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