Recursive Decomposition Network for Deformable Image Registration

作者：Bo Hu, S. Kevin Zhou, Zhiwei Xiong, Feng Wu · 发表于：IEEE Journal of Biomedical and Health Informatics · 年份：2022 · DOI：10.1109/jbhi.2022.3189696 · 被引用次数：54 · 研究领域：Medical Image Segmentation Techniques、Advanced Neural Network Applications、Medical Imaging and Analysis

Deformation decomposition serves as a good solution for deformable image registration when the deformation is large. Current deformation decomposition methods can be categorized into cascade-based methods and pyramid-based methods. However, cascade-based methods suffer from heavy computational burdens and long inference time due to their structures of repeated subnetworks, while the effectiveness of pyramid-based methods is constrained by their limited numbers of resolution levels. In this paper, to address both the insufficient and inefficient decomposition problems in current deformation decomposition methods, we propose a recursive decomposition network (RDN) to offer a novel solution for deformable image registration. Stage-wise recursion can efficiently decompose a large deformation into different pyramid estimation stages without using repeated subnetworks like in cascade-based methods. Level-wise recursion can sufficiently decompose the deformation inside each resolution level instead of only one-time estimation like in pyramid-based methods. Extensive experiments and ablation studies on two representative datasets validate the effectiveness and efficiency of our proposed RDN.