Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction
Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Jawook Gu;J. C. Ye
中科院分区：
文献类型：
--
作者：
Jawook Gu;J. C. Ye
有限角度计算机断层扫描（CT）常用于临床应用，如c臂CT用于介入成像。然而，由于投影数据不完整，有限角度的CT图像存在严重的伪影。现有的迭代方法需要大量的计算，但不能得到令人满意的结果。基于观察到有限角度的伪信号具有一定的方向性和全局分布，提出了一种新的多尺度小波域残差学习结构，对伪信号进行补偿。实验表明，该方法有效地消除了伪影，从而保持了图像的边缘和全局结构。
Limited-angle computed tomography (CT) is often used in clinical applications such as C-arm CT for interventional imaging. However, CT images from limited angles suffers from heavy artifacts due to incomplete projection data. Existing iterative methods require extensive calculations but can not deliver satisfactory results. Based on the observation that the artifacts from limited angles have some directional property and are globally distributed, we propose a novel multi-scale wavelet domain residual learning architecture, which compensates for the artifacts. Experiments have shown that the proposed method effectively eliminates artifacts, thereby preserving edge and global structures of the image.