Nonparametric intensity priors for level set segmentation of low contrast structures.
Nonparametric intensity priors for level set segmentation of low contrast structures.
复制标题
用于低对比度结构水平集分割的非参数强度先验。
DOI：
10.1007/978-3-642-04268-3_30
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Vass,Melissa
中科院分区：
文献类型：
--
作者：
Makrogiannis,Sokratis;Bhotika,Rahul;Miller,JamesV;SkinnerJr,John;Vass,Melissa
低对比度对象的分割在诸如病变分析和血管壁重构分析的临床应用中是一项重要任务。先前已经提出了利用高级信息的低对比度分割的几种解决方案，例如形状先验和生成模型。在这项工作中，我们将强度和低级别图像信息的priordistributions转换为非参数相异性度量，该度量定义了属于前景对象的可能性的局部指示函数。然后，我们将指标函数集成到一个水平集制定分割低对比度结构。我们将该技术应用于心脏CT血管造影图像中血管壁正性重塑的临床问题。我们目前的结果在25个病人扫描的数据集上，显示了传统的基于梯度的水平集的改进。
Segmentation of low contrast objects is an important task in clinical applications like lesion analysis and vascular wall remodeling analysis. Several solutions to low contrast segmentation that exploit high-level information have been previously proposed, such as shape priors and generative models. In this work, we incorporatea prioridistributions of intensity and low-level image information into a nonparametric dissimilarity measure that defines a local indicator function for the likelihood of belonging to a foreground object. We then integrate the indicator function into a level set formulation for segmenting low contrast structures. We apply the technique to the clinical problem of positive remodeling of the vessel wall in cardiac CT angiography images. We present results on a dataset of twenty five patient scans, showing improvement over conventional gradient-based level sets.