肺结节球表面网格向量化特征分类  

Classification method of vectorization characteristics of pulmonary nodule surface

作　　者：刘通 徐久强 朱宏博 孟昭岩 窦圣昶 LiuTong;Xu jiuqlang;Zhu Hongbo;Meng Zhaoyan;Dou Shengchang(School of Computer Science and Engineering,Northeastern University,Shenyang 110819,China;Liaoning Embedded Key Laboratory,Shenyang 110819,China;Shenyang lot Application Basic Research Engineering Laboratory,Shenyang 110819,China)

机构地区：[1]东北大学计算机科学与工程学院,沈阳110819 [2]辽宁省嵌入式重点实验室,沈阳110819 [3]沈阳市物联网应用基础研究工程实验室,沈阳110819

出　　处：《中国图象图形学报》2019年第1期124-134,共11页Journal of Image and Graphics

基　　金：中央高校基本科研业务费专项基金项目(N171903002);辽宁省教育厅重点实验室基金项目(LZ2014015)~~

摘　　要：目的基于球谐函数与容斥映射算法向量化球面表面纹理与结节形状用以进行胸部CT图像肺结节良恶性判定。区别于基于深度学习解决肺结节良恶性筛查的方法,目前方法多集中于框架改进而忽略了数据预处理,文中所提方法旨在对球面纹理与结节形状进行向量表达,使其可以输入深度森林进行特征分类训练。方法首先采用辽宁中医药大学附属医院数据,通过3维重构获得3维肺结节图像。其次使用球谐函数与容斥映射算法在保留空间信息的同时将纹理以网格方式映射到标准球面上。再次使用网格-LBP与映射形变能量分别完成对球面纹理与结节形状信息的构建。最后提出一种基于网格的多粒度扫描方法对深度森林训练框架进行改进,并将向量化后的纹理和形状特征加入到改进的深度森林训练框架中进行实验验证。结果通过大量的实验结果验证,在准确率(ACC)、特异度(SPE)、敏感度(SEN)和受试者工作特征曲线下的面积(AUC)4个衡量指标下,本文方法具有优于现存先进方法的表现,其中ACC、SPE、SEN和AUC分别达到76. 06%、69. 46%、88. 46%和0. 84。结论基于球谐函数与容斥映射算法可成功地对肺结节表面和形状两个特征进行向量化并训练,不仅考虑了数据预处理,而且通过两个特征对肺结节良恶性检测的准确率要高于传统1个特征检测的结果,同时也为3维模型中特征的提取及向量化提供了一个有效的方法。Objective In this paper,the spherical surface texture and nodule shape are vectorized through spherical harmonics and repulsive mapping algorithm for the benign and malignant determination of pulmonary nodule in chest CT( computed tomography) images. The current methods of deep learning during benign and malignant screening of pulmonary nodules neglect data-preprocessing while focusing more on framework improvement. So far,the depth-learning method is mainly oriented to feature information,which can be vectored. In image-processing,two kinds of targets are mainly included in twoand three-dimensional processing. In two-dimensional processing,the existence of input data must be an equal-length problem. Considering that the obtained size of the pulmonary nodules is different,we must compress large-scale images in the input process and stretch the small-scale images,which will undoubtedly affect the quality of feature extraction and the final classification results. In the classification of CT nodules for the three-dimensional treatment of pulmonary nodules,the CT image angle is more stringent due to the different sizes of pulmonary nodules and the uncertainty of growth position,and the angle factors are uncontrollable during actual CT shooting. Hence,if we insist on the characteristics of the convolution channel,it is necessary to give priority to the solution. So we have to standardize different pulmonary nodules. Different from traditional pulmonary nodule classification method,the proposed method aims on how to vectorize the spherical texture and nodule shape to allow input of data to the depth forest for feature classification training. Method First,the threedimensional pulmonary nodule images are produced by three-dimensional reconstruction of the data from the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine. The data is divided into training and test set at 8 ∶ 2 ratio.Second,the spherical harmonic function and the repulsive mapping algorithm are used to map the texture to the stan

关 键 词：球谐函数 容斥映射算法 向量化表达 网格-LBP 形变能量 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]