Learning Multi-axis Representation in Frequency Domain for Medical Image Segmentation
This addresses medical image segmentation for healthcare applications by introducing a frequency-domain approach, though it appears incremental as it builds on existing U-shape architectures and ViT frameworks.
The paper tackles medical image segmentation by proposing a Multi-axis External Weights UNet (MEW-UNet) that replaces self-attention in Visual Transformers with a block operating in the frequency domain, achieving competitive performance on four datasets including Synapse, ACDC, ISIC17, and ISIC18.
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.