Noise-inspired diffusion model for generalizable low-dose CT reconstruction.
Authors
Affiliations (6)
Affiliations (6)
- Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai 200433, China. Electronic address: [email protected].
- Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai 200433, China.
- School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong 510515, China.
- School of Computer Science, Fudan University, Shanghai 200433, China.
- School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Electronic address: [email protected].
- Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai 200433, China; MOE Frontiers Center for Brain Science, Fudan University, Shanghai 200433, China; Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Ministry of Education), Fudan University, Shanghai 200433, China; State Key Laboratory of Brain Function and Disorders, Fudan University, Shanghai 200433, China. Electronic address: [email protected].
Abstract
The generalization of deep learning-based low-dose computed tomography (CT) reconstruction models to doses unseen in the training data is important and remains challenging. Previous efforts heavily rely on paired data to improve the generalization performance and robustness through collecting either diverse CT data for re-training or a few test data for fine-tuning. Recently, diffusion models have shown promising and generalizable performance in low-dose CT (LDCT) reconstruction, however, they may produce unrealistic structures due to the CT image noise deviating from Gaussian distribution and imprecise prior information from the guidance of noisy LDCT images. In this paper, we propose a noise-inspired diffusion model for generalizable LDCT reconstruction, termed NEED, which tailors diffusion models for noise characteristics of each domain. First, we propose a novel shifted Poisson diffusion model to denoise projection data, which aligns the diffusion process with the noise model in pre-log LDCT projections. Second, we devise a doubly guided diffusion model to refine reconstructed images, which leverages LDCT images and initial reconstructions to more accurately locate prior information and enhance reconstruction fidelity. By cascading these two diffusion models for dual-domain reconstruction, our NEED requires only normal-dose data for training and can be effectively extended to various unseen dose levels during testing via a time step matching strategy. Extensive qualitative, quantitative, and segmentation-based evaluations on two datasets demonstrate that our NEED consistently outperforms state-of-the-art methods in reconstruction and generalization performance. Source code is made available at https://github.com/qgao21/NEED.