基于双域Transformer耦合特征学习的CT截断数据重建模型  

Reconstruction from CT truncated data based on dual-domain transformer coupled feature learning

作　　者：汪辰 蒙铭强 李明强 王永波[1,2] 曾栋 边兆英[1,2] 马建华 WANG Chen;MENG Mingqiang;LI Mingqiang;WANG Yongbo;ZENG Dong;BIAN Zhaoying;MA Jianhua(School of Biomedical Engineering,Southern Medical University,Guangzhou 510515,China;Pazhou Lab(Huangpu),Guangzhou 510005,China)

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515 [2]琶洲实验室(黄埔),广东广州510005

出　　处：《南方医科大学学报》2024年第5期950-959,共10页Journal of Southern Medical University

基　　金：国家自然科学基金(U21A6005)。

摘　　要：目的为解决CT扫描视野(FOV)不足导致的截断伪影和图像结构失真问题,本文提出了一种基于投影和图像双域Transformer耦合特征学习的CT截断数据重建模型(DDTrans)。方法基于Transformer网络分别构建投影域和图像域恢复模型,利用Transformer注意力模块的远距离依赖建模能力捕捉全局结构特征来恢复投影数据信息,增强重建图像。在投影域和图像域网络之间构建可微Radon反投影算子层,使得DDTrans能够进行端到端训练。此外,引入投影一致性损失来约束图像前投影结果,进一步提升图像重建的准确性。结果Mayo仿真数据实验结果表明,在部分截断和内扫描两种截断情况下,本文方法DDTrans在去除FOV边缘的截断伪影和恢复FOV外部信息等方面效果均优于对比算法。结论DDTrans模型可以有效去除CT截断伪影,确保FOV内数据的精确重建,同时实现FOV外部数据的近似重建。Objective To propose a CT truncated data reconstruction model(DDTrans)based on projection and image dual-domain Transformer coupled feature learning for reducing truncation artifacts and image structure distortion caused by insufficient field of view(FOV)in CT scanning.Methods Transformer was adopted to build projection domain and image domain restoration models,and the long-range dependency modeling capability of the Transformer attention module was used to capture global structural features to restore the projection data information and enhance the reconstructed images.We constructed a differentiable Radon back-projection operator layer between the projection domain and image domain networks to enable end-to-end training of DDTrans.Projection consistency loss was introduced to constrain the image forward-projection results to further improve the accuracy of image reconstruction.Results The experimental results with Mayo simulation data showed that for both partial truncation and interior scanning data,the proposed DDTrans method showed better performance than the comparison algorithms in removing truncation artifacts at the edges and restoring the external information of the FOV.Conclusion The DDTrans method can effectively remove CT truncation artifacts to ensure accurate reconstruction of the data within the FOV and achieve approximate reconstruction of data outside the FOV.

关 键 词：CT截断伪影 TRANSFORMER 深度学习 双域 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R817[自动化与计算机技术—计算机科学与技术]