基于语义属性的肺结节良恶性分类

doi:10.3969/j.issn.0372-2112.2015.12.020

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

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. 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 Ping^1,2, CHENG Yu-hu¹, WANG Xue-song¹

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/Abstract

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:

TP391.4

巩萍, 程玉虎, 王雪松. 基于语义属性的肺结节良恶性分类[J]. 电子学报, 2015, 43(12): 2476-2483.

GONG Ping, CHENG Yu-hu, WANG Xue-song. Benign or Malignant Classification of Lung Nodules Based on Semantic Attributes[J]. Acta Electronica Sinica, 2015, 43(12): 2476-2483.

参考文献

[1] Tartar A,Akan A,Kilic N.A novel approach to malignant-benign classification of pulmonary nodules by using ensemble learning classifiers[A].Proceedings of the 36th IEEE International Conference on Engineering in Medicine and Biology Society[C].Piscataway:IEEE Press,2014.4651-4654.
[2] Suzuki K,Li F,Sone S,Doi K.Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network[J].IEEE Transactions on Medical Imaging,2005,24(9):1138-1150.
[3] 姜慧研,何炜.基于胸部CT图像的肺癌识别方法的研究[J].电子学报,2009,37(8):1664-1668. JIANG Hui-Yan,HE Wei.Research of lung cancer recognition based on chest CT images[J].Acta Electronica Sinica,2009,37(8):1664-1668.(in Chinese)
[4] 刘露,刘宛予,楚春雨,吴军,周洋,张红霞,鲍劼.胸部CT图像中孤立性肺结节良恶性快速分类[J].光学精密工程,2009,17(8):2060-2066. LIU Lu,LIU Wan-Yu,CHU Chun-Yu,WU Jun,ZHOU Yang,ZHANG Hong-Xia,BAO Jie.Fast classification of benign and malignant solitary pulmonary nodules in CT image[J].Optics and Precision Engineering,2009,17(8):2060-2066.(in Chinese)
[5] Shen W C,Yu Y H,Chuang C H.Computer aided diagnosis for pulmonary nodule on low-dose computed tomography (LDCT)using density features[A].Proceedings of 2011 8th International Conference on Computer Graphics,Imaging and Visualization[C].Piscataway:IEEE Press,2011.166-169.
[6] El-Baz A,Gimel'farb G,Abou El-Ghar M,Falk R.Appearance based diagnostic system for early assessment of malignant lung nodules[A].Proceedings of 2012 19th IEEE International Conference on Image Processing[C].Piscataway:IEEE Press,2012.533-536.
[7] Babbie E.The Practice of Social Research[M].San Francisco:Wadsworth Publishing,2009.14-18.
[8] Horsthemke W H,Raicu D S,Furst J D.Evaluation challenges for bridging semantic gap:shape disagreenment on pulmonary nodules in the lung image database consortium[J].International Journal of Healthcare Information Systems and Informatics,2009,4(1):17-33.
[9] Li G,Kim H,Tan J K,Ishikawa S,Hirano Y,Kido S,Tachibana R.Semantic characteristics prediction of pulmonary nodule using artificial neural networks[A].Proceedings of 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society[C].Piscataway:IEEE Press,2013.5465-5468.
[10] Zinovev D,Raicu D S,Furst J,Lii S G A.Predicting radiological panel opinions using a panel of machine learning classifiers[J].Algorithms,2009,2 (4):1473-1502.
[11] Armato S G,McLennan G,McNitt-Gray M F,Meyer C R,David Y,Aberle D R,et al.Lung image database consortium:developing a resource for the medical imaging research community[J].Radiology,2004,232(3):739-748.
[12] Shodayu T,Shusuke S,Feng L,Yuichiro M,Minoru H,Tsuyoshi M,et al.Small solitary pulmonary nodules ([13] Wosiak A,Zakrzewska D.Feature selection for classification incorporating less meaningful attribute in medical diagnostics[A].Proceedings of the 2014 Federated Conference on Computer Science and Information Systems[C].Piscataway:IEEE Press,2014.235-240.
[14] 程玉虎,仝瑶瑶,王雪松.类相关性影响可变选择性贝叶斯分类器[J].电子学报,2011,39(7):1628-1633. CHENG Yu-hu,TONG Yao-yao,WANG Xue-song.A selective bayesian classifier based on change of class relevance influence[J].Acta Electronica Sinica,2011,39(7):1628-1633.(in Chinese)
[15] Zhang D Q,Chen S C,Zhou Z H.Constraint score:a new filter method for feature selection with pair-wise constraints[J].Pattern Recognition,2008,41(5):1440-1445.
[16] 陈洪波,李蓓蕾,陈真诚.基于ICA的脑电信号P300少次自动提取[J].电子学报,2012,40(6):1257-1262. CHEN Hong-bo,LI Bei-lei,CHEN Zhen-cheng.Automatically extract P300 within several trials from EEG based on ICA[J].Acta Electronica Sinica,2012,40(6):1257-1262.(in Chinese)
[17] Lampert C H,Nickisch H,Harmeling S.Learning to detect unseen object classes by between-class attribute transfer[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].Piscataway:IEEE Press,2009.951-958.
[18] Armato S G,Roberts R Y,Kocherginsky M,Aberle D R,Kazerooni E A,MacMahon H,et al.Assessment of radiologist performance in the detection of lung nodules[J].Academic Radiology,2009,16(1):28-38.

