EUVIMEDEUVIMED entdecken
Open Access

A multi‐stage deep learning framework for half‐detector truncation and metal artifact reduction in CBCT

Junhyun Ahn, Jongduk Baek

Medical Physics · 2026-08 · 53 (8)

DOI: 10.1002/mp.70604 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 06.08.2026. Verfasst von Junhyun Ahn und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Integrated Technology, Yonsei University, Seoul, South Korea. Hauptthemen laut MEDLINE: Artifacts, Metals, Deep Learning, Cone-Beam Computed Tomography. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Research Foundation of Korea, Institute for Information and communications Technology Promotion.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cone‐beam computed tomography (CBCT) is widely utilized for its high spatial resolution and compact design. However, image quality is often compromised in the half‐detector (HD) geometry, where data truncation arising from the offset detector configuration coexists with metal artifacts caused by metallic implants. These artifacts interact synergistically, leading to severe image degradation that conventional correction methods fail to address.

Purpose

We propose a multi‐stage deep learning framework, HD‐TMAR, to systematically decompose and correct combined truncation and metal artifacts in HD CBCT.

Methods

The proposed framework adopts a multi‐stage restoration strategy comprising three stages: (1) Sinogram Correction, which explicitly isolates the artifact residuals from the projection data and synergizes them with structural prior‐normalized features to systematically suppress global truncation biases and metal artifacts; (2) Merging and Reconstruction, which employs a specialized overlapping patching and selective replacement strategy to accurately reconstruct the truncated regions and metal traces; and (3) Image Refinement, where ImgNet further enhances the reconstructed image to restore fine anatomical textures.

Results

Experiments using realistic simulation datasets demonstrated that the proposed method achieved the highest qualitative fidelity and quantitative metrics compared to previous deep learning MAR methods. The framework effectively suppressed severe artifacts while preserving dental morphology, whereas comparative methods suffered from secondary artifacts or blurring.

Conclusions

HD‐TMAR successfully disentangles complex artifact interactions. By synergizing sinogram‐domain correction with image‐domain refinement, the framework demonstrates promising potential for clinical application in enhancing the diagnostic performance of HD CBCT systems in the presence of metallic implants.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ArtifactsMetalsDeep LearningCone-Beam Computed TomographyImage Processing, Computer-Assisted

Stichwörter der Autor:innen

computed tomography (CT) imagedeep learningdetector offsetmetal artifacts reduction

Substanzen

Metals

Autor:innen und Institutionen

  • School of Integrated Technology, Yonsei University, Seoul, South Korea.
  • Department of Artificial Intelligence, Yonsei University, Seoul, South Korea.
  • BareuneX Imaging Inc., Seoul, South Korea.

Förderung

  • National Research Foundation of Korea
  • Institute for Information and communications Technology Promotion

Zitieren

APA

Ahn, J., & Baek, J. (2026). A multi‐stage deep learning framework for half‐detector truncation and metal artifact reduction in CBCT. Medical Physics, 53(8). https://doi.org/10.1002/mp.70604

Vancouver

Ahn J, Baek J. A multi‐stage deep learning framework for half‐detector truncation and metal artifact reduction in CBCT. Medical Physics. 2026;53(8). doi:10.1002/mp.70604

BibTeX
@article{Ahn2026,
  author = {Ahn, Junhyun and Baek, Jongduk},
  title = {A multi‐stage deep learning framework for half‐detector truncation and metal artifact reduction in CBCT},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {8},
  doi = {10.1002/mp.70604}
}
Kostenlos starten →