感兴趣区域在临床医学图像分析中占有重要地位.提出了一种基于单调推进曲线进化的感兴趣区域提取新方法.首先,通过极小化ROI(region of interest)能量函数,推导出区域速度函数项,并与基于边界的速度函数融合,提出融合ROI信息的单调推进S...感兴趣区域在临床医学图像分析中占有重要地位.提出了一种基于单调推进曲线进化的感兴趣区域提取新方法.首先,通过极小化ROI(region of interest)能量函数,推导出区域速度函数项,并与基于边界的速度函数融合,提出融合ROI信息的单调推进Snake模型.ROI信息能够增强曲线深入到对比度低且细窄的区域中的传播能力.其次,提出了多初始化快速推进算法,选择性地种植种子曲线有助于局部区域的生长从而进一步改善分割结果.此外,为提高计算效率,在多尺度空间进行数值求解,其中利用快速解传递方法实现粗一级尺度到细一级尺度解的传递,可以加速收敛.利用医学图像分割实验对该方法进行评估,结果表明:该方法能够快速、精确地提取低对比度和细窄的ROI区域.与现有方法相比,该方法的高效性同时体现在分割结果和计算代价上.展开更多
Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are ...Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are most important in performing diagnosis and planning the follow-up therapies. In this paper, we propose an efficient approach to pulmonary vessels extraction based on the curve evolution. This approach models the vessels as monotonically marching front under the speed field integrating both the region and the edge information where a new region speed function is designed and integrated with the edge based speed function. Due to the region based speed term, the front could even propagate in small narrow vessel branches. To further improve the segmentation results, a multi-initial fast marching algorithm is developed to fast implement the numerical solution, which may avoid the monotonically marching front leaking out of the weak boundary too earlier and also reduce the computational cost. The validity of our approach is demonstrated by CT pulmonary vessels extraction. Experiments show that the segmentation results by our approach, especially on the narrow thin vessel branches extraction, are more precise than that of the existing method.展开更多
文摘感兴趣区域在临床医学图像分析中占有重要地位.提出了一种基于单调推进曲线进化的感兴趣区域提取新方法.首先,通过极小化ROI(region of interest)能量函数,推导出区域速度函数项,并与基于边界的速度函数融合,提出融合ROI信息的单调推进Snake模型.ROI信息能够增强曲线深入到对比度低且细窄的区域中的传播能力.其次,提出了多初始化快速推进算法,选择性地种植种子曲线有助于局部区域的生长从而进一步改善分割结果.此外,为提高计算效率,在多尺度空间进行数值求解,其中利用快速解传递方法实现粗一级尺度到细一级尺度解的传递,可以加速收敛.利用医学图像分割实验对该方法进行评估,结果表明:该方法能够快速、精确地提取低对比度和细窄的ROI区域.与现有方法相比,该方法的高效性同时体现在分割结果和计算代价上.
基金Supported by the national Natural Science Foundation of China under Grant No.6 0 2 710 2 2 and the Creative Research Group Science Foundation of China under Grant No.6 0 0 2 4 30 1
文摘Pulmonary vessels extraction is a challenging task in clinical medicine. Many pulmonary diseases are accompanied by the changes of vessel diameters. The vessels and their branches, which exhibit much variability, are most important in performing diagnosis and planning the follow-up therapies. In this paper, we propose an efficient approach to pulmonary vessels extraction based on the curve evolution. This approach models the vessels as monotonically marching front under the speed field integrating both the region and the edge information where a new region speed function is designed and integrated with the edge based speed function. Due to the region based speed term, the front could even propagate in small narrow vessel branches. To further improve the segmentation results, a multi-initial fast marching algorithm is developed to fast implement the numerical solution, which may avoid the monotonically marching front leaking out of the weak boundary too earlier and also reduce the computational cost. The validity of our approach is demonstrated by CT pulmonary vessels extraction. Experiments show that the segmentation results by our approach, especially on the narrow thin vessel branches extraction, are more precise than that of the existing method.
