GCHA-Net: Global context and hybrid attention network for automatic liver segmentation. (January 2023)

• Record Type: Journal Article
• Authors: Liu, Huaxiang; Fu, Youyao; Zhang, Shiqing; Liu, Jun; Wang, Yong; Wang, Guoyu; Fang, Jiangxiong
• Is Part Of: Computers in biology and medicine. Volume 152(2023)
• Publication Date: 2023-01
• Subjects: Convolutional neural network -- U-Net -- Liver segmentation -- Attention mechanism; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106352
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Liver segmentation is a critical step in liver cancer diagnosis and surgical planning. The U-Net's architecture is one of the most efficient deep networks for medical image segmentation. However, the continuous downsampling operators in U-Net causes the loss of spatial information. To solve these problems, we propose a global context and hybrid attention network, called GCHA-Net, to adaptive capture the structural and detailed features. To capture the global features, a global attention module (GAM) is designed to model the channel and positional dimensions of the interdependencies. To capture the local features, a feature aggregation module (FAM) is designed, where a local attention module (LAM) is proposed to capture the spatial information. LAM can make our model focus on the local liver regions and suppress irrelevant information. The experimental results on the dataset LiTS2017 show that the dice per case (DPC) value and dice global (DG) value of liver were 96.5% and 96.9%, respectively. Compared with the state-of-the-art models, our model has superior performance in liver segmentation. Meanwhile, we test the experiment results on the 3Dircadb dataset, and it shows our model can obtain the highest accuracy compared with the closely related models. From these results, it can been seen that the proposed model can effectively capture the global context information and build the correlation between different convolutional layers. The code is available at the website: https://github.com/HuaxiangLiu/GCAU-Net . Highlights: A global attention module (GAM) located between encoders and decoders by incorporating the channel attention branch and the position attention branch with self-attention mechanism, which can not only learn the long-range dependence of the channel and position but also enhance the global information. A local attention module (LAM) was designed by computing the spatial weights of the low-level features by introducing the global context features. During the up-sampling process, with the output of the LAM, we propose a FAM to adaptively combine the high-level and low-level features, which not only improve the semantic information but also can suppress the irrelevant low-level features. We proposed an end-to-end network with an encoder-decoder structure by integrating the GAM into FAM with LAM for liver image segmentation.