非刚体图像配准的变形场拓扑约束研究.pdfVIP

信号处理 第 29 卷第 10 期 Vol. 29 No. 10 2013 年 10 月 JOURNAL OF SIGNAL PROCESSING Oct. 2013 非刚体图像配准的变形场拓扑约束研究 林相波 (大连理工大学电子信息与电气工程学部，辽宁大连， 11ω24) 摘 要:利用正则化方法约束非线性变形场是非刚体图像配准领域的一个重要研究方向。为得到具有拓扑保持 能力的非线性变形场，本文在分析粘流体配准和扩散模型配准算法的实现原理基础上，提出一种基于弹簧约束 的变形场拓扑保持方法。该方法在可变形图像上附加不规则网格，通过保持网格结点间的连接关系不变达到控 制图像变形的目的。将本文算法应用在不同人脑磁共振图像配准和脑内核结构分割中，结果表明，本文方法具 有保持变形场拓扑不变的能力，且能够给出更为准确的分割结果。 关键词:非刚体图像配准;拓扑保持;弹簧约束 中固分类号: 1刊91 文献标识码:A 文章编号: 1∞3-0530 (2013) 10-13∞-07 Research of Deformation Field Topology Constraint Method in Non-rigid Image Registration LIN Xiang-bo (Faculty of Electronic Information and Electrical Engineeri吨， Dalian University of Technology , Dalian 116024 , China) Abstract: Regularizing nonlinear deformation field is an important aspect in non-rigid medical image registration. By an- alyzing the implementation principles of vicious fluid registration and diffusion registration method , this paper proposed to preserve the topologies of the deformation field using a spring constraints. The template image is covered wi出 a triangular mesh , and the connection relationship between mesh vertices is preserved. The method is evaluated by registering cerebral MRI (m略netic resonance imaging) image data obtained from different individuals and by segmenting internal brain struc- tures. Experimental results show that the proposed method has good deformation abili可 and topology preserving ability. 币le segmentation results 缸它 more accurate. Key words: non-rigid image registration; topology prese凹ation; spring constraints