Multimodal feature‐guided diffusion model for low‐count PET image denoising
Medical Physics · 2025
DOI: 10.1002/mp.17764 ↗At a glance
Journal article in Medical Physics, 2025. Written by Gengjia Lin and 11 co-authors. Institution: College of Computer Science and Engineering, Northeastern University, Shenyang, China. Major MEDLINE topics: Positron-Emission Tomography, Signal-To-Noise Ratio, Image Processing, Computer-Assisted. Cited 6 times so far (Crossref); 61 references. Funded by: Shenzhen Medical Research Fund of China, Natural Science Foundation of Guangdong Province, Basic and Applied Basic Research Foundation of Guangdong Province.
Abstract (original language)
Background
To minimize radiation exposure while obtaining high‐quality Positron Emission Tomography (PET) images, various methods have been developed to derive standard‐count PET (SPET) images from low‐count PET (LPET) images. Although deep learning methods have enhanced LPET images, they rarely utilize the rich complementary information from MR images. Even when MR images are used, these methods typically employ early, intermediate, or late fusion strategies to merge features from different CNN streams, failing to fully exploit the complementary properties of multimodal fusion.
Purpose
In this study, we introduce a novel multimodal feature‐guided diffusion model, termed MFG‐Diff, designed for the denoising of LPET images with the full utilization of MRI.
Methods
MFG‐Diff replaces random Gaussian noise with LPET images and introduces a novel degradation operator to simulate the physical degradation processes of PET imaging. Besides, it uses a novel cross‐modal guided restoration network to fully exploit the modality‐specific features provided by the LPET and MR images and utilizes a multimodal feature fusion module employing cross‐attention mechanisms and positional encoding at multiple feature levels for better feature fusion.
Results
Under four counts (2.5%, 5.0%, 10%, and 25%), the images generated by our proposed network showed superior performance compared to those produced by other networks in both qualitative and quantitative evaluations, as well as in statistical analysis. In particular, the peak‐signal‐to‐noise ratio of the generated PET images improved by more than 20% under a 2.5% count, the structural similarity index improved by more than 16%, and the root mean square error reduced by nearly 50%. On the other hand, our generated PET images had significant correlation (Pearson correlation coefficient, 0.9924), consistency, and excellent quantitative evaluation results with the SPET images.
Conclusions
The proposed method outperformed existing state‐of‐the‐art LPET denoising models and can be used to generate highly correlated and consistent SPET images obtained from LPET images.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- College of Computer Science and Engineering, Northeastern University, Shenyang, China.
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China.
- Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China.
Funding
- Shenzhen Medical Research Fund of China
- Natural Science Foundation of Guangdong Province
- Basic and Applied Basic Research Foundation of Guangdong Province
- Shenzhen Excellent Technological Innovation Talent Training Project of China
- Key Laboratory for Magnetic Resonance and Multimodality Imaging of Guangdong Province
- Shenzhen Science and Technology Program
- National Natural Science Foundation of China
Cite
APA
Lin, G., Jin, Y., Huang, Z., Chen, Z., Liu, H., Zhou, C., Zhang, X., Fan, W., Zhang, N., Liang, D., Cao, P., & Hu, Z. (2025). Multimodal feature‐guided diffusion model for low‐count PET image denoising. Medical Physics. https://doi.org/10.1002/mp.17764
Vancouver
Lin G, Jin Y, Huang Z, Chen Z, Liu H, Zhou C, et al. Multimodal feature‐guided diffusion model for low‐count PET image denoising. Medical Physics. 2025. doi:10.1002/mp.17764
BibTeX
@article{Lin2025,
author = {Lin, Gengjia and Jin, Yuxi and Huang, Zhenxing and Chen, Zixiang and Liu, Haizhou and Zhou, Chao and Zhang, Xu and Fan, Wei and Zhang, Na and Liang, Dong and Cao, Peng and Hu, Zhanli},
title = {Multimodal feature‐guided diffusion model for low‐count PET image denoising},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.17764}
}
EUVIMED