基于自注意力机制U-net的微焦CT去射线源模糊方法  

Source Blur Elimination in Micro-CT Using Self-Attention-Based U-Net

作　　者：刘川江 王奥 张根源 袁伟[2] 刘丰林[1,2] Liu Chuanjiang;Wang Ao;Zhang Genyuan;Yuan Wei;Liu Fenglin(College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400044,China;Engineering Research Center of Industrial Computed Tomography Non-Destructive Testing,Ministry of Education,Chongqing University,Chongqing 400044,China)

机构地区：[1]重庆大学机械与运载工程学院,重庆400044 [2]重庆大学工业CT无损检测教育部工程研究中心,重庆400044

出　　处：《光学学报》2024年第7期293-301,共9页Acta Optica Sinica

基　　金：国家重点研发计划(2022YFF0706400);中央高校基本科研业务费(2023CDJXY-005)。

摘　　要：在微焦CT成像中,通常利用增大X射线源管电压、管电流来提高扫描效率,但射线源功率增加会导致焦点尺寸增大,投影图像模糊,从而降低重建图像的空间分辨率。为了解决因非理想射线源焦点引起的图像模糊问题,本文提出利用深度学习在投影域映射非理想焦点与理想焦点投影之间的关系。推导了理想焦点投影与非理想焦点投影的正向关系,基于该关系构建配对数据集;提出一种基于自注意力机制的U-net网络(SU-net)学习非理想焦点投影到理想焦点投影的逆向关系。仿真实验和实际实验结果表明,提出的SU-net方法能准确地从非理想焦点投影中估计出理想焦点投影,可有效减少焦点导致的图像模糊。Objective Spatial resolution of X-ray imaging systems is crucial for microstructural object studies due to the small size of the subjects.Specifically,the focal spot size of the X-ray source is a main factor affecting the spatial resolution of microcomputed tomography(micro-CT),which will produce penumbra blur on detectors and thus blur the reconstructed images and reduce spatial resolution.Meanwhile,reducing the focal spot size by decreasing the X-ray tube power is a straightforward solution,but will prolong the scan duration.Therefore,we aim to develop a deep learning-based strategy by learning the inverse finite focal spot model to mitigate the penumbra blur for obtaining CT images with high spatial resolution even in the case of a non-ideal X-ray source.Methods First,we derive the finite focal spot model that builds a relationship from the ideal point source projection to the finite focal spot projection.Based on the derived model,we numerically compute a paired projection dataset.Second,we utilize the neural network U-net and an attention mechanism module of convolution modulation block to build a selfattention mechanism-based U-net(SU-net)and thus learn the inverse finite focal spot model.The goal is to estimate the ideal point source projection from the actual non-ideal focal spot projection.SU-net(Fig.1)which introduces convolution modulation blocks into the contracting path of the U-net is proposed to boost the U-net property.Finally,the standard filtered back-projection(FBP)is employed for reconstruction using the estimated ideal point projection.Results and Discussions Simulation experiments are performed by the public dataset 2DeteCT to verify the effectiveness of the SU-net,which consists of a wide variety of dried fruits,nuts,and different types of rocks.Two groups of results are randomly selected in the test dataset for visualization(Fig.2)and quantitative indicators are tested on the whole test dataset(Fig.3).The results show that our proposed SU-net can estimate the ideal point source projection

关 键 词：计算机断层扫描 微焦点CT 空间分辨率 深度学习 X射线源焦点 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]