Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction
Journal of Imaging Informatics in Medicine · 2025
DOI: 10.1007/s10278-024-01314-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2025. Verfasst von Feng Yang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Nuclear Technology and Automation Engineering, Chengdu University of Technology, No. 1 East 3rd Road, Erxianqiao, Chengdu, 610059, Sichuan…. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Image Processing, Computer-Assisted, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Foundation of Sichuan Province, Medical Engineering Innovation Fund for Cancer.
Abstract (Originalsprache)
X-ray computed tomography (CT) is a commonly used imaging modality in clinical practice. Recent years have seen increasing public concern regarding the ionizing radiation from CT. Low-dose CT (LDCT) has been proven to be effective in reducing patients' radiation exposure, but it results in CT images with low signal-to-noise ratio (SNR), failing to meet the image quality required for diagnosis. To enhance the SNR of LDCT images, numerous denoising strategies based on deep learning have been introduced, leading to notable advancements. Despite these advancements, most methods have relied on a supervised training paradigm. The challenge in acquiring aligned pairs of low-dose and normal-dose images in a clinical setting has limited their applicability. Recently, some self-supervised deep learning methods have enabled denoising using only noisy samples. However, these techniques are based on overly simplistic assumptions about noise and focus solely on CT sinogram denoising or image denoising, compromising their effectiveness. To address this, we introduce the Dual-Domain Self-supervised framework, termed DDoS, to accomplish effective LDCT denoising and reconstruction. The framework includes denoising in the sinogram domain, filtered back-projection reconstruction, and denoising in the image domain. By identifying the statistical characteristics of sinogram noise and CT image noise, we develop sinogram-denoising and CT image-denoising networks that are fully adapted to these characteristics. Both networks utilize a unified hybrid architecture that combines graph convolution and incorporates multiple channel attention modules, facilitating the extraction of local and non-local multi-scale features. Comprehensive experiments on two large-scale LDCT datasets demonstrate the superiority of DDoS framework over existing state-of-the-art methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Nuclear Technology and Automation Engineering, Chengdu University of Technology, No. 1 East 3rd Road, Erxianqiao, Chengdu, 610059, Sichuan, China.
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, No. 55, Section 4, Renmin South Road,…
- School of Mechanical and Electrical Engineering, Chengdu University of Technology, No. 1 East 3rd Road, Erxianqiao, Chengdu, 610059, Sichuan, China.
- School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Ouhai District, Wenzhou, 325000, Zhejiang, China. liumz@cdut.edu.cn.
Förderung
- Natural Science Foundation of Sichuan Province
- Medical Engineering Innovation Fund for Cancer
Zitieren
APA
Yang, F., Zhao, F., Liu, Y., Liu, M., & Liu, M. (2025). Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01314-4
Vancouver
Yang F, Zhao F, Liu Y, Liu M, Liu M. Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction. Journal of Imaging Informatics in Medicine. 2025. doi:10.1007/s10278-024-01314-4
BibTeX
@article{Yang2025,
author = {Yang, Feng and Zhao, Feixiang and Liu, Yanhua and Liu, Min and Liu, Mingzhe},
title = {Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction},
journal = {Journal of Imaging Informatics in Medicine},
year = {2025},
doi = {10.1007/s10278-024-01314-4}
}
EUVIMED