| 基于CUDA的2D、3D刚性配准方法 |
| |
| 引用本文： | 徐建,秦安,孟晓林,陈武凡,冯前进.基于CUDA的2D、3D刚性配准方法[J].中国医学物理学杂志,2010,27(2):1721-1725,1730. |
| |
| 作者姓名： | 徐建 秦安 孟晓林 陈武凡 冯前进 |
| |
| 作者单位： | 南方医科大学生物医学工程学院,广东,广州,510515 |
| |
| 摘 要： | 目的:实时医学图像配准技术是外科手术导航系统的关键技术之一。在医学图像分析中,图像配准通常是一个非常耗时的操作,不利于临床实时性需求,本文研究实现了图像配准过程的加速。方法:为了提高配准速度,本文提出了一种基于CUDA(compute unified device architecture)编程模型的硬件加速配准新技术,采用并行的方法实现像素的坐标变换,线性插值,同时计算对应像素的灰度值残差。结果:配准误差为亚像素级别,配准速度要比基于CPU的配准快几十甚至上百倍。结论:该方法在保持配准精度不变的前提下,大大提高了刚性配准的速度。
|
| 关 键 词： | 医学图像配准 GPU（图形处理器） CUDA（统一计算设备架构） |
2D,3D Rigid Registration Algorithm Base on CUDA |
| |
| XU Jian,QIN An,MENG Xiao-lin,CHEN Wu-fan,FENG Qian-jin.2D,3D Rigid Registration Algorithm Base on CUDA[J].Chinese Journal of Medical Physics,2010,27(2):1721-1725,1730. |
| |
| Authors: | XU Jian QIN An MENG Xiao-lin CHEN Wu-fan FENG Qian-jin |
| |
| Institution: | XU Jian,QIN An,MENG Xiao-lin,CHEN Wu-fan,FENG Qian-jin(The Department of Biomedical Engineering,Southern Medical University,Guangzhou Guangdong 510515,China) |
| |
| Abstract: | Objective:Real time medical image registration technique is one of the key techniques in image based surgery navigation system. While in medical image analysis,image registration is usually a very time-consuming operation,and this is not conducive to clinical real-time requirements. This paper studies and realizes the acceleration of the process of image registration. Methods:In order to improve the registration rate,in this paper,we propose a new technology which is based on CUDA(Compute Unified Device Arc... |
| |
| Keywords: | medical image registration GPU (graphic processing unit) CUDA (compute unified device architecture) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
