Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging
Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging
复制标题
基于生成对抗网络的超有限角度计算机断层扫描成像正弦图修复方法有前景
作者：
Ziheng Li;Ailong Cai;Linyuan Wang;Wenkun Zhang;Chao Tang;Lei Li;Ningning Liang;Bin Yan
有限角度CT图像重建是CT成像领域的一个具有挑战性的问题。在某些特殊应用中，受成像系统几何空间和机械结构的限制，只能在小于90°的扫描范围内采集投影。我们称这种严重的角度受限问题为超角度受限问题，传统的迭代重建算法难以有效缓解。随着深度学习的发展，生成对抗网络（GAN）在图像修复任务中表现良好，可以添加有效的图像信息来恢复图像的缺失部分。针对GAN产生缺失信息的特点，提出了基于正弦图修复的GAN（SI-GAN）算法，以抑制截断正弦图的奇异性，实现超限角重建。我们在SI-GAN中提出了U-Net生成器和补丁设计算法，使网络适用于标准医学CT图像。此外，我们提出了一个联合投影域和图像域损失函数，其中加权图像域损失可以通过反投影操作添加。然后，将成对的有限角度/180°正弦图输入网络进行训练，得到提取了正弦图数据连续性特征的训练模型。最后，在获得估计的正弦图后，使用经典的CT重建方法来重建图像。仿真研究和实际数据实验表明，该方法能有效地消除超限角扫描造成的严重伪影。
Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90°. We call this kind of serious limited-angle problem the ultra-limited-angle problem, which is difficult to effectively alleviate by traditional iterative reconstruction algorithms. With the development of deep learning, the generative adversarial network (GAN) performs well in image inpainting tasks and can add effective image information to restore missing parts of an image. In this study, given the characteristic of GAN to generate missing information, the sinogram-inpainting-GAN (SI-GAN) is proposed to restore missing sinogram data to suppress the singularity of the truncated sinogram for ultra-limited-angle reconstruction. We propose the U-Net generator and patch-design discriminator in SI-GAN to make the network suitable for standard medical CT images. Furthermore, we propose a joint projection domain and image domain loss function, in which the weighted image domain loss can be added by the back-projection operation. Then, by inputting a paired limited-angle/180° sinogram into the network for training, we can obtain the trained model, which has extracted the continuity feature of sinogram data. Finally, the classic CT reconstruction method is used to reconstruct the images after obtaining the estimated sinograms. The simulation studies and actual data experiments indicate that the proposed method performed well to reduce the serious artifacts caused by ultra-limited-angle scanning.
登录
查看更多内容
影响因子：
2.1
作者：
R. Tovey;Martin Benning;C. Brune;M. J. Lagerwerf;S. Collins;R. Leary;P. Midgley;C. Schoenlieb
通讯作者：
R. Tovey;Martin Benning;C. Brune;M. J. Lagerwerf;S. Collins;R. Leary;P. Midgley;C. Schoenlieb
影响因子：
3.5
作者：
Han X;Bian J;Ritman EL;Sidky EY;Pan X
通讯作者：
Pan X
DOI：
--
发表时间：
2016-07
期刊：
ArXiv
影响因子：
--
作者：
Hanming Zhang;Liang Li;Kai Qiao;Linyuan Wang;Bin Yan;Lei Li;Guoen Hu
通讯作者：
Hanming Zhang;Liang Li;Kai Qiao;Linyuan Wang;Bin Yan;Lei Li;Guoen Hu
DOI：
--
发表时间：
2017-03
期刊：
ArXiv
影响因子：
--
作者：
Jawook Gu;J. C. Ye
通讯作者：
Jawook Gu;J. C. Ye
DOI：
10.4018/978-1-7998-1192-3.ch008
发表时间：
2020
期刊：
Advances in Systems Analysis, Software Engineering, and High Performance Computing
影响因子：
--
作者：
Menaga D.;R. S.
通讯作者：
Menaga D.;R. S.