MC-DC: An MLP-CNN Based Dual-path Complementary Network for Medical Image Segmentation

•A novel MLP-CNN based dual-path complementary network (MC-DC) for medical image segmentation.•The CNN encoder can focus on local spatial contextual information. The MLP encoder is employed to capture the long-range dependency, without using a complex self-attention mechanism.•A dual-path complementary (DPC) module is designed to effectively fuse multi-level features from MLP and CNN.•The cross-scale global feature fusion (CS-GF) module aims to rebuild global semantic information with the help of cross-scale attention, while the proposed cross-scale local feature fusion (CS-LF) module pays attention to reconstructing local spatial contextual information.•The comprehensive experiments on three typical medical image segmentation tasks demonstrate the effectiveness of the proposed MC-DC network for improving medical image segmentation. Fusing the CNN and Transformer in the encoder has recently achieved outstanding performance in medical image segmentation. However, two obvious limitations require addressing: (1) The utilization of Transformer leads to heavy parameters, and its intricate structure demands ample data and resources for training, and (2) most previous research had predominantly focused on enhancing the performance of the feature encoder, with little emphasis placed on the design of the feature decoder. To this end, we propose a novel MLP-CNN based dual-path complementary (MC-DC) network for medical image segmentation, which replaces the complex Transformer with a cost-effective Multi-Layer Perceptron (MLP). Specifically, a dual-path complementary (DPC) module is designed to effectively fuse multi-level features from MLP and CNN. To respectively reconstruct global and local information, the dual-path decoder is proposed which is mainly composed of cross-scale global feature fusion (CS-GF) module and cross-scale local feature fusion (CS-LF) module. Moreover, we leverage a simple and efficient segmentation mask feature fusion (SMFF) module to merge the segmentation outcomes generated by the dual-path decoder. Comprehensive experiments were performed on three typical medical image segmentation tasks. For skin lesions segmentation, our MC-DC network achieved 91.69% Dice and 9.52mm ASSD on the ISIC2018 dataset. In addition, the 91.6% Dice and 94.4% Dice were respectively obtained on the Kvasir-SEG dataset and CVC-ClinicDB dataset for polyp segmentation. Moreover, we also conducted experiments on the private COVID-DS36 dataset for lung lesion segmentati