EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Automatic landmark identification in cone‐beam computed tomography

Maxime Gillot, Felicia Miranda iD, Baptiste Baquero, Antonio Ruellas, Marcela Gurgel iD, Najla Al Turkestani iD, Luc Anchling, Nathan Hutin, Elizabeth Biggs, Marilia Yatabe iD, Beatriz Paniagua, Jean-Christophe Fillion-Robin und 4 weitere

Orthodontics & Craniofacial Research · 2023

DOI: 10.1111/ocr.12642 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Orthodontics & Craniofacial Research, 2023. Verfasst von Maxime Gillot und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthodontics and Pediatric Dentistry, University of Michigan School of Dentistry, MI, Ann Arbor, USA. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Anatomic Landmarks. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIDCR NIH HHS, American Association of Orthodontists Foundation, National Institute of Dental and Craniofacial Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To present and validate an open‐source fully automated landmark placement (ALICBCT) tool for cone‐beam computed tomography scans. Materials and Methods One hundred and forty‐three large and medium field of view cone‐beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi‐scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position.

Results

Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D‐CBCT scan using a conventional GPU.

Conclusion

The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalAnatomic LandmarksCephalometryReproducibility of ResultsCone-Beam Computed Tomography

Stichwörter der Autor:innen

anatomic landmarksfiducial markersmachine learning

Autor:innen und Institutionen

  • Department of Orthodontics and Pediatric Dentistry, University of Michigan School of Dentistry, MI, Ann Arbor, USA.
  • CPE Lyon, Lyon, France.
  • Department of Orthodontics, Bauru Dental School, University of São Paulo, Bauru, Brazil.
  • Department of Orthodontics and Pediatric Dentistry, School of Dentistry, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil.
  • Department of Restorative and Aesthetic Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah, Saudi Arabia.
  • Kitware Inc., Chapel Hill, NC, USA.

ORCID-Profile: Felicia Miranda, Marcela Gurgel, Najla Al Turkestani, Marilia Yatabe, Jonas Bianchi, Lucia Cevidanes, Juan Carlos Prieto

Förderung

  • NIDCR NIH HHS
  • American Association of Orthodontists Foundation
  • National Institute of Dental and Craniofacial Research

Zitieren

APA

Gillot, M., Miranda, F., Baquero, B., Ruellas, A., Gurgel, M., Al Turkestani, N., Anchling, L., Hutin, N., Biggs, E., Yatabe, M., Paniagua, B., Fillion-Robin, J. C., Allemang, D., Bianchi, J., Cevidanes, L., & Prieto, J. C. (2023). Automatic landmark identification in cone‐beam computed tomography. Orthodontics & Craniofacial Research. https://doi.org/10.1111/ocr.12642

Vancouver

Gillot M, Miranda F, Baquero B, Ruellas A, Gurgel M, Al Turkestani N, et al. Automatic landmark identification in cone‐beam computed tomography. Orthodontics & Craniofacial Research. 2023. doi:10.1111/ocr.12642

BibTeX
@article{Gillot2023,
  author = {Gillot, Maxime and Miranda, Felicia and Baquero, Baptiste and Ruellas, Antonio and Gurgel, Marcela and Al Turkestani, Najla and Anchling, Luc and Hutin, Nathan and Biggs, Elizabeth and Yatabe, Marilia and Paniagua, Beatriz and Fillion-Robin, Jean-Christophe and Allemang, David and Bianchi, Jonas and Cevidanes, Lucia and Prieto, Juan Carlos},
  title = {Automatic landmark identification in cone‐beam computed tomography},
  journal = {Orthodontics & Craniofacial Research},
  year = {2023},
  doi = {10.1111/ocr.12642}
}
Kostenlos starten →