EUVIMEDEUVIMED entdecken
Validierungsstudie

Analysis of the generalizability of an artificial intelligence-based software for tomographic segmentation of posterior teeth—an external validation study

Erielma Lomba Dias Julião iD, Gabriel Cunha Adiverci iD, Fernanda Bulhões Fagundes iD, André Ferreira Leite iD, Frederico Sampaio Neves iD, Deborah Queiroz de Freitas iD, Rocharles Cavalcante Fontenele iD, Reinhilde Jacobs iD, Francisco Haiter-Neto iD, Sergio Lins de-Azevedo-Vaz iD

Dentomaxillofacial Radiology · 01.07.2026 · 55 (5) · 508-519

DOI: 10.1093/dmfr/twag018 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 08.04.2026. Verfasst von Erielma Lomba Dias Julião und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, SP, 13414-903, Brazil. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Artificial Intelligence, Software, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior, Foundation for Research and Innovation Support of Espírito Santo (FAPES), The Brazilian National Council for Scientific and Technological Development (CNPq).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To evaluate the generalizability of an artificial intelligence (AI)-based software for automated segmentation of posterior teeth in cone beam CT (CBCT) scans and to identify the variables that influence the need for refinement of automatic segmentations (AS).

Methods

A total of 190 scans from 190 patients, acquired using 5 CBCT systems were imported into the Virtual Patient Creator (Relu, Leuven, Belgium) for AS. Two dental surgeons qualitatively assessed the segmentations of posterior teeth and refined those requiring correction. Manual segmentation (MS) of 20% of the sample was performed using Mimics software (Materialise, Leuven, Belgium). Performance was analyzed through voxel-by-voxel and surface-based comparisons, in addition to the evaluation of time efficiency. Associations between independent variables and the need for refinement were analyzed using mixed logistic regression (α = 5%).

Results

Among the 1005 teeth evaluated, only 12.7% required refinement. Age and the presence of brackets were significant predictors (P < .001). The unexplained variability was attributed mainly to the patients, with minimal influence from the CBCT systems. AS showed agreement with refined segmentations (R-AI) (IoU: 0.93-0.96; DSC: 0.96-0.98; precision: 0.99-1.00; recall: 0.94-0.96; accuracy: 0.98-0.99; MAD: 0.05-0.07; RMSE: 0.06-0.14) and excellent performance compared to MS (IoU: 0.94; DSC: 0.97; precision: 0.98; recall: 0.95; accuracy: 0.98; MAD: 0.05; RMSE: 0.09). AS was more time-efficient (12 [AIQ: 5]) compared to R-AI (202 [AIQ: 334]) and MS (1726 [AIQ: 863]).

Conclusion

The AI-based software demonstrated high accuracy and generalizability for automated segmentation of posterior teeth in CBCT scans.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyArtificial IntelligenceSoftwareRadiographic Image Interpretation, Computer-AssistedHumansFemaleMaleAdultMiddle AgedReproducibility of ResultsAgedAdolescent

Stichwörter der Autor:innen

artificial intelligencecone beam CTconvolutional neural networkdeep learningtooth

Autor:innen und Institutionen

  • Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, SP, 13414-903, Brazil.
  • Dental Sciences Graduate Program, Federal University of Espírito Santo, Vitória, ES, 29047-105, Brazil.
  • Department of Dentistry, University of Brasília, Brasília, DF, 70910-900, Brazil.
  • Division of Oral Radiology, Department of Propaedeutics and Integrated Clinic, School of Dentistry, Federal University of Bahia, Salvador, BA, 40110-150, Brazil.
  • Department of Stomatology, Public Oral Health and Forensic Dentistry, Division of Oral Radiology, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, 14040-904, Brazil.
  • OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven & Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven 3000, Belgium.

ORCID-Profile: Erielma Lomba Dias Julião, Gabriel Cunha Adiverci, Fernanda Bulhões Fagundes, André Ferreira Leite, Frederico Sampaio Neves, Deborah Queiroz de Freitas, Rocharles Cavalcante Fontenele, Reinhilde Jacobs, Francisco Haiter-Neto, Sergio Lins de-Azevedo-Vaz

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nivel Superior
  • Foundation for Research and Innovation Support of Espírito Santo (FAPES)
  • The Brazilian National Council for Scientific and Technological Development (CNPq)

Zitieren

APA

Julião, E. L. D., Adiverci, G. C., Fagundes, F. B., Leite, A. F., Neves, F. S., Queiroz de Freitas, D., Fontenele, R. C., Jacobs, R., Haiter-Neto, F., & de-Azevedo-Vaz, S. L. (2026). Analysis of the generalizability of an artificial intelligence-based software for tomographic segmentation of posterior teeth—an external validation study. Dentomaxillofacial Radiology, 55(5), 508-519. https://doi.org/10.1093/dmfr/twag018

Vancouver

Julião ELD, Adiverci GC, Fagundes FB, Leite AF, Neves FS, Queiroz de Freitas D, et al. Analysis of the generalizability of an artificial intelligence-based software for tomographic segmentation of posterior teeth—an external validation study. Dentomaxillofacial Radiology. 2026;55(5):508-519. doi:10.1093/dmfr/twag018

BibTeX
@article{Julio2026,
  author = {Julião, Erielma Lomba Dias and Adiverci, Gabriel Cunha and Fagundes, Fernanda Bulhões and Leite, André Ferreira and Neves, Frederico Sampaio and Queiroz de Freitas, Deborah and Fontenele, Rocharles Cavalcante and Jacobs, Reinhilde and Haiter-Neto, Francisco and de-Azevedo-Vaz, Sergio Lins},
  title = {Analysis of the generalizability of an artificial intelligence-based software for tomographic segmentation of posterior teeth—an external validation study},
  journal = {Dentomaxillofacial Radiology},
  year = {2026},
  volume = {55},
  number = {5},
  pages = {508--519},
  doi = {10.1093/dmfr/twag018}
}
Kostenlos starten →