Cong Wenxiang, Xi Yan, Fitzgerald Paul, De Man Bruno, Wang Ge
Biomedical Imaging Center, Center for Biotechnology & Interdisciplinary, Department of Biomedical Engineering, School of Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USA.
Shanghai First-Imaging Tech, Shanghai, China.
Patterns (N Y). 2020 Oct 19;1(8):100128. doi: 10.1016/j.patter.2020.100128. eCollection 2020 Nov 13.
Conventional single-spectrum computed tomography (CT) reconstructs a spectrally integrated attenuation image and reveals tissues morphology without any information about the elemental composition of the tissues. Dual-energy CT (DECT) acquires two spectrally distinct datasets and reconstructs energy-selective (virtual monoenergetic [VM]) and material-selective (material decomposition) images. However, DECT increases system complexity and radiation dose compared with single-spectrum CT. In this paper, a deep learning approach is presented to produce VM images from single-spectrum CT images. Specifically, a modified residual neural network (ResNet) model is developed to map single-spectrum CT images to VM images at pre-specified energy levels. This network is trained on clinical DECT data and shows excellent convergence behavior and image accuracy compared with VM images produced by DECT. The trained model produces high-quality approximations of VM images with a relative error of less than 2%. This method enables multi-material decomposition into three tissue classes, with accuracy comparable with DECT.
传统的单谱计算机断层扫描（CT）重建的是光谱积分衰减图像，只能显示组织形态，而不提供任何关于组织元素组成的信息。双能CT（DECT）获取两个光谱不同的数据集，并重建能量选择性（虚拟单能[VM]）和物质选择性（物质分解）图像。然而，与单谱CT相比，DECT增加了系统复杂性和辐射剂量。本文提出了一种深度学习方法，用于从单谱CT图像生成VM图像。具体而言，开发了一种改进的残差神经网络（ResNet）模型，将单谱CT图像映射到预先指定能量水平的VM图像。该网络在临床DECT数据上进行训练，与DECT生成的VM图像相比，显示出优异的收敛行为和图像准确性。训练后的模型生成的VM图像高质量近似值的相对误差小于2%。该方法能够将多物质分解为三种组织类型，其准确性与DECT相当。
