Physics-Guided Flow Matching for CT Image Reconstruction
作者: Davide Evangelista
分类: cs.AI, cs.CV
发布日期: 2026-08-28
备注: 16 pages, 6 figures, 2 tables
💡 一句话要点
提出基于物理引导的流匹配方法以解决CT图像重建问题
🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)
关键词: CT图像重建 流匹配 深度生成模型 逆问题 医学成像 数据增强 高分辨率
📋 核心要点
- 现有的扩散模型在CT图像重建中存在计算效率低和数值稳定性差的问题,尤其是在高分辨率情况下。
- 本文提出了一种基于流匹配的生成先验,通过两阶段训练策略来提高模型的解剖一致性和结构保真度。
- 实验结果显示,流匹配方法在多个CT逆问题设置中,性能超越了现有的基于扩散的重建算法。
📝 摘要(中文)
近年来,深度生成模型作为解决CT逆问题的强大先验,尤其是基于扩散的方法已取得了最先进的重建性能。然而,扩散模型通常依赖于随机采样过程、长推理轨迹和精心调整的噪声调度,这限制了计算效率和数值稳定性。本文探讨了流匹配作为CT重建的替代生成先验,通过在Mayo Clinic低剂量CT数据集上训练高分辨率的矩形流匹配模型,采用两阶段训练策略以减轻过拟合并提高解剖变异性。实验结果表明,流匹配方法在PSNR、SSIM和感知质量方面均优于基于扩散的方法,同时需要更少的采样步骤。最后,研究团队公开了训练好的流匹配模型和代码,以促进可重复性和未来研究。
🔬 方法详解
问题定义:本文旨在解决CT图像重建中的逆问题,现有的扩散模型在高分辨率图像重建时面临计算效率低和数值稳定性差的挑战。
核心思路:提出流匹配作为CT重建的替代生成先验,通过高分辨率的矩形流匹配模型来生成高质量的CT样本,采用两阶段训练策略以增强模型的解剖一致性。
技术框架:整体架构包括两个主要阶段:第一阶段使用强的解剖信息数据增强进行初步训练,第二阶段则减少或不使用数据增强以精细调整模型的结构保真度。
关键创新:流匹配方法提供了一种稳定、高效且有效的替代方案,与传统的扩散模型相比,显著提高了重建质量并减少了采样步骤。
关键设计:在训练过程中,采用了特定的损失函数和网络结构设计,以确保模型在生成CT图像时的高保真度和解剖一致性。
🖼️ 关键图片
📊 实验亮点
实验结果表明,流匹配方法在PSNR、SSIM和感知质量等指标上均优于现有的扩散模型,且在多个CT逆问题设置中,流匹配方法的性能提升幅度显著,尤其是在减少采样步骤方面表现突出。
🎯 应用场景
该研究在医学成像领域具有广泛的应用潜力,特别是在低剂量CT扫描中,可以有效提高图像重建的质量和效率,减少患者的辐射暴露。此外,流匹配方法的稳定性和高效性也为其他逆问题的解决提供了新的思路。
📄 摘要(原文)
Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion models typically rely on stochastic sampling procedures, long inference trajectories, and carefully tuned noise schedules, which can limit computational efficiency and numerical stability, especially at high spatial resolutions. In this work, we investigate Flow Matching as an alternative generative prior for CT reconstruction. We train a high-resolution Rectified Flow Matching model on 256x256 chest images from the Mayo Clinic Low-Dose CT dataset. To mitigate overfitting and limited anatomical variability, we employ a two-stage training strategy consisting of an initial phase with strong, anatomically informed data augmentation, followed by a fine-tuning phase with reduced or no augmentation to refine structural fidelity. The resulting model is capable of generating high-quality and anatomically coherent CT-like images, serving as a strong learned prior. We then evaluate multiple reconstruction methods specifically designed for Flow Matching models, including Plug-and-Play Flow, FlowDPS, Flower, and Flow-Priors (ICTM), and compare them against state-of-the-art diffusion-based reconstruction algorithms such as DDRM, DPS, and DiffPIR. Experimental results across several CT inverse problem settings show that Flow Matching-based approaches consistently outperform diffusion-based methods in terms of PSNR, SSIM, and perceptual quality, while requiring fewer sampling steps. Finally, we publicly release the trained Flow Matching model and accompanying code to facilitate reproducibility and future research. Overall, this work demonstrates that Flow Matching provides a stable, efficient, and effective alternative to diffusion models for high-resolution CT image reconstruction.