期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2014
卷号：11
期号：6
页码：239-244
DOI：10.14445/22312803/IJCTT-V11P151
出版社：Seventh Sense Research Group
摘要：Comparative analysis of nine textural feature measures derived from graylevel cooccurrence matrix obtained from the region(s) of interest (ROI) among the normal and abnormal anatomical structures that appear in the patient’s ultrasound liver images is presented in this paper. Selection of the most robust discriminating features for classification experiment is performed through analysis of each feature classes’ separability power. The results analysis shows that cluster prominence, cluster shade, maximum probability, and entropy have high classes’ separability power and were selected for the classification of liver ultrasound images into normal liver (NL), primary liver cell carcinoma (PLCC) and hepatocellular carcinoma (HCC) at 0.4, 0.4, 0.2 and 0.6 sensitivity respectively.
