A method for the segmentation of an object of interest in an image of a patient with such an object is described. Each of a plurality of training forms is deformed, in order to superimpose a reference shape, wherein a parameter θi a measure for the thickness of the deformation is, which is necessary in order to effect the superposition. A vector of the parameters θi for each of the training forms by minimizing a cost function together with an estimate of the degree of uncertainty for each of the resulting vectors of parameters θi is obtained, whereby such an uncertainty in the form of a covariance matrix σi is quantified. A statistical model the form of a is shown, with the sum of cores, with a means θi and covariance σi generates. The desired object of interest in the image of the patient is identified, in that the reference shape on the image is arranged and deformed, in order to superimpose the image obtained, wherein a parameter θ is a measure for the thickness of the deformation is, which is necessary in order to effect the superposition. An uncertainty in the form of a covariance matrix σ is quantified and an energy function e = eshape + Eimage is calculated, the probability of the current form in the statistical model and the fitting into the image eimage to obtain.
展开▼
机译:描述了一种用于用这种对象分割患者的图像中的关注对象的方法。为了叠加参考形状而使多个训练形式中的每一个变形,其中,为了实现叠加所必需的参数θ i Sub>是变形厚度的量度。每个训练形式的参数θ i Sub>的向量,通过最小化成本函数以及对每个所得参数θ i Sub的向量的不确定度的估计来最小化,从而以协方差矩阵σ i Sub>的形式对这种不确定性进行了量化。显示了a形式的统计模型,其中包含核的总和,并且均值θ i Sub>和协方差σ i Sub>生成。通过将图像上的参考形状进行排列和变形,以便叠加所获得的图像,来识别患者图像中的所需感兴趣对象,其中参数θ是变形厚度的度量,为了实现叠加,这是必需的。量化协方差矩阵σ形式的不确定性,并计算能量函数e = e shape Sub> + E image Sub>,在统计模型中当前形式的概率并拟合到图像e image Sub>中以获得。
展开▼