X-ray2Shape: Reconstruction of 3D Liver Shape from a Single 2D Projection Image
X-ray2Shape: Reconstruction of 3D Liver Shape from a Single 2D Projection Image
复制标题
DOI：
10.1109/embc44109.2020.9176655
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Fei Tong;M. Nakao;Shuqiong Wu;M. Nakamura;T. Matsuda
中科院分区：
文献类型：
--
作者：
Fei Tong;M. Nakao;Shuqiong Wu;M. Nakamura;T. Matsuda
计算机断层扫描（CT）和磁共振成像（MRI）扫描仪测量患者的三维（3D）图像。然而，在手术或放射治疗期间仅可以获得低维局部二维（2D）图像。尽管计算机视觉技术已经表明可以从多个2D图像估计3D形状，但是从诸如内窥镜图像或X射线图像的单个2D图像进行形状重建仍然是一个挑战。在这项研究中，我们提出了X-ray 2Shape，它允许从单个2D投影图像重建基于深度学习的3D器官网格。该方法从平均模板和从各个投影图像计算的深度特征学习网格变形。通过器官网格和腹部数字重建X射线图像的实验，验证了该方法的估计性能。
Computed tomography (CT) and magnetic resonance imaging (MRI) scanners measure three-dimensional (3D) images of patients. However, only low-dimensional local two-dimensional (2D) images may be obtained during surgery or radiotherapy. Although computer vision techniques have shown that 3D shapes can be estimated from multiple 2D images, shape reconstruction from a single 2D image such as an endoscopic image or an X-ray image remains a challenge. In this study, we propose X-ray2Shape, which permits a deep learning-based 3D organ mesh to be reconstructed from a single 2D projection image. The method learns the mesh deformation from a mean template and deep features computed from the individual projection images. Experiments with organ meshes and digitally reconstructed radiograph (DRR) images of abdominal regions were performed to confirm the estimation performance of the methods.