摘要
目的探讨采用CT平扫图像纹理分析的方法对肝癌和肝血管瘤进行鉴别诊断的可行性。方法回顾性纳入2014年1月至2014年9月期间在四川大学华西医院行CT平扫检查且经病理检查结果证实为肝癌和肝血管瘤患者共56例,男35例,女21例;年龄(52.4±12.079)岁。排除图像有伪影干扰和病灶直径小于1.0 cm的患者4例,剩余52例患者共57个病灶(肝癌25个、肝血管瘤32个)的CT平扫图像用于纹理分析,从灰度直方图、共生矩阵、绝对梯度、自回归模型及小波变换中提取纹理特征值,再利用费希尔参数法(Fisher)、最小分类误差与最小平均相关系数法(POE+ACC)及相关信息测度法(MI)分别选择10个最优纹理特征值,然后用Mazda中的B11模块提供的线性判别分析法(LDA)和非线性判别分析法(NDA)对纹理特征进行分析,计算出其识别肝癌和肝血管瘤的最小错误率。LDA的最大分类特征应用于K邻近分类(KNN),NDA提取出的数据用于神经网络(ANN)进行鉴别诊断。结果 NDA/ANN-POE+ACC法鉴别肝癌和肝血管瘤最好,最小错误率最低,该方法分别与LDA/KNN-Fisher、LDA/KNN-POE+ACC、LDA/KNN-MI、NDA/ANN-Fisher及NDA/ANN-MI法对比分析,差异均有统计学意义(χ~2值分别为4.56、4.26、3.14、3.14、3.33,P值分别为0.020、0.018、0.026、0.026、0.022)。结论 Mazda纹理分析软件的不同纹理特征选择方法以及不同分析方法对CT平扫图像中肝癌和肝血管瘤鉴别的最小错误概率均较低,其中NDA/ANN-POE+ACC法鉴别效果最好。因此,利用CT平扫图像纹理分析的方法对肝癌和肝血管瘤进行鉴别诊断是可行的。
Objective To determine feasibility of texture analysis of non-enhanced CT scan for differential diagnosis of liver cancer and hepatic hemangioma. Methods Fifty-six patients with liver cancer or hepatic hemangioma confirmed by pathology were enrolled in this retrospective study. After exclusion of images of 4 patients with artifacts and lesion diameter less than 1.0 cm, images of 52 patients （57 lesions） were available to further analyze. Texture features derived from the gray-level histogram, co-occurrence and run-length matrix, absolute gradient, autoregressive model, and wavelet transform were calculated. Fisher, probability of classification error and average correlation （POE＋ACC）, and mutual information coefficients （MI） were used to extract 10 optimized texture features. The texture characteristics were analyzed by using linear discriminant analysis （LDA） and nonlinear discriminant analysis （NDA） provided by B 11 module in the Mazda software, the minimum error probability of differential diagnosis of liver cancer and hepatic hemangioma was calculated. Most discriminating features （MDF） of LDA was applied to K nearest neighbor classification （KNN）; NDA to extract the data used in artificial neural network （ANN） for differential diagnosis. Results The NDA/ANN-POE＋ACC was the best for identifying liver cancer and hepatic hemangioma, and the minimum error probability was the lowest as compared with the LDA/KNN-Fisher, LDA/KNN-POE＋ACC, LDA/KNN-MI, NDA/ANN-Fisher, and NDA/ANN-MI respectively, the differences were statistically significant （X^2=4.56, 4.26, 3.14, 3.14, 3.33; P=0.020, 0.018, 0.026, 0.026, 0.022）. Conclusions The minimum error probability is low for different texture feature selection methods and different analysis methods of Mazda texture analysis software in identifying liver cancer and hepatic hemangioma, and NDA/ANN- POE＋ACC method is best. So it is feasible to use texture analysis of non-enhanced CT images to identify liver cancer and hepatic hemangioma.
出处
《中国普外基础与临床杂志》
CAS
2017年第2期254-258,共5页
Chinese Journal of Bases and Clinics In General Surgery
关键词
CT平扫
肝癌
肝血管瘤
纹理分析
图像处理
CT
liver cancer
hepatic hemangioma
texture analysis
image processing
