Diffusion probabilistic priors for zero‐shot low‐dose CT image denoising
Medical Physics · 2025-01 · 52 (1) · 329-345
DOI: 10.1002/mp.17431 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 16.10.2024. Verfasst von Xuan Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted, Signal-To-Noise Ratio, Radiation Dosage. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Background
Denoising low‐dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning‐based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low‐dose and normal‐dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning‐based methods often require training with a large number of low‐dose CT images or rely on specially designed data acquisition processes to obtain training data.
Purpose
To address these limitations, we propose a novel unsupervised method that only utilizes normal‐dose CT images during training, enabling zero‐shot denoising of low‐dose CT images.
Methods
Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high‐quality normal‐dose CT images from low‐resolution to high‐resolution. The cascaded architecture makes the training of high‐resolution diffusion models more feasible. Subsequently, we introduce low‐dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low‐dose CT images.
Results
We test our method on low‐dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state‐of‐the‐art unsupervised method and surpasses several supervised deep learning‐based methods. Our method achieves PSNR of 45.02 and 35.35 dB on the abdomen CT dataset and the chest CT dataset, respectively, surpassing the best unsupervised algorithm Noise2Sim in the comparative methods by 0.39 and 0.85 dB, respectively.
Conclusions
We propose a novel low‐dose CT image denoising method based on diffusion model. Our proposed method only requires normal‐dose CT images as training data, greatly alleviating the data scarcity issue faced by most deep learning‐based methods. At the same time, as an unsupervised algorithm, our method achieves very good qualitative and quantitative results. The Codes are available in https://github.com/DeepXuan/Dn‐Dp .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.
- Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Radiation Oncology Department, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, Chi…
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Liu, X., Xie, Y., Liu, C., Cheng, J., Diao, S., Tan, S., & Liang, X. (2025). Diffusion probabilistic priors for zero‐shot low‐dose CT image denoising. Medical Physics, 52(1), 329-345. https://doi.org/10.1002/mp.17431
Vancouver
Liu X, Xie Y, Liu C, Cheng J, Diao S, Tan S, et al. Diffusion probabilistic priors for zero‐shot low‐dose CT image denoising. Medical Physics. 2025;52(1):329-345. doi:10.1002/mp.17431
BibTeX
@article{Liu2025,
author = {Liu, Xuan and Xie, Yaoqin and Liu, Chenbin and Cheng, Jun and Diao, Songhui and Tan, Shan and Liang, Xiaokun},
title = {Diffusion probabilistic priors for zero‐shot low‐dose CT image denoising},
journal = {Medical Physics},
year = {2025},
volume = {52},
number = {1},
pages = {329--345},
doi = {10.1002/mp.17431}
}
EUVIMED