Normalized euclidean super-pixels for medical image segmentation | |
Liu, Feihong1; Feng, Jun1; Su, Wenhuo2; Lv, Zhaohui1; Xiao, Fang1; Qiu, Shi3; Feng, Jun (fengjun@nwu.edu.cn) | |
2017 | |
会议名称 | 13th International Conference on Intelligent Computing, ICIC 2017 |
会议录名称 | Intelligent Computing Methodologies - 13th International Conference, ICIC 2017, Proceedings |
卷号 | 10363 LNAI |
页码 | 586-597 |
会议日期 | 2017-08-07 |
会议地点 | Liverpool, United kingdom |
出版者 | Springer Verlag |
产权排序 | 3 |
摘要 | We propose a super-pixel segmentation algorithm based on normalized Euclidean distance for handling the uncertainty and complexity in medical image. Benefited from the statistic characteristics, compactness within super-pixels is described by normalized Euclidean distance. Our algorithm banishes the balance factor of the Simple Linear Iterative Clustering framework. In this way, our algorithm properly responses to the lesion tissues, such as tiny lung nodules, which have a little difference in luminance with their neighbors. The effectiveness of proposed algorithm is verified in The Cancer Imaging Archive (TCIA) database. Compared with Simple Linear Iterative Clustering (SLIC) and Linear Spectral Clustering (LSC), the experiment results show that, the proposed algorithm achieves competitive performance over super-pixel segmentation in the state of art. © Springer International Publishing AG 2017. |
作者部门 | 光学影像学习与分析中心 |
DOI | 10.1007/978-3-319-63315-2_51 |
收录类别 | EI ; ISTP |
ISBN号 | 9783319633145 |
语种 | 英语 |
ISSN号 | 03029743 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/29242 |
专题 | 光谱成像技术研究室 |
通讯作者 | Feng, Jun (fengjun@nwu.edu.cn) |
作者单位 | 1.School of Information and Technology, Northwest University, Xi’an, China 2.Center for Nonlinear Studies, Department of Mathematicals, Northwest University, Xi’an, China 3.Xi’an Institute of Optics and Precision Mechanics of CAS, Xi’an, China |
推荐引用方式 GB/T 7714 | Liu, Feihong,Feng, Jun,Su, Wenhuo,et al. Normalized euclidean super-pixels for medical image segmentation[C]:Springer Verlag,2017:586-597. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Normalized euclidean(4532KB) | 会议论文 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论