中文摘要：

提出一种新的基于图割和边缘行进的腹部CT序列图像肝脏分割方法。首先,针对输入序列的数据特征,建立肝脏亮度和外观模型,突出肝脏区域抑制非肝脏区域;然后,将肝脏亮度、外观模型以及相邻切片之间的位置信息有效融入图割能量函数,实现CT序列肝脏的自动初步分割;最后,针对血管欠分割问题,提出了一种基于边缘行进的结果优化方法。通过对XHCSU14和SLIVER07数据库提供的30个病人肝脏序列的分割实验,以及与其他多种肝脏分割方法的比较,表明该方法能完整有效地分割肝脏,准确性高,鲁棒性强。

英文摘要：

A novel method for liver segmentation from abdominal CT volumes based on graph cuts and border marching is proposed. First, to exclude complex background and highlight liver region, liver intensity and appearance models are built according to the characteristics of a given CT volume. Then, the intensity and appearance models together with location information from neighbor segmented slice are effectively integrated into graph cuts cost computation to segment the CT volume initially and automatically. Finally, to solve the under-segmentation issue of liver vessel, a boundary compensation method based on border marching is proposed. The proposed method is tested and compared with some other methods on 30 CT volumes from XHCSU14 and SLIVER07 databases. The experimental results show that the proposed method can segment livers integrally and effectively from abdominal CT volumes, with higher accuracy and robustness.