Unified-distribution residual diffusion model for cross-scanner generalizable low-dose CT denoising.
Authors
Affiliations (5)
Affiliations (5)
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangzhou, 510515, China.
- Southern Medical University, Guangzhou, Guangzhou, Guangdong, 510515, China.
- Guilin University of Electronic Technology, Guilin, Guilin, 541004, China.
- Key Laboratory of Biomedical Information Engineering of Ministry of Education， School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, Xi'an, 710049, China.
- Key Laboratory of Biomedical Information Engineering of Ministry of Education, Xi'an Jiaotong University, Xi'an, Xi'an, 710049, China.
Abstract
The growing adoption of multi-center diagnostic and treatment protocols has heightened the demand for consistent image quality across CT devices, yet scanner-specific variations in image characteristics pose a significant challenge. Recently, deep learning (DL)-based low-dose computed tomography (LDCT) reconstruction algorithms have been widely developed and successfully deployed in commercial clinical systems. However, existing methods for cross-scanner LDCT imaging suffer from inadequate alignment of data distributions across different scanners, which constrains their generalization performance. This study aims to propose a single model for cross-scanner LDCT image denoising. We propose a unified-distribution residual diffusion model (UDRDiff) for generalizable LDCT image denoising across diverse scanners. Specifically, we design a unified-distribution degeneration operator to progressively map cross-scanner LDCT data into a shared latent distribution by incorporating an input-suppression term (IST), effectively mitigating inter-scanner discrepancies. To enhance the interpretability of the forward diffusion process, we introduce a residual diffusion mechanism that establishes a deterministic degradation process from normal-dose CT to LDCT, which can clearly guide the reverse image restoration process and significantly accelerate the sampling process. We extensively validated our method on datasets from four scanners, covering two manufacturers and two anatomical regions. Experimental results demonstrate that our method outperforms existing approaches across all test scenarios. Taking two representative test sets as examples: on the Scanner 1 (abdominal images) dataset, our method improves PSNR from 43.0765 dB to 43.5324 dB and SSIM from 0.9634 to 0.9660; on the Scanner 4 (head images) dataset, PSNR improves from 44.3582 dB to 45.9250 dB and SSIM from 0.9545 to 0.9744. These results sufficiently validate the effectiveness and generalization capability of our method across different scanners and anatomical regions. UDRDiff effectively addresses the data distribution alignment problem in cross-scanner LDCT denoising, thereby enhancing model generalizability under multi-center, multi-scanning conditions, and provides a feasible path for cross-scanner denoising of clinical LDCT images.