Adaptive Liver Segmentation from Multi-slice CT Scans

摘要：

In this paper,an adaptive method was proposed to segment the liver from computed tomography (CT) images.Four sets of CT images were segmented by a binary classification method,support vector machine (SVM),after supervised thresholding and K means clustering.A leave-one-out method was applied to compare with the adaptive method.The result shows that the adaptive method can more accurately identify the class of the pixel with evidently lower false negative volume fraction than that of the leave-one-out method.

关键词： Adaptive method Segmentation Texture analysis Thresholding Support Vector Machine

作者: J.Liu Q.Hu Z.Chen P.Heng

作者单位: Shenzhen Institute of Advanced Technology,Shenzhen,China

会议类型: 国际会议

会议名称: 7th Asian-Pacific Conference on Medical and Biological Engineering(第七届亚太地区生物工程学术会议)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-04-22（万方平台首次上网日期，不代表论文的发表时间）