| 引用本文: | 张庭宇,吴凡,金潼,孙宇,刘进,亢艳芹.基于 Transformer 块的混合域网络稀疏角度 CT 成像(J/M/D/N,J:杂志，M：书，D：论文，N：报纸).期刊名称,2024，41（5）：38-48 |
| CHEN X. Adap tive slidingmode contr ol for discrete2ti me multi2inputmulti2 out put systems[ J ]. Aut omatica, 2006, 42(6): 4272-435 |
|
| 摘要: |
| 目的 针对计算机断层扫描( Computed Tomography,CT) 中由于不完全扫描数据导致图像噪声伪影严重的问
题,提出一种基于 Transformer 块的混合域网络稀疏角度 CT 成像算法( Hybrid Domain network for sparse view CT
imaging based on Transformer,HDTransformer) 。 方法 算法的主要思想是借助于新型的 Transformer 网络,构建适用于
多阶段稀疏角度 CT 投影数据及图像数据的处理流,以提高稀疏角度 CT 图像重建质量;与现有两阶段混合域处理
方法相比,本方法采用图像域-投影域-图像域三阶段混合处理流程,通过多阶段信息的联合互补提高成像质量;此
外,针对不同阶段数据噪声伪影特点设计不同的 Transformer 块,以实现差异化的处理;更进一步,算法采用可微分
的解析重建和投影运算,建立投影域与图像域数据的转换,最终实现端到端的稀疏角度 CT 优质成像流。 结果 通
过 Mayo 数据实验验证,其视觉结果表明:处理后的不同部位 CT 图像噪声伪影均能够得到较好的抑制;量化结果表
明:处理后的 CT 图像峰值信噪比和特征相似性均优于对比方法。 结论 实验的定性和定量结果表明:所提算法在
去除图像伪影噪声方面要优于其他算法,具有更高的质量,验证了该方法的有效性。 |
| 关键词: 深度学习 图像修复 Transformer 模块 混合域 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| ybrid Domain Network for Sparse View CT Imaging Based on Transformer Blocks |
|
ZHANG Tingyu, WU Fan, JIN Tong, SUN Yu, LIU Jin KANG, Yanqin
|
|
School of Computer and Information Anhui Polytechnic University Anhui Wuhu 241000 China
|
| Abstract: |
| A hybrid domain network for sparse view CT imaging based on Transformer HDTransformer was
proposed to address the serious image noise artifacts caused by incomplete scanning data in computed tomography CT .
Methods The main concept of the algorithm was to utilize a novel Transformer network to construct a processing flow
suitable for multi-stage sparse view CT projection data and image data to improve the quality of sparse view CT image
reconstruction. In comparison to existing two-stage hybrid domain processing methods this approach adopted a three-stage
hybrid processing flow of image domain-projection domain-image domain enhancing imaging quality through the joint
complementary information of multiple stages. Furthermore different Transformer blocks were designed based on the
characteristics of noise and artifacts in data at different stages for differentiated processing. Moreover the algorithm
adopted differentiable analytical reconstruction and projection operations to establish the conversion of data between
projection domain and image domain ultimately achieving end-to-end high-quality sparse view CT imaging flow. Results
Through Mayo data experimental verification the visual results showed that the processed CT images of different parts
effectively suppressed noise artifacts. The quantization results showed that the peak signal-to-noise ratio and feature
similarity of the processed CT images were better than those of the comparison method. Conclusion The qualitative and quantitative results of the experiment indicate that the proposed algorithm outperforms other algorithms in removing image
artifacts and has higher quality verifying the effectiveness of this method. |
| Key words: deep learning image restoration Transformer blocks hybrid domain |
