[1]姜婷,袭肖明,岳厚光.基于分布先验的半监督FCM的肺结节分类[J].智能系统学报,2017,12(05):729-734.[doi:10.11992/tis.201706018]
 JIANG Ting,XI Xiaoming,YUE Houguang.Classification of pulmonary nodules by semi-supervised FCM based on prior distribution[J].CAAI Transactions on Intelligent Systems,2017,12(05):729-734.[doi:10.11992/tis.201706018]
点击复制

基于分布先验的半监督FCM的肺结节分类(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第12卷
期数:
2017年05期
页码:
729-734
栏目:
出版日期:
2017-10-25

文章信息/Info

Title:
Classification of pulmonary nodules by semi-supervised FCM based on prior distribution
作者:
姜婷 袭肖明 岳厚光
山东财经大学 计算机科学与技术学院, 山东 济南 250014
Author(s):
JIANG Ting XI Xiaoming YUE Houguang
School of Computer Science and Technology, Shandong University of Finance and Economics, Ji’nan 250014, China
关键词:
肺结节分类半监督FCM先验分布信息图像处理LIDC数据库
Keywords:
classification of pulmonary nodulessemi-supervised FCMprior distributionimage processingLIDC database
分类号:
TP399
DOI:
10.11992/tis.201706018
摘要:
肺结节的良恶性分类对于肺癌的早期发现及诊断具有重要意义。然而实际应用中,标记的图像数量较少,且获取标记将耗费大量的人力,在这种情况下,使用半监督学习算法是有效提高分类性能的一个思路。作为一种经典的半监督学习算法,传统的半监督FCM在未标记样本与标记样本分布不平衡情况下不能充分利用标记信息。针对此问题,本文提出了一种基于分布先验的半监督FCM算法。首先计算样本的先验分布概率,基于获得的先验概率,给样本赋予权重,并将其融入到半监督FCM聚类中,从而强化少量的标记样本在聚类过程中的指导作用。文中在LIDC数据库上进行了相应的实验,实验结果证明,相比较传统的半监督FCM算法,提出的算法能够取得更好的肺结节分类性能。
Abstract:
The classification of pulmonary nodules is significant for the early detection and treatment of lung cancer. However, in real clinical applications, few medical images are labeled and it is difficult to obtain these labels. Semi-supervised learning methods that utilize supervised information to label images may be employed to improve the classification performance of pulmonary nodules. Traditional semi-supervised methods ignore the use of label information when the distribution between labeled and unlabeled specimens is imbalanced. To solve this problem, we propose a semi-supervised fuzzy c-means (FCM) algorithm based on prior distribution for classifying pulmonary nodules. This algorithm first calculates the prior probability of the specimens. Based on the obtained probability, a weight is assigned to each specimen for clustering to intensify the instruction role of a few labeled specimens in the clustering process. We conducted a corresponding test for Lung Image Database Consortium (LIDC) database. The result shows that, compared with the traditional semi-supervised FCM algorithm, the proposed algorithm can obtain better classification performances of pulmonary nodules.

参考文献/References:

