Fisher准则下面向判别性特征的字典学习方法及其组织病理图像分类研究  

Discriminative Feature-oriented Dictionary Learning Method With Fisher Criterion for Histopathological Image Classification

作　　者：汤红忠[1,2,3] 李骁 张小刚[2] 张东波 王翔[1,3] 毛丽珍[1,3] TANG Hong-Zhong;LI Xiao;ZHANG Xiao-Gang;ZHANG Dong-Bo;WANG Xiang;MAO Li-Zhen(College of Information Engineering,Xiangtan University,Xiangtan 411105;College of Electrical and Information En-gineering,Hunan University,Changsha 410082;Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education,Xiangtan University,Xiangtan 411105)

机构地区：[1]湘潭大学信息工程学院,湘潭411105 [2]湖南大学电气与信息工程学院,长沙410082 [3]湘潭大学智能计算与信息处理教育部重点实验室,湘潭411105

出　　处：《自动化学报》2018年第10期1842-1853,共12页Acta Automatica Sinica

基　　金：国家自然科学基金(61573299;61673162;61672216);湖南省自然科学基金(2017JJ3315;2017JJ2251;2016JJ3125);湖南省教育厅项目(15C1328)资助~~

摘　　要：针对当前面向组织病理图像特征提取的字典学习方法中存在着学习的无病字典与有病字典相似程度高,判别性弱的问题,本文提出一种新的面向判别性特征字典学习方法 (Discriminative feature-oriented dictionary learning based on Fisher criterion, FCDFDL).该方法基于Fisher准则构造目标函数的惩罚项,最小化学习字典的类内距离与最大化学习字典的类间距离,大大降低无病字典与有病字典间的相似性.同时,优化学习字典对同类样本的重构性能,并约束学习字典对非同类样本的重构性能.然后,利用本文学习的无病与有病字典对测试样本进行稀疏表示,采用重构误差向量的统计量构造分类器.最后,分别在ADL数据集与BreaKHis数据集上验证了本文方法的有效性.实验结果表明,本文学习字典的判别性更强,获得了更优的分类性能.The problem of high similarity between learned healthy dictionary and diseased dictionary and low discrimination exists in the current dictionary learning methods for histopathological image feature extraction. In this paper,we present a novel discriminative feature-oriented dictionary learning method based on Fisher criterion（FCDFDL）. This method constructs a penalty item of the objective function using Fisher criterion to minimize the intra-class distance of learned dictionaries and maximize the inter-class distance of learned dictionaries. Thus, the similarity between healthy and diseased dictionaries is reduced. Furthermore, the reconstruction of the same class samples is improved over the learned dictionaries, while reconstruction of different class samples is suppressed. Then, the sparse representation of test samples is respectively performed on the learned healthy dictionary and the diseased dictionary, and the classifier is constructed by employing the reconstruction error vector of test samples. Finally, the proposed FCDFDL is tested on ADL and BreaKHis datasets, and experimental results show that the learned dictionaries have stronger discrimination and improved classification performance as compared to the other dictionary learning methods, for histopathological image.

关 键 词：组织病理图像 FISHER准则 字典学习 判别性特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]