Automated middle hepatic vessel extraction method using electronic atlas and line enhancement filter on non-contrast torso X-ray CT images

Abstract

Classification of the liver region of the Couinaud segment provides significant information for a computer-aided diagnostic system to localize the position of lesions in the liver region. Hepatic vessels provide essential information to classify the liver region of the Couinaud segment. However, automated segmentation and classification of hepatic vessels are difficult in non-contrast CT images owing to the low contrast between hepatic vessels and liver tissue. In this paper, we propose an automated extraction schema for extracting the middle hepatic vein (MHV), and we employ this schema to classify the liver region into right and left lobes. We applied our method to 22 non-contrast X-ray CT images. All of the cases were normal liver cases. The results for the MHV extraction were evaluated using three parameters for the volume ratio to the correct region of liver. The results show that hepatic vessels extracted using the proposed method were found to be satisfactory in 41% (9/22) of cases.