Characterization of Hepatocellular Carcinoma (HCC) in CT Images using Texture Analysis Technique

A new approach to texture characterization from dynamic CT scans of the liver is presented. This study was aimed to use the texture analysis and classification methods to characterize the hepatocellular carcinoma (HCC), liver and other abdominal regions in CT images using image processing program (IDL, interactive data language). Tri-phasic Multi detectors CT with contrast enhanced images of 200 adult subjects with hepatocellular carcinoma were used as entry data. Tiff format was created as IDL variables and then using 3x3 window the image was scanned and based on the image histogram the selected feature also called FOS was calculated using this window. Linear discriminant analysis was used for the tissue classification. The study found that the HCC texture reveal a different underlying pattern compared to the liver and other abdominal tissues with classification sensitivity and specificity 96.5 % and 86.6 % respectively, and the combination of the texture features throughout the different tri-phasic image phases provide the highest predictive overall accuracy of 89.1 % using linear discriminant analysis.