A joint deep learning model to recover information and reduce artifacts in missing-wedge sinograms for electron tomography and beyond
A joint deep learning model to recover information and reduce artifacts in missing-wedge sinograms for electron tomography and beyond
复制标题
DOI：
10.1038/s41598-019-49267-x
复制
发表时间：
2019-09-05
影响因子：
4.6
通讯作者：
Xin, Huolin L.
中科院分区：
文献类型：
--
作者：
Ding, Guanglei;Liu, Yitong;Xin, Huolin L.
我们提出了一个基于深度学习的联合模型，该模型旨在对电子断层扫描的缺失楔形sinogram进行涂漆，并减少重建断层扫描中的残余伪影。传统的方法，如加权反投影（WBP）和同步代数重建技术（SART），由于倾斜范围有限，缺乏恢复未获取项目信息的能力；因此，使用这些方法重建的层析图是扭曲的，并受到伸长，条纹和鬼尾伪影的污染。为了解决这个问题，我们首先设计了一个基于在生成对抗网络（GAN）中使用残差密集块的正弦图填充模型。然后，我们使用U-net结构化的生成对抗网络来减少残余伪像。我们构建了一个两步模型，在各自合适的领域中执行信息恢复和工件移除。与传统方法相比，该方法具有更高的峰值信噪比（PSNR）和结构相似指数（SSIM）；即使缺失了45度的楔形，我们的方法也能提供与地面真实情况非常相似的重建图像，几乎没有人工制品。此外，我们的模型不需要人工操作员的输入，也不需要像基于电视的方法那样设置迭代步长和松弛系数等超参数，这些超参数高度依赖于人类的经验和参数微调。
We present a joint model based on deep learning that is designed to inpaint the missing-wedge sinogram of electron tomography and reduce the residual artifacts in the reconstructed tomograms. Traditional methods, such as weighted back projection (WBP) and simultaneous algebraic reconstruction technique (SART), lack the ability to recover the unacquired project information as a result of the limited tilt range; consequently, the tomograms reconstructed using these methods are distorted and contaminated with the elongation, streaking, and ghost tail artifacts. To tackle this problem, we first design a sinogram filling model based on the use of Residual-in-Residual Dense Blocks in a Generative Adversarial Network (GAN). Then, we use a U-net structured Generative Adversarial Network to reduce the residual artifacts. We build a two-step model to perform information recovery and artifacts removal in their respective suitable domain. Compared with the traditional methods, our method offers superior Peak Signal to Noise Ratio (PSNR) and the Structural Similarity Index (SSIM) to WBP and SART; even with a missing wedge of 45 degrees, our method offers reconstructed images that closely resemble the ground truth with nearly no artifacts. In addition, our model has the advantage of not needing inputs from human operators or setting hyperparameters such as iteration steps and relaxation coefficient used in TV-based methods, which highly relies on human experience and parameter fine turning.