发表机构
Nanchang University; School of Information Engineering, Nanchang University; School of Biomedical Engineering, Sun Yat-sen University（南昌大学; 南昌大学信息工程学院; 中山大学医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对自监督低剂量CT去噪中未建模混合泊松-高斯噪声的问题，提出跨域迭代的物理驱动框架，通过生成独立训练对训练图像域网络，在模拟和真实数据上均优于自监督基线，性能接近监督基线。
AI 中文摘要
低剂量计算机断层扫描（LDCT）测量值包含混合泊松-高斯噪声。然而，大多数自监督方法依赖通用图像统计，未明确建模该噪声，这可能限制其有效抑制真实LDCT噪声的能力。为解决此问题，我们提出一种用于自监督LDCT去噪的跨域迭代物理驱动框架。该框架主要分为三个步骤：首先，学习到的正弦图先验与LDCT噪声模型引导光子计数的后验推理，实现泊松分量与高斯分量的分离；其次，分离后的泊松分量和高斯分量分别通过二项稀疏化和高斯数据稀疏化处理，构建两个分支，再通过残差缩放使每个分支的噪声水平与观测值匹配，从而从一次低剂量测量中生成一对具有近似独立噪声实现的训练样本；最后，该样本对用于训练图像域网络，网络的前向投影输出会更新先验。通过跨域迭代，先验和训练样本对在保持与CT采集物理一致性的同时逐步优化。在AAPM、LIDC-IDRI和LoDoPaB-CT的模拟数据及真实LDCT数据上的实验表明，该方法在各剂量水平下均优于所评估的自监督基线方法，性能与所评估的监督基线方法相当。
英文摘要
Low-dose computed tomography (LDCT) measurements contain mixed Poisson-Gaussian noise. However, most self-supervised methods rely on generic image statistics and do not explicitly model this noise, which may limit their ability to effectively suppress realistic LDCT noise. To address this issue, we propose a physics-driven framework with cross-domain iteration for self-supervised LDCT denoising. The proposed framework proceeds in three main steps. First, a learned sinogram prior and the LDCT noise model guide posterior inference of photon counts, enabling separation of the Poisson and Gaussian components. Second, the separated Poisson and Gaussian components are respectively processed by binomial thinning and Gaussian data thinning to construct two branches, and residual scaling matches each branch's noise level to that of the observation, yielding a training pair with approximately independent noise realizations from one low-dose measurement. Finally, the pair is used to train an image-domain network whose forward-projected outputs update the prior. Through cross-domain iteration, the prior and the training pair are progressively refined while maintaining consistency with CT acquisition physics. Experiments on simulated data from AAPM, LIDC-IDRI, and LoDoPaB-CT and on real LDCT data show consistent gains over the evaluated self-supervised baselines across dose levels, with performance comparable to the evaluated supervised baseline.
Comments10 pages, 11 figures, 3 tables. Includes a 1-page appendix. Submitted to IEEE Transactions on Circuits and Systems for Video Technology
