Medical image segmentation plays a crucial role in medical image processing, focusing on the automated extraction of regions of interest (such as organs, lesions, etc.) from medical images. This process supports various clinical applications, including diagnosis, surgical planning, and treatment. In this paper, we introduce a Boundary-guided Context Fusion U-Net (BCF-UNet), a novel approach designed to tackle a critical shortcoming in current methods: the inability to effectively integrate boundary information with semantic context. The BCF-UNet introduces a Adaptive Multi-Frequency Encoder (AMFE), which uses multi-frequency analysis inspired by the Wavelet Transform (WT) to capture both local and global features efficiently. The Adaptive Multi-Frequency Encoder (AMFE) decomposes images into different frequency components and adapts more effectively to boundary texture information through a learnable activation function. Additionally, we introduce a new multi-scale feature fusion module, the Atten-kernel Adaptive Fusion Module (AKAFM), designed to integrate deep semantic information with shallow texture details, significantly bridging the gap between features at different scales. Furthermore, each layer of the encoder sub-network integrates a Boundary-aware Pyramid Module (BAPM), which utilizes a simple and effective method and combines it with a priori knowledge to extract multi-scale edge features to improve the accuracy of boundary segmentation. In BCF-UNet, semantic context is used to guide edge information extraction, enabling the model to more effectively comprehend and identify relationships among various organizational structures. Comprehensive experimental evaluations on two datasets demonstrate that the proposed BCF-UNet achieves superior performance compared to existing state-of-the-art methods.
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.
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 ExtractionBlock (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.