BIRNet: Brain image registration using dual-supervised fully convolutional networks
BIRNet: Brain image registration using dual-supervised fully convolutional networks
复制标题
DOI：
10.1016/j.media.2019.03.006
复制
发表时间：
2019-05-01
影响因子：
10.9
通讯作者：
Shen, Dinggang
中科院分区：
文献类型：
--
作者：
Fan, Jingfan;Cao, Xiaohuan;Shen, Dinggang
在本文中，我们提出了一种通过预测图像外观的变形来进行图像配准的深度学习方法。由于获得用于训练的真地变形场是具有挑战性的，我们设计了一个受双重引导的全卷积网络：(1)使用现有配准方法获得的变形场进行真地引导；(2)利用配准后图像之间的差异进行图像差异引导。后者的指导有助于避免过度依赖训练变形场的监督，这可能是不准确的。为了有效训练，我们进一步改进了深度卷积网络，采用了间隙填充、分层损失和多源策略。在各种数据集上的实验表明，与现有方法相比，该方法具有良好的配准精度和效率。(C) 2019 Elsevier B.V.版权所有
In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Ground-truth guidance using deformation fields obtained by an existing registration method; and (2) Image dissimilarity guidance using the difference between the images after registration. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods. (C) 2019 Elsevier B.V. All rights reserved.