Multimodal image registration is an important technique for many clinical applications. However, it is particularly challenging to obtain good spatial alignment. This paper introduces a novel architecture named the constrained affine network, which combines deformable image registration with affine transformation for multimodal MR image registration. A weakly supervised manner is adapted to train the network and anatomical labels are used in training. The network directly learns to predict a displacement vector field (DVF) between pairs of input images. Different from the existing deformable image registration methods based on the convolutional neural network (CNN), the method proposes a global constrained affine module, which can predict an affine transformation by pre-computing the range of affine parameters, and the model can be combined with a deformable registration network. We evaluated the proposed method on 3D multimodal medical images. Experimental results indicate that the proposed method has better performance.

多模态图像配准是许多临床应用的重要技术。然而，获得良好的空间对齐尤其具有挑战性。本文介绍了一种名为约束仿射网络的新架构，它将可变形图像配准与仿射变换相结合，用于多模态 MR 图像配准。弱监督方式适用于训练网络，并在训练中使用解剖标签。网络直接学习预测输入图像对之间的位移矢量场 (DVF)。与现有的基于卷积神经网络（CNN）的可变形图像配准方法不同，该方法提出了全局约束仿射模块，可以通过预先计算仿射参数的范围来预测仿射变换，并且该模型可以与可变形配准网络相结合。我们在 3D 多模态医学图像上评估了所提出的方法。实验结果表明，所提出的方法具有更好的性能。