MBUTransNet: multi-branch U-shaped network fusion transformer architecture for medical image segmentation

Recently, transformers have been adopted to computer vision applications and achieve great success in image segmentation. However by simply applying transformers to medical segmentation task it is hard to achieve much higher accuracy than by traditional U-shaped network structures, which are based on CNNs and has been extensively researched. On the other hand, CNN structure pays more attention to local information and ignores global information, which is very important for the medical image segmentation dataset with cell scattered background. This motivates us to explore the feasibility of using U-shape effective fusion transformer network architectures for medical image segmentation tasks.

In this paper, we propose a multibranch U-shaped structure fusion transformer network (MBUTransNet), which consists of two distinct branches. In branch 1, Coordinate attention transformer is designed to extract long-term dependency information through weight coordinates. In branch 2, small U-net blocks and multiscale feature fusion block are proposed to replace convolution blocks of each layer and fuse the feature maps from different layers, respectively.

Our experiments demonstrate that the proposed MBUTransNet has achieved a 0.076 and 0.1269 improvement in DICE compared to the previous best method on MoNuSeg and Synapse multiorgan segmentation dataset, respectively, while the model parameters will be no significant increase.

Without bells and whistles, MBUTransNet achieves better performance on medical image datasets, including medical cell segmentation and abdominal organs segmentation. Compared with transformer-based methods, our proposed model also obtains quite competitive parameters.