分维和孔隙度在肝癌超声纹理识别中协同作用-计算机工程与应用.PDF

Computer Engineering and Applications 计算机工程与应用 2013 ，49 （2 ） 211 分维和孔隙度在肝癌超声纹理识别中协同作用 1，2 3 季桂树 ，禹智夫 JI Guishu1，2 , YU Zhifu3 1.中南大学 地球科学与信息物理学院，长沙 410083 2.中南大学 信息科学与工程学院，长沙 410083 3.长沙市第八医院 超声科，长沙 410100 1.School of Geosciences and Info-physics, Central South University, Changsha 410083, China 2.School of Information Science and Engineering, Central South University, Changsha 410083, China 3.Ultrasound Department, Changsha City Eighth Hospital, Changsha 410100, China JI Guishu, YU Zhifu. Synergy between fractal dimension and lacunarity discriminating liver cancer form normal liver from ultrasonic images. Computer Engineering and Applications, 2013, 49 （2 ）：211-218. Abstract ：The performance of describing ultrasonic liver cancer image texture feature with fractal and lacunarity and their com- bined factors is studied. The fractal dimension and lacunarity values are estimated with 4 fractal dimension and a lacunarity methods based on the samples of 14 ultrasonic images each for normal liver and liver cancer. ROC （Receiver Operating Charac- teristic ）analysis shows that the single factors for FPS and LBCM hold higher AUCs （area under ROC curve ）. The train and test results for the single factors and the combined factors with SVM （Support Vector Machine）exhibit that FPS （Fourier Power Spec- trum ）+ LBCM （Lacunarity of Box Column Mean ）（4 kernals ）and DBC （Differential Box Counting ）+ LBCM （except SIG- MOID ）get higher classification accuracy rate than the single factors. Key words ：ultrasonic liver cancer image; texture analysis; fractal dimension; lacunarity; synergy; Support Vector Machine （SVM ） 摘 要：对分维和孔隙度及其组合因子表征超声肝癌图像纹理特征的性能进行了对比研究。以正常肝和肝癌各14 幅超声 图像为样本，用4 种分维和一种孔隙度方法计算分维和孔隙度值。用ROC 进行评估，单因子的傅里叶功率谱分维和盒柱 平均值孔隙度值有较大的ROC 曲线下面积。用SVM 对单因子和组合因子进行训练和检验表明，傅里叶功率谱分维与盒 柱平均值孔隙度（FPS+LBCM ）（4 个核）和差分盒计数分维与盒柱平均值孔隙度（DBC+LBCM ）（除SIGMOID 外）构成的组 合因子有比单因子较高的分类准