Due to their extreme long-range modeling capability, vision transformer-based
networks have become increasingly popular in deformable image registration. We
believe, however, that the receptive field of a 5-layer convolutional U-Net is
sufficient to capture accurate deformations without needing long-range
dependencies. The purpose of this study is therefore to investigate whether
U-Net-based methods are outdated compared to modern transformer-based
approaches when applied to medical image registration. For this, we propose a
large kernel U-Net (LKU-Net) by embedding a parallel convolutional block to a
vanilla U-Net in order to enhance the effective receptive field. On the public
3D IXI brain dataset for atlas-based registration, we show that the performance
of the vanilla U-Net is already comparable with that of state-of-the-art
transformer-based networks (such as TransMorph), and that the proposed LKU-Net
outperforms TransMorph by using only 1.12% of its parameters and 10.8% of its
mult-adds operations. We further evaluate LKU-Net on a MICCAI Learn2Reg 2021
challenge dataset for inter-subject registration, our LKU-Net also outperforms
TransMorph on this dataset and ranks first on the public leaderboard as of the
submission of this work. With only modest modifications to the vanilla U-Net,
we show that U-Net can outperform transformer-based architectures on
inter-subject and atlas-based 3D medical image registration. Code is available
at this https URL

本研究旨在探究在医学图像配准领域中，基于 U-Net 神经网络是否比现代 transformer-based 方法更陈旧。通过提出一种大卷积核 U-Net 模型并在公共数据集和 MICCAI Learn2Reg 2021 挑战数据集上进行测试，结果表明新模型在参数和计算复杂度较低的情况下可以优于 state-of-the-art 的 TransMorph 模型及其他现有 transformer-based 方法，证明 U-Net 仍然在 inter-subject 和 atlas-based 3D 医学图像配准中具有优势。