Automatic Segmentation of Hepatic Vessels in Abdominal MDCT Image

Hepatic vessel trees are the key structures for hepatic disease diagnosis and liver surgery planning. They are especially useful in estimating the volumes of the left and right hepatic lobes, integral for maximizing the safety of the donor and the recipient during a living donors liver transplantation (LDLT). In this paper, we propose the following steps for the automated segmentation of hepatic vessel trees in contrast abdominal MDCT images: (1) canny edge detection for ascertaining the location of the hepatic vessel, (2) extraction of hepatic vessel candidates by threshold filtering around the detected edge, (3) addition of true negatives, defined as hepatic vessel pixels - except for the extracted vessels, as the brightness of these pixels is less than the threshold, according to the pre and post section connections, and (4) removal of false positives, defined as small connected regions smaller than 9 voxels without connections to pre or post sections. The proposed method correctly segments the hepatic vessel regions.