SwinT-Unet: Hybrid architecture for Medical Image Segmentation Based on Swin transformer block and Dual-Scale Information

The fast development of Convolution Neural Networks (CNN) based on U-shaped architecture has shown innovative improvements in the fields of image segmentation. However, these approaches cannot learn global information in images due to the local aspect of the convolution operation. This paper deals with designing a hybrid method of medical image segmentation. Taking advantage of Shifted windows (Swin) transformer block to extract fine-grained features and the Transformer Interactive Fusion (TIF) module to create a fusion between features of different scales, the proposed approach consists of a dual-Scale encoder–Swin transformer U-shaped architecture (SwinT-Unet). The effectiveness of this method has been evaluated on the Synapse multi-organ CT dataset. The suggested segmentation demonstrated more efficiency than the results of some other current methods.