Scholarlink

<p>Recently, Visual Transformer (ViT) has been extensively used in medical image segmentation (MIS) due to applying self-attention mechanism in the spatial domain to modeling global knowledge. However, many studies have focused on improving models in the spatial domain while neglecting the importance of frequency domain information. Therefore, we propose <b>M</b>ulti-axis <b>E</b>xternal <b>W</b>eights <b>UNet</b> (<b>MEW-UNet</b>) based on the U-shape architecture by replacing self-attention in ViT with our Multi-axis External Weights block. Specifically, our block performs a Fourier transform on the three axes of the input features and assigns the external weight in the frequency domain, which is generated by our External Weights Generator. Then, an inverse Fourier transform is performed to change the features back to the spatial domain. We evaluate our model on four datasets, including Synapse, ACDC, ISIC17 and ISIC18 datasets, and our approach demonstrates competitive performance, owing to its effective utilization of frequency domain information.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Learning multi-axis representation in frequency domain for medical image segmentation

  • 期刊论文

  • 发表日期：

    2025年1月15日

查看全文
  • Jiacheng Ruan,
  • Jingsheng Gao,
  • Mingye Xie,
  • Suncheng Xiang

摘要

Recently, Visual Transformer (ViT) has been extensively used in medical image segmentation (MIS) due to applying self-attention mechanism in the spatial domain to modeling global knowledge. However, many studies have focused on improving models in the spatial domain while neglecting the importance of frequency domain information. Therefore, we propose Multi-axis External Weights UNet (MEW-UNet) based on the U-shape architecture by replacing self-attention in ViT with our Multi-axis External Weights block. Specifically, our block performs a Fourier transform on the three axes of the input features and assigns the external weight in the frequency domain, which is generated by our External Weights Generator. Then, an inverse Fourier transform is performed to change the features back to the spatial domain. We evaluate our model on four datasets, including Synapse, ACDC, ISIC17 and ISIC18 datasets, and our approach demonstrates competitive performance, owing to its effective utilization of frequency domain information.