ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
ADN: Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
复制标题
DOI：
10.1109/tmi.2019.2933425
复制
发表时间：
2020-03-01
影响因子：
10.6
通讯作者：
Luo, Jiebo
中科院分区：
文献类型：
--
作者：
Liao, Haofu;Lin, Wei-An;Luo, Jiebo
当前基于深度神经网络的计算机断层扫描（CT）金属伪影减少（MAR）方法是依赖于合成金属伪影进行训练的监督方法。然而，由于合成数据可能无法准确模拟CT成像的潜在物理机制，因此监督方法通常难以推广到临床应用。为了解决这个问题，我们提出，据我们所知，第一个无监督学习方法MAR。具体来说，我们引入了一种新的工件解开网络，解开金属工件从CT图像中的潜在空间。它支持不同形式的生成（伪影减少，伪影转移和自重建等）。具有专门的损失函数，以利用合成数据来满足监督的需要。大量的实验表明，当应用于合成数据集时，我们的方法解决金属伪影显着优于现有的无监督模型设计的自然图像到图像的翻译问题，并实现了与现有的监督模型MAR的性能相当。当应用于临床数据集，我们的方法表现出更好的泛化能力的监督模型。本文的源代码可在https：//www.example.com上公开获取。github.com/liaohaofu/adn
Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training. However, as synthesized data may not accurately simulate the underlying physical mechanisms of CT imaging, the supervised methods often generalize poorly to clinical applications. To address this problem, we propose, to the best of our knowledge, the first unsupervised learning approach to MAR. Specifically, we introduce a novel artifact disentanglement network that disentangles the metal artifacts from CT images in the latent space. It supports different forms of generations (artifact reduction, artifact transfer, and self-reconstruction, etc.) with specialized loss functions to obviate the need for supervision with synthesized data. Extensive experiments show that when applied to a synthesized dataset, our method addresses metal artifacts significantly better than the existing unsupervised models designed for natural image-to-image translation problems, and achieves comparable performance to existing supervised models for MAR. When applied to clinical datasets, our method demonstrates better generalization ability over the supervised models. The source code of this paper is publicly available at https:// github.com/liaohaofu/adn.