当前位置: X-MOL 学术IEEE Trans. Med. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DICDNet: Deep Interpretable Convolutional Dictionary Network for Metal Artifact Reduction in CT Images
IEEE Transactions on Medical Imaging ( IF 8.9 ) Pub Date : 2021-11-09 , DOI: 10.1109/tmi.2021.3127074
Hong Wang 1 , Yuexiang Li 1 , Nanjun He 1 , Kai Ma 1 , Deyu Meng 2 , Yefeng Zheng 1
Affiliation  

Computed tomography (CT) images are often impaired by unfavorable artifacts caused by metallic implants within patients, which would adversely affect the subsequent clinical diagnosis and treatment. Although the existing deep-learning-based approaches have achieved promising success on metal artifact reduction (MAR) for CT images, most of them treated the task as a general image restoration problem and utilized off-the-shelf network modules for image quality enhancement. Hence, such frameworks always suffer from lack of sufficient model interpretability for the specific task. Besides, the existing MAR techniques largely neglect the intrinsic prior knowledge underlying metal-corrupted CT images which is beneficial for the MAR performance improvement. In this paper, we specifically propose a deep interpretable convolutional dictionary network (DICDNet) for the MAR task. Particularly, we first explore that the metal artifacts always present non-local streaking and star-shape patterns in CT images. Based on such observations, a convolutional dictionary model is deployed to encode the metal artifacts. To solve the model, we propose a novel optimization algorithm based on the proximal gradient technique. With only simple operators, the iterative steps of the proposed algorithm can be easily unfolded into corresponding network modules with specific physical meanings. Comprehensive experiments on synthesized and clinical datasets substantiate the effectiveness of the proposed DICDNet as well as its superior interpretability, compared to current state-of-the-art MAR methods. Code is available at https://github.com/hongwang01/DICDNet .

中文翻译:


DICDNet:用于减少 CT 图像中金属伪影的深度可解释卷积字典网络



计算机断层扫描(CT)图像常常因患者体内金属植入物造成的不良伪影而受损,这会对后续的临床诊断和治疗产生不利影响。尽管现有的基于深度学习的方法在 CT 图像的金属伪影减少(MAR)方面取得了可喜的成功,但大多数方法将该任务视为一般图像恢复问题,并利用现成的网络模块来增强图像质量。因此,此类框架总是缺乏针对特定任务的足够的模型可解释性。此外,现有的 MAR 技术很大程度上忽略了金属损坏 CT 图像背后的内在先验知识,这有利于 MAR 性能的提高。在本文中,我们专门为 MAR 任务提出了一种深度可解释卷积字典网络(DICDNet)。特别是,我们首先探索金属伪影在 CT 图像中总是呈现非局部条纹和星形图案。基于这些观察结果,部署卷积字典模型来对金属制品进行编码。为了求解该模型,我们提出了一种基于近端梯度技术的新型优化算法。只需简单的算子,该算法的迭代步骤就可以很容易地展开为具有特定物理意义的相应网络模块。与当前最先进的 MAR 方法相比,对合成和临床数据集的综合实验证实了所提出的 DICDNet 的有效性及其卓越的可解释性。代码可在 https://github.com/hongwang01/DICDNet 获取。
更新日期:2021-11-09
down
wechat
bug