Convergent–Diffusion Denoising Model for multi-scenario CT Image Reconstruction
Computerized Medical Imaging and Graphics · 2025-03 · 120 · 102491
DOI: 10.1016/j.compmedimag.2024.102491 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2025-03. Verfasst von Xinghua Ma und 10 weiteren Autor:innen. Beteiligte Einrichtung: The Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, China; The Computational Bioscience Research Center, King Abdullah Un…. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 61 Literaturangaben.
Abstract (Originalsprache)
A generic and versatile CT Image Reconstruction (CTIR) scheme can efficiently mitigate imaging noise resulting from inherent physical limitations, substantially bolstering the dependability of CT imaging diagnostics across a wider spectrum of patient cases. Current CTIR techniques often concentrate on distinct areas such as Low-Dose CT denoising (LDCTD), Sparse-View CT reconstruction (SVCTR), and Metal Artifact Reduction (MAR). Nevertheless, due to the intricate nature of multi-scenario CTIR, these techniques frequently narrow their focus to specific tasks, resulting in limited generalization capabilities for diverse scenarios. We propose a novel Convergent-Diffusion Denoising Model (CDDM) for multi-scenario CTIR, which utilizes a stepwise denoising process to converge toward an imaging-noise-free image with high generalization. CDDM uses a diffusion-based process based on a priori decay distribution to steadily correct imaging noise, thus avoiding the overfitting of individual samples. Within CDDM, a domain-correlated sampling network (DS-Net) provides an innovative sinogram-guided noise prediction scheme to leverage both image and sinogram (i.e., dual-domain) information. DS-Net analyzes the correlation of the dual-domain representations for sampling the noise distribution, introducing sinogram semantics to avoid secondary artifacts. Experimental results validate the practical applicability of our scheme across various CTIR scenarios, including LDCTD, MAR, and SVCTR, with the support of sinogram knowledge.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, China; The Computational Bioscience Research Center, King Abdullah University of Science and Technology, Thuwal, Makkah, Saudi Arabia.
- The Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, China.
- The Faculty of Computing, Harbin Institute of Technology, Shenzhen, Guangdong, China. Electronic address: wangwei2019@hit.edu.cn.
- The College of Computer and Control Engineering, Northeast Forestry University, Harbin, Heilongjiang, China. Electronic address: dongsuyu@nefu.edu.cn.
- The Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang, China. Electronic address: lixiangyu@hit.edu.cn.
- The Department of Thoracic Surgery at No. 4 Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang, China.
Zitieren
APA
Ma, X., Zou, M., Fang, X., Luo, G., Wang, W., Dong, S., Li, X., Wang, K., Dong, Q., Tian, Y., & Li, S. (2025). Convergent–Diffusion Denoising Model for multi-scenario CT Image Reconstruction. Computerized Medical Imaging and Graphics, 120, 102491. https://doi.org/10.1016/j.compmedimag.2024.102491
Vancouver
Ma X, Zou M, Fang X, Luo G, Wang W, Dong S, et al. Convergent–Diffusion Denoising Model for multi-scenario CT Image Reconstruction. Computerized Medical Imaging and Graphics. 2025;120:102491. doi:10.1016/j.compmedimag.2024.102491
BibTeX
@article{Ma2025,
author = {Ma, Xinghua and Zou, Mingye and Fang, Xinyan and Luo, Gongning and Wang, Wei and Dong, Suyu and Li, Xiangyu and Wang, Kuanquan and Dong, Qing and Tian, Ye and Li, Shuo},
title = {Convergent–Diffusion Denoising Model for multi-scenario CT Image Reconstruction},
journal = {Computerized Medical Imaging and Graphics},
year = {2025},
volume = {120},
pages = {102491},
doi = {10.1016/j.compmedimag.2024.102491}
}
EUVIMED