EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Automated Cone Beam Computed Tomography Segmentation of Multiple Impacted Teeth With or Without Association to Rare Diseases: Evaluation of Four Deep Learning‐Based Methods

Eloi Sinard, Laurent Gajny, Muriel de La Dure-Molla, Rufino Felizardo iD, Gauthier Dot iD

Orthodontics & Craniofacial Research · 2025-06 · 28 (3) · 433-440

DOI: 10.1111/ocr.12890 ↗

At a glance

Journal article in Orthodontics & Craniofacial Research, published online on 2025-01-02. Written by Eloi Sinard and 4 co-authors. Institution: UFR Odontologie, Université Paris Cité, Paris, France. Major MEDLINE topics: Cone-Beam Computed Tomography, Deep Learning, Tooth, Impacted, Image Processing, Computer-Assisted. Cited 16 times so far (Crossref); 27 references. The full text is freely available (open access, CC BY 4.0). Funded by: Fédération Française d'Orthodontie.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Objective

To assess the accuracy of three commercially available and one open‐source deep learning (DL) solutions for automatic tooth segmentation in cone beam computed tomography (CBCT) images of patients with multiple dental impactions. Materials and Methods Twenty patients (20 CBCT scans) were selected from a retrospective cohort of individuals with multiple dental impactions. For each CBCT scan, one reference segmentation and four DL segmentations of the maxillary and mandibular teeth were obtained. Reference segmentations were generated by experts using a semi‐automatic process. DL segmentations were automatically generated according to the manufacturer's instructions. Quantitative and qualitative evaluations of each DL segmentation were performed by comparing it with expert‐generated segmentation. The quantitative metrics used were Dice similarity coefficient (DSC) and the normalized surface distance (NSD).

Results

The patients had an average of 12 retained teeth, with 12 of them diagnosed with a rare disease. DSC values ranged from 88.5% ± 3.2% to 95.6% ± 1.2%, and NSD values ranged from 95.3% ± 2.7% to 97.4% ± 6.5%. The number of completely unsegmented teeth ranged from 1 (0.1%) to 41 (6.0%). Two solutions (Diagnocat and DentalSegmentator) outperformed the others across all tested parameters.

Conclusion

All the tested methods showed a mean NSD of approximately 95%, proving their overall efficiency for tooth segmentation. The accuracy of the methods varied among the four tested solutions owing to the presence of impacted teeth in our CBCT scans. DL solutions are evolving rapidly, and their future performance cannot be predicted based on our results.

Subjects

MeSH terms (MEDLINE)

Cone-Beam Computed TomographyDeep LearningTooth, ImpactedImage Processing, Computer-AssistedHumansRetrospective StudiesMaleFemaleAdolescentAdultYoung Adult

Author keywords

computer‐assistedcone beam computed tomographydeep learningimpactedorthodonticssurgerytooth

Authors and institutions

  • UFR Odontologie, Université Paris Cité, Paris, France.
  • Service de Medecine Bucco-Dentaire, AP-HP, Hopital Pitie Salpetriere, Paris, France.
  • Institut de Biomecanique Humaine Georges Charpak, Arts et Metiers Institute of Technology, Paris, France.
  • Reference Center for Oral and Dental Rare Disease, ORARES, AP-HP, Rothschild Hospital, Paris, France.

ORCID profiles: Rufino Felizardo, Gauthier Dot

Funding

  • Fédération Française d'Orthodontie

Cite

APA

Sinard, E., Gajny, L., de La Dure-Molla, M., Felizardo, R., & Dot, G. (2025). Automated Cone Beam Computed Tomography Segmentation of Multiple Impacted Teeth With or Without Association to Rare Diseases: Evaluation of Four Deep Learning‐Based Methods. Orthodontics & Craniofacial Research, 28(3), 433-440. https://doi.org/10.1111/ocr.12890

Vancouver

Sinard E, Gajny L, de La Dure-Molla M, Felizardo R, Dot G. Automated Cone Beam Computed Tomography Segmentation of Multiple Impacted Teeth With or Without Association to Rare Diseases: Evaluation of Four Deep Learning‐Based Methods. Orthodontics & Craniofacial Research. 2025;28(3):433-440. doi:10.1111/ocr.12890

BibTeX
@article{Sinard2025,
  author = {Sinard, Eloi and Gajny, Laurent and de La Dure-Molla, Muriel and Felizardo, Rufino and Dot, Gauthier},
  title = {Automated Cone Beam Computed Tomography Segmentation of Multiple Impacted Teeth With or Without Association to Rare Diseases: Evaluation of Four Deep Learning‐Based Methods},
  journal = {Orthodontics & Craniofacial Research},
  year = {2025},
  volume = {28},
  number = {3},
  pages = {433--440},
  doi = {10.1111/ocr.12890}
}
Start for free →