[1] MCGUIRE S. World Cancer Report 2014. Geneva,Switzerland:World Health Organization, International Agency for Research on Cancer, WHO Press, 2015[R]. Advances in nutrition, 2016, 7(2):418-419.
[2] 伍长荣, 接标, 叶明全. CT图像肺结节计算机辅助检测与诊断技术研究综述[J]. 数据采集与处理, 2016, 31(5):868-881.WU Changrong, JIE Biao, YE Mingquan. Reviews on computer-aided detection and diagnosis of pulmonary nodules in CT images[J]. Journal of data acquisition and processing, 2016, 31(5):868-881.
[3] LEE S L A, KOUZANI A Z, HU E J. Automated detection of lung nodules in computed tomography images:a review[J]. Machine vision and applications, 2012, 23(1):151-163.
[4] VALENTE I R S, CORTEZ P C, NETO E C, et al. Automatic 3D pulmonary nodule detection in CT images:A survey[J]. Computer methods and programs in biomedicine, 2016, 124(C):91-107.
[5] HAN F, WANG H, ZHANG G, et al. Texture feature analysis for computer-aided diagnosis on pulmonary nodules[J]. Journal of digital imaging, 2015, 28(1):99.
[6] HADY M F A, SCHWENKER F. Semi-supervised learning[J]. Intelligent systems reference library, 2010, 49(2):215-239.
[7] BENSAID A M, HALL L O, BEZDEK J C, et al. Partially supervised clustering for image segmentation[J]. Pattern recognition, 1996, 29(5):859-871.
[8] 张慧哲, 王坚. 基于初始聚类中心选取的改进FCM聚类算法[J]. 计算机科学, 2009, 36(6):206-209.ZHANG Huizhe, WANG Jian. Improved fuzzy C means clustering algorithm based on selecting initial clustering centers[J]. Computer science, 2009, 36(6):206-209.
[9] 李春芳, 庞雅静, 钱丽璞,等. 半监督FCM聚类算法目标函数研究[J]. 计算机工程与应用, 2009, 45(14):128-132.LI Chunfang, PANG Yajing, QIAN Lipu, et al. Objective function of semi-supervised FCM clustering algorithm[J]. Computer engineering and application, 2009, 45(14):128-132.
[10] WU K L. Analysis of parameter selections for fuzzy C-means[J]. Pattern recognition, 2012, 45(1):407-415.
[11] 侯薇, 董红斌, 印桂生. 一种基于隶属度优化的演化聚类算法[J]. 计算机研究与发展, 2013, 50(3):548-558.HOU Wei, DONG Hongbin, YIN Guisheng. A membership degree refinement-based evolutionary clustering algorithm[J]. Journal of computer research and development, 2013, 50(3):548-558.
[12] 李斌, 狄岚, 王少华,等. 基于改进核模糊C均值类间极大化聚类算法[J]. 计算机应用, 2016, 36(7):1981-1987.LI Bin, DI Lan, WANG Shaohua, et al. Clustering algorithm with maximum distance between clusters based on improved kernel fuzzy C-means[J]. Journal of computer applications, 2016, 36(7):1981-1987.
[13] 文传军, 汪庆淼, 詹永照. 均衡模糊C均值聚类算法[J]. 计算机科学, 2014, 41(8):250-253.WEN Chuanjun, WANG Qingmiao, ZHAN Yongzhao, et al. Equalization fuzzy C-means clustering algorithm[J]. Computer science, 2014, 41(8):250-253.
[14] 蔡加欣, 杨丰, 冯国灿. 改进退化的半监督模糊聚类应用于MR图像分割[J]. 中国图象图形学报, 2011, 16(5):784-791.CAI Jiaxin, YANG Feng, FENG Guocan, et al. Degeneracy-improved semi-supervised fuzzy clustering with application in MR image segmentation[J]. Journal of image and graphics, 2011, 16(5):784-791.
[15] 苏志远, 刘慧, 尹义龙. 基于弱监督ECOC算法的肺结节辅助检测[J]. 数据采集与处理, 2015, 30(5):1003-1010.SU Zhiyuan, LIU Hui, YIN Yilong, et al. Pulmonary nodule aided detection based on weakly-supervised ECOC algorithm[J]. Jornal of data acqusition and processing, 2015, 30(5):1003-1010.
[16] MURRAY P, MARSHALL S. A new design tool for feature extraction in noisy images based on grayscale hit-or-miss transforms[J]. IEEE transactions on image processing a publication of the ieee signal processing society, 2011, 20(7):1938-48.
[17] BAE H J, KANG E Y, YONG H S, et al. Paratracheal air cysts on thoracic multidetector CT:incidence, morphological characteristics and relevance to pulmonary emphysema[J]. British journal of radiology, 2013, 86(1021):20120218.
[18] BEZDEK J C, EHRLICH R, FULL W. FCM:the fuzzy C-means clustering algorithm[J]. Computers and geosciences, 1984, 10(2/3):191-203.
[19] PEDRYCZ W, WEMBER J, WALETZKY J. Fuzzy clusteringwith partial supervision[J]. IEEE transaction on system, man, and cybernetics, part B:cybernetics,1997, 27(5):787-795.
[20] MCNITT-GRAY M F, MEYER C R, REEVES A P, et al. The lung image database consortium (LIDC) data collection process for nodule detection and annotation[J]. Academic radiology, 2008, 14(12):1464-1474.
[21] 李秋萍, 刘慧, 苏志远. 基于改进的半监督FCM聚类算法的肺结节分类与识别[J]. 图学学报, 2015, 36(2):244-250.LI Qiuping, LIU Hui, SU Zhiyuan. Modified fuzzy clustering with partial supervision algorithm in classification and recognition of pulmonary nodules[J]. Journal of graphics, 2015, 36(2):244-250.

备注/Memo

备注/Memo:
收稿日期:2017-06-07。
基金项目:国家自然科学基金项目(61573219,61671274);山东省自然科学基金项目(ZR2016FQ18,ZR2014HM065);医药卫生科技发展计划项目(2014ws0109).
作者简介:姜婷,女,1991年生,硕士研究生,主要研究方向为数据挖掘、机器学习。参与多项国家自然科学基金等科研项目;袭肖明,男,1987年生,博士,主要研究方向为生物识别、机器学习。主持国家自然科学基金、省自然科学基金等多项科学研究项目;岳厚光,男,1971年生,副教授,主要研究方面为数据挖掘、机器学习。
通讯作者:袭肖明.E-mail:fyzq10@126.com
更新日期/Last Update: 2017-10-25