EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Segmenting beyond the imaging data: creation of anatomically valid edentulous mandibular geometries for surgical planning using artificial intelligence

Stefan Raith, Tobias Pankert, Srikrishna Jaganathan, Kristina Pankert, Hyun Lee, Florian Peters, Frank Hölzle, Ali Modabber

Clinical Oral Investigations · 2025

DOI: 10.1007/s00784-025-06471-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical Oral Investigations, 2025. Verfasst von Stefan Raith und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral and Maxillofacial Surgery, RWTH Aachen University Hospital, Pauwelsstraße 30, 52074, Aachen, Germany. sraith@ukaachen.de. Hauptthemen laut MEDLINE: Artificial Intelligence, Tomography, X-Ray Computed, Mandible, Jaw, Edentulous. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitätsklinikum RWTH Aachen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and objectives Mandibular reconstruction following continuity resection due to tumor ablation or osteonecrosis remains a significant challenge in maxillofacial surgery. Virtual surgical planning (VSP) relies on accurate segmentation of the mandible, yet existing AI models typically include teeth, making them unsuitable for planning of autologous transplants dimensions aiming for reconstructing edentulous mandibles optimized for dental implant insertion. This study investigates the feasibility of using deep learning-based segmentation to generate anatomically valid, toothless mandibles from dentate CT scans, ensuring geometric accuracy for reconstructive planning.

Methods

A two-stage convolutional neural network (CNN) approach was employed to segment mandibles from computed tomography (CT) data. The dataset ( n = 246) included dentate, partially dentate, and edentulous mandibles. Ground truth segmentations were manually modified to create Class III (moderate alveolar atrophy) and Class V (severe atrophy) models, representing different degrees of post-extraction bone resorption. The AI models were trained on the original (O), Class III (Cl. III), and Class V (Cl. V) datasets, and performance was evaluated using Dice similarity coefficients (DSC), average surface distance, and automatically detected anatomical curvatures.

Results

AI-generated segmentations demonstrated high anatomical accuracy across all models, with mean DSCs exceeding 0.94. Accuracy was highest in edentulous mandibles (DSC 0.96 ± 0.014) and slightly lower in fully dentate cases, particularly for Class V modifications (DSC 0.936 ± 0.030). The caudolateral curve remained consistent, confirming that baseline mandibular geometry was preserved despite alveolar ridge modifications.

Conclusions

This study confirms that AI-driven segmentation can generate anatomically valid edentulous mandibles from dentate CT scans with high accuracy. The innovation of the work is the precise adaptation of alveolar ridge geometry, making it a valuable tool for patient-specific virtual surgical planning in mandibular reconstruction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceTomography, X-Ray ComputedMandibleJaw, EdentulousPatient Care PlanningMandibular ReconstructionHumansNeural Networks, ComputerDeep LearningMaleFeasibility StudiesFemaleSurgery, Computer-Assisted

Stichwörter der Autor:innen

Computed tomographyConvolutional neural networksDeep learningMandibleMedical image analysisReconstructionSegmentationVirtual surgical planning

Autor:innen und Institutionen

  • Department of Oral and Maxillofacial Surgery, RWTH Aachen University Hospital, Pauwelsstraße 30, 52074, Aachen, Germany. sraith@ukaachen.de.
  • Inzipio GmbH, Krantzstr. 7 Building 80, 52070, Aachen, Germany. sraith@ukaachen.de.
  • Department of Oral and Maxillofacial Surgery, RWTH Aachen University Hospital, Pauwelsstraße 30, 52074, Aachen, Germany.
  • Inzipio GmbH, Krantzstr. 7 Building 80, 52070, Aachen, Germany.

Förderung

  • Universitätsklinikum RWTH Aachen

Zitieren

APA

Raith, S., Pankert, T., Jaganathan, S., Pankert, K., Lee, H., Peters, F., Hölzle, F., & Modabber, A. (2025). Segmenting beyond the imaging data: creation of anatomically valid edentulous mandibular geometries for surgical planning using artificial intelligence. Clinical Oral Investigations. https://doi.org/10.1007/s00784-025-06471-6

Vancouver

Raith S, Pankert T, Jaganathan S, Pankert K, Lee H, Peters F, et al. Segmenting beyond the imaging data: creation of anatomically valid edentulous mandibular geometries for surgical planning using artificial intelligence. Clinical Oral Investigations. 2025. doi:10.1007/s00784-025-06471-6

BibTeX
@article{Raith2025,
  author = {Raith, Stefan and Pankert, Tobias and Jaganathan, Srikrishna and Pankert, Kristina and Lee, Hyun and Peters, Florian and Hölzle, Frank and Modabber, Ali},
  title = {Segmenting beyond the imaging data: creation of anatomically valid edentulous mandibular geometries for surgical planning using artificial intelligence},
  journal = {Clinical Oral Investigations},
  year = {2025},
  doi = {10.1007/s00784-025-06471-6}
}
Kostenlos starten →