甲状腺超声影像的元优化多级对抗域适应网络  

Meta-optimized multi-adversarial domain adaptation for thyroid ultrasound image

作　　者：应翔 刘振[1,2,3] 朱佳琳 姜汉 张瑞璇 高洁 Ying Xiang;Liu Zhen;Zhu Jialin;Jiang Han;Zhang Ruixuan;Gao Jie(College of Intelligence and Computing,Tianjin University,Tianjin 300350,China;Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin 300350,China;Tianjin Key Laboratory of Advanced Networking,Tianjin 300350,China;Medical University Cancer Institute and Hospital,Tianjin 300060,China;OpenBayes(Tianjin)IT Co.,Ltd.,Tianjin 300456,China)

机构地区：[1]天津大学智能与计算学部,天津300350 [2]天津市认知计算与应用重点实验室,天津300350 [3]天津市先进网络技术与应用重点实验室,天津300350 [4]天津医科大学肿瘤医院,天津300060 [5]贝式计算(天津)信息技术有限公司,天津300456

出　　处：《中国图象图形学报》2023年第1期234-247,共14页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61976155);天津市企业科技特派员项目(21YDTPJC00090)。

摘　　要：目的计算机辅助诊断是临床诊断中一种重要的辅助手段。然而在多机型超声影像的应用现状中,单一深度卷积神经网络面临难以从不同数据源中提取样本特征的问题,导致模型在区分多源数据方面性能欠佳。为提升单一深度模型在多源数据的泛化能力,本文提出一种无监督域自适应网络。方法将深度对抗域适应方法应用于多源甲状腺超声影像分类任务,通过生成对抗思想提取源域图像与目标域图像的域不变特征,提出一种多级对抗域自适应网络(multi-level adversarial domain adaptation network,MADAN)。将元优化(meta-optimized)策略引入对抗域适应的学习中,将域对齐目标和样本分类目标以协调的方式联合优化,提升了模型对无标记目标域数据的分类性能。结果在包含4种域的甲状腺超声影像数据集上实验,与7种经典域自适应方法比较。实验结果表明,MADAN在全部迁移任务中取得90.141%的目标域样本平均分类准确率,优于残差分类网络和多种经典域自适应分类网络。融合元优化训练策略后的MADAN在目标域的测试平均准确率提升约1.67%。结论本文提出的元优化多级对抗域适应网络一方面通过多级对抗学习进行图像域不变特征的提取,另一方面使用元优化方式改进模型训练过程的优化策略,将带有人工标记的源域信息有效迁移至目标域,提升了单一模型对于不同域数据的泛化性能。Objective Artificial intelligence based(AI-based)medical clinical diagnosis technique has been developing in recent years.It can alleviate the problems of medical image analysis in China via deep networks modeling and medical image data analysis,such as the shortage of expertises,the imbalance of urban and rural medical resources allocation,and the the imaging accuracy issues.However,clinical-aided are often linked to multi-model data with different characteristics distribution in different hospitals.Therefore,improving the generalization and stability of the cross-model medical diagnosis-consistent model is required for quick response intensively.In order to alleviate the domain shift existing in the ultrasound imaging field,the unsupervised domain adaptation method can be as the one of the most concerning methods at present.It can avoid the manual labeling of ultrasound image data of various models,a single model can be learnt to adapt to the target domain sample set with data deviation through the labeled source domain sample set,which improves the generalizability of convolutional neural network(CNN)to a certain extent.However,current unsupervised domain adaptation research has some challenging constraints,such as poor feature extraction and inconsistent optimization of domain fusion and sample classification.In view of the limitations in related to domain adaptation network,we develop an intergrated domain adaptation network,which focuses on the under-expressed feature of nodular region features in thyroid ultrasound images.This research is aimed to enhance the fusion of source domain features space and target domain features space.Method In this study,a new domain adaptation network is constructed called based on domain-adversarial training of neural networks(DANN),called multi-level adversarial domain adaptation network(MADAN).In the training process,we first build a three-layer generator and discriminator structure according to the transition from general to special features,which can obtain more semantic

关 键 词：计算机辅助诊断(CAD) 多机型甲状腺超声影像 域自适应 元优化 生成对抗网络(GAN) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]