Awesome Computed Tomography EN 在 GitHub 上加星标

内部、感兴趣区与截断重建

当物体宽于 X 射线束或探测器时,每个投影都会缺失一部分,这就是截断。在感兴趣区(ROI)与内部重建中,截断是有意为之——只照射需要的区域以降低剂量;而当患者体型较大,或牙科、C 形臂探测器较小、身体有一部分落在视野之外时,截断则无法避免。

滤波反投影需要完整的投影,截断数据会在图像中产生明亮的边缘与低频阴影。内部问题——只用穿过某区域的射线重建该区域——一般没有唯一解,但只要有少量先验知识(例如一块已知子区域)就可以求解。实用方法包括外推缺失的投影数据、使用微分反投影,或做正则化迭代重建。

学习型方法如今被用来扩展截断扫描的视野、减少锥束与牙科 CT 的截断伪影,并直接重建内部区域;扩散先验与隐式神经表示是其中较新的工具。

在可检索的目录中浏览全部 12 篇「内部、感兴趣区与截断重建」论文

入门推荐

如果你刚接触这个主题,可以先读这几篇;由维护者挑选。

论文

全部 12 篇,按时间倒序。

论文发表出处年份链接
Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based RefinementMICAD2026paper · code
Texture-preserving implicit neural representation for cone-beam CT truncated reconstruction预印本2026paper
Truncated projection adaptive weighting combined with adaptive TV for artifact reduction in linear computed laminographyOpt. Laser Technol.2026paper
Truncation artifact reduction in cone-beam computed tomography scans using conditional generative diffusion modelsBMC Med Imaging2026paper
An Iterative Reconstruction Method for Dental Cone-Beam Computed Tomography with a Truncated Field of View预印本2025paper
Disentangled deep learning method for interior tomographic reconstruction of low-dose x-ray CTPMB2025paper
Deep learning-based volume of interest imaging in helical CT for image quality improvement and radiation dose reductionBr. J. Radiol.2025paper
Deep-Interior: A new pathway to interior tomographic image reconstruction via a weighted backprojection and deep learningMed Phys2024paper
Deep learning-based extended field of view computed tomography image reconstruction: influence of network design on image estimation outside the scan field of viewBiomed. Phys. Eng. Express2022paper
End-to-End Deep Learning for Interior Tomography with Low-Dose X-ray CTPMB2022paper
One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated BackprojectionMed Phys2019paper
Tiny a priori knowledge solves the interior problem in computed tomographyPMB2008paper

在可检索的目录中浏览全部 12 篇「内部、感兴趣区与截断重建」论文

其他主题