基于对抗学习的医学图像分割领域自适应研究  

Research on domain adaptation medical image segmentation based on adversarial learning

作　　者：王绍帆 马驰[1,2] 胡辉 路生亮 Wang Shaofan;Ma Chi;Hu Hui;Lu Shengliang(School of Computer&Software Engineering,University of Science&Technology Liaoning,Anshan Liaoning 114051,China;School of Computer Science&Engineering,Huizhou University,Huizhou Guangdong 516007,China)

机构地区：[1]辽宁科技大学计算机与软件工程学院,辽宁鞍山114051 [2]惠州学院计算机科学与工程学院,广东惠州516007

出　　处：《计算机应用研究》2022年第4期1270-1273,共4页Application Research of Computers

基　　金：国家自然科学基金项目(U1731128);广东省教育厅项目(2018KTSCX218)。

摘　　要：为了解决跨领域医学图像分析中不匹配的问题,提出了一种基于对抗学习的无监督领域自适应框架(UAL-DAF)。具体而言,该框架通过外观转移模块(ATM)和结合条件生成对抗网络的语义转移模块(STM)分别缩小了跨领域医学图像外观和语义层次的差异。最后,在具有挑战性的医学图像分割实验中,结果显著优于已有方法。因此,该框架能够提取领域自适应知识的外观和语义层次信息,实现领域知识的协同融合。In order to solve the problem of mismatch in cross-domain medical image analysis,this paper proposed an UAL-DAF.Specifically,the framework used the ATM and the STM that combined conditional generative adversarial networks to reduce the differences in the appearance and semantic levels of cross-domain medical images,respectively.Finally,in the challenging medical image segmentation,the results are significantly better than existing methods.Therefore,the framework can extract the appearance and semantic level information of domain adaptation knowledge,and realize the collaborative integration of domain knowledge.

关 键 词：医学图像分割 无监督领域自适应 条件生成对抗网络 深度学习 领域知识的协同融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]