电子学报 ›› 2015, Vol. 43 ›› Issue (12): 2476-2483.DOI: 10.3969/j.issn.0372-2112.2015.12.020

• 学术论文 • 上一篇    下一篇

基于语义属性的肺结节良恶性分类

巩萍1,2, 程玉虎1, 王雪松1   

  1. 1. 中国矿业大学信息与电气工程学院, 江苏徐州 221116;
    2. 徐州医学院医学影像学院, 江苏徐州 221004
  • 收稿日期:2014-08-05 修回日期:2015-01-20 出版日期:2015-12-25
    • 通讯作者:
    • 程玉虎
    • 作者简介:
    • 巩萍 女,1980年出生于江苏徐州,现为徐州医学院讲师,中国矿业大学信息与电气工程学院博士生,研究方向为医学图像处理、属性学习等.E-mail:gongpingcumt@126.com;王雪松 女,1974年出生于安徽泗县,中国矿业大学信息与电气工程学院教授,博士生导师.主要研究方向为机器学习与模式识别.E-mail:wangxuesongcumt@163.com
    • 基金资助:
    • 国家自然科学基金 (No.61273143,No.61472424); 中央高校基本科研业务费 (No.2013RC10,No.2013RC12,No.2014YC07); 徐州市科技计划项目 (No.KC14SM089)

Benign or Malignant Classification of Lung Nodules Based on Semantic Attributes

GONG Ping1,2, CHENG Yu-hu1, WANG Xue-song1   

  1. 1. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China;
    2. School of Medical Imaging, Xuzhou Medical College, Xuzhou, Jiangsu 221004, China
  • Received:2014-08-05 Revised:2015-01-20 Online:2015-12-25 Published:2015-12-25

摘要:

现有肺结节良恶性计算机辅助诊断的依据通常为肺部CT图像的底层特征,而临床医生的诊断依据为高级语义特征.为克服这种图像底层特征和高级语义特征之间的不一致性,提出一种基于语义属性的肺结节良恶性判别方法.首先,利用阈值概率图方法提取肺结节图像;其次,一方面提取肺结节图像的形状、灰度、纹理、大小和位置等底层特征,组成样本特征集.另一方面,根据专家对肺结节属性的标注,提取结节属性集;然后,根据特征集和属性集建立属性预测模型,实现两者之间的映射;最后,利用预测的属性进行肺结节的良恶性分类.LIDC数据库上的实验结果表明所提方法具有较高的分类精度和AUC值.

关键词: 底层特征, 语义属性, 属性预测模型, 肺结节, 分类

Abstract:

The current computer aided diagnosis system classifies benign or malignant lung nodules mainly according to the low-level features of lung CT images.However,clinicians use the high-level semantic features of lung CT images.To overcome the inconsistency between the low-level features and high-level semantic features,a new approach of benign or malignant lung nodules classification based on semantic attributes is proposed.Firstly,lung nodule images are extracted using the threshold probability-map method.Secondly,on the one hand,some features including shape,gray,texture,size and position are extracted from lung nodule images to constitute the low-level feature set;on the other hand,according to the experts' annotation of lung nodules,the attributes are extracted to constitute the high-level attribute set.Thirdly,attribute prediction models are built to map the low-level features to the high-level attributes.Finally,the benign or malignant classification of lung nodules is performed using the predicted attributes.Experimental results on the LIDC dataset show that the proposed classification method possesses high classification accuracy and AUC value.

Key words: low-level feature, semantic attribute, attribute prediction model, lung nodule, classification

中图分类号: