Automated liver segmentation for whole-body low-contrast CT images from PET-CT scanners.

Accurate objective automated liver segmentation in PET-CT studies is important to improve the identification and localization of hepatic tumor. However, this segmentation is an extremely challenging task from the low-contrast CT images captured from PET-CT scanners because of the intensity similarity between liver and adjacent loops of bowel, stomach and muscle. In this paper, we propose a novel automated three-stage liver segmentation technique for PET-CT whole body studies, where: 1) the starting liver slice is automatically localized based on the liver - lung relations; 2) the "masking" slice containing the biggest liver section is localized using the ratio of liver ROI size to the right half of abdomen ROI size; 3) the liver segmented from the "masking" slice forms the initial estimation or mask for the automated liver segmentation. Our experimental results from clinical PET-CT studies show that this method can automatically segment the liver for a range of different patients, with consistent objective selection criteria and reproducible accurate results.