Make U-Net Greater: An Easy-to-Embed Approach to Improve Segmentation Performance Using Hypergraph

作     者：Jing Peng Jingfu Yang Chaoyang Xia Xiaojie Li Yanfen Guo Ying Fu Xinlai Chen Zhe Cui 

作者机构：Chengdu Institute of Computer ApplicationUniversity of Chinese Academy of SciencesChengdu610041China School of Computer ScienceChengdu University of Information TechnologyChengdu610225China University of Chinese Academy of SciencesBeijing100049China Department of Experimental RheumatologyNijmegen6525GANetherlands 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2022年第42卷第7期

页      面：319-333页

核心收录：

学科分类：04[教育学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Sichuan Science and Technology Program(Grant No.2019ZDZX0005 2019YFG0496 2020YFG0143 2019JDJQ0002 and 2020YFG0009). 

主　　题：Convolutional neural network semantic segmentation hypergraph neural network LGIA module 

摘      要：semantics information while maintaining spatial detail con-texts.Long-range context information plays a crucial role in this scenario.How-ever,the traditional convolution kernel only provides the local and small size of the receptivefield.To address the problem,we propose a plug-and-play module aggregating both local and global information(aka LGIA module)to capture the high-order relationship between nodes that are far apart.We incorporate both local and global correlations into hypergraph which is able to capture high-order rela-tionships between nodes via the concept of a hyperedge connecting a subset of nodes.The local correlation considers neighborhood nodes that are spatially adja-cent and similar in the same CNN feature maps of magnetic resonance(MR)image;and the global correlation is searched from a batch of CNN feature maps of MR images in feature space.The influence of these two correlations on seman-tic segmentation is complementary.We validated our LGIA module on various CNN segmentation models with the cardiac MR images dataset.Experimental results demonstrate that our approach outperformed several baseline models.