Please wait a minute...
J4  2012, Vol. 46 Issue (1): 170-176    DOI: 10.3785/j.issn.1008-973X.2012.01.27
生物医学工程     
基于磁共振图像的脑瘤MGMT表达状况检测算法
刘晨彬1,潘颖1,张海石2,黄峰平2,夏顺仁1
1.浙江大学 生物医学工程教育部重点实验室,浙江 杭州 310027;
2.复旦大学附属华山医院,上海 200040
Detecting MGMT expression status of glioma with magnetic
resonance image
LIU Chen-bin1, PAN Ying1, ZHANG Hai-shi2, HUANG Feng-ping2, XIA Shun-ren1
1. Key Laboratory of Biomedical Engineering, Ministry of Education, Zhejiang University, Hangzhou 310027, China;
2. Fudan University Affiliated Huashan Hospital, Shanghai 200040, China
 全文: PDF  HTML
摘要:

针对脑胶质瘤的O6甲基鸟嘌呤-DNA甲基转移酶(MGMT)表达状况检测受主观影响的问题,以中国脑胶质瘤患者的磁共振图像(MRI)为研究对象,提出一种包括特征提取、特征优化和模式分类的图像处理方法.利用图像的灰度共生矩阵、灰度梯度共生矩阵和二维离散正交S变换(2D-DOST)提取肿瘤病变区域的纹理特征,结合环形增强和年龄特征构成初始特征集.将k最邻近法(KNN)与支持向量机(SVM)结合,进行特征优化.使用留一交叉检验法(LOOCV),将最优特征集进行SVM分类.分别对25位脑胶质瘤患者的T1加权、T1增强和FLAIR序列的磁共振图像进行分析.结果表明,该算法能够降低特征集的冗余程度,克服小样本分类困难,准确有效地检测MGMT表达状况.

Abstract:

In order to overcome the deficiency of strong subjectivity in detecting O6-methylguanine-DNA methyltransferase (MGMT) expression of gliomas, an image processing method was proposed to analyze the magnetic resonance images (MRI) of Chinese glioma patients. The method included feature extraction, feature optimization and pattern recognition. Gray co-occurrence matrix, gray level-gradient co-occurrence matrix and two-dimensional discrete orthogonal S-transform (2D-DOST) were utilized to extract the texture features in the tumor area. Ring enhancement and age were also added in the initial feature set. Then k-nearest neighbor (KNN) and support vector machine (SVM) were combined to search optimal features. The optimal feature set was classified by SVM in a leave-one-out cross validation strategy (LOOCV). T1-weighted, T1-enhanced and FLAIR MRI of 25 glioma patients were analyzed. Results show that the algorithm can reduce the redundance of feature set, overcome the difficulty of small sample classification and identify the status of MGMT expression accurately and effectively.

出版日期: 2012-02-22
:  TP 391.41  
基金资助:

国家自然科学基金资助项目(60772092).

通讯作者: 夏顺仁,男,教授,博导.     E-mail: srxia@zju.edu.cn
作者简介: 刘晨彬(1985-),男,博士生,从事医学图像处理研究. E-mail: chenbin.liu@gmail.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

刘晨彬,潘颖,张海石,黄峰平,夏顺仁. 基于磁共振图像的脑瘤MGMT表达状况检测算法[J]. J4, 2012, 46(1): 170-176.

LIU Chen-bin, PAN Ying, ZHANG Hai-shi, HUANG Feng-ping, XIA Shun-ren. Detecting MGMT expression status of glioma with magnetic
resonance image. J4, 2012, 46(1): 170-176.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2012.01.27        http://www.zjujournals.com/eng/CN/Y2012/V46/I1/170

[1] HEGI M E, DISERENS A C, GORLIA T, et al. MGMT gene silencing and benefit from temozolomide in glioblastoma [J]. New England Journal of Medicine, 2005, 352(10): 997-1003.
[2] 孙彦辉,张亚卓,王忠诚,等. MGMT在脑胶质瘤组织中的表达及其与患者生存期的关系[J]. 癌症, 2004, 23(9): 1052-1055.
SUN Yanhui, ZHANG Yazhuo, WANG Zhongcheng, et al. Relationship between the expression of O6methylguanineDNA methyltransferase; hypermethylaton in glioma and the survival time of patients [J].Chinese Journal of Cancer, 2004, 23(9): 1052-1055.
[3] SEIDAL T, BALATON A J, BATTIFORA H. Interpretation and quantification of immunostains [J]. The American Journal of Surgical Pathology, 2001, 25(9): 1204-1207.
[4] MOSKALUK C A. Standardization of clinical immunohistochemistry [J]. American Journal of Clinical Pathology, 2002, 118(5): 669-671.
[5] BRUZZONE M G, EOLI M, CUCCARINI V, et al. Genetic signature of adult gliomas and correlation with MRI features [J]. Expert Review of Molecular Diagnostics, 2009, 9(7): 709-720.
[6] LEVNER I, DRABYCZ S, ROLDAN G, et al. Predicting MGMT methylation status of glioblastomas from MRI texture [C]∥ Proceedings of the 12th International Conference on Medical Image Computing and ComputerAssisted Intervention: Part II. London: Springer, 2009: 522-530.
[7] DRABYCZ S, ROLDAN G, DE ROBLES P, et al. An analysis of image texture, tumor location, and MGMT promoter methylation in glioblastoma using magnetic resonance imaging [J]. NeuroImage, 2010, 49(2): 1398-1405.
[8] WIENCKE J K. Molecular features of adult glioma associated with patient race/ethnicity, age, and a polymorphism in O6MethylguanineDNAMethyltransferase [J]. Cancer Epidemiology Biomarkers and Prevention, 2005, 14(7): 1774-1783.
[9] ZHANG J, TONG L Z, WANG L, et al. Texture analysis of multiple sclerosis: a comparative study [J]. Magnetic Resonance Imaging, 2008, 26(8): 1160-1166.
[10] ROLHION C, PENAULTLLORCA F, KEMENY J L, et al. O6methylguanineDNA methyltransferase gene (MGMT) expression in human glioblastomas in relation to patient characteristics and p53 accumulation [J]. International Journal of Cancer, 1999, 84(4): 416-420.
[11] BRELL M, TORTOSA A, VERGER E, et al. Prognostic significance of O6methylguanineDNA methyltransferase determined by promoter hypermethylation and immunohistochemical expression in anaplastic gliomas [J]. Clinical Cancer Research, 2005, 11(14): 5167-5174.
[12] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification [J]. IEEE Transaction on Systems, Man and Cybernetics, 1973, 3(6): 610-622.
[13] 洪继光. 灰度梯度共生矩阵纹理分析方法[J]. 自动化学报, 1984, 10(1): 22-25.
HONG Jiguang. Gray levelgradient coocurrence matrix texture analysis method [J]. Acta Automatica Sinica, 1984, 10(1): 22-25.
[14] 王士浩,何杰,朱海青,等. 脑胶质瘤MGMT基因启动子甲基化与蛋白表达的研究[J]. 现代医学, 2009, 37(3): 216-219.
WANG Shihao, HE Jie, ZHU Haiqing, et al. A research of promoter hypermethlation and expression of MGMT in gliomas [J]. Modern Medical Journal, 2009, 37(3): 216-219.
[15] DRABYCZ S, STOCKWELL R G, MITCHELL J R. Image texture characterization using the discrete orthonormal Stransform [J]. Journal of Digital Imaging, 2009, 22(6): 696-708.
[16] SAEYS Y, INZA I, LARRANAGA P. A review of feature selection techniques in bioinformatics [J]. Bioinformatics, 2007, 23(19): 2507-2517.
[17] 姚莉秀,杨杰,叶晨洲,等. 用于特征筛选的最近邻(KNN)法[J]. 计算机与应用化学, 2001, 18(2): 135-138.
YAO Lixiu, YANG Jie, YE Chenzhou, et al. K nearest neighbor (KNN) method used in feature selection [J]. Computers and Applied Chemistry, 2001, 18(2): 135-138.
[18] VAPNIK V N. The nature of statistical learning theory [M]. New York: Springer, 1995: 138-167.
[19] VAPNIK V N. Statistical learning theory [M]. New York: Wiley, 1998: 321-327.
[20] CHANG C C, LIN C J. LIBSVM: a library for support vector machine [EB/OL]. [20110913]. http:∥www.csie.ntu.edu.tw/~cjlin/libsvm.
[21] FAWCETT T. An introduction to ROC analysis [J]. Pattern Recognition Letters, 2006, 27(8): 861-874.

[1] 杨玉婷, 史玉回, 夏顺仁. 基于讨论机制的头脑风暴优化算法[J]. J4, 2013, 47(10): 1705-1711.
[2] 朱晓恩, 郝欣, 夏顺仁. 基于Levy flight的特征选择算法[J]. J4, 2013, 47(4): 638-643.
[3] 孙创日,甄帅,夏顺仁. 基于吸引区域的多模态脑磁共振图像仿射配准[J]. J4, 2012, 46(9): 1722-1728.
[4] 谢迪, 童若锋, 唐敏, 冯阳. 具有高区分度的视频火焰检测方法[J]. J4, 2012, 46(4): 698-704.
[5] 戴渊明, 韦巍, 林亦宁. 基于颜色纹理特征的均值漂移目标跟踪算法[J]. J4, 2012, 46(2): 212-217.
[6] 李启雷, 金文光, 耿卫东. 基于无线惯性传感器的人体动作捕获方法[J]. J4, 2012, 46(2): 280-285.
[7] 钱诚, 张三元. 适用于目标跟踪的加权增量子空间学习算法[J]. J4, 2011, 45(12): 2240-2246.
[8] 曹颖, 郝欣, 朱晓恩, 夏顺仁. 基于自动随机游走的乳腺肿块分割算法[J]. J4, 2011, 45(10): 1753-1760.
[9] 吕谷来, 李建平, 李锵, 俞利兴, 朱松明, 楼建忠, 袁祎琳. 基于机器视觉的砧木定位识别方法[J]. J4, 2011, 45(10): 1766-1770.
[10] 赖小波,朱世强. 基于互相关信息的非参数变换立体匹配算法[J]. J4, 2011, 45(9): 1636-1642.
[11] 王金德, 寿黎但, 李晓燕, 陈刚. 基于多重分割捆绑特征的目标图像检索[J]. J4, 2011, 45(2): 259-266.
[12] 刘建明, 鲁东明, 葛蓉. 基于全局优化的图像修复及其在GPU上实现[J]. J4, 2011, 45(2): 247-252.
[13] 梁文锋,项志宇. 鲁棒的PTZ摄像机目标跟踪算法[J]. J4, 2011, 45(1): 59-63.
[14] 战江涛,刘强,柴春雷. 基于三维模型与Gabor小波的人脸特征点跟踪方法[J]. J4, 2011, 45(1): 30-36.
[15] 宋坤坡, 夏顺仁, 徐清. 考虑小波系数相关性的超声图像降噪算法[J]. J4, 2010, 44(11): 2203-2208.