Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration
This work addresses the challenge of accurate image registration in medical imaging, which is crucial for applications like diagnosis and treatment planning, but it appears incremental as it builds on existing deep learning and Transformer approaches.
The authors tackled the problem of deformable medical image registration by proposing a Deformer module and multi-scale framework to better capture spatial correspondences, achieving superior performance compared to existing methods on two public datasets.
Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural network, ignoring its limited ability to capture spatial correspondence. On the other hand, Transformer can better characterize the spatial relationship with attention mechanism, its long-range dependency may be harmful to the registration task, where voxels with too large distances are unlikely to be corresponding pairs. In this study, we propose a novel Deformer module along with a multi-scale framework for the deformable image registration task. The Deformer module is designed to facilitate the mapping from image representation to spatial transformation by formulating the displacement vector prediction as the weighted summation of several bases. With the multi-scale framework to predict the displacement fields in a coarse-to-fine manner, superior performance can be achieved compared with traditional and learning-based approaches. Comprehensive experiments on two public datasets are conducted to demonstrate the effectiveness of the proposed Deformer module as well as the multi-scale framework.