Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, Germany.
Munich School of BioEngineering, Technical University of Munich, Garching, Germany.
Med Phys. 2024 Oct;51(10):7404-7414. doi: 10.1002/mp.17305. Epub 2024 Jul 16.
Computed tomography (CT) relies on the attenuation of x-rays, and is, hence, of limited use for weakly attenuating organs of the body, such as the lung. X-ray dark-field (DF) imaging is a recently developed technology that utilizes x-ray optical gratings to enable small-angle scattering as an alternative contrast mechanism. The DF signal provides structural information about the micromorphology of an object, complementary to the conventional attenuation signal. A first human-scale x-ray DF CT has been developed by our group. Despite specialized processing algorithms, reconstructed images remain affected by streaking artifacts, which often hinder image interpretation. In recent years, convolutional neural networks have gained popularity in the field of CT reconstruction, amongst others for streak artefact removal.
Reducing streak artifacts is essential for the optimization of image quality in DF CT, and artefact free images are a prerequisite for potential future clinical application. The purpose of this paper is to demonstrate the feasibility of CNN post-processing for artefact reduction in x-ray DF CT and how multi-rotation scans can serve as a pathway for training data.
We employed a supervised deep-learning approach using a three-dimensional dual-frame UNet in order to remove streak artifacts. Required training data were obtained from the experimental x-ray DF CT prototype at our institute. Two different operating modes were used to generate input and corresponding ground truth data sets. Clinically relevant scans at dose-compatible radiation levels were used as input data, and extended scans with substantially fewer artifacts were used as ground truth data. The latter is neither dose-, nor time-compatible and, therefore, unfeasible for clinical imaging of patients.
The trained CNN was able to greatly reduce streak artifacts in DF CT images. The network was tested against images with entirely different, previously unseen image characteristics. In all cases, CNN processing substantially increased the image quality, which was quantitatively confirmed by increased image quality metrics. Fine details are preserved during processing, despite the output images appearing smoother than the ground truth images.
Our results showcase the potential of a neural network to reduce streak artifacts in x-ray DF CT. The image quality is successfully enhanced in dose-compatible x-ray DF CT, which plays an essential role for the adoption of x-ray DF CT into modern clinical radiology.
计算机断层扫描（CT）依赖于 X 射线的衰减，因此对于身体中衰减较弱的器官（如肺）的成像效果有限。X 射线暗场（DF）成像是一种最近开发的技术，它利用 X 射线光学光栅来实现小角度散射作为替代对比机制。DF 信号提供了关于物体微观形态的结构信息，与传统的衰减信号互补。我们小组已经开发出了第一个人类规模的 X 射线 DF CT。尽管使用了专门的处理算法，但重建图像仍然受到条纹伪影的影响，这常常阻碍图像解释。近年来，卷积神经网络在 CT 重建领域得到了广泛的应用，包括用于去除条纹伪影。
减少条纹伪影对于优化 DF CT 的图像质量至关重要，无伪影的图像是潜在未来临床应用的前提。本文的目的是证明在 X 射线 DF CT 中使用 CNN 后处理减少伪影的可行性，以及多旋转扫描如何作为训练数据的途径。
我们使用了一种基于三维双帧 UNet 的监督深度学习方法来去除条纹伪影。所需的训练数据是从我们研究所的实验性 X 射线 DF CT 原型中获得的。使用两种不同的操作模式生成输入和相应的地面真实数据集。使用剂量兼容的辐射水平的临床相关扫描作为输入数据，使用伪影少得多的扩展扫描作为地面真实数据。后者既不具有剂量兼容性，也不具有时间兼容性，因此对于患者的临床成像是不可行的。
训练好的 CNN 能够极大地减少 DF CT 图像中的条纹伪影。该网络针对具有完全不同、以前未见的图像特征的图像进行了测试。在所有情况下，CNN 处理都显著提高了图像质量，这通过增加图像质量指标得到了定量确认。尽管输出图像看起来比地面真实图像更平滑，但在处理过程中仍保留了细微的细节。
我们的结果展示了神经网络在 X 射线 DF CT 中减少条纹伪影的潜力。在剂量兼容的 X 射线 DF CT 中，图像质量得到了成功增强，这对于将 X 射线 DF CT 应用于现代临床放射学至关重要。
