摘要
目的为了提高放射治疗中对运动器官照射的准确性,改善放疗中剂量分布的效果,开发了一种鲁棒的基于控制体的图像配准算法。方法算法将控制体的自动匹配和薄板样条结合起来,提高了弹性配准的准确性。还研究出了控制体的双向匹配方法,进一步提高算法的精度。结果采用临床图像对两步法进行了验证,即使在大变形的情况下也是有效的,说明算法是鲁棒和通用的。结论所提出的算法提供了比手动选取标志点以及单步配准算法更方便、更鲁棒的解决方案,它将有助于实现放疗中自动配准的目标。
Objective To increase the accuracy of beam targeting and improve the dose distributions in radiotherapy using a robust image registration algorithm based on control volumes.Methods Control volume mapping and thin-plate spline deformable transformation were combined.The use of the control volumes increased the accuracy for the deformable registration.A bi-directional mapping method was also employed to correctly match the control volumes.Results The clinical images were simulated using the proposed two-step image registration algorithm.The simulation results indicated that the registration algorithm was robust and universal,even in cases of obvious deformation.Conclusions The algorithm provides a more convenient and robust resolution as compared to manual landmark-based methods and single-step deformable transformations,and may help in automatic image registration in radiation therapy.
出处
《南方医科大学学报》
CAS
CSCD
北大核心
2011年第11期1801-1805,共5页
Journal of Southern Medical University
基金
Supported in part by grants from NSFC Joint Research Fund for Overseas,Hong Kong and Macao Young Scholars(30928030)
National Basic Research 973 Program(2010CB732606)
a joint grant from Guangdong Province and State Ministry of Education(2010A090200003)~~
关键词
图像配准
控制体
特征提取
自动匹配
薄板样条
image registration
control volume
feature extraction
auto-mapping
thin-plate spline
