EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development and evaluation of a deep learning model to reduce exomass-related metal artefacts in cone-beam CT: an ex vivo study using porcine mandibles

Matheus L Oliveira iD, Susanne Schaub iD, Dorothea Dagassan-Berndt iD, Florentin Bieder iD, Philippe C Cattin iD, Michael M Bornstein iD

Dentomaxillofacial Radiology · 2025

DOI: 10.1093/dmfr/twae062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, 2025. Verfasst von Matheus L Oliveira und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, 13414-903, Brazil. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Artifacts, Mandible, Deep Learning. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: São Paulo Research Foundation, Swiss Association of Dentomaxillofacial Radiology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and evaluate a deep learning (DL) model to reduce metal artefacts originating from the exomass in cone-beam CT (CBCT) of the jaws.

Methods

Five porcine mandibles, each featuring six tubes filled with a radiopaque solution, were scanned using four CBCT units before and after the incremental insertion of up to three titanium, titanium-zirconium, and zirconia dental implants in the exomass of a small field of view. A conditional denoising diffusion probabilistic model, using DL techniques, was employed to correct axial images from exomass-related metal artefacts across the CBCT units and implant scenarios. Three examiners independently scored the image quality of all datasets, including those without an implant (ground truth), with implants in the exomass (original), and DL-generated ones. Quantitative analysis compared contrast-to-noise ratio (CNR) to validate artefact reduction using repeated measures analysis of variance in a factorial design followed by Tukey test (α = .05).

Results

The visualisation of the hard tissues and overall image quality was reduced in the original and increased in the DL-generated images. The score variation observed in the original images was not observed in the DL-generated images, which generally scored higher than the original images. DL-generated images revealed significantly greater CNR than both the ground truth and their corresponding original images, regardless of the material and quantity of dental implants and the CBCT unit (P < .05). Original images revealed significantly lower CNR than the ground truth (P < .05).

Conclusions

The developed DL model using porcine mandibles demonstrated promising performance in correcting exomass-related metal artefacts in CBCT, serving as a proof-of-principle for future applications of this approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyArtifactsMandibleDeep LearningDental ImplantsMetalsAnimalsSwine

Stichwörter der Autor:innen

artefactsartificial intelligencecone-beam CTdeep learningdental implants

Substanzen

Dental ImplantsMetals

Autor:innen und Institutionen

  • Department of Oral Diagnosis, Division of Oral Radiology, Piracicaba Dental School, University of Campinas, Piracicaba, 13414-903, Brazil.
  • Department of Oral Health & Medicine,University Center for Dental Medicine Basel UZB, University of Basel, Basel, 4058, Switzerland.
  • Department of Biomedical Engineering, Faculty of Medicine, University of Basel, Allschwil, 4123, Switzerland.
  • Center for Dental Imaging, University Center for Dental Medicine Basel UZB, University of Basel, Basel, 4058, Switzerland.

ORCID-Profile: Matheus L Oliveira, Susanne Schaub, Dorothea Dagassan-Berndt, Florentin Bieder, Philippe C Cattin, Michael M Bornstein

Förderung

  • São Paulo Research Foundation
  • Swiss Association of Dentomaxillofacial Radiology

Zitieren

APA

Oliveira, M. L., Schaub, S., Dagassan-Berndt, D., Bieder, F., Cattin, P. C., & Bornstein, M. M. (2025). Development and evaluation of a deep learning model to reduce exomass-related metal artefacts in cone-beam CT: an ex vivo study using porcine mandibles. Dentomaxillofacial Radiology. https://doi.org/10.1093/dmfr/twae062

Vancouver

Oliveira ML, Schaub S, Dagassan-Berndt D, Bieder F, Cattin PC, Bornstein MM. Development and evaluation of a deep learning model to reduce exomass-related metal artefacts in cone-beam CT: an ex vivo study using porcine mandibles. Dentomaxillofacial Radiology. 2025. doi:10.1093/dmfr/twae062

BibTeX
@article{Oliveira2025,
  author = {Oliveira, Matheus L and Schaub, Susanne and Dagassan-Berndt, Dorothea and Bieder, Florentin and Cattin, Philippe C and Bornstein, Michael M},
  title = {Development and evaluation of a deep learning model to reduce exomass-related metal artefacts in cone-beam CT: an ex vivo study using porcine mandibles},
  journal = {Dentomaxillofacial Radiology},
  year = {2025},
  doi = {10.1093/dmfr/twae062}
}
Kostenlos starten →