Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2026 Feb;53(2):e70299.
doi: 10.1002/mp.70299.

Multi-dimensional attention-enhanced reconstruction for sparse-view CBCT

Yuhao Liu  1 , Wan Li  2 , Yiyuan Tao  1 , Tianling Lyu  3 , Yan Xi  4 , Yikun Zhang  1 , Feng Wang  2 , Pengcheng Zhang  5 , Jian Yang  6 , Yang Chen  1
Affiliations

Multi-dimensional attention-enhanced reconstruction for sparse-view CBCT

Yuhao Liu et al. Med Phys. 2026 Feb.

Abstract

Background: Cone-beam computed tomography (CBC T) is a high-resolution 3D imaging modality that has been widely applied clinically. However, it faces limitations due to the lag effect and concerns about radiation dose. While sparse-view CBCT can alleviate these problems by reducing the detector readout frequency and the exposure time, it introduces streak artifacts that can degrade image quality. Recent research has explored techniques for sparse-view CBCT reconstruction. Nevertheless, it remains an ongoing challenge to achieve improved image quality.

Purpose: The purpose of this study is to eliminate the streak artifacts and recover image details with dual-domain deep learning networks.

Methods: This study proposed a Multi-dimensional Attention-Enhanced reconstruction (MAE-Recon) algorithm for sparse-view CBCT. MAE-Recon consists of four key components: a linear interpolation module, a projection domain network, an FDK operator, and an image domain network. Firstly, the linear interpolation module generates an initial full-view projection. Subsequently, the projection domain network predicts high-quality projection data. The FDK operator then reconstructs CBCT images. Finally, the image domain network refines the reconstructed images. Considering the long-range dependency among projections and the information redundancy within features, this study introduces two plug-and-play modules for enhancement.

Results: A real chest dataset and a simulated abdomen dataset were chosen for validation. The RMSE was reduced by 5 × 10 - 5 $5\times 10^{-5}$ mm - 1 ${\rm mm}^{-1}$ and 5.6 × 10 - 5 $5.6\times 10^{-5}$ mm - 1 ${\rm mm}^{-1}$ , respectively, and the SSIM and PSNR scores were improved by 0.066, 0.009, and 4.62 dB, 1.44 dB on the two datasets. An ablation study was also performed. The improved RMSE, SSIM, and PSNR scores illustrate that the modules are practical and efficient.

Conclusions: The MAE-Recon proposed in this study obtains high-quality images in sparse-view CBCT reconstruction, demonstrating the application potential.

Keywords: cone‐beam computed tomography; deep learning; sparse‐view reconstruction.

PubMed Disclaimer

References

REFERENCES

    1. Tomography C. physical principles, clinical applications and quality control. 2009.
    1. Jin‐zhou Z, Shao‐dong L. Review of the application of computed tomography technology in safety inspection domain. CT Theory Appl. 2012;21(1):157‐165.
    1. Martz H, Azevedo S, Brase J, Waltjen K, Schneberk D. Computed tomography systems and their industrial applications. Int J Radiat Appl Instrum Part A. 1990;41(10‐11):943‐961.
    1. Kau C, Richmond S, Palomo J, Hans M. Current products and practice: three‐dimensional cone beam computerized tomography in orthodontics. J. Orthod. 2005;32(4):282‐293.
    1. Alamri HM, Sadrameli M, Alshalhoob MA, Alshehri MA. Applications of CBCT in dental practice: a review of the literature. General dentistry. 2012;60(5):390‐400.

LinkOut - more resources