Comparison of 2D, 2.5D, and 3D landmark localization networks for 3D cephalometry in CT images
Comprehensive experiments demonstrate that the 2.5D network offers an optimal trade-off between computational load and accuracy. These findings highlight the potential for more efficient and reliable 3D cephalometry under limited computational resources.
Authors
- Won-Jin Yi (ORCID: https://orcid.org/0000-0002-5977-6634)
- Min-Suk Heo (ORCID: https://orcid.org/0000-0003-3406-0645)
- Kyung‐Hoe Huh (ORCID: https://orcid.org/0000-0002-8771-0392)
- Jo‐Eun Kim (ORCID: https://orcid.org/0000-0003-0218-5304)
- Seung-Hee Han (ORCID: https://orcid.org/0000-0002-0273-3609)
- Soo-Min Kim (ORCID: https://orcid.org/0000-0003-4834-9941)
- Minjin Kim (ORCID: https://orcid.org/0000-0002-9164-8149)
- Minhyuk Choi
- Sam-Sun Lee
Institutions
- Seoul National University of Science and Technology (KR)
- Seoul National University (KR)
- Kyung Hee University (KR)
- National University College (PR)
- Seoul National University Dental Hospital (KR)
Publication Details
- Journal
- BMC Oral Health
- Published
- 2025-11-26
- DOI
- https://doi.org/10.1186/s12903-025-07189-3
- Primary Topic
- Dental Radiography and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation
- Ministry of Trade, Industry and Energy
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea