ATLAS CONSTRUCTION FROM HIGH ANGULAR RESOLUTION DIFFUSION IMAGING DATA REPRESENTED BY GAUSSIAN MIXTURE FIELDS.
ATLAS CONSTRUCTION FROM HIGH ANGULAR RESOLUTION DIFFUSION IMAGING DATA REPRESENTED BY GAUSSIAN MIXTURE FIELDS.
复制标题
根据高斯混合场表示的高分辨率扩散成像数据构建图集。
DOI：
10.1109/isbi.2011.5872466
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Forder,JohnR
中科院分区：
文献类型：
--
作者：
Cheng,Guang;Vemuri,BabaC;Hwang,Min-Sig;Howland,Dena;Forder,JohnR
图像配准是医学图像图谱构建的重要组成部分，而图谱构建是医学图像分析中一项非常重要且具有挑战性的任务。在本文中，我们提出了一种新的图集建设技术，使用groupwise注册的高角分辨率扩散（MR）成像数据集，其中每一个是由高斯混合场。为了解决配准问题，使用L2距离来度量两个高斯混合体之间的相似性，这导致能量函数，其梯度可以以封闭形式计算。一个投影方法的开发，以构建一个“尖锐”（不模糊）的图集，从这个groupwise注册的结果。合成和真实的数据实验证明了所提出的方法的有效性。
Groupwise image registration is an essential part of atlas construction which is a very import and challenging task in medical image analysis. In this paper, we present a novel atlas construction technique using a groupwise registration of high angular resolution diffusion (MR) imaging datasets each of which is represented by a Gaussian Mixture field. To solve the registration problem, an L2distance is used to measure the similarity between two Gaussian Mixtures, which leads to an energy function whosegradient can be computed in closed form. A projection method is developed to construct a “sharp” (not blurred) atlas from the result of this groupwise registration. Synthetic and real data experiments are presented to demonstrate the efficacy of the proposed method.