基于语义属性的肺结节良恶性分类

Benign or Malignant Classification of Lung Nodules Based on Semantic Attributes

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.
[2]	陆克中, 陈超凡, 蔡桓, 吴定明. 面向概念漂移和类不平衡数据流的在线分类算法[J]. 电子学报, 2022, 50(3): 585-597.
[3]	王雪松, 张翰林, 程玉虎. 基于自编码器和超图的半监督宽度学习系统[J]. 电子学报, 2022, 50(3): 533-539.
[4]	孙晨峰, 吕卫民, 戴洪德, 张浩晨. 一种基于TimeGAN和OCSVM的多元退化设备小子样数据增广方法[J]. 电子学报, 2022, 50(11): 2678-2687.
[5]	刘浩阳, 林耀进, 刘景华, 吴镒潾, 毛煜, 李绍滋. 由粗到细的分层特征选择[J]. 电子学报, 2022, 50(11): 2778-2789.
[6]	高雷阜, 张梦瑶, 赵世杰. 融合簇边界移动与自适应合成的混合采样算法[J]. 电子学报, 2022, 50(10): 2517-2529.
[7]	管永明, 王刚, 骆凯波, 吕梁, 吕晓雯, 史玉良. 基于极端不平衡学习的泛化低压异常箱表关系识别研究与应用[J]. 电子学报, 2021, 49(8): 1507-1514.
[8]	杨国为, 万鸣华, 赖志辉, 张凡龙, 黄伟强. 具有合适拒识机制的高正确识别率分类器设计[J]. 电子学报, 2021, 49(8): 1569-1576.
[9]	郑海颖, 王峰, 姜维, 王志强, 姚西文. 神经网络训练策略对高分辨率遥感图像场景分类性能影响的评估[J]. 电子学报, 2021, 49(8): 1599-1614.
[10]	吕亚平, 贾向东, 路艺, 牛春雨, 曹胜男. 基于簇用户设备分类和频谱共享分配的D2D网络覆盖分析[J]. 电子学报, 2021, 49(7): 1392-1399.
[11]	张昱, 刘开峰, 张全新, 王艳歌, 高凯龙. 基于组合-卷积神经网络的中文新闻文本分类[J]. 电子学报, 2021, 49(6): 1059-1067.
[12]	李大鹏, 陈剑, 王晨, 闻英友, 赵大哲. 基于模板张量分解和双向LSTM的司法案件罪名认定[J]. 电子学报, 2021, 49(4): 760-767.
[13]	唐焕玲, 郑涵, 刘艳红, 马思源, 窦全胜, 鲁明羽. Tr-SLDA:一种面向交叉领域的迁移主题模型[J]. 电子学报, 2021, 49(3): 605-613.
[14]	崔子熙, 胡宇翔, 兰巨龙, 王雨. 基于流分类的数据中心网络负载均衡机制[J]. 电子学报, 2021, 49(3): 559-565.
[15]	李海, 尚金雷, 孙婷逸, 冯青, 庄子波. 一种基于离散属性BNT的双偏振气象雷达降水粒子分类方法[J]. 电子学报, 2021, 49(3): 619-624.