将深度展开与 Direct Diffusion Bridges 相结合用于计算机断层扫描重建
Integrating Deep Unfolding with Direct Diffusion Bridges for Computed Tomography Reconstruction
AI总结：
本文提出将深度展开与 DDB 融合用于低剂量 CT 重建，通过嵌入物理模型、跳过高噪声中间阶段并定制训练流程，减少采样步骤与累积误差，提升图像保真度。
摘要：
计算机断层扫描（CT）在医疗保健中被广泛用于获取精细成像。然而，低剂量 CT 尽管能够减少辐射暴露，却往往会因噪声增加而导致图像质量受损。传统方法包括预处理、后处理以及利用物理原理的基于模型的方法，被用于改善由含噪投影或正弦图重建图像的质量。近年来，深度学习显著推动了该领域的发展，其中扩散模型的表现优于传统方法和其他深度学习方法。这些模型有效地将深度学习与物理相结合，为 CT 中的逆问题提供了鲁棒的先验。然而，它们在采样过程中通常需要很长的计算时间。本文介绍了首个将深度展开与 Direct Diffusion Bridges（DDB）相结合用于 CT 的方法，该方法将物理过程融入网络架构，并通过绕开扩散模型中常见的过度含噪中间阶段，促进从退化图像到清晰图像的转换。此外，该方法包含一种定制的训练流程，可消除采样过程中通常会累积的误差。所提出的方法需要更少的采样步骤，并展现出更高的保真度指标，优于许多现有的最先进技术。
英文摘要：
Computed Tomography (CT) is widely used in healthcare for detailed imaging. However, Low-dose CT, despite reducing radiation exposure, often results in images with compromised quality due to increased noise. Traditional methods, including preprocessing, post-processing, and model-based approaches that leverage physical principles, are employed to improve the quality of image reconstructions from noisy projections or sinograms. Recently, deep learning has significantly advanced the field, with diffusion models outperforming both traditional methods and other deep learning approaches. These models effectively merge deep learning with physics, serving as robust priors for the inverse problem in CT. However, they typically require prolonged computation times during sampling. This paper introduces the first approach to merge deep unfolding with Direct Diffusion Bridges (DDBs) for CT, integrating the physics into the network architecture and facilitating the transition from degraded to clean images by bypassing excessively noisy intermediate stages commonly encountered in diffusion models. Moreover, this approach includes a tailored training procedure that eliminates errors typically accumulated during sampling. The proposed approach requires fewer sampling steps and demonstrates improved fidelity metrics, outperforming many existing state-of-the-art techniques.
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。
