Deep learning-based motion compensation for four-dimensional cone-beam computed tomography (4D-CBCT) reconstruction.
Deep learning-based motion compensation for four-dimensional cone-beam computed tomography (4D-CBCT) reconstruction.
复制标题
DOI：
10.1002/mp.16103
复制
发表时间：
2023-02
期刊：
影响因子：
3.8
通讯作者：
Hugo, Geoffrey D.
中科院分区：
文献类型：
--
作者：
Zhang, Zhehao;Liu, Jiaming;Yang, Deshan;Kamilov, Ulugbek S.;Hugo, Geoffrey D.
运动补偿 (MoCo) 重建在提高四维锥形束计算机断层扫描 (4D-CBCT) 图像质量方面显示出巨大的前景。使用 CBCT 成像时的运动信息进行 4D-CBCT 的 MoCo 重建可能比从以前的 4D-CT 扫描获得的信息更准确。然而，这种数据驱动的方法受到用于运动建模的初始 4D-CBCT 图像质量的阻碍。本研究旨在开发一种深度学习方法来生成用于 MoCo 重建的高质量运动模型，以提高最终 4D-CBCT 图像的质量。提出了一种 3D 伪影减少卷积神经网络 (CNN)，通过减少欠采样引起的条纹伪影，同时保持运动信息，来改进传统的相位相关 Feldkamp-Davis-Kress (PCF) 重建。然后使用 CNN 生成的消除伪影的 4D-CBCT 图像（CNN 增强）来构建 MoCo 重建所使用的运动模型 ()。使用体内患者数据集、扩展心脏躯干 (XCAT) 模型和公共 SPARE 挑战数据集对所提出的程序进行了评估。使用均方根误差 (RMSE) 和归一化互相关 (NCC) 定量评估 XCAT 体模和 SPARE 数据集的重建图像的质量。经过训练的 CNN 有效减少了所有数据集的 PCF CBCT 图像的条纹伪影。使用所提出的重建程序可以恢复更详细的结构。 XCAT体模实验表明，使用CNN增强图像估计运动模型的准确性比PCF有很大提高。 与 PCF、CNN 增强和传统 MoCo 相比，显示出更低的 RMSE 和更高的 NCC。对于 SPARE 数据集，PCF、CNN 增强、传统 MoCo 的身体区域的平均（±标准差）RMSE（以 mm−1 为单位）分别为 0.0040 ± 0.0009、0.0029 ± 0.0002、0.0024 ± 0.0003 和 0.0021 ± 0.0003。相应的 NCC 为 0.84 ± 0.05、0.91 ± 0.05、0.91 ± 0.05 和 0.93 ± 0.04。基于 CNN 的伪影减少可以大幅减少初始 4D-CBCT 图像中的伪影。改进后的图像可用于增强运动建模，并最终提高使用 MoCo 重建的最终 4D-CBCT 图像的质量。
Motion-compensated (MoCo) reconstruction shows great promise in improving four-dimensional cone-beam computed tomography (4D-CBCT) image quality. MoCo reconstruction for a 4D-CBCT could be more accurate using motion information at the CBCT imaging time than that obtained from previous 4D-CT scans. However, such data-driven approaches are hampered by the quality of initial 4D-CBCT images used for motion modeling. This study aims to develop a deep-learning method to generate high-quality motion models for MoCo reconstruction to improve the quality of final 4D-CBCT images. A 3D artifact-reduction convolutional neural network (CNN) was proposed to improve conventional phase-correlated Feldkamp–Davis–Kress (PCF) reconstructions by reducing undersampling-induced streaking artifacts while maintaining motion information. The CNN-generated artifact-mitigated 4D-CBCT images (CNN enhanced) were then used to build a motion model which was used by MoCo reconstruction (). The proposed procedure was evaluated using in-vivo patient datasets, an extended cardiac-torso (XCAT) phantom, and the public SPARE challenge datasets. The quality of reconstructed images for XCAT phantom and SPARE datasets was quantitatively assessed using root-mean-square-error (RMSE) and normalized cross-correlation (NCC). The trained CNN effectively reduced the streaking artifacts of PCF CBCT images for all datasets. More detailed structures can be recovered using the proposed reconstruction procedure. XCAT phantom experiments showed that the accuracy of estimated motion model using CNN enhanced images was greatly improved over PCF. showed lower RMSE and higher NCC compared to PCF, CNN enhanced and conventional MoCo. For the SPARE datasets, the average (± standard deviation) RMSE in mm−1 for body region of PCF, CNN enhanced, conventional MoCo and were 0.0040 ± 0.0009, 0.0029 ± 0.0002, 0.0024 ± 0.0003 and 0.0021 ± 0.0003. Corresponding NCC were 0.84 ± 0.05, 0.91 ± 0.05, 0.91 ± 0.05 and 0.93 ± 0.04. CNN-based artifact reduction can substantially reduce the artifacts in the initial 4D-CBCT images. The improved images could be used to enhance the motion modeling and ultimately improve the quality of the final 4D-CBCT images reconstructed using MoCo.
登录
查看更多内容
影响因子：
3.8
作者：
Riblett MJ;Christensen GE;Weiss E;Hugo GD
通讯作者：
Hugo GD
影响因子：
3.8
作者：
Huang, Xiaokun;Zhang, You;Wang, Jing
通讯作者：
Wang, Jing
DOI：
10.1016/s0360-3016(02)02884-5
发表时间：
2002-08-01
影响因子：
7
作者：
Jaffray, DA;Siewerdsen, JH;Martinez, AA
通讯作者：
Martinez, AA
影响因子：
3.5
作者：
Li, T;Schreibmann, E;Xing, L
通讯作者：
Xing, L
DOI：
10.1016/j.ijrobp.2008.11.066
发表时间：
2009-11-01
影响因子：
7
作者：
Bissonnette, Jean-Pierre;Franks, Kevin N.;Bezjak, Andrea
通讯作者：
Bezjak, Andrea