journal article·2025-07-11Open access

A Hybrid Framework for Metal Artifact Suppression in CT Imaging of Metal Lattice Structures via Radon Transform and Attention-Based Super-Resolution Reconstruction

Bingyang Wang, Zhiwei Zhang, Heng Li, Ronghai Wu

Applied Sciences· Volume 15· Issue 14

Abstract

High-density component-induced metal artifacts in industrial computed tomography (CT) severely impair image quality and make further analysis more difficult. To suppress artifacts and improve image quality, this research suggests a practical approach that combines lightweight attention-enhanced super-resolution networks with Radon-domain artifact elimination. First, the original CT slices are subjected to bicubic interpolation, which enhances resolution and reduces sampling errors during transformation. The Radon transform, which detects and suppresses metal artifacts in the Radon domain, is then used to convert the interpolated pictures into sinograms. The artifact-suppressed sinograms are then reconstructed at better resolution using a lightweight Enhanced Deep Super-Resolution (EDSR) network with a channel attention mechanism, which consists of only one residual block. The inverse Radon transform is used to recreate the final CT images. An average peak signal-to-noise ratio (PSNR) of 40.39 dB and an average signal-to-noise ratio (SNR) of 29.75 dB, with an SNR improvement of 15.48 dB over the original artifact-laden images, show the success of the suggested strategy in experiments. This method offers a workable and effective way to improve image quality in industrial CT applications that involve intricate structures that incorporate metal.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced X-ray and CT Imaging · Radiation Dose and Imaging · Medical Imaging Techniques and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Materials, Northwestern Polytechnical University, Xi’an 710072, China

AVIC Manufacturing Technology Institute, Beijing 100024, China

Funding

Science & Technology Program of Hebei

References (23)

Show source-provided references
1. CT artifacts: Causes and reduction techniques10.2217/iim.12.13 ↗
2. Metal artifact reduction techniques in musculoskeletal CT-imaging10.1016/j.ejrad.2018.08.010 ↗
3. Metal artifact reduction in CT: Where are we after four decades?10.1109/ACCESS.2016.2608621 ↗
4. Advances in metal artifact reduction in CT images: A review of traditional and novel metal artifact reduction techniques10.1016/j.ejrad.2023.111276 ↗
5. Reduction of CT artifacts caused by metallic implants10.1148/radiology.164.2.3602406 ↗
6. Normalized metal artifact reduction (NMAR) in computed tomography10.1118/1.3484090 ↗
7. Frequency split metal artifact reduction (FSMAR) in computed tomography10.1118/1.3691902 ↗
8. CALIMAR-GAN: An unpaired mask-guided attention network for metal artifact reduction in CT scans10.1016/j.compmedimag.2025.102565 ↗
9. Yu, L., Zhang, Z., Li, X., Ren, H., Zhao, W., and Xing, L. (2021). Metal artifact reduction in 2D CT images with self-supervised cross-domain learning. Phys. Med. Biol., 66.10.1088/1361-6560/ac195c ↗
10. Zhu, L., Han, Y., Xi, X., Li, L., and Yan, B. (2021). Completion of metal-damaged traces based on deep learning in sinogram domain for metal artifacts reduction in CT images. Sensors, 21.10.3390/s21248164 ↗
11. An irregular metal trace inpainting network for x-ray CT metal artifact reduction10.1002/mp.14295 ↗
12. MFGAN: Multi-modal feature-fusion for CT metal artifact reduction using GANs10.1145/3599730 ↗
13. DICDNet: Deep interpretable convolutional dictionary network for metal artifact reduction in CT images10.1109/TMI.2021.3127074 ↗
14. A semi-supervised learning method of latent features based on convolutional neural networks for CT metal artifact reduction10.1002/mp.15633 ↗
15. Convolutional neural network–based metal and streak artifacts reduction in dental CT images with sparse-view sampling scheme10.1002/mp.15884 ↗
16. A deep recurrent neural network with FISTA optimization for CT metal artifact reduction10.1109/TCI.2022.3212825 ↗
17. Regularized three-dimensional generative adversarial nets for unsupervised metal artifact reduction in head and neck CT images10.1109/ACCESS.2020.3002090 ↗
18. Deep learning-based metal artifact reduction using cycle-consistent adversarial network for intensity-modulated head and neck radiation therapy treatment planning10.1016/j.ejmp.2020.08.018 ↗
19. ADN: Artifact disentanglement network for unsupervised metal artifact reduction10.1109/TMI.2019.2933425 ↗
20. Sinogram+ image domain neural network approach for metal artifact reduction in low-dose cone-beam computed tomography10.1117/1.JMI.8.5.052103 ↗
21. A metal artifact reduction method using a fully convolutional network in the sinogram and image domains for dental computed tomography10.1007/s10278-019-00297-x ↗
22. Deep sinogram completion with image prior for metal artifact reduction in CT images10.1109/TMI.2020.3025064 ↗
23. Wang, T., Xia, W., Huang, Y., Sun, H., Liu, Y., Chen, H., Zhou, J., and Zhang, Y. (2021). DAN-Net: Dual-domain adaptive-scaling non-local network for CT metal artifact reduction. Phys. Med. Biol., 66.10.1088/1361-6560/ac1156 ↗