北京生物医学工程

基于Curvelet变换的肺结节CT图像良恶性分类研究

Classification of Malignant and Benign Pulmonary Nodules in CT Image Based on Curvelet Transformation

作者：吴海丰刘韫宁孙涛李霞郭秀花贺文

单位：首都医科大学公共卫生与家庭医学学院（北京100069）

分类号：

出版年·卷·期（页码）：2011·30·5（471-473）

摘要：

目的早期肺癌患者的CT图像表现为结节状（在肺野内直径≤3cm的病灶），需要与结核球等良性病
变鉴别开, 以提高患者的5年生存率。方法本文基于Curvelet变换提取能量、熵、灰度均值及灰度标准
差四种纹理特征值，按7∶3比例将样本分为训练集与验证集。使用BP(back propagation)神经网络作为
分类器。每一种纹理参数测试集的神经网络仿真值结合病理诊断结果绘制受试者工作特征曲线
（receiver operator characteristic curve, ROC曲线），根据ROC下面积得到最优的几种纹理参数用
于良恶性分类，并将分类结果与病理诊断结果进行比较。结果四种纹理参数构建的BP网络均具有诊断价
值，每种纹理参数诊断价值各不相同，其中熵与灰度标准差的诊断价值优于能量与灰度均值，并且通过
组合多种纹理参数可以提高诊断准确性。结论使用熵与灰度标准差两种纹理特征值构建BP神经网络能达
到最好的分类效果，在一定程度上有利于肺癌的早期诊断。

Objective To raise the 5-year survival rate,the CT detected pulmonary
nodules,which size is defined smaller than 30mm, is needed to be distinguished between
benign or malignantones. Methods Curvelet transformation was introduced in this paper and
four texture features, including energy, entropy, gray scale mean and gray scale
standardized deviation, were calculated. The samples were divided into 2 parts, 70% in test
set, and the 30% in validation set. A back propagation(BP) artificial neutral network was
used as the classifier. The testing set of each texture feature obtained a ROC (receiver
operator characteristic curve) by using its simulation result of the BP artificial neutral
network and pathological diagnosis. The optimal texture features were chosen to predict the
characteristic of small solitary pulmonary nodules in the CT images compared with other
texture features, it was more proper to use the entropy and standard deviation as
parameters to establish the prediction model. Results The BP artificial neutral network
established by parameters entropy and standard deviation provided the best discrimination
of the benign and the malignant small solitary pulmonary nodules. Conclusions We can
profit from the diagnosis of early stage carcinoma of the lung to some extent with the BP
artificial neutral network, which utilizes the entropy and standard deviation as
parameters.

参考文献：

［1］Jemal A, Siegel R, Xu J, et al. cancer statistics 2010［J/OL］. CA Cancer J Clin，
2010. doi: 10.3322/caac.20073.
［2］Kusumoto M, Tateishi U, Arai Y, et al. Diagnostic imaging of cancer on multislice CT［
J］. Cancer & Chemotherapy， 2005, 32(6): 759-764.
［3］Liu YN， Wang H, Guo XH, et al Application of artificial neural networks in
prediction model of early-stage lung cancer［J］. Chinese Journal of Medical
Statistics,2008, 1(1): 30-33.
［4］Candes EJ, Demanet L, Donoho DL, et al. Fast discrete curvelet transforms［R］.Applied
and Computational Mathematics, California Institute of Technology, 2005: 1-43.
［5］Dettori L, Semler L. A comparison of wavelet, ridgelet, and curvelet-based texture
classification algorithms in computed tomography［J］ . Computers in Biology and Medicine,
2009 (37): 486-498.
［6］Mohamed ME, Ibrahima F, Brahim BS. Breast cancer diagnosis in digital mammogram using
multiscale curvelet transform［J］. Computerized Medical Imaging and Graphics,2010, 34(4):
269-276.
［7］Mohamed ME, Ibrahima F, Brahim BS. A comparison of wavelet and curvelet for breast
cancer diagnosis in digital mammogram［J］. Computerized Medical Imaging and Graphics,
2010, 40(4): 384-391.
［8］Arivazhagan S, Ganesan L, Kumar TS. Texture classification using curvelet statistical
and co-occurrence feature. In Proceedings of the 18th International Conference on Pattern
Recognition (ICPR 2006), 2006, 2: 938-941.
［9］倪雪, 李庆武, 孟凡,等. Curvelet变换用于人脸特征提取与识别［J］. 应用科学学报, 2009,
27(1): 34-38.
［10］许学斌, 张德运, 张新曼,等. 采用离散曲波变换和支持向量机的掌纹识别方法［J］.红外与毫米
波学报, 2009, 28(6): 456-460.
［11］Ondimu S, Murase NH. Effect of probability-distance based Markovian texture
extraction on discrimination in biological imaging. Computers and Electronics in
Agriculture,2008, 63(1): 2-12.
［12］Wang H, Guo XH, Jia ZW,et al Multilevel binomial logistic prediction model for
malignant pulmonary nodules based on texture features of CT image［J］. European Journal of
Radiology,2010, 74 (1): 124-129.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录