发表机构
Boston University（波士顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PhyDiCT提出无需训练的即插即用框架，结合Beer-Lambert物理模型与文本条件扩散先验，通过分裂吉布斯采样引导生成，实现稀疏X射线下的高质量三维肺部CT重建，SSIM较全训练方法提升7.5%。
AI 中文摘要
从少量X射线投影重建三维计算机断层扫描（CT）图像是一个高度病态的反演问题，因为体积信息会丢失。我们提出了PhyDiCT，一个无需训练的框架，它将基于Beer-Lambert定律的可微物理正向模型与文本条件扩散模型作为强先验相结合，以重建三维肺部CT图像。我们称该方法为无需训练，因为先验模型无需微调即可使用，我们的目标是引导去噪过程生成与X射线观测一致的样本。我们使用分裂吉布斯采样来引导扩散生成，以联合优化投影保真度（奖励）和与先验知识的一致性。此外，我们引入了一个测试时细化步骤，以增强图像真实感和解剖一致性。我们在公开可用的三维CT数据集上使用感知和语义指标进行了广泛评估，结果表明该方法超越了现有的即插即用扩散和完全训练的重建方法。我们的发现强调，将强生成先验与图像形成的底层物理相结合，显著提高了重建质量，例如，与完全训练方法相比，SSIM提高了7.5%。代码将在该https URL发布。
英文摘要
Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information. We propose PhyDiCT, a training-free framework that integrates a differentiable Physics-based forward model, grounded in the Beer-Lambert law, with a text-conditioned Diffusion as a strong prior to reconstruct 3D lung CT images. We refer to our approach as training-free since the prior model is used without fine-tuning, and our goal is to steer the denoising procedure to generate samples consistent with X-ray observations. We guide the diffusion generation using Split Gibbs sampling to jointly optimize for projection fidelity (reward) and consistency with prior knowledge. Also, we introduce a test-time refinement step that enhances image realism and anatomical coherence. We extensively evaluate our method on publicly available 3D CT datasets using both perceptual and semantic metrics, demonstrating that it surpasses existing plug-and-play diffusion and fully trained reconstruction approaches. Our findings highlight that combining a strong generative prior with the underlying physics of image formation substantially improves reconstruction quality, e.g., 7.5\% improvement on SSIM compared to full training methods. Code will be released at https://github.com/batmanlab/PhyDiCT.
CommentsAccepted at MICCAI 2026; to appear in LNCS 16888
Journal refMICCAI 2026, LNCS 16888, pp. 392-402, Springer (2027)
DOI：10.1007/978-3-032-38179-8_38
