Unsupervised class labeling of diffuse lung diseases using frequent attribute patterns
Unsupervised class labeling of diffuse lung diseases using frequent attribute patterns
复制标题
使用频繁属性模式对弥漫性肺疾病进行无监督分类标记
DOI：
10.1007/s11548-016-1476-2
复制
发表时间：
2016
影响因子：
3
通讯作者：
and S. Kido
中科院分区：
文献类型：
--
作者：
S. Mabu;M. Obayashi M;T. Kuremoto;N. Hashimoto;Y. Hirano;and S. Kido
为了实现CT图像的计算机辅助诊断（CAD），许多模式识别方法已被应用于正常和异常阴影的自动分类，然而为了学习准确的分类器，需要大量具有正确标签的图像。对于放射科医生来说，对大量的CT图像进行正确的标记是一项非常耗时且不切实际的任务。本文针对上述问题，提出了一种新的基于频繁属性模式的肺部弥漫性疾病聚类算法，并实现了一种无需使用正确标签的无监督类标注机制，并利用遗传算法将提取的模式自动分配到多个聚类中。本文利用肺部CT图像对正常和弥漫性肺部疾病进行聚类分析。结果利用GNP进行模式提取后，提取出1,148个频繁属性模式，然后利用GA进行聚类分析。本文涉及使正常和五种异常混浊（即，六类问题），然后，在训练中不使用正确的类标签的情况下，所提出的方法显示了47.7%的聚类准确率.ConclusionIt澄清了所提出的方法可以在不使用正确标签的情况下进行聚类，并且具有应用于CAD的潜力，减少了标记CT图像的时间成本。
PurposeFor realizing computer-aided diagnosis (CAD) of computed tomography (CT) images, many pattern recognition methods have been applied to automatic classification of normal and abnormal opacities; however, for the learning of accurate classifier, a large number of images with correct labels are necessary. It is a very time-consuming and impractical task for radiologists to give correct labels for a large number of CT images. In this paper, to solve the above problem and realize an unsupervised class labeling mechanism without using correct labels, a new clustering algorithm for diffuse lung diseases using frequent attribute patterns is proposed.MethodsA large number of frequently appeared patterns of opacities are extracted by a data mining algorithm named genetic network programming (GNP), and the extracted patterns are automatically distributed to several clusters using genetic algorithm (GA). In this paper, lung CT images are used to make clusters of normal and diffuse lung diseases.ResultsAfter executing the pattern extraction by GNP, 1,148 frequent attribute patterns were extracted; then, GA was executed to make clusters. This paper deals with making clusters of normal and five kinds of abnormal opacities (i.e., six-class problem), and then, the proposed method without using correct class labels in the training showed 47.7 % clustering accuracy.ConclusionIt is clarified that the proposed method can make clusters without using correct labels and has the potential to apply to CAD, reducing the time cost for labeling CT images.