乳腺癌的发病率在女性癌症中居首位,在计算机辅助下精确地提取出乳腺图像中包含的结构信息和功能信息是当前面临的难题。本研究主要探讨利用水平集分割方法对超声乳腺图像进行肿瘤的自动分割。基本思路:①粗提取肿瘤所在的区域;②采取...乳腺癌的发病率在女性癌症中居首位,在计算机辅助下精确地提取出乳腺图像中包含的结构信息和功能信息是当前面临的难题。本研究主要探讨利用水平集分割方法对超声乳腺图像进行肿瘤的自动分割。基本思路:①粗提取肿瘤所在的区域;②采取改进的各项异性扩散方程(MCDE),在保证乳腺肿瘤边界信息不被削弱的前提下削减超声图像的噪声;③利用图像梯度获取边界的潜在图像;④设置初始轮廓;⑤调整水平集中的速度函数,寻求适用于乳腺超声图像中肿瘤轮廓的提取方法,探索过程涉及两种改进的LevelSet方法:测地活动轮廓(geodesic active contour)和阈值水平集(threshold LevelSet)。结果表明,针对乳腺超声肿瘤的弱边界信息,利用阈值水平集分割可以自动获取与手动勾画较为相似的轮廓。展开更多
Nonparametric method based on the mutual information is an efficient technique for the image segmentation. In this method, the image is divided into the internal and external labeled regions, and the segmentation prob...Nonparametric method based on the mutual information is an efficient technique for the image segmentation. In this method, the image is divided into the internal and external labeled regions, and the segmentation problem constrained by the total length of the region boundaries will be changed into the maximization of the mutual information between the region labels and the image pixel intensities. The maximization problem can be solved by deriving the associated gradient flows and the curve evolutions. One of the advantages for this method does not need to choose the segmentation parameter;another is not sensitive to the noise. By employing the narrowband levelset and Fast Gauss Transformation, the computation time is reduced clearly and the algorithm efficiency is greatly improved.展开更多
SMAC method is adopted to solve Navier-Stokes equations, by using fifth-order WENO scheme and TVD R-K scheme, LevelSet methods are used to capture moving interfaces with improved Ghost techniques. Some examples, e.g. ...SMAC method is adopted to solve Navier-Stokes equations, by using fifth-order WENO scheme and TVD R-K scheme, LevelSet methods are used to capture moving interfaces with improved Ghost techniques. Some examples, e.g. the incompressible inviscid flame interfaces of one and two dimensions and the rising-merging of oil bubbles in water, are computed and the comparison with the result of commercial CFD software Fluent has been done. The rationality of LevelSet methods with Ghost technique in capturing moving interfaces with jump conditions is affirmed. It is shown that Level Set method can capture interfaces sharply without complicated reconstruction and can be easily programmed.展开更多
文摘乳腺癌的发病率在女性癌症中居首位,在计算机辅助下精确地提取出乳腺图像中包含的结构信息和功能信息是当前面临的难题。本研究主要探讨利用水平集分割方法对超声乳腺图像进行肿瘤的自动分割。基本思路:①粗提取肿瘤所在的区域;②采取改进的各项异性扩散方程(MCDE),在保证乳腺肿瘤边界信息不被削弱的前提下削减超声图像的噪声;③利用图像梯度获取边界的潜在图像;④设置初始轮廓;⑤调整水平集中的速度函数,寻求适用于乳腺超声图像中肿瘤轮廓的提取方法,探索过程涉及两种改进的LevelSet方法:测地活动轮廓(geodesic active contour)和阈值水平集(threshold LevelSet)。结果表明,针对乳腺超声肿瘤的弱边界信息,利用阈值水平集分割可以自动获取与手动勾画较为相似的轮廓。
文摘Nonparametric method based on the mutual information is an efficient technique for the image segmentation. In this method, the image is divided into the internal and external labeled regions, and the segmentation problem constrained by the total length of the region boundaries will be changed into the maximization of the mutual information between the region labels and the image pixel intensities. The maximization problem can be solved by deriving the associated gradient flows and the curve evolutions. One of the advantages for this method does not need to choose the segmentation parameter;another is not sensitive to the noise. By employing the narrowband levelset and Fast Gauss Transformation, the computation time is reduced clearly and the algorithm efficiency is greatly improved.
基金The authors wish to express their gratitude to CAS&973 Project for sponsoring the research,Proj No:KZCX2-YW-302National Natural Science Foundation of China,Proj No:40501017
文摘SMAC method is adopted to solve Navier-Stokes equations, by using fifth-order WENO scheme and TVD R-K scheme, LevelSet methods are used to capture moving interfaces with improved Ghost techniques. Some examples, e.g. the incompressible inviscid flame interfaces of one and two dimensions and the rising-merging of oil bubbles in water, are computed and the comparison with the result of commercial CFD software Fluent has been done. The rationality of LevelSet methods with Ghost technique in capturing moving interfaces with jump conditions is affirmed. It is shown that Level Set method can capture interfaces sharply without complicated reconstruction and can be easily programmed.
