Filtered back projection (FBP) is the most widely used method for image reconstruction in X-ray computed tomography (CT) scanners, and can produce excellent images in many cases. However, the presence of dense materials, such as metals, can strongly attenuate or even completely block X-rays, producing severe streaking artifacts in the FBP reconstruction. These metal artifacts can greatly limit subsequent object delineation and information extraction from the images, restricting their diagnostic value. This problem is particularly acute in the security domain, where there is great heterogeneity in the objects that can appear in a scene, highly accurate decisions must be made quickly, and processing time is highly constrained. The standard practical approaches to reducing metal artifacts in CT imagery are either simplistic nonadaptive interpolation-based projection data completion methods or direct image post-processing methods. These standard approaches have had limited success. Motivated primarily by security applications, we present a new deep-learning-based metal artifact reduction approach that tackles the problem in the projection data domain. We treat the projection data corresponding to dense, metal objects as missing data and train an adversarial deep network to complete the missing data directly in the projection domain. The subsequent complete projection data is then used with conventional FBP to reconstruct an image intended to be free of artifacts. This new approach results in an end-to-end metal artifact reduction algorithm that is computationally efficient textcolorredand therefore practical and fits well into existing CT workflows allowing easy adoption in existing scanners. Training deep networks can be challenging, and another contribution of our work is to demonstrate that training data generated using an accurate X-ray simulation can be used to successfully train the deep network, when combined with transfer learning using limited real data sets. We demonstrate the effectiveness and potential of our algorithm on simulated and real examples.

中文翻译：

---

使用 Data Domain 深度学习快速增强 CT 金属伪影减少

滤波反投影 (FBP) 是 X 射线计算机断层扫描 (CT) 扫描仪中最广泛使用的图像重建方法，并且在许多情况下可以产生出色的图像。然而，金属等致密材料的存在会强烈衰减甚至完全阻挡 X 射线，在 FBP 重建中产生严重的条纹伪影。这些金属伪影会极大地限制随后从图像中提取对象和信息，从而限制其诊断价值。这个问题在安全领域尤为突出，场景中可能出现的对象存在很大的异质性，必须快速做出高度准确的决策，并且处理时间受到高度限制。减少 CT 图像中金属伪影的标准实用方法是简单的基于非自适应插值的投影数据完成方法或直接图像后处理方法。这些标准方法的成功有限。主要受安全应用程序的启发，我们提出了一种新的基于深度学习的金属伪影减少方法，该方法可以解决投影数据领域的问题。我们将与密集、金属物体对应的投影数据视为缺失数据，并训练对抗性深度网络直接在投影域中完成缺失数据。随后的完整投影数据随后与传统 FBP 一起使用，以重建旨在消除伪影的图像。这种新方法产生了一种端到端的金属伪影减少算法，该算法在计算上是高效的 textcolorred，因此实用且非常适合现有的 CT 工作流程，允许在现有扫描仪中轻松采用。训练深度网络可能具有挑战性，我们工作的另一个贡献是证明了使用准确的 X 射线模拟生成的训练数据，当与使用有限真实数据集的迁移学习相结合时，可用于成功训练深度网络。我们证明了我们的算法在模拟和真实示例上的有效性和潜力。我们工作的另一个贡献是证明了使用准确的 X 射线模拟生成的训练数据，当与使用有限真实数据集的迁移学习相结合时，可以成功地训练深度网络。我们证明了我们的算法在模拟和真实示例上的有效性和潜力。我们工作的另一个贡献是证明了使用准确的 X 射线模拟生成的训练数据，当与使用有限真实数据集的迁移学习相结合时，可以成功地训练深度网络。我们证明了我们的算法在模拟和真实示例上的有效性和潜力。