DGEAHorNet: High-order Spatial Interaction Network with Dual Cross Global Efficient Attention for Skin Lesion Segmentation

Skin lesion segmentation is a complex and severe project, which aims to accurately segment abnormal regions in skin lesion images. However, obtaining accurate segmentation results is difficult because of the great uncertainty in the shape, location, and scale of the target region. To address these challenges, we propose a higher-order spatial interaction framework with dual cross global efficient attention (DGEAHorNet), which employs a neural network architecture based on recursive gate convolution to adequately extract multi-scale contextual information from images. Specifically, a Dual Cross-Attentions (DCA) is added to the skip connection that can effectively blend multi-stage encoder features and narrow the semantic gap. In the bottleneck stage, global channel spatial attention module (GCSAM) is used to extract image global information. To obtain better feature representation, we feed the output from the GCSAM into the multi-branch dense layer (SENetV2) for excitation. Furthermore, we adopt Depthwise Over-parameterized Convolutional Layer (DO-Conv) in order to replace the common convolutional layer in the input and output part of our network, then add Efficient Attention (EA) to diminish computational complexity and enhance our model’s performance. For evaluating the effectiveness of our proposed DGEAHorNet, we conduct comprehensive experiments on three publicly-available skin datasets, and achieving 0.9320, 0.9337 and 0.9474 in Dice similarity coefficient on ISIC2018, ISIC2017, and PH2 severally. Our proposed method outperforms other state-of-the-art methods. The code is available at https://github.com/penghaixin/mymodel.