DPM-UNet: A Mamba-Based Network with Dynamic Perception Feature Enhancement for Medical Image Segmentation

In medical image segmentation, effective integration of global and local features is crucial. Current methods struggle to simultaneously model long-range dependencies and fine local details. Convolutional Neural Networks (CNNs) excel at extracting local features but are limited by their local receptive fields for capturing long-range dependencies. While global self-attention mechanisms (e.g., in Transformers) can capture long-range spatial relationships, their quadratic computational complexity incurs high costs for high-resolution medical images. To address these limitations, State Space Models (SSMs), which maintain linear complexity while effectively establishing long-range dependencies, have been introduced to visual tasks. Leveraging the advantages of SSMs, this paper proposes DPM-UNet. The network employs a Dual-path Residual Fusion Module (DRFM) at shallow layers to extract local detailed features and a DPMamba Module at deep layers to model global semantic information, achieving effective local global feature fusion. A Multi-scale Aggregation Attention Network (MAAN) is further incorporated to enhance multi-scale representations. The proposed method collaboratively captures local details, long-range dependencies, and multi-scale information in medical images. Experiments on three public datasets demonstrate that DPM-UNet outperforms existing methods across multiple evaluation metrics.