CMUNEXT: An Efficient Medical Image Segmentation Network Based on Large Kernel and Skip Fusion

Fenghe Tang, Jianrui Ding, Quan Quan, Lingtao Wang, Chunping Ning, S. Kevin Zhou

Abstract: The u-shaped architecture has emerged as a crucial paradigm in the design of medical image segmentation networks. However, due to the inherent local limitations of convolution, a fully convolutional segmentation network with u-shaped architecture struggles to effectively extract global context information, which is vital for the precise localization of lesions. While hybrid architectures combining CNN and Transformer can address these issues, their applications are limited due to the computational resource. In addition, the inductive bias of convolution in lightweight networks adeptly fits the scarce medical data, which is lacking in the Transformer based network. To extract global context information while taking advantage of the inductive bias, we propose CMUNeXt, an efficient lightweight segmentation network, which leverages large kernel and inverted bottleneck design to thoroughly mix distant spatial and location information, efficiently extracting global context information. We also introduce the Skip-fusion block, designed to enable smooth skip-connections and ensure ample feature fusion. Experimental results demonstrate that CMUNeXt outperforms existing heavyweight and lightweight medical image segmentation networks, while offering a faster inference speed, lighter weights, and a reduced computational cost. The code is available at https://github.com/FengheTan9/CMUNeXt.