Region-specific Dictionary Learning-based Low-dose Thoracic CT Reconstruction
Region-specific Dictionary Learning-based Low-dose Thoracic CT Reconstruction
复制标题
DOI：
--
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Qiong Xu;Jeff Wang;H. Shirato;L. Xing
中科院分区：
文献类型：
--
作者：
Qiong Xu;Jeff Wang;H. Shirato;L. Xing
为了最大限度地利用稀疏数据处理技术进行CT图像重建，提出了一种基于字典学习的区域特定图像拼接方法。考虑到CT图像特征和噪声的非均匀分布，在迭代重建中使用了特定区域的字典定制。根据胸部CT图像的结构和噪声特点，将其划分为多个区域。然后，从分割的胸部CT图像中学习特定于每个区域的词典，并将其应用于该区域的后续图像重建。根据每个区域的结构和噪声特性，确定字典学习和稀疏表示的参数。与传统的基于单个字典的重建方法相比，该方法在恢复结构和抑制噪声方面具有更好的性能。定量地，仿真研究表明，在结构相似性(SSIM)和均方根误差(RMSE)指标方面，整个胸部的图像质量最大可以分别提高4.88%和11.1%。对于人体成像数据，发现可以更好地恢复肺和心脏的结构，同时有效地降低椎体周围的噪声。所提出的策略考虑了重建对象内部固有的区域差异，并导致图像得到改善。该方法可以很容易地扩展到其他解剖区域的CT成像和其他应用。
This paper presents a dictionary learning-based method with region-specific image patches to maximize the utility of the powerful sparse data processing technique for CT image reconstruction. Considering heterogeneous distributions of image features and noise in CT, region-specific customization of dictionaries is utilized in iterative reconstruction. Thoracic CT images are partitioned into several regions according to their structural and noise characteristics. Dictionaries specific to each region are then learned from the segmented thoracic CT images and applied to subsequent image reconstruction of the region. Parameters for dictionary learning and sparse representation are determined according to the structural and noise properties of each region. The proposed method results in better performance than the conventional reconstruction based on a single dictionary in recovering structures and suppressing noise in both simulation and human CT imaging. Quantitatively, the simulation study shows maximum improvement of image quality for the whole thorax can achieve 4.88% and 11.1% in terms of the Structure-SIMilarity (SSIM) and Root-Mean-Square Error (RMSE) indices, respectively. For human imaging data, it is found that the structures in the lungs and heart can be better recovered, while simultaneously decreasing noise around the vertebra effectively. The proposed strategy takes into account inherent regional differences inside of the reconstructed object and leads to improved images. The method can be readily extended to CT imaging of other anatomical regions and other applications.