EUVIMEDSkopri EUVIMED
Crossref

Adaptive multi‐resolution hash‐encoding framework for INR‐based dental CBCT reconstruction with truncated FOV

Hyoung Suk Park, Kiwan Jeon

Medical Physics · 2026

DOI: 10.1002/mp.70226 ↗

At a glance

Journal article in Medical Physics, 2026. Written by Hyoung Suk Park and 1 co-authors. Institution: National Institute for Mathematical Sciences, Daejeon, Republic of Korea. Major MEDLINE topics: Cone-Beam Computed Tomography, Image Processing, Computer-Assisted, Neural Networks, Computer. 35 references. Funded by: Ministry of Science and ICT, South Korea, National Research Foundation of Korea.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Implicit neural representation (INR), particularly in combination with hash encoding, has recently emerged as a promising approach for computed tomography (CT) image reconstruction. However, directly applying INR techniques to 3D dental cone‐beam computed tomography (CBCT) with a truncated field of view (FOV) is challenging. During the training process, if the FOV does not fully encompass the patient's head, a discrepancy arises between the measured projections and the forward projections computed within the truncated domain. This mismatch leads the network to estimate attenuation values inaccurately, producing severe artifacts in the reconstructed images.

Purpose

This study aims to develop a computationally efficient INR‐based reconstruction framework that leverages multi‐resolution hash encoding for 3D dental CBCT with a truncated FOV.

Methods

To mitigate truncation artifacts, we train the network over an expanded reconstruction domain that fully encompasses the patient's head. For computational efficiency, we adopt an adaptive training strategy that uses a multi‐resolution grid: finer resolution levels and denser sampling inside the truncated FOV, and coarser resolution levels with sparser sampling outside. To maintain consistent input dimensionality of the network across spatially varying resolutions, we introduce an adaptive hash encoder that selectively activates the lower‐level features of the hash hierarchy for points outside the truncated FOV.

Results

The proposed method with an extended FOV effectively mitigates truncation artifacts. Compared with a naive domain extension, using fixed resolution levels and a fixed sampling rate, the adaptive strategy reduces computational time by 60% for an image volume of , while preserving the peak signal‐to‐noise ratio (PSNR) within the truncated FOV.

Conclusions

We propose an INR‐based reconstruction framework for 3D dental CBCT with a truncated FOV, effectively reducing truncation artifacts and training cost.

Subjects

MeSH terms (MEDLINE)

Cone-Beam Computed TomographyImage Processing, Computer-AssistedNeural Networks, ComputerHumansImaging, Three-DimensionalArtifacts

Author keywords

dental cone‐beam computed tomographyimplicit neural representationtruncated field of view

Authors and institutions

  • National Institute for Mathematical Sciences, Daejeon, Republic of Korea.

Funding

  • Ministry of Science and ICT, South Korea
  • National Research Foundation of Korea

Cite

APA

Park, H. S., & Jeon, K. (2026). Adaptive multi‐resolution hash‐encoding framework for INR‐based dental CBCT reconstruction with truncated FOV. Medical Physics. https://doi.org/10.1002/mp.70226

Vancouver

Park HS, Jeon K. Adaptive multi‐resolution hash‐encoding framework for INR‐based dental CBCT reconstruction with truncated FOV. Medical Physics. 2026. doi:10.1002/mp.70226

BibTeX
@article{Park2026,
  author = {Park, Hyoung Suk and Jeon, Kiwan},
  title = {Adaptive multi‐resolution hash‐encoding framework for INR‐based dental CBCT reconstruction with truncated FOV},
  journal = {Medical Physics},
  year = {2026},
  doi = {10.1002/mp.70226}
}
Start for free →