期刊
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS
卷 11, 期 2, 页码 402-408出版社
AMER SCIENTIFIC PUBLISHERS
DOI: 10.1166/jmihi.2021.3280
关键词
Low-Rank Constraints; Multiview; Possibility C-Means Clustering (PCM); MR Brain Images
The LR-FW-MVPCM algorithm proposed in this study combines low-rank constraints and fuzzy weighted mechanism for the segmentation of MR brain images, showing significant improvements over other algorithms in terms of effectiveness and segmentation performance.
To expand the multiview clustering abilities of traditional PCM in increasingly complex MR brain image segmentation tasks, a fuzzy weighted multiview possibility clustering algorithm with low-rank constraints (LR-FW-MVPCM) is proposed. The LR-FW-MVPCM can effectively mine both the internal consistency and diversity of multiview data, which are two principles for constructing a multiview clustering algorithm. First, a kernel norm is introduced as a low-rank constraint of the fuzzy membership matrix among multiple perspectives. Second, to ensure the clustering accuracy of the algorithm, the view fuzzy weighted mechanism is introduced to the framework of possibility c-means clustering, and the weights of each view are adaptively allocated during the iterative optimization process. The segmentation results of different brain tissues based on the proposed algorithm and three other algorithms illustrate that the LR-FW-MVPCM algorithm can segment MR brain images much more effectively and ensure better segmentation performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据