Image quality restoration in 15‐s breath‐hold PET using a diffusion‐based neural network
Medical Physics · 2026-03 · 53 (3)
DOI: 10.1002/mp.70361 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 27.02.2026. Verfasst von Jingxi Hu und 10 weiteren Autor:innen. Beteiligte Einrichtung: Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. Hauptthemen laut MEDLINE: Breath Holding, Positron-Emission Tomography, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 43 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province.
Abstract (Originalsprache)
Background
Breath‐hold PET imaging helps reduce respiratory motion artifacts in thoracoabdominal scans. However, its clinical application is limited by the short acquisition time, which results in significant image noise and poor lesion detectability. Enhancing image quality under such conditions remains a technical challenge.
Purpose
To improve the image quality of 15‐s breath‐hold PET scans, we investigated a deep learning‐based framework using a diffusion probabilistic model. The goal was to suppress noise and enhance lesion visibility while maintaining quantitative accuracy under severely limited acquisition durations.
Methods
We propose TAM‐DiffPET, a denoising diffusion probabilistic model (DDPM) augmented with Temporal Attention Modulation (TAM) to refine intermediate feature representations by injecting diffusion time‐step embeddings and temporal contextual cues. The model was trained on paired PET datasets comprising 15‐s breath‐hold scans and 5‐min free‐breathing scans from 230 patients at Ren Ji Hospital; 180 cases were used for training and 50 for quantitative and qualitative evaluation. Performance was assessed using PSNR, SSIM, and voxel‐wise SUV distributions within lesion ROIs. Visual and statistical comparisons were conducted against U‐Net, CycleGAN, and a vanilla DDPM.
Results
The proposed method demonstrated superior performance compared to existing deep learning‐based approaches. Quantitatively, it achieved the highest PSNR (40.2 ± 1.2 dB) and SSIM (0.995 ± 0.004), significantly outperforming previous deep learning based methods such as U‐Net, CycleGAN, and DDPM. Voxel‐wise SUV error distributions showed lower standard deviation and mean absolute error within lesion ROIs. Visual assessments revealed enhanced lesion contrast, sharper anatomical boundaries, and reduced background noise. Difference maps confirmed minimal deviation from the 5‐min reference scans. Furthermore, SUV distribution analysis across representative patients confirmed that the proposed method preserves tracer uptake consistency, offering improved fidelity in clinical lesion quantification.
Conclusion
Our diffusion‐based framework effectively denoises breath‐hold PET images acquired under ultrashort durations, offering improved visual clarity and quantitative fidelity. These results support its clinical utility in motion‐prone scenarios, such as thoracic or abdominal imaging, and suggest its potential for enhancing diagnostic accuracy while reducing scan time and radiation burden on patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, State Key Laboratory of Biomedical Imaging Science and System, Shenzhen, China.
- University of Nottingham Ningbo China, Ningbo, China.
- Department of Nuclear Medicine, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
- Shenzhen Excellent Technological Innovation Talent Training Project of China
- Shenzhen Science and Technology Program of China
- Shenzhen Medical Research Fund of China
- Yongjiang Technology Innovation Project
Zitieren
APA
Hu, J., Li, L., Zhang, Q., Wei, W., Huang, G., Liu, J., Liang, D., Zheng, H., Hu, Z., He, X., & Zhang, N. (2026). Image quality restoration in 15‐s breath‐hold PET using a diffusion‐based neural network. Medical Physics, 53(3). https://doi.org/10.1002/mp.70361
Vancouver
Hu J, Li L, Zhang Q, Wei W, Huang G, Liu J, et al. Image quality restoration in 15‐s breath‐hold PET using a diffusion‐based neural network. Medical Physics. 2026;53(3). doi:10.1002/mp.70361
BibTeX
@article{Hu2026,
author = {Hu, Jingxi and Li, Lianghua and Zhang, Qiyang and Wei, Weijun and Huang, Gang and Liu, Jianjun and Liang, Dong and Zheng, Hairong and Hu, Zhanli and He, Xiangjian and Zhang, Na},
title = {Image quality restoration in 15‐s breath‐hold PET using a diffusion‐based neural network},
journal = {Medical Physics},
year = {2026},
volume = {53},
number = {3},
doi = {10.1002/mp.70361}
}
EUVIMED