Viscous Fluid Model-based Non-rigid Registration Incorporating Scale Space Keypoints

摘要：

Non-rigid registration of monomodal image oftentakes an important role in image-guided radiotherapyand surgery.Viscous fluid model is widely used toenforce the topological properties on the deformation,and thus constrain the enormous solution space.lntensity-based method is popular in non-rigidregistration,but it is sensitive to intensity variations.In this paper,we develop a new algorithm integratingthe intensity and feature of images.The local keypointinformation extracted by scale invariant featuretransform(SIFT)in scale space is incorporated intointensity similarity measures as the body force ofviscous fluid model in a Bayesian framework.Experiments were performed on synthetic and clinicalimages of CT and MR.It is shown that the keypointinformation significantly improves fluid model for non-rigid registration in accuracy.

作者: Xuesong Lu Su Zhang Wei Yang Yazhu Chen

作者单位: Dept.of Biomedical Engineering,Shanghai Jiao Tong Univ.,Shanghai,China,200240

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 1111-1116

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）