Diagnostic analysis of liver B ultrasonic texture features based on LM neural network
Qingyun Chi, Hua Hu, Menglin Liu, Xiuying Jiang · AIP conference proceedings · 2017
In this study, B ultrasound images of 124 benign and malignant patients were randomly selected as the study objects. The B ultrasound images of the liver were treated by enhanced de-noising. By constructing the gray level co-occurrence matrix which reflects the information of each angle, Principal Component Analysis of 22 texture features were extracted and combined with LM neural network for diagnosis and classification. Experimental results show that this method is a rapid and effective diagnostic method for liver imaging, which provides a quantitative basis for clinical diagnosis of liver diseases.