arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.11880cs.CVcs.AI
收藏

SynthRAR: 通过展开网络和合成数据训练的CT环状伪影减少

SynthRAR: Ring Artifacts Reduction in CT with Unrolled Network and Synthetic Data Training

Science&Technology Organization, GE HealthCare(科学与技术组织,通用电气医疗)

Hongxu Yang, Levente Lippenszky, Edina Timko, Gopal Avinash

AI总结:

SynthRAR通过展开网络和合成数据训练,有效减少CT环状伪影,无需真实临床数据即可提升重建图像质量。

摘要:

CT检测器的缺陷和不一致响应会导致重建图像中出现环状和条纹伪影,使其无法用于临床用途。近年来,已有几种基于图像域或sinogram域的监督深度学习方法被提出,用于解决环状伪影问题。然而,这些方法需要专门的数据集进行训练,导致数据收集成本较高。此外,现有方法仅专注于图像空间或sinogram空间的修正,忽略了CT几何学前向运算中的内在相关性。基于非理想CT检测器响应的理论分析,通过展开网络将RAR问题重新表述为逆问题,同时考虑非理想响应与线性前向投影的CT几何学。此外,通过从自然图像中衍生出的合成数据,利用sinogram和图像域之间环状伪影的内在相关性,使训练好的模型能够在不需真实临床数据的情况下纠正伪影。在多种扫描几何和解剖区域上的广泛评估表明,训练于合成数据的模型在性能上始终优于现有最先进方法。

英文摘要:

Defective and inconsistent responses in CT detectors can cause ring and streak artifacts in the reconstructed images, making them unusable for clinical purposes. In recent years, several ring artifact reduction solutions have been proposed in the image domain or in the sinogram domain using supervised deep learning methods. However, these methods require dedicated datasets for training, leading to a high data collection cost. Furthermore, existing approaches focus exclusively on either image-space or sinogram-space correction, neglecting the intrinsic correlations from the forward operation of the CT geometry. Based on the theoretical analysis of non-ideal CT detector responses, the RAR problem is reformulated as an inverse problem by using an unrolled network, which considers non-ideal response together with linear forward-projection with CT geometry. Additionally, the intrinsic correlations of ring artifacts between the sinogram and image domains are leveraged through synthetic data derived from natural images, enabling the trained model to correct artifacts without requiring real-world clinical data. Extensive evaluations on diverse scanning geometries and anatomical regions demonstrate that the model trained on synthetic data consistently outperforms existing state-of-the-art 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。

↑