基于TV正则化OSEM算法的低剂量CT重建网络
A Low-dose CT Reconstruction Network Based on TV-regularized OSEM Algorithm
AI总结：
针对低剂量CT重建中传统EM正则化方法过度平滑且收敛慢的问题，提出将TV正则化整合进EM算法的M步，结合CP算法与OS策略构建OSEM-CP算法，并展开为端到端网络OSEM-CPNN，实现单次全视图迭代的高质量重建。
摘要：
低剂量计算机断层扫描（LDCT）在减少对人体潜在危害方面具有显著优势。然而，在CT扫描中降低X射线剂量通常会导致重建图像出现严重噪声和伪影，可能对诊断产生不利影响。通过利用期望最大化（EM）算法，可以将统计先验与人工先验相结合，以提升LDCT重建质量。然而，传统的基于EM的正则化方法采用交替求解策略，即先进行完整重建再进行图像正则化，导致过度平滑和收敛缓慢。本文提出将TV正则化整合到EM算法的“M”步骤中，从而实现有效且高效的正则化。此外，通过采用Chambolle-Pock（CP）算法和有序子集（OS）策略，提出了用于LDCT重建的OSEM-CP算法，其中重建和正则化均逐视图进行。进一步地，通过展开OSEM-CP，提出了一种端到端重建神经网络（NN），命名为OSEM-CPNN，具有卓越的性能和效率，仅需一次全视图迭代即可实现高质量重建。在不同模型和数据集上的实验表明，与传统和最先进的深度学习方法相比，本文方法表现出色。
英文摘要：
Low-dose computed tomography (LDCT) offers significant advantages in reducing the potential harm to human bodies. However, reducing the X-ray dose in CT scanning often leads to severe noise and artifacts in the reconstructed images, which might adversely affect diagnosis. By utilizing the expectation maximization (EM) algorithm, statistical priors could be combined with artificial priors to improve LDCT reconstruction quality. However, conventional EM-based regularization methods adopt an alternating solving strategy, i.e. full reconstruction followed by image-regularization, resulting in over-smoothing and slow convergence. In this paper, we propose to integrate TV regularization into the ``M''-step of the EM algorithm, thus achieving effective and efficient regularization. Besides, by employing the Chambolle-Pock (CP) algorithm and the ordered subset (OS) strategy, we propose the OSEM-CP algorithm for LDCT reconstruction, in which both reconstruction and regularization are conducted view-by-view. Furthermore, by unrolling OSEM-CP, we propose an end-to-end reconstruction neural network (NN), named OSEM-CPNN, with remarkable performance and efficiency that achieves high-quality reconstructions in just one full-view iteration. Experiments on different models and datasets demonstrate our methods' outstanding performance compared to traditional and state-of-the-art deep-learning methods.
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。
