Motion artifact reduction is one of the most concerned problems in magnetic resonance imaging. In recent years, deep learning-based methods have been widely investigated for artifact reduction tasks in MRI. As a retrospective processing method, neural network does not cost additional acquisition time or require new acquisition equipment, and seems to work better than traditional artifact reduction methods. In the previous study, training such models require the paired motion-corrupted and motion-free MR images. However, it is extremely tough or even impossible to obtain these images in reality because patients have difficulty in maintaining the same state during two image acquisition, which makes the training in a supervised manner impractical. In this paper, we proposed a new unsupervised abnormality extraction network (UNAEN) to alleviate this problem. Our network realizes the transition from artifact domain to motion-free domain by processing the abnormal information introduced by artifact in unpaired MR images. Different from directly generating artifact reduction results from motion-corrupted MR images, we adopted the strategy of abnormality extraction to indirectly correct the impact of artifact in MR images by learning the deep features. Experimental results show that our method is superior to state-of-the-art networks and can potentially be applied in real clinical settings.

翻译：运动伪影抑制是磁共振成像中最受关注的问题之一。近年来，基于深度学习的方法被广泛研究用于MRI中的伪影抑制任务。作为一种回顾性处理技术，神经网络无需额外的采集时间或新设备，且表现优于传统伪影抑制方法。以往研究需要配对的有伪影和无伪影MR图像来训练此类模型，然而由于患者两次采集过程中难以保持相同状态，现实中获取这些配对图像极为困难甚至不可能，这使得有监督训练方式难以实现。本文提出了一种新型无监督异常提取网络（UNAEN）以缓解该问题。该网络通过处理非配对MR图像中伪影引入的异常信息，实现从伪影域到无伪影域的转换。与直接从运动伪影MR图像生成伪影抑制结果不同，本文采用异常提取策略，通过学习深层特征间接修正MR图像中伪影的影响。实验结果表明，本方法优于当前最优网络，并具有在真实临床场景中应用的潜力。