Automated Determination of the Liver Boundary in CT Data Based on Anatomical Knowledge and Level Set Method

概要

論文の詳細を見る
Automatic determination of the liver boundary in CT images is difficult due to similar intensity of liver with respect to its surrounding tissues, poor in-plane and inter-plane resolutions, and partial volume effect. Assumptions made in previous liver segmentation algorithms cannot be used to all cases since liver shape and location varies much in abdomen. In this article, we first estimate an initial mask to find intensity of liver accurately. We then convert gray-scale CT images to colored images so that separate liver tissues in lower slices can be seen well. The borders of these estimated tissues are used as the initial border of liver and tuned by active contour method. We extract the required parameters of each dataset from itself. Results are in agreement with the proposed method.
社団法人電子情報通信学会の論文
2007-01-20