A frequency-spatial dual perception network for efficient and accurate medical image segmentation

The acquisition mechanism of medical images differs from that of natural images, consequently enabling frequency-domain information to reveal deeper-level pathological features in medical image analysis. However, extracting the significant pathological features from diverse frequency domains remain a core challenge in medical image segmentation. In this paper, we proposed an efficient medical image segmentation network, called FDE-Net, that effectively utilizes frequency-domain information. First, a Low-Frequency Information Extraction Block (LFIEB) is designed to selectively enhance critical information in frequency-domain features, thereby extracting the most discriminative pathological features. Furthermore, for seamless integration of frequency-domain and spatial features, a Multi-head Perception Visual State Space (MPVSS) is adopted with structural optimizations implemented to significantly improve multi-scale spatial feature extraction capabilities. Finally, a U-shaped network architecture was constructed, incorporating the Context Focus Attention (CFA) module to more efficiently propagate shallow features to the decoder. We validate FDE-Net on three publicly available medical image datasets. On ISIC-2018, our method achieves 84.10% IoU and 91.29% DSC, surpassing UNet by 6.24% and 3.74%, respectively, while maintaining computational efficiency. Comprehensive ablation studies confirm the individual contributions of the LFIEB and MPVSS modules. These results demonstrate that FDE-Net effectively balances segmentation accuracy and computational efficiency, making it promising for clinical deployment.