论文标题
用于自动医疗图像细分的高分辨率SWIN变压器
High-Resolution Swin Transformer for Automatic Medical Image Segmentation
论文作者
论文摘要
特征图的分辨率对于医学图像分割至关重要。用于医学图像分割的大多数现有基于变压器的网络都是U-NET样架构，其中包含一个编码器，该编码器利用一系列变压器块将输入医疗图像从高分辨率特征图转换为低分辨率特征图和一个解码器，并逐渐从低分辨率特征图中恢复高分辨率表示。与以前的研究不同，在本文中，我们利用高分辨率网络（HRNET）的网络设计样式，用变压器块替换卷积层，并从变压器块生成的不同分辨率特征图中连续交换信息。本文介绍的新基于变压器的网络表示为高分辨率SWIN Transformer网络（HRSTNET）。广泛的实验表明，HRSTNET可以与基于最先进的变压器的U-NET样结构（BRATS）2021和Medical Sementation DeCathlon的肝脏数据集实现可比的性能。 HRSTNET代码将在https://github.com/auroua/hrstnet上公开获得。
The Resolution of feature maps is critical for medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation are U-Net-like architecture that contains an encoder that utilizes a sequence of Transformer blocks to convert the input medical image from high-resolution representation into low-resolution feature maps and a decoder that gradually recovers the high-resolution representation from low-resolution feature maps. Unlike previous studies, in this paper, we utilize the network design style from the High-Resolution Network (HRNet), replace the convolutional layers with Transformer blocks, and continuously exchange information from the different resolution feature maps that are generated by Transformer blocks. The newly Transformer-based network presented in this paper is denoted as High-Resolution Swin Transformer Network (HRSTNet). Extensive experiments illustrate that HRSTNet can achieve comparable performance with the state-of-the-art Transformer-based U-Net-like architecture on Brain Tumor Segmentation(BraTS) 2021 and the liver dataset from Medical Segmentation Decathlon. The code of HRSTNet will be publicly available at https://github.com/auroua/HRSTNet.
