Material Decomposition Problem in Spectral CT: A Transfer Deep Learning Approach
Material Decomposition Problem in Spectral CT: A Transfer Deep Learning Approach
复制标题
DOI：
10.1109/isbiworkshops50223.2020.9153440
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
J. Abascal;N. Ducros;V. Pronina;S. Bussod;A. Hauptmann;S. Arridge;P. Douek;F. Peyrin
中科院分区：
文献类型：
--
作者：
J. Abascal;N. Ducros;V. Pronina;S. Bussod;A. Hauptmann;S. Arridge;P. Douek;F. Peyrin
目前用于解决谱计算机层析成像中非线性材料分解问题的基于模型的变分方法依赖于扫描器能量响应的先验知识，但这通常是未知的或在空间上变化的。我们提出了一种两步深度迁移学习方法，该方法可以学习扫描器的能量响应及其在探测器像素上的变化。首先，我们在假设理想数据的大数据集上预训练U-Net，其次，我们使用与非理想场景相对应的少量数据来微调预先训练的模型。我们通过数字胸腔模体来评估它，这些模体包括软组织、骨骼和用Gd标记的肾脏，这些都是从Kits19数据集建立的。我们发现，该方法在不需要扫描器能量响应的先验知识的情况下解决了材料分解问题。我们将我们的方法与正则化的高斯-牛顿法进行了比较，获得了更好的图像质量。
Current model-based variational methods used for solving the nonlinear material decomposition problem in spectral computed tomography rely on prior knowledge of the scanner energy response, but this is generally unknown or spatially varying. We propose a twostep deep transfer learning approach that can learn the energy response of the scanner and its variation across the detector pixels. First, we pretrain U-Net on a large data set assuming ideal data, and, second, we fine-tune the pretrained model using few data corresponding to a non-ideal scenario. We assess it on numerical thorax phantoms that comprise soft tissue, bone and kidneys marked with gadolinium, which are built from the kits19 dataset. We find that the proposed method solves the material decomposition problem without prior knowledge of the scanner energy response. We compare our approach to a regularized Gauss-Newton method and obtain a superior image quality.