Li Liang, Wang Bigong, Wang Ge
Department of Engineering Physics, Tsinghua University, Beijing, China.
Key Laboratory of Particle & Radiation Imaging (Tsinghua University), Ministry of Education, China.
J Xray Sci Technol. 2016;24(1):161-75. doi: 10.3233/XST-160540.
In this paper, we formulate the joint/simultaneous X-ray CT and MRI image reconstruction. In particular, a novel algorithm is proposed for MRI image reconstruction from highly under-sampled MRI data and CT images. It consists of two steps. First, a training dataset is generated from a series of well-registered MRI and CT images on the same patients. Then, an initial MRI image of a patient can be reconstructed via edge-oriented dual-dictionary guided enrichment (EDGE) based on the training dataset and a CT image of the patient. Second, an MRI image is reconstructed using the dictionary learning (DL) algorithm from highly under-sampled k-space data and the initial MRI image. Our algorithm can establish a one-to-one correspondence between the two imaging modalities, and obtain a good initial MRI estimation. Both noise-free and noisy simulation studies were performed to evaluate and validate the proposed algorithm. The results with different under-sampling factors show that the proposed algorithm performed significantly better than those reconstructed using the DL algorithm from MRI data alone.
在本文中，我们阐述了联合/同步X射线计算机断层扫描（CT）与磁共振成像（MRI）图像重建方法。具体而言，我们提出了一种用于从高度欠采样的MRI数据和CT图像重建MRI图像的新算法。该算法包括两个步骤。首先，从同一患者的一系列配准良好的MRI和CT图像生成一个训练数据集。然后，基于该训练数据集和患者的CT图像，通过基于边缘导向双字典引导富集（EDGE）的方法重建患者的初始MRI图像。其次，使用字典学习（DL）算法从高度欠采样的k空间数据和初始MRI图像重建MRI图像。我们的算法可以在两种成像模态之间建立一对一的对应关系，并获得良好的初始MRI估计。我们进行了无噪声和有噪声的模拟研究，以评估和验证所提出的算法。不同欠采样因子的结果表明，所提出的算法比仅使用DL算法从MRI数据重建的算法表现显著更好。
