当前位置: X-MOL 学术IEEE J. Biomed. Health Inform. › 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.)
Multi-Task Learning for Registering Images With Large Deformation
IEEE Journal of Biomedical and Health Informatics ( IF 6.7 ) Pub Date : 2020-08-14 , DOI: 10.1109/jbhi.2020.3016699
Bo Du , Jiandong Liao , Baris Turkbey , Pingkun Yan

Accurate registration of prostate magnetic resonance imaging (MRI) images of the same subject acquired at different time points helps diagnose cancer and monitor the tumor progress. However, it is very challenging especially when one image was acquired with the use of endorectal coil (ERC) but the other was not, which causes significant deformation. Classical iterative image registration methods are also computationally intensive. Deep learning based registration frameworks have recently been developed and demonstrated promising performance. However, the lack of proper constraints often results in unrealistic registration. In this paper, we propose a multi-task learning based registration network with anatomical constraint to address these issues. The proposed approach uses a cycle constraint loss to achieve forward/backward registration and an inverse constraint loss to encourage diffeomorphic registration. In addition, an adaptive anatomical constraint aiming for regularizing the registration network with the use of anatomical labels is introduced through weak supervision. Our experiments on registering prostate MR images of the same subject obtained at different time points with and without ERC show that the proposed method achieves very promising performance under different measures in dealing with the large deformation. Compared with other existing methods, our approach works more efficiently with average running time less than a second and is able to obtain more visually realistic results.

中文翻译:


用于配准大变形图像的多任务学习



准确配准同一受试者在不同时间点获取的前列腺磁共振成像 (MRI) 图像有助于诊断癌症并监测肿瘤进展。然而,这是非常具有挑战性的,特别是当一张图像是使用直肠内线圈(ERC)获取的,而另一张图像不是使用直肠内线圈(ERC)获取的,这会导致显着的变形。经典的迭代图像配准方法也是计算密集型的。最近开发了基于深度学习的注册框架,并展示了有希望的性能。然而,缺乏适当的约束往往会导致注册不切实际。在本文中,我们提出了一种具有解剖约束的基于多任务学习的配准网络来解决这些问题。所提出的方法使用循环约束损失来实现前向/后向配准,并使用逆约束损失来鼓励微分同胚配准。此外,通过弱监督引入了一种自适应解剖约束,旨在使用解剖标签来规范配准网络。我们对在有和没有 ERC 的情况下在不同时间点获得的同一受试者的前列腺 MR 图像进行配准的实验表明,所提出的方法在处理大变形的不同措施下取得了非常有前途的性能。与其他现有方法相比,我们的方法工作效率更高,平均运行时间不到一秒,并且能够获得视觉上更真实的结果。
更新日期:2020-08-14
down
wechat
bug