Iterative quality enhancement via residual-artifact learning networks for low-dose CT
Iterative quality enhancement via residual-artifact learning networks for low-dose CT
复制标题
DOI：
10.1088/1361-6560/aae511
复制
发表时间：
2018-10
影响因子：
3.5
通讯作者：
Yongbo Wang;Yuting Liao;Yuanke Zhang;Ji He;Sui Li;Z. Bian;Hao Zhang;Yuanyuan Gao;Deyu Meng-Dey
中科院分区：
文献类型：
--
作者：
Yongbo Wang;Yuting Liao;Yuanke Zhang;Ji He;Sui Li;Z. Bian;Hao Zhang;Yuanyuan Gao;Deyu Meng-Dey
计算机断层扫描（CT）扫描中患者的辐射暴露和相关癌症风险一直是主要的临床问题。通过降低X射线管电流（mA）可有效降低辐射暴露。然而，这种策略可能会导致过多的噪声和条纹伪影在传统的滤波反投影重建图像。为了解决这个问题，一些基于深度卷积神经网络（ConvNet）的方法已经被开发用于低剂量CT成像，这是受到机器学习最近发展的启发。然而，ConvNet重建的一些图像纹理可能会被严重的条纹破坏，特别是在超低剂量的情况下，这可能接近假体并妨碍诊断。因此，在这项工作中，我们提出了一种迭代残差伪影学习ConvNet（IRLNet）方法，以提高基于ConvNet的方法的重建性能。具体而言，建议IRLNet估计噪声中的高频细节，然后迭代地去除它们;在消除低剂量CT图像中的严重条纹后，剩余的低频细节可以通过常规网络进行处理。此外，所提出的IRLNet方案可以扩展为定量双能CT/脑灌注CT成像和统计迭代重建的鲁棒处理。利用真实的患者数据对所提出的IRLNet方法进行了评价，实验结果表明，所提出的IRLNet方法在有效降低图像噪声和条纹伪影的同时，较好地保留了边缘细节，优于以往基于ConvNet的方法，表明所提出的IRLNet方法可用于改善CT图像质量，特别是在超低剂量情况下。
Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.