基于GPU的血管造影图像增强方法

Angiogram images enhancement method based on GPU

血管增强扩散算法遵循多尺度方法,利用非线性各向异性扩散方法进行血管增强,该方法在可视化不同半径的血管和增强血管外观上比现存的大部分方法都要好,但医学图像数据分辨率和灰度级都很高,多尺度选择和求解非线性各向异性扩散的偏微分方程时运算量很大,执行速率低,不适合实际应用。提出一种基于GPU(graphic processing unit)的血管造影图像增强方法,采用计算统一设备架构(CUDA)技术,利用像素的独立性和偏微分方程求解的并发性,实现了并行血管增强扩散算法。实验结果表明,该方法在保持血管增强效果一样的同时降低了处理时间,加速比达到27倍以上。

The vessel enhancing diffusion（VED）algorithm follows a multiscale approach to enhance vessels using a nonlinear anisotropic diffusion scheme.This method performs better than most of the existing techniques in visualizing vessels with varying radii and in enhancing vessel appearance.But typical medical images have high resolution and grayscale,selection of multiscale and computation of nonlinear anisotropic diffusion partial differential equation have a large computational burden,the algorithm has a low execution rate thus is not suitable for its applications in practice.This paper proposed an angiogram images enhancement method based on GPU.By taking use of the independence of image pixel and concurrence of partial differential equation,the vessel enhancing diffusion algorithm was parallel implemented on CUDA.Experimental results show that this method not only maintains the same good performance of vessel enhancement,but also greatly reduces the computing time with the speed ratio of more than twenty seven times.