基于光流场模型的医学图像弹性配准  

Elastic registration of medical images based on optical flow field model

作　　者：杨敏[1] 唐思源[1] 白金牛[1] YANG Min;TANG Siyuan;BAI Jinniu(Baotou Medical College,Inner Mongolia University of Science&Technology,Baotou Inner Mongolia 014040,China)

机构地区：[1]内蒙古科技大学包头医学院,内蒙古包头014040

出　　处：《激光杂志》2020年第7期104-108,共5页Laser Journal

基　　金：内蒙古自治区科学基金项目(No.2016MS0601);内蒙古自治区高等学校科学研究项目(No.NJZY17266);内蒙古自治区高等学校科学研究项目(No.NJZY17266);包头医学院科学研究基金项目(No.BYJJ-QM201777);包头市医药卫生科技计划项目(No.Wsjj2019040)。

摘　　要：针对传统医学图像弹性配准方法中存在配准不连续、配准过程复杂,且配准用时较长等问题,提出基于光流场模型的医学图像弹性配准方法。首先通过加权矩阵控制对医学图像梯度进行平滑处理,构建光流场模型;采用该模型确定医学图像目标的具体运动情况;然后计算图像序列中不同像素点光流场,设置医学图像光流场的初始条件和边界条件;最后对医学图像进行几何变化,获取医学图像的目标函数,完成基于光流场模型的医学图像弹性配准。实验结果表明:采用本文方法对医学图像进行弹性配准的效果较为理想,获取的医学图像较为清晰,且配准的工作效率较高。In order to solve the problems of discontinuous registration,complex registration process and long registration time in traditional medical image elastic registration method,an elastic registration method based on optical flow field model is proposed.Firstly,the gradient of medical image is smoothed by weighted matrix control,and the optical flow field model is constructed.The specific movement of medical image target is determined by the model.Then the optical flow field of different pixels in image sequence is calculated,and the initial and the boundary conditions of medical image optical flow field are set.Finally,the geometric changes of medical image are carried out to obtain objective function of medical image.The medical image elastic registration based on optical flow field model is completed.The experimental results show that the effect of elastic registration is ideal,the medical image obtained is clear,and the efficiency of registration is high.

关 键 词：光流场模型 医学图像 弹性配准 几何变化 目标函数 

分 类 号：TN248.1[电子电信—物理电子学]