EUVIMEDOpdag EUVIMED
Crossref

High-resolution parallel-translation CT reconstruction based on a patch-based adaptive-regularization-guided diffusion model

Xuanheng Li iD, Mingze Lv, Jiahong Liu, Yu He, Yi Sun

Optics Express · 2026-11-16 · 34 (23) · 44233

DOI: 10.1364/oe.613003 ↗

At a glance

Journal article in Optics Express, published online on 2026-11-09. Written by Xuanheng Li and 4 co-authors. Institution: School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China. 33 references. Funded by: National Natural Science Foundation of China, Major Science and Technology Project in Liaoning Province, Liaoning Huanghai Laboratory Foundation.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Computed tomography (CT) is an effective technique for industrial non-destructive testing (NDT). However, conventional rotational CT is difficult to apply to the scanning and reconstruction of large plate-like objects, while its mechanical system is also relatively complex. In response to these limitations, parallel translation CT (PTCT) has been introduced. Nevertheless, due to its limited scanning range, PTCT acquires incomplete projection data, which leads to aliasing artifacts and makes accurate reconstruction challenging. To address these issues and achieve high-resolution PTCT reconstruction, this paper proposes a patch-based adaptive-regularization-guided diffusion model. Specifically, an initial estimate obtained by the Simultaneous Iterative Reconstruction Technique (SIRT) is first employed, introducing structural prior information into the reconstruction process. Based on this, a split-and-reassemble denoising module (SRDM) is designed to perform patch-wise reconstruction, where positional encoding is incorporated as conditional guidance to enhance the representation of local structural details. Furthermore, an adaptive-regularization-based correction module (ARCM) is introduced, in which seam-based and mask-based regularization terms are adaptively adjusted according to the denoising stage to support global structural recovery and improve local structural continuity. To evaluate the proposed method, a PCB dataset containing samples with defect structures is constructed. The results demonstrate that the proposed method achieves reliable performance in global reconstruction while effectively recovering fine structural details within defect regions.

Authors and institutions

  • School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China.

ORCID profiles: Xuanheng Li

Funding

  • National Natural Science Foundation of China
  • Major Science and Technology Project in Liaoning Province
  • Liaoning Huanghai Laboratory Foundation
  • Major Project of Dalian Science and Technology Innovation Foundation
  • Xiaomi Young Talents Program

Cite

APA

Li, X., Lv, M., Liu, J., He, Y., & Sun, Y. (2026). High-resolution parallel-translation CT reconstruction based on a patch-based adaptive-regularization-guided diffusion model. Optics Express, 34(23), 44233. https://doi.org/10.1364/oe.613003

Vancouver

Li X, Lv M, Liu J, He Y, Sun Y. High-resolution parallel-translation CT reconstruction based on a patch-based adaptive-regularization-guided diffusion model. Optics Express. 2026;34(23):44233. doi:10.1364/oe.613003

BibTeX
@article{Li2026,
  author = {Li, Xuanheng and Lv, Mingze and Liu, Jiahong and He, Yu and Sun, Yi},
  title = {High-resolution parallel-translation CT reconstruction based on a patch-based adaptive-regularization-guided diffusion model},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {23},
  pages = {44233},
  doi = {10.1364/oe.613003}
}
Start for free →