MR Image Segmentation by Nonparametric Model

摘要：

Nonparametric Dirichlet Process Mixtures (MDP) model algorithm is applied to segment images, which can obtain the segmentation class numbers automatically without initialization. The algorithm is used to segment noisy natural images and magnetic resonance images with biasing field. Compared with classical Markov Field (MRF) segmentation, the nonparametric segmentation results show the greater performance. This method is also analyzed quantitatively on the belly magnetic resonance images. The Dice Similarity Coefficients (DSC) of all slices exceed 93％, which show that the proposed method is robust and accurate.

关键词： image segmentation Nonparametric Dirichlet process mixtures clustering

作者: LUYi-su CHEN Wu-fan

作者单位: Key Lab for Medical Image Processing,Southern Medical University,Guangzhou, China Electronic Enginee Key Lab for Medical Image Processing,Southern Medical University,Guangzhou, China

会议类型: 国际会议

会议名称: 2011 4th International Conference on Biomedical Engineering and Informatics(第四届生物医学工程与信息学国际会议 BMEI 2011)

会议地点: 上海

会议语种:英文

页码: 390-394

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）