标题: 利用混合模型的方法对正子电脑断层扫描影像做影像分割并与K-means及常态混合模型的方法比较
Segmentation of PET/CT images by Flexible Mixture Models and Comparison with K-means and Gaussian Mixture Models
作者: 叶孟樵
Ye, Meng-Ciao
卢鸿兴
Lu, Horng-Shing
统计学研究所
关键字: k平均演算法;高斯混合模型;混合模型;核密度估计;K-means;Gaussian mixture model;Flexible mixture model;Kernel Density Estimation
公开日期: 2008
摘要: 正子电脑断层扫描影像能协助医师判定异常部位,在PET影像上特异的亮点或暗点则表示这些异常部位可能发生的位置,因此PET影像的分割是非常重要。我们使用了以下方法去进行影像的分割以圈选出我们所感兴趣的区域,包含了K-means, Gaussian mixture model (GMM)以及Flexible mixture model (FMM)。FMM与GMM最大的差异在于两者所使用的混合分配,FMM此混合模型多考虑了PET影像的结构的特性,使用右偏分配估计背景的部份,另外以常态分配的混合估计非背影之影像。而FMM之分群结果也比K-means与GMM较佳。
Positron Emission Tomography (PET) helps doctors determine the abnormal regions. The specific brightened regions in PET images show the location of abnormal region. Hence the segmentation of the data form PET images is very important. There are three methods to classify the data from PET image to obtain the region of interest, K-means with KDE, Gaussian mixture model (GMM) with KDE and flexible mixture model (FMM) with KDE. The main difference between GMM and FMM is that, GMM uses several normal distributions to fit the original PET data, while FMM does not. FMM considers the property and structure of PET image data. It uses a right-skewed distribution to fit the background images. The mixture normal distribution is used to fit other regions. Finally, the result of FMM with KDE is better than the result of K-means with KDE and GMM with KDE.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT079626516
http://hdl.handle.net/11536/42676
显示于类别:Thesis


文件中的档案:

  1. 651601.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.