A multi-scale information fusion medical image segmentation network based on convolutional kernel coupled updata mechanism

Medical image segmentation is pivotal in disease diagnosis and treatment. This paper presents a novel network architecture for medical image segmentation, termed TransDLNet, which is engineered to enhance the efficiency of multi-scale information utilization. TransDLNet integrates convolutional neural networks and Transformers, facilitating cross-level multi-scale information fusion for complex medical images. Key to its innovation is the attention-dilated depthwise convolution (ADDC) module, utilizing depthwise convolution (DWConv) with varied dilation rates to enhance local detail capture. A convolution kernel coupled update mechanism and channel information compensation method ensure robust feature representation. Furthermore, the cross-level grouped attention merge (CGAM) module in both encoder and decoder enhances feature interaction and integration across scales, boosting comprehensive representation. We conducted a comprehensive experimental analysis and quantitative evaluation on four datasets representing diverse modalities. The results indicate that the proposed method has good segmentation performance and generalization ability. •A joint adjustment strategy with DWConv and multiple dilation rates is proposed to the capture efficiency of crucial local details.•A convolutional kernel coupled update mechanism is introduced to ensure consistent feature representation.•A channel information compensation method is proposed to compensate for the inter-channel interaction limitations of DWConv.•Connections are established between cross-level and multi-scale features, enhancing feature correlation.