计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (23): 176-182.DOI: 10.3778/j.issn.1002-8331.1708-0317

• 图形图像处理 • 上一篇    下一篇

基于改进的GLCM甲状腺纹理特征提取与分析

汪  娟1, 刘  哲1, 宋余庆1, 陈香远2   

  1. 1.江苏大学 计算机科学与通信工程学院 医学图像处理实验室,江苏 镇江 212013
    2.江苏大学 医学院,江苏 镇江 212013
  • 出版日期:2018-12-01 发布日期:2018-11-30

Extraction and analysis of thyroid texture features based on improved GLCM

WANG Juan1, LIU Zhe1, SONG Yuqing1, CHEN Xiangyuan2   

  1. 1.Medical Image Processing Lab, School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China
    2.School of Medicine,Jiangsu University, Zhenjiang, Jiangsu 212013, China
  • Online:2018-12-01 Published:2018-11-30

摘要: 为了提高病变和正常的甲状腺核磁共振图像(MR)的分类准确率,提出了改进的窗口自适应灰度共生矩阵(Gray Level Co-occurrence Matrix,GLCM)纹理特征提取算法。采用基于统计的纹理特征GLCM算法提取感兴趣区域(ROIs)的纹理特征,由HOG特征启示,研究基于梯度信息的GLCM窗口自适应算法,考虑了梯度信息对GLCM中滑动窗口大小设置的影响,克服了传统方法的固定窗口对图像细节保留的影响,同时为了消除各向异性,取四个方向的共生矩阵的均值作为最终的共生矩阵,最后计算GLCM的相关、能量、对比、逆差矩和熵的均值和方差。对94幅甲状腺图像采用逻辑回归模型分析来预测分类准确度,结果显示,该方法优于其他的方法,对甲状腺图像诊断性能更好,预分类准确率达到96.8%,灵敏度97.90%,特异度95.7%,ROC曲线下面积(Area Under the Curve, AUC)为0.968。实验结果表明改进的GLCM能够有效辅助医生对甲状腺MR图像做出正确诊断。

关键词: 灰度共生矩阵, 甲状腺核磁共振图像, Logistic回归模型, ROC曲线下面积

Abstract: To improve the predictive accuracy of the lesions and the normal areas of the thyroid MR images, an adaptive window sizes approach is proposed based on Gray Level Co-occurrence Matrix(GLCM) texture feature. Firstly, it considers the effect of the gradient information of ROIs on sliding window size set when it computes GLCM and extracts the gradient information of ROIs. Then, it sets different sliding window size on the gradient. Moreover, it obtains the mean of the co-occurrence matrix in four directions in order to eliminate the anisotropy. Finally, it computes the mean and variance of correlation, energy, contrast, homogeneity and entropy in GLCM. In this study, 94 cases of thyroid images are used to predict the classification accuracy by using logistic regression model analysis. The experimental result shows that the improved method outperforms other methods, and has the better diagnostic performance with an accuracy of 96.8%, a sensitivity of 97.9%, a specificity of 95.7% and an AUC of 0.968. The experimental result indicates that the feature extraction method can effectively assist the doctors to make the correct diagnosis of thyroid MR images.

Key words: Gray Level Co-occurrence Matrix(GLCM), thyroid magnetic resonance, logistic regression model, area under ROC curve