Towards Developing a Liver Segmentation Method for Hepatocellular Carcinoma Treatment Planning

The delineation of liver difficult due to its similar intensity distributions in CT images. Additionally, there have been other challenges such that the variability in shape, size, and proximity to the other neighboring organs. The blurred liver edges and low contrast on the CT image make the segmentation further challenging. Furthermore, the patient movement during CT data acquisition along with spatial averaging lead to reconstruction artifacts; these are all reflected on the CT image complicating the segmentation task. In this paper, we have proposed a UNet-based automatic liver segmentation approach to delineate the boundaries between the liver and other abdominal organs. The algorithm is tested on publicly available datasets. The average values of Dice similarity coefficient (DC), Relative absolute volume difference (RAVD), Average symmetric surface distance (ASSD), Maximum symmetric surface distance (MSSD), Hausdorff distance (HD), and Precision are found to be 0.95±0.02, 0.04±0.02, 1.03±0.39, 1.15±0.5, 2.85±1.89, and 0.91±0.12, respectively.