EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Artificial Intelligence Segmentation Errors in Implant Planning Software Programs: An Overview

Ghida Lawand iD, Luiz Gonzaga iD, Julien Issa, Marta Revilla-Leon iD, Hani Tohme iD, Adam Saleh, William Martin

Clinical Implant Dentistry and Related Research · 2025

DOI: 10.1111/cid.70095 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Clinical Implant Dentistry and Related Research, 2025. Verfasst von Ghida Lawand und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for Implant Dentistry, Department of Oral and Maxillofacial Surgery, College of Dentistry, University of Florida, Gainesville, Florida, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Software, Surgery, Computer-Assisted, Dental Implantation, Endosseous. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 72 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Static computer‐assisted implant surgery (s‐CAIS) utilizes 3D imaging data to guide implant placement with high precision. Accurate segmentation of CBCT and intraoral scan data is crucial to creating reliable anatomical models. While AI‐driven segmentation has emerged as a promising solution to reduce manual workload, its performance is hindered by technical and algorithmic limitations.

Objective

To evaluate the accuracy and limitations of AI‐based segmentation in dental implant planning software and to identify common sources of segmentation errors, their clinical implications, and strategies for mitigation.

Methods

This work is framed as a narrative literature review and educational practice overview. Observations on software functionality were based on direct use and exploration of varying implant planning software programs. This was conducted to qualitatively describe common segmentation error patterns (boundary errors, over‐/under‐segmentation, misidentification, and partial volume effects), and demonstrate editing functionalities across four implant planning systems (coDiagnostiX, BlueSkyPlan, Atomica, and Relu). These demonstrations are intended for illustrative purposes and do not constitute a formal, reproducible performance comparison.

Results

AI‐based segmentation frequently encounters errors due to imaging artifacts, motion blur, anatomical variability, and algorithmic biases. These errors can lead to inaccurate implant positioning, compromised surgical guide designs, and clinical complications. While advanced methods such as U‐Net, GANs, and SISTR improve segmentation quality, manual intervention remains essential. The effectiveness of AI tools varies significantly across platforms, and limited editing capabilities often hinder error correction.

Conclusion

Despite advances in AI, segmentation errors remain a critical barrier in s‐CAIS workflows. Enhanced imaging protocols, algorithmic refinement, clinician oversight, and regulatory transparency are essential to improve segmentation accuracy and ensure safe, effective digital implant planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceSoftwareSurgery, Computer-AssistedDental Implantation, EndosseousPatient Care PlanningHumansCone-Beam Computed TomographyImaging, Three-DimensionalAlgorithmsDental Implants

Substanzen

Dental Implants

Autor:innen und Institutionen

  • Center for Implant Dentistry, Department of Oral and Maxillofacial Surgery, College of Dentistry, University of Florida, Gainesville, Florida, USA.
  • Department of Oral Radiology & Digital Dentistry, Academic Center for Dentistry Amsterdam (ACTA), University of Amsterdam & Vrije Universiteit Amsterdam, Amsterdam, the Netherlands.
  • Department of Restorative Dentistry, School of Dentistry, University of Washington, Seattle, Washington, USA.
  • Kois Center, Seattle, Washington, USA.
  • Department of Prosthodontics, School of Dental Medicine, Tufts University, Boston, Massachusetts, USA.
  • Department of Digital Dentistry, AI, and Evolving Technologies, College of Dental Medicine, Saint Joseph University of Beirut, Beirut, Lebanon.

ORCID-Profile: Ghida Lawand, Luiz Gonzaga, Marta Revilla-Leon, Hani Tohme

Zitieren

APA

Lawand, G., Gonzaga, L., Issa, J., Revilla-Leon, M., Tohme, H., Saleh, A., & Martin, W. (2025). Artificial Intelligence Segmentation Errors in Implant Planning Software Programs: An Overview. Clinical Implant Dentistry and Related Research. https://doi.org/10.1111/cid.70095

Vancouver

Lawand G, Gonzaga L, Issa J, Revilla-Leon M, Tohme H, Saleh A, et al. Artificial Intelligence Segmentation Errors in Implant Planning Software Programs: An Overview. Clinical Implant Dentistry and Related Research. 2025. doi:10.1111/cid.70095

BibTeX
@article{Lawand2025,
  author = {Lawand, Ghida and Gonzaga, Luiz and Issa, Julien and Revilla-Leon, Marta and Tohme, Hani and Saleh, Adam and Martin, William},
  title = {Artificial Intelligence Segmentation Errors in Implant Planning Software Programs: An Overview},
  journal = {Clinical Implant Dentistry and Related Research},
  year = {2025},
  doi = {10.1111/cid.70095}
}
Kostenlos starten →