paper

重尾分布

1. Three-dimensional coupled-object segmentation using symmetry  and tissue type information
Payam B. Bijari a,b, Alireza Akhondi-Asla,b, Hamid Soltanian-Zadeha,

fuzzy c-means clustering. eliminates the need for statistical shape models of the structures,

 

2. Image  segmentation   methods    for    intracranial  aneurysm  haemo-dynamic research   

 Patient-specific haemo dynamic  technology 

 In this study,we   compared   three  segmentation methods  to   segment  the  geometry of  the  aneurysm.

These include:theRegionGrowing  Threshold (RGT),Chan-Vesemodel(CV)andThreshold-BasedLevelSet(TLS).The  results  obtained  were
evaluated  via  measurement of  arterial  volume  differences(VD),local geometric  shapes,and  haemod-ynamic simulation results

 From this,we discovered that the average VD of all three segmentation methods lay in the vicinity of 9.3%(SD¼74.6%).The  computational haemodynamic  simulation was performed via the use of the vessel geometries.Analyses  produced an average of 23.2%
(SD¼78.7%) difference in energy loss(EL) between the varying segmentation methods,with the
difference in Wall Shear Stress (WSS) averaging 24.0%(SD¼78.5%) and 126.4%(SD¼7124.4%)for
the highest and lowest volumes of WSS respectively.TheresultsofthelowestWSS,was seen to be
significantly dependent upon the geometry ofthe aneurysm surface.It is therefore essential,inorder to
confirm the quality of segmentation processes in the application of patient-specific analyses of
cerebro vascular haemodynamics – to validate these individual segmentation methods.

 结果表明，具有最低WSS的血流明显依赖于动脉瘤的几何形状，因此，为了确认分割效果， 针对具体病人的   颅内血管分析 来分别验证分割方法是很必要的。

http://www.cprogramming.com/tutorial/

 

3.   最大类间方差法(otsu)的原理    图像预处理      频域处理 

转载于:https://www.cnblogs.com/iamgoodman/p/3569424.html