前进 (2022-08-24 22:22):
#paper arXiv:2208.04939v1 ,2022,U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration? 基于Transformer的网络由于其长距离建模能力,在可变形图像配准中越来越流行。然而本文认为,一个具有5层卷积Unet网络的感受野足以在不需要依赖长距离建模能力的情况下捕捉精确的图像形变。本文想要探究UNet网络在应用于医学图像配准时,与现代基于Transformer的方法相比是否已经过时?为此,作者提出了一个具有大的卷积核的UNet网络(LKU-Net),即通过在一个普通的UNet网络内嵌入平行的卷积块来争强网络的感受野。在公用3D IXI 大脑数据集上进行基于atlas的配准实验,作者证明了LKU-Net的变现依旧可以和如今最先进的基于Transformer的方法相当甚至超越,而且只用了TransMorph 1.12%的参数量和10.8%的计算量。作者进一步将算法应用在MICCAI 2021的配准比赛中,同样超越了Transmorph,目前排在第一。只对UNet进行了简单的改造,基于Unet的配准算法依旧可以达到最先进的效果,证明基于UNet的配准网络并未过时。
U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?
翻译
Abstract:
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 The purpose of this study is therefore to investigate whether U-Net-based methods are outdated compared to modern transformer-based approaches when applied to medical image registration.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.
翻译
回到顶部