Method for Segmenting Digital Medical Image

专利名称：Method for Segmenting Digital Medical

Image

发明人：Marek Suliga,Piet Dewaele,Rudi

Deklerck,Edgard Nyssen,Gert Behiels

申请号：US11923201申请日：20071024

公开号：US20080101678A1公开日：20080501

专利附图：

摘要：A Markov Random Field (MRF)-based technique is described for performingclustering of images characterized by poor or limited data. The proposed method is a

statistical classification model that labels the image pixels based on the description oftheir statistical and contextual information. Apart from evaluating the pixel statistics thatoriginate from the definition of the K-means clustering scheme, the model expands theanalysis by the description of the spatial dependence between pixels and their labels(context), hence leading to the reduction of the inhomogeneity of the segmentationoutput with respect to the result of pure K-means clustering.

申请人：Marek Suliga,Piet Dewaele,Rudi Deklerck,Edgard Nyssen,Gert Behiels

地址：Koszalim PL,Sint-Niklaas BE,Vilvoorde BE,Brussels BE,Edegem BE

国籍：PL,BE,BE,BE,BE

更多信息请下载全文后查看