上海交通大学学报(自然版)

• 自动化技术、计算机技术 • 上一篇    下一篇

基于光流和多层次B样条自由变形的医学图像鲁棒形变配准

王敏尤,胡海波,秦斌杰   

  1. (上海交通大学 生命科学技术学院,上海 200240)
  • 收稿日期:2007-11-01 修回日期:1900-01-01 出版日期:2008-10-28 发布日期:2008-10-28
  • 通讯作者: 秦斌杰

Robust Deformable Medical Image Registration Using Optical Flow and Multilevel Free Form Deformation

WANG Min-you, HU Hai-bo, QIN Bin-jie   

  1. (School of Life Science and Biotechnology, Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2007-11-01 Revised:1900-01-01 Online:2008-10-28 Published:2008-10-28
  • Contact: QIN Bin-jie

摘要: 为了跟踪肿瘤病灶对周围正常组织挤压变形,以及脑部手术软组织变形对手术的影响,提出了光流估计框架下的多层次B样条自由变形鲁棒形变配准方法.利用光流法约束下的多层次B样条自由变形,通过加密局部控制点以加强局部形变,能有效建模肿瘤信号及异常变形区域的局部较大形变.通过引入鲁棒估计,给予异常信号(病灶、灰度突变或形变不连续区域)以较小的权值,可减小图像灰度差异、局部不连续形变场所造成异常信号对形变配准优化的不利影响.采用了LBFGS方法,可减少内存开销,提高优化速度.实验表明:形变配准算法得到了较好的效果,可较好建模术前和术中脑部医学图像的形变,本配准算法可用于指导图像导向手术.

关键词: 异常信号, 形变配准, 光流法, 自由形变模型, 鲁棒估计

Abstract: In order to track the brain tissue shift due to tumor resection during image guided surgery, this paper presented a framework for robust deformable registration based on the theory of optical flow, within which outlier detection is used to set up locallyrefined control points in multilevel free form deformation (FFD) model. Robust Mestimator was also introduced to weaken the effect of outliers in global optimization for getting improved registration result. This proposed method has successfully been applied to a number of registration tasks to demonstrate its applicability and robustness to outliers.

中图分类号: