system for locating craniofacial landmarks. IEEE Trans Med Imaging. 1994;13(2):275–89.

    Article  PubMed  Google Scholar 

  23. El-Feghi I, Sid-Ahmed MA, Ahmadi M. Automatic localization of craniofacial landmarks for assisted cephalometry. Pattern Recogn. 2004;37(3):609–21.

    Article  Google Scholar 

  24. Hassan B, van der Stelt P, Sanderink G. Accuracy of three-dimensional measurements obtained from cone beam computed tomography surface-rendered images for cephalometric analysis: influence of patient scanning position. Eur J Orthod. 2009;31(2):129–34.

    Article  PubMed  Google Scholar 

  25. Swennen GR, Schutyser F. Three-dimensional cephalometry: spiral multi-slice vs cone-beam computed tomography. Am J Orthod Dentofacial Orthop. 2006;130(3):410–6.

    Article  PubMed  Google Scholar 

  26. Lagravère MO, Carey J, Toogood RW, Major PW. Three-dimensional accuracy of measurements made with software on cone-beam computed tomography images. Am J Orthod Dentofacial Orthop. 2008;134(1):112–6.

    Article  PubMed  Google Scholar 

  27. Ongkosuwito E, Katsaros C, Van’t Hof M, Bodegom J, Kuijpers-Jagtman A. The reproducibility of cephalometric measurements: a comparison of analogue and digital methods. Eur J Orthod. 2002;24(6):655–65.

    Article  PubMed  Google Scholar 

  28. Sayinsu K, Isik F, Trakyali G, Arun T. An evaluation of the errors in cephalometric measurements on scanned cephalometric images and conventional tracings. Eur J Orthod. 2007;29(1):105–8.

    Article  PubMed  Google Scholar 

  29. Zhang L, Luo Z, Chai R, Arefan D, Sumkin J, Wu S, editors. Deep-learning method for tumor segmentation in breast DCE-MRI. In: Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications; 2019: SPIE.

  30. Zhang L, Arefan D, Guo Y, Wu S, editors. Fully automated tumor localization and segmentation in breast DCEMRI using deep learning and kinetic prior. In: Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications; 2020: International Society for Optics and Photonics.

  31. Zhang L, Mohamed AA, Chai R, Guo Y, Zheng B, Wu S. Automated deep learning method for whole-breast segmentation in diffusion-weighted breast MRI. J Magn Reson Imaging. 2020;51(2):635–43.

    Article  PubMed  Google Scholar 

  32. Celik E, Polat-Ozsoy O, Toygar Memikoglu TU. Comparison of cephalometric measurements with digital versus conventional cephalometric analysis. Eur J Orthod. 2009;31(3):241–6.

    Article  PubMed  Google Scholar 

  33. Kassani SH, Kassani PH, Wesolowski MJ, Schneider KA, Deters R. Classification of histopathological biopsy images using ensemble of deep learning networks. In: Proceedings of the 29th Annual International Conference on Computer Science and Software Engineering; 2019. p. 92–9.

  34. Kharel N, Alsadoon A, Prasad P, Elchouemi A, editors. Early diagnosis of breast cancer using contrast limited adaptive histogram equalization (CLAHE) and Morphology methods. In: 2017 8th International Conference on Information and Communication Systems (ICICS); 2017. https://doi.org/10.1109/IACS.2017.7921957.

  35. Makandar A, Halalli B. Breast cancer image enhancement using median filter and CLAHE. Int J Sci Eng Res. 2015;6(4):462–5.

    Google Scholar 

  36. Asnaoui KE, Chawki Y, Idri A. Automated methods for detection and classification pneumonia based on x-ray images using deep learning. arXiv preprint http://arxiv.org/abs/200314363. 2020. https://doi.org/10.1007/978-3-030-74575-2_14.

  37. Ronneberger O, Fischer P, Brox T, editors. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Med Image Comput Comput Assist Interv; 2015. https://doi.org/10.1007/978-3-319-24574-4_28.

  38. LeClerc AJ, Heilenkötter N, Otero Baguer D, Hauberg-Lotte L, Boskamp T, Hetzer S, et al. Deeply supervised UNet for semantic segmentation to assist dermatopathological assessment of basal cell carcinoma. J Imaging. 2021;7(4):71.

    Article  Google Scholar 

  39. Kingma D, Ba J, editors. ADAM: A method for stochastic optimization. In: 3rd International Conference on Learning Representations. Conference Track Proceedings; 2015.

Download references

Acknowledgements

The data was provided by the Oral Health Sciences Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh.

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, 201002, India

    Kaushlesh Singh Shakya

  2. CSIR-Central Scientific Instruments Organisation, Chandigarh, 160030, India

    Kaushlesh Singh Shakya & Amit Laddi

  3. Oral Health Sciences Centre, PGIMER, Chandigarh, 160012, India

    Manojkumar Jaiswal

Authors
  1. Kaushlesh Singh Shakya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Amit Laddi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Manojkumar Jaiswal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Manojkumar Jaiswal.

Ethics declarations

Conflict of interest

The authors refuse to have any potential conflicts of interest in the current work.

Ethics approval

Ethical approval was obtained from the Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh Institutional Ethics Committee (IEC-09/2021-2119). Furthermore, this study was conducted with approval no: PGI/IEC/2021/001488. ‘This article does not contain any studies with human or animal subjects performed by the any of the authors.’

Informed consent

Not applicable.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shakya, K.S., Laddi, A. & Jaiswal, M. Automated methods for sella turcica segmentation on cephalometric radiographic data using deep learning (CNN) techniques. Oral Radiol 39, 248–265 (2023). https://doi.org/10.1007/s11282-022-00629-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11282-022-00629-8

Keywords

Search

Navigation