Spectral computed tomography (CT) has attracted much attention in radiation dose reduction, metal artifacts removal, tissue quantification and material discrimination. The x-ray energy spectrum is divided into several bins, each energy-bin-specific projection has a low signal-noise-ratio (SNR) than the current-integrating counterpart, which makes image reconstruction a unique challenge. Traditional wisdom is to use prior knowledge based iterative methods. However, this kind of methods demands a great computational cost. Inspired by deep learning, here we first develop a deep learning based reconstruction method; i.e., U-net with ${\mathit{L}}_p^p$-norm, Total variation, Residual learning, and Anisotropic adaption (ULTRA). Specifically, we emphasize the various multi-scale feature fusion and multichannel filtering enhancement with a denser connection encoding architecture for residual learning and feature fusion. To address the image deblurring problem associated with the $L_2^2$- loss, we propose a general $L_p^p$-loss, $p>0$. Furthermore, the images from different energy bins share similar structures of the same object, the regularization characterizing correlations of different energy bins is incorporated into the $L_p^p$- loss function, which helps unify the deep learning based methods with traditional compressed sensing based methods. Finally, the anisotropically weighted total variation is employed to characterize the sparsity in the spatial–spectral domain to regularize the proposed network In particular, we validate our ULTRA networks on three large-scale spectral CT datasets, and obtain excellent results relative to the competing algorithms. In conclusion, our quantitative and qualitative results in numerical simulation and preclinical experiments demonstrate that our proposed approach is accurate, efficient and robust for high-quality spectral CT image reconstruction.

光谱计算机断层扫描 (CT) 在辐射剂量降低、金属伪影去除、组织量化和材料鉴别方面引起了很多关注。X 射线能谱被分成几个区间，每个特定于能量区间的投影的信噪比 (SNR) 比当前积分对应物低，这使得图像重建成为一项独特的挑战。传统智慧是使用基于先验知识的迭代方法。然而，这种方法需要很大的计算成本。受深度学习的启发，这里我们首先开发了一种基于深度学习的重建方法；即，U- net 与${\mathit{升}}_p^p$范数，Ť otal变型中，- [R esidual学习，和甲nisotropic适应（ULTRA）。具体来说，我们强调各种多尺度特征融合和多通道滤波增强，以及用于残差学习和特征融合的更密集连接编码架构。为了解决与图像相关的图像去模糊问题${升}_2^2$- 损失，我们建议一般 ${升}_p^p$-损失， $p>0$. 此外，来自不同能量仓的图像共享同一对象的相似结构，将表征不同能量仓的相关性的正则化纳入到${升}_p^p$- 损失函数，有助于将基于深度学习的方法与基于传统压缩感知的方法统一起来。最后，使用各向异性加权的总变差来表征空间光谱域中的稀疏性，以正则化所提出的网络 特别是，我们在三个大规模光谱 CT 数据集上验证了我们的 ULTRA 网络，并获得了相对于竞争算法的出色结果. 总之，我们在数值模拟和临床前实验中的定量和定性结果表明，我们提出的方法对于高质量光谱 CT 图像重建是准确、有效和稳健的。