用正则化扩散采样提升3D CT图像重建质量
NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography
- 在扩散采样中引入L1正则项，增强切片间空间连续性
- 在真实医疗CT数据上达到顶尖或接近顶尖的重建效果
- 适合需要高质量3D医学影像重建的研究者与工程师
基于扩散模型（DM）的方法在解决逆成像问题方面已取得进展。近期工作将采样过程建模为优化问题，强制满足测量一致性、前向扩散一致性以及逐步和反向扩散一致性。然而，这些方法仅适用于2D重建任务，难以直接扩展到3D成像问题，如计算机断层扫描（CT）。为此，我们提出用于3D CT的网络正则化扩散采样方法（NERD），通过在优化目标中加入L1正则项，促进相邻切片间的空间连续性，减少切片间伪影，实现更连贯的体数据重建。此外，我们设计了两种高效优化策略：基于交替方向乘子法（ADMM）和原始对偶混合梯度（PDHG）的方法。在真实医疗3D CT数据上的实验表明，该方法实现了当前最优或极具竞争力的重建性能。
原文摘要 · Abstract (English)
Numerous diffusion model (DM)-based methods have been proposed for solving inverse imaging problems. Among these, a recent line of work has demonstrated strong performance by formulating sampling as an optimization procedure that enforces measurement consistency, forward diffusion consistency, and both step-wise and backward diffusion consistency. However, these methods have only considered 2D reconstruction tasks and do not directly extend to 3D image reconstruction problems, such as in Computed Tomography (CT). To bridge this gap, we propose NEtwork-Regularized diffusion sampling for 3D CT (NERD) by incorporating an L1 regularization into the optimization objective. This regularizer encourages spatial continuity across adjacent slices, reducing inter-slice artifacts and promoting coherent volumetric reconstructions. Additionally, we introduce two efficient optimization strategies to solve the resulting objective: one based on the Alternating Direction Method of Multipliers (ADMM) and another based on the Primal-Dual Hybrid Gradient (PDHG) method. Experiments on medical 3D CT data demonstrate that our approach achieves either state-of-the-art or highly competitive results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。