arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00205eess.IVcs.AIcs.CV
收藏

用于稀疏视图CT重建的高效流匹配

Efficient Flow Matching for Sparse-View CT Reconstruction

Centrum Wiskunde en Informatica(数学与信息学研究中心);LIACS, Leiden University(莱顿大学LIACS);Great Bay University(大湾大学);Mathematical Institute, Utrecht University(乌得勒支大学数学研究所)

Jiayang Shi, Lincen Yang, Zhong Li, Tristan van Leeuwen, Daniel M. Pelt, K. Joost Batenburg

AI总结:

研究利用流匹配(FM)模型进行CT重建,因其确定性与数据一致性操作天然兼容。提出基于FM的CT重建框架及高效变体,通过重用预测速度场减少神经网络函数评估次数,提高推理效率,实验证明效果良好。

摘要:

生成模型,特别是扩散模型(DM),在计算机断层扫描(CT)重建中显示出强大潜力,可作为解决不适定逆问题的表达先验。然而,基于扩散的重建依赖随机微分方程(SDEs)进行正向扩散和反向去噪,这种随机性会干扰CT重建中的重复数据一致性校正。相比之下,流匹配(FM)模型作为确定性常微分方程(ODE)进行采样,产生无随机噪声注入的平滑轨迹。这种确定性公式自然与重复数据一致性操作兼容。此外,我们观察到FM预测的速度场在相邻步骤之间表现出很强的相关性。受此启发,我们提出了一个基于FM的CT重建框架(FMCT)和一个高效变体(EFMCT),该变体在连续步骤中重用先前预测的速度场,以大幅减少神经网络函数评估(NFE)的数量,从而提高推理效率。我们提供了理论分析,表明在结合数据一致性操作时,速度重用引入的误差是有界的。大量实验表明,与基于扩散的方法相比,FMCT/EFMCT在显著提高计算效率的同时,实现了具有竞争力的重建质量。代码库在这个https URL上开源。

英文摘要:

Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems. However, diffusion-based reconstruction relies on Stochastic Differential Equations (SDEs) for forward diffusion and reverse denoising, where such stochasticity can interfere with repeated data consistency corrections in CT reconstruction. Since CT reconstruction is often time-critical in clinical and interventional scenarios, improving reconstruction efficiency is essential. In contrast, Flow Matching (FM) models sampling as a deterministic Ordinary Differential Equation (ODE), yielding smooth trajectories without stochastic noise injection. This deterministic formulation is naturally compatible with repeated data consistency operations. Furthermore, we observe that FM-predicted velocity fields exhibit strong correlations across adjacent steps. Motivated by this, we propose an FM-based CT reconstruction framework (FMCT) and an efficient variant (EFMCT) that reuses previously predicted velocity fields over consecutive steps to substantially reduce the number of Neural network Function Evaluations (NFEs), thereby improving inference efficiency. We provide theoretical analysis showing that the error introduced by velocity reuse is bounded when combined with data consistency operations. Extensive experiments demonstrate that FMCT/EFMCT achieve competitive reconstruction quality while significantly improving computational efficiency compared with diffusion-based methods. The codebase is open-sourced at https://github.com/EFMCT/EFMCT.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