Building the imagistic textural model of the liver pathological stages for the early detection of hepatocellular carcinoma based on ultrasound images

Delia MITREA, Sergiu NEDEVSCHI, Monica LUPSOR, Radu BADEA 1 Technical University of Cluj-Napoca, Computer-Science Department, Baritiu str, no. 26-28, Cluj-Napoca ROMANIA, 2 3 rd Medical Clinic, University of Medicine and Pharmacy, Department of Ultrasonography, Croitorilor str, no 19-21, Cluj-Napoca, ROMANIA [email protected], http://www.utcluj.ro Abstract: The purpose of this study is to find the relevant features in order to detect the forerunner and early stages of the hepatocellular carcinoma (HCC); thus, we aim to characterize the evolution of the liver diseases towards hepatocellular carcinoma (HCC), by detecting the relevant textural features obtained from ultrasound images, which accurately surprise the changes of the liver tissue in the context of this evolution. For the computation of the textural features the following methods are chosen in order to emphasize the chaotic nature of the malignant tumor: first and second order statistics, edge-based statistics, fractal-based methods and multiresolution methods; specific methods for feature-selection are applied in order to determine the exhaustive set of independent and relevant features for each evolution phase. We focus on modeling the cirrhosis and hepatocellular carcinoma, but the differentiation of HCC and normal state is also taken into consideration. The final purpose is that of providing a reliable method for non-invasive characterization of the evolution towards HCC, in order to prevent this malignant tumor.