CSA-UNet: An Efficient Context Separable Attention UNet for Medical Image Segmentation

Accurate segmentation of lesions in medical images is crucial for early diagnosis and treatment, significantly improving patient survival rates. However, the inherent characteristics of medical imaging render precise lesion segmentation a highly challenging task. Traditional manual segmentation methods are time-consuming and heavily dependent on expert knowledge, while the standard convolutions used in the U-Net model fail to capture sufficient contextual information. To address these challenges, we propose an enhanced context-separable attention U-Net model for lesion segmentation in medical images. This model introduces Separable Attention (SA) block and Context Attention (CA) block to extract and integrate local and global contextual information, thereby enhancing the model’s feature extraction capabilities. The proposed method increases the model’s receptive field while reducing the number of parameters, incorporating attention mechanisms to improve segmentation accuracy and efficiency. Experimental results across various datasets demonstrate that the proposed model outperforms the original U-Net in terms of segmentation accuracy and efficiency, achieving higher mean Intersection over Union values in lesion segmentation while reducing the model’s parameters.