EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Deep learning-based artefact reduction in low-dose dental cone beam computed tomography with high-attenuation materials

Hyoung Suk Park, Kiwan Jeon, J K Seo iD

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · 2025

DOI: 10.1098/rsta.2024.0045 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2025. Verfasst von Hyoung Suk Park und 2 weiteren Autor:innen. Beteiligte Einrichtung: National Institute for Mathematical Sciences, Daejeon, Republic of Korea. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Deep Learning, Artifacts, Radiography, Dental. Die Arbeit nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper examines the current challenges in computed tomography (CT), with a critical exploration of existing methodologies from a mathematical perspective. Specifically, it aims to identify research directions to enhance image quality in low-dose, cost-effective cone beam CT (CBCT) systems, which have recently gained widespread use in general dental clinics. Dental CBCT offers a substantial cost advantage over standard medical CT, making it affordable for local dental practices; however, this affordability brings significant challenges related to image quality degradation, further complicated by the presence of metallic implants, which are particularly common in older patients. This paper investigates metal-induced artefacts stemming from mismatches in the forward model used in conventional reconstruction methods and explains an alternative approach that bypasses the traditional Radon transform model. Additionally, it examines both the potential and limitations of deep learning-based methods in tackling these challenges, offering insights into their effectiveness in improving image quality in low-dose dental CBCT. This article is part of the theme issue ‘Frontiers of applied inverse problems in science and engineering’.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyDeep LearningArtifactsRadiography, DentalHumansRadiation DosageImage Processing, Computer-AssistedRadiographic Image Interpretation, Computer-Assisted

Stichwörter der Autor:innen

CBCTcomputed tomographydeep learningimplicit neural representationmetal artefact reduction

Autor:innen und Institutionen

  • National Institute for Mathematical Sciences, Daejeon, Republic of Korea.
  • School of Mathematics and Computing (Computational Science and Engineering), Yonsei University, Seodaemun-gu, Seoul, Republic of Korea.

ORCID-Profile: J K Seo

Zitieren

APA

Park, H. S., Jeon, K., & Seo, J. K. (2025). Deep learning-based artefact reduction in low-dose dental cone beam computed tomography with high-attenuation materials. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. https://doi.org/10.1098/rsta.2024.0045

Vancouver

Park HS, Jeon K, Seo JK. Deep learning-based artefact reduction in low-dose dental cone beam computed tomography with high-attenuation materials. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2025. doi:10.1098/rsta.2024.0045

BibTeX
@article{Park2025,
  author = {Park, Hyoung Suk and Jeon, Kiwan and Seo, J K},
  title = {Deep learning-based artefact reduction in low-dose dental cone beam computed tomography with high-attenuation materials},
  journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
  year = {2025},
  doi = {10.1098/rsta.2024.0045}
}
Kostenlos starten →