English

GroupRegNet: A Groupwise One-shot Deep Learning-based 4D Image Registration Method

Image and Video Processing 2021-01-15 v2

Abstract

Accurate deformable 4-dimensional (4D) (3-dimensional in space and time) medical images registration is essential in a variety of medical applications. Deep learning-based methods have recently gained popularity in this area for the significant lower inference time. However, they suffer from drawbacks of non-optimal accuracy and the requirement of a large amount of training data. A new method named GroupRegNet is proposed to address both limitations. The deformation fields to warp all images in the group into a common template is obtained through one-shot learning. The use of the implicit template reduces bias and accumulated error associated with the specified reference image. The one-shot learning strategy is similar to the conventional iterative optimization method but the motion model and parameters are replaced with a convolutional neural network (CNN) and the weights of the network. GroupRegNet also features a simpler network design and a more straightforward registration process, which eliminates the need to break up the input image into patches. The proposed method was quantitatively evaluated on two public respiratory-binned 4D-CT datasets. The results suggest that GroupRegNet outperforms the latest published deep learning-based methods and is comparable to the top conventional method pTVreg. To facilitate future research, the source code is available at https://github.com/vincentme/GroupRegNet.

Keywords

Cite

@article{arxiv.2009.02613,
  title  = {GroupRegNet: A Groupwise One-shot Deep Learning-based 4D Image Registration Method},
  author = {Yunlu Zhang and Xue Wu and H. Michael Gach and Harold Li and Deshan Yang},
  journal= {arXiv preprint arXiv:2009.02613},
  year   = {2021}
}
R2 v1 2026-06-23T18:20:18.777Z