Simultaneous tumor segmentation, image restoration, and blur kernel estimation in PET using multiple regularizations

详细信息    查看全文

• 作者：Laquan Li^a ; Jian Wang^a ; Wei Lu^b ; ^c ; Shan Tan^a ; ^{shantan@mail.hust.edu.cn}
• 关键词：Image restoration ; Tumor segmentation ; Blur kernel estimation ; Variational method ; TV regularization ; L2 regularization
• 刊名：Computer Vision and Image Understanding
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：155
• 期：Complete
• 页码：173-194
• 全文大小：5393 K
• 卷排序：155

文摘

A simultaneous restoration and segmentation variational method is proposed for PET. Multiple regularizations are employed to fit multiple image components in PET. Metabolic uptake values on tumor edges in PET are regularized. The blur kernel is modeled as an anisotropic Gaussian. The proposed method can handle PVE and is independent to imaging systems.