Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation This paper introduces Swin-Unet, a novel pure Transformer-based U-shaped encoder-decoder architecture for medical image segmentation. The authors leverage the hierarchical Swin Transformer with shifted windows to extract context features and a symmetric Swin Transformer-based decoder with a patch expanding layer to perform up-sampling. The method is evaluated on multi-organ and cardiac segmentation tasks, demonstrating superior performance compared to full-convolutional and hybrid CNN-Transformer methods. The key contributions include the design of a pure Transformer-based U-shaped architecture, the development of a patch expanding layer, and the effectiveness of skip connections in Transformers. Experiments on the Synapse and ACDC datasets show that Swin-Unet achieves high segmentation accuracy and robust generalization. The code and trained models are available at https://github.com/HuCaoFighting/Swin-Unet.Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation This paper introduces Swin-Unet, a novel pure Transformer-based U-shaped encoder-decoder architecture for medical image segmentation. The authors leverage the hierarchical Swin Transformer with shifted windows to extract context features and a symmetric Swin Transformer-based decoder with a patch expanding layer to perform up-sampling. The method is evaluated on multi-organ and cardiac segmentation tasks, demonstrating superior performance compared to full-convolutional and hybrid CNN-Transformer methods. The key contributions include the design of a pure Transformer-based U-shaped architecture, the development of a patch expanding layer, and the effectiveness of skip connections in Transformers. Experiments on the Synapse and ACDC datasets show that Swin-Unet achieves high segmentation accuracy and robust generalization. The code and trained models are available at https://github.com/HuCaoFighting/Swin-Unet